Dr. Michael D. Feldman Profile

Dr. Michael D. Feldman

Professor

SPIE Involvement:

Conference Program Committee | Author

Publications (22)

Proceedings Article | 7 April 2023 Presentation + Paper

Biopsy and surgical specimen specific deep learning models for prostate cancer detection on digitized pathology images

Brennan Flannery, Priti Lal, Michael Feldman, María Natalizio, Juan Santa-Rosario, Anant Madabhushi

Proceedings Volume 12471, 124710H (2023) https://doi.org/10.1117/12.2654212

KEYWORDS: Cancer detection, Biopsy, Performance modeling, Cancer, Biological samples, Tissues

Read Abstract +

The detection of prostate cancer within H&E-stained tissue slides helps identify the presence, location, and extent of the disease. Machine learning approaches have been developed to accomplish this task for biopsies and radical prostatectomies. Deep learning approaches, primarily using convolutional neural networks (CNN), have demonstrated substantial ability to identify cancer in each of these sample types. Some models trained on biopsies have even been approved for clinical application. Biopsies are small tissue samples acquired through a syringe to establish cancer diagnosis while radical prostatectomies are large planar sections of prostate tissue acquired post-surgery. This leads to differing morphology and heterogeneity between sample types, making it unclear whether algorithms trained on biopsies are robust enough to perform well on radical prostatectomies and vice versa. Our goal was to investigate whether morphological differences between sample types affected the performance of radical prostatectomy trained CNN models when applied to biopsies and vice versa. Radical prostatectomies (N=100) and biopsies (N=50) were acquired from The University of Pennsylvania to train (80%) and validate (20%) a CNN using the Densenet architecture for biopsies (M^B), radical prostatectomies (M^R), and a combined dataset (M^B+R). Model performance was compared using sensitivity, specificity, and F1 score. To isolate the effect of morphological differences on performance, we acquired all data from the same institution, ensured no batch effects were present via UMAP, applied data augmentation during training, and applied stain normalization. Additionally, the radical prostatecomy training set was optimized for transfer to biopsies by reducing heterogeneity (M^R*). This reduction was based on distance from the centroid of a texture feature distribution. Models performed well when applied to their own sample type (F1 > 0.88) but performed poorly when applied across sample types (F1 < 0.65). Reducing heterogeneity to optimize the radical prostatectomy training set resulted in M^R* (F1=0.72) noticeably outperforming M^R (F1=0.53) on biopsies. This indicates that differences in morphology and heterogeneity drive performance differences between cancer detection models trained on different sample types. Our results suggest that these morphological differences can be overcome with sample type specific models or training set optimization methods.

Proceedings Article | 6 July 2018 Paper

Simulation of sequential pathology images for the virtual clinical trials with rad-path correlation

Predrag Bakic, David Pokrajac, Michael Feldman, Andrew D. Maidment

Proceedings Volume 10718, 107180F (2018) https://doi.org/10.1117/12.2318492

KEYWORDS: Pathology, Breast, Tissues, Image segmentation, Computer simulations, Optical simulations, Clinical trials, Virtual reality, Collagen, Visualization

Read Abstract +

SPIE Journal Paper | 24 October 2016

Evaluating stability of histomorphometric features across scanner and staining variations: prostate cancer diagnosis from whole slide images

Patrick Leo, George Lee, Natalie N. Shih, Robin Elliott, Michael Feldman, Anant Madabhushi

JMI, Vol. 3, Issue 04, 047502, (October 2016) https://doi.org/10.1117/12.10.1117/1.JMI.3.4.047502

KEYWORDS: Scanners, Image segmentation, Lithium, Feature extraction, Prostate cancer, Pathology, Cancer, Tumors, RGB color model, Tissues

Read Abstract +

Proceedings Article | 23 March 2016 Paper

Preliminary evaluation of a fully automated quantitative framework for characterizing general breast tissue histology via color histogram and color texture analysis

Brad Keller, Aimilia Gastounioti, Rebecca Batiste, Despina Kontos, Michael Feldman

Proceedings Volume 9791, 97910A (2016) https://doi.org/10.1117/12.2217094

KEYWORDS: Tissues, Feature extraction, Breast, Visualization, Collagen, Image segmentation, Tissue optics, Image analysis, Breast cancer, Pathology, Cancer

Read Abstract +

SPIE Journal Paper | 27 October 2014

Quantitative identification of magnetic resonance imaging features of prostate cancer response following laser ablation and radical prostatectomy

Geert J. S. Litjens, Henkjan J. Huisman, Robin M. Elliott, Natalie Nc. Shih, Michael D. Feldman, Satish Viswanath, Jurgen Fütterer, Joyce G. R. Bomers, Anant Madabhushi

JMI, Vol. 1, Issue 03, 035001, (October 2014) https://doi.org/10.1117/12.10.1117/1.JMI.1.3.035001

KEYWORDS: Magnetic resonance imaging, Prostate cancer, Tissues, Prostate, Laser therapeutics, Feature extraction, Laser ablation, Image registration, Scanners, Pathology

Read Abstract +

SPIE Journal Paper | 10 October 2014

Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features

Haibo Wang, Angel Cruz Roa, Ajay Basavanhally, Hannah Gilmore, Natalie Shih, Mike Feldman, John Tomaszewski, Fabio Gonzalez, Anant Madabhushi

JMI, Vol. 1, Issue 03, 034003, (October 2014) https://doi.org/10.1117/12.10.1117/1.JMI.1.3.034003

KEYWORDS: Breast cancer, Pathology, Feature extraction, Image segmentation, Computing systems, Neurons, RGB color model, Scanners, Convolutional neural networks, Microscopes

Read Abstract +

Breast cancer (BCa) grading plays an important role in predicting disease aggressiveness and patient outcome. A key component of BCa grade is the mitotic count, which involves quantifying the number of cells in the process of dividing (i.e., undergoing mitosis) at a specific point in time. Currently, mitosis counting is done manually by a pathologist looking at multiple high power fields (HPFs) on a glass slide under a microscope, an extremely laborious and time consuming process. The development of computerized systems for automated detection of mitotic nuclei, while highly desirable, is confounded by the highly variable shape and appearance of mitoses. Existing methods use either handcrafted features that capture certain morphological, statistical, or textural attributes of mitoses or features learned with convolutional neural networks (CNN). Although handcrafted features are inspired by the domain and the particular application, the data-driven CNN models tend to be domain agnostic and attempt to learn additional feature bases that cannot be represented through any of the handcrafted features. On the other hand, CNN is computationally more complex and needs a large number of labeled training instances. Since handcrafted features attempt to model domain pertinent attributes and CNN approaches are largely supervised feature generation methods, there is an appeal in attempting to combine these two distinct classes of feature generation strategies to create an integrated set of attributes that can potentially outperform either class of feature extraction strategies individually. We present a cascaded approach for mitosis detection that intelligently combines a CNN model and handcrafted features (morphology, color, and texture features). By employing a light CNN model, the proposed approach is far less demanding computationally, and the cascaded strategy of combining handcrafted features and CNN-derived features enables the possibility of maximizing the performance by leveraging the disconnected feature sets. Evaluation on the public ICPR12 mitosis dataset that has 226 mitoses annotated on 35 HPFs (400× magnification) by several pathologists and 15 testing HPFs yielded an F-measure of 0.7345. Our approach is accurate, fast, and requires fewer computing resources compared to existent methods, making this feasible for clinical use.

Proceedings Article | 21 March 2014 Paper

Spectral embedding-based registration (SERg) for multimodal fusion of prostate histology and MRI

Eileen Hwuang, Mirabela Rusu, Sudha Karthigeyan, Shannon Agner, Rachel Sparks, Natalie Shih, John Tomaszewski, Mark Rosen, Michael Feldman, Anant Madabhushi

Proceedings Volume 9034, 90343P (2014) https://doi.org/10.1117/12.2044317

KEYWORDS: Image registration, Magnetic resonance imaging, Prostate, Independent component analysis, Chromium, Feature extraction, Image restoration, Image segmentation, Brain, Neuroimaging

Read Abstract +

Multi-modal image registration is needed to align medical images collected from different protocols or imaging sources, thereby allowing the mapping of complementary information between images. One challenge of multimodal image registration is that typical similarity measures rely on statistical correlations between image intensities to determine anatomical alignment. The use of alternate image representations could allow for mapping of intensities into a space or representation such that the multimodal images appear more similar, thus facilitating their co-registration. In this work, we present a spectral embedding based registration (SERg) method that uses non-linearly embedded representations obtained from independent components of statistical texture maps of the original images to facilitate multimodal image registration. Our methodology comprises the following main steps: 1) image-derived textural representation of the original images, 2) dimensionality reduction using independent component analysis (ICA), 3) spectral embedding to generate the alternate representations, and 4) image registration. The rationale behind our approach is that SERg yields embedded representations that can allow for very different looking images to appear more similar, thereby facilitating improved co-registration. Statistical texture features are derived from the image intensities and then reduced to a smaller set by using independent component analysis to remove redundant information. Spectral embedding generates a new representation by eigendecomposition from which only the most important eigenvectors are selected. This helps to accentuate areas of salience based on modality-invariant structural information and therefore better identifies corresponding regions in both the template and target images. The spirit behind SERg is that image registration driven by these areas of salience and correspondence should improve alignment accuracy. In this work, SERg is implemented using Demons to allow the algorithm to more effectively register multimodal images. SERg is also tested within the free-form deformation framework driven by mutual information. Nine pairs of synthetic T1-weighted to T2-weighted brain MRI were registered under the following conditions: five levels of noise (0%, 1%, 3%, 5%, and 7%) and two levels of bias field (20% and 40%) each with and without noise. We demonstrate that across all of these conditions, SERg yields a mean squared error that is 81.51% lower than that of Demons driven by MRI intensity alone. We also spatially align twenty-six ex vivo histology sections and in vivo prostate MRI in order to map the spatial extent of prostate cancer onto corresponding radiologic imaging. SERg performs better than intensity registration by decreasing the root mean squared distance of annotated landmarks in the prostate gland via both Demons algorithm and mutual information-driven free-form deformation. In both synthetic and clinical experiments, the observed improvement in alignment of the template and target images suggest the utility of parametric eigenvector representations and hence SERg for multimodal image registration.

Proceedings Article | 20 March 2014 Paper

Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks

Angel Cruz-Roa, Ajay Basavanhally, Fabio González, Hannah Gilmore, Michael Feldman, Shridar Ganesan, Natalie Shih, John Tomaszewski, Anant Madabhushi

Proceedings Volume 9041, 904103 (2014) https://doi.org/10.1117/12.2043872

KEYWORDS: Tissues, Visualization, Tumors, Image segmentation, Convolution, Breast cancer, RGB color model, Pathology, Convolutional neural networks, Tumor growth modeling

Read Abstract +

This paper presents a deep learning approach for automatic detection and visual analysis of invasive ductal carcinoma (IDC) tissue regions in whole slide images (WSI) of breast cancer (BCa). Deep learning approaches are learn-from-data methods involving computational modeling of the learning process. This approach is similar to how human brain works using different interpretation levels or layers of most representative and useful features resulting into a hierarchical learned representation. These methods have been shown to outpace traditional approaches of most challenging problems in several areas such as speech recognition and object detection. Invasive breast cancer detection is a time consuming and challenging task primarily because it involves a pathologist scanning large swathes of benign regions to ultimately identify the areas of malignancy. Precise delineation of IDC in WSI is crucial to the subsequent estimation of grading tumor aggressiveness and predicting patient outcome. DL approaches are particularly adept at handling these types of problems, especially if a large number of samples are available for training, which would also ensure the generalizability of the learned features and classifier. The DL framework in this paper extends a number of convolutional neural networks (CNN) for visual semantic analysis of tumor regions for diagnosis support. The CNN is trained over a large amount of image patches (tissue regions) from WSI to learn a hierarchical part-based representation. The method was evaluated over a WSI dataset from 162 patients diagnosed with IDC. 113 slides were selected for training and 49 slides were held out for independent testing. Ground truth for quantitative evaluation was provided via expert delineation of the region of cancer by an expert pathologist on the digitized slides. The experimental evaluation was designed to measure classifier accuracy in detecting IDC tissue regions in WSI. Our method yielded the best quantitative results for automatic detection of IDC regions in WSI in terms of F-measure and balanced accuracy (71.80%, 84.23%), in comparison with an approach using handcrafted image features (color, texture and edges, nuclear textural and architecture), and a machine learning classifier for invasive tumor classification using a Random Forest. The best performing handcrafted features were fuzzy color histogram (67.53%, 78.74%) and RGB histogram (66.64%, 77.24%). Our results also suggest that at least some of the tissue classification mistakes (false positives and false negatives) were less due to any fundamental problems associated with the approach, than the inherent limitations in obtaining a very highly granular annotation of the diseased area of interest by an expert pathologist.

Proceedings Article | 20 March 2014 Paper

Sparse representation of multi parametric DCE-MRI features using K-SVD for classifying gene expression based breast cancer recurrence risk

Majid Mahrooghy, Ahmed Ashraf, Dania Daye, Carolyn Mies, Mark Rosen, Michael Feldman, Despina Kontos

Proceedings Volume 9035, 90350X (2014) https://doi.org/10.1117/12.2043719

KEYWORDS: Associative arrays, Feature extraction, Tumors, Breast cancer, Breast, Feature selection, Medicine, Magnetic resonance imaging, Cancer, Genetic algorithms

Read Abstract +

Proceedings Article | 20 March 2014 Paper

Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection

Haibo Wang, Angel Cruz-Roa, Ajay Basavanhally, Hannah Gilmore, Natalie Shih, Mike Feldman, John Tomaszewski, Fabio Gonzalez, Anant Madabhushi

Proceedings Volume 9041, 90410B (2014) https://doi.org/10.1117/12.2043902

KEYWORDS: Feature extraction, RGB color model, Computing systems, Scanners, Breast cancer, Data modeling, Microscopes, Image segmentation, Convolutional neural networks, Glasses

Read Abstract +

Breast cancer (BCa) grading plays an important role in predicting disease aggressiveness and patient outcome. A key component of BCa grade is mitotic count, which involves quantifying the number of cells in the process of dividing (i.e. undergoing mitosis) at a specific point in time. Currently mitosis counting is done manually by a pathologist looking at multiple high power fields on a glass slide under a microscope, an extremely laborious and time consuming process. The development of computerized systems for automated detection of mitotic nuclei, while highly desirable, is confounded by the highly variable shape and appearance of mitoses. Existing methods use either handcrafted features that capture certain morphological, statistical or textural attributes of mitoses or features learned with convolutional neural networks (CNN). While handcrafted features are inspired by the domain and the particular application, the data-driven CNN models tend to be domain agnostic and attempt to learn additional feature bases that cannot be represented through any of the handcrafted features. On the other hand, CNN is computationally more complex and needs a large number of labeled training instances. Since handcrafted features attempt to model domain pertinent attributes and CNN approaches are largely unsupervised feature generation methods, there is an appeal to attempting to combine these two distinct classes of feature generation strategies to create an integrated set of attributes that can potentially outperform either class of feature extraction strategies individually. In this paper, we present a cascaded approach for mitosis detection that intelligently combines a CNN model and handcrafted features (morphology, color and texture features). By employing a light CNN model, the proposed approach is far less demanding computationally, and the cascaded strategy of combining handcrafted features and CNN-derived features enables the possibility of maximizing performance by leveraging the disconnected feature sets. Evaluation on the public ICPR12 mitosis dataset that has 226 mitoses annotated on 35 High Power Fields (HPF, x400 magnification) by several pathologists and 15 testing HPFs yielded an F-measure of 0.7345. Apart from this being the second best performance ever recorded for this MITOS dataset, our approach is faster and requires fewer computing resources compared to extant methods, making this feasible for clinical use.

Proceedings Article | 18 March 2014 Paper

Distinguishing prostate cancer from benign confounders via a cascaded classifier on multi-parametric MRI

G.J.S. Litjens, R. Elliott, N. Shih, M. Feldman, J. Barentsz, C. Hulsbergen - van de Kaa, I. Kovacs, H. Huisman, A. Madabhushi

Proceedings Volume 9035, 903512 (2014) https://doi.org/10.1117/12.2043751

KEYWORDS: Magnetic resonance imaging, Prostate cancer, Cancer, Feature selection, Prostate, Feature extraction, Tissues, Pathology, Scanners, Diagnostics

Read Abstract +

Learning how to separate benign confounders from prostate cancer is important because the imaging characteristics of these confounders are poorly understood. Furthermore, the typical representations of the MRI parameters might not be enough to allow discrimination. The diagnostic uncertainty this causes leads to a lower diagnostic accuracy. In this paper a new cascaded classifier is introduced to separate prostate cancer and benign confounders on MRI in conjunction with specific computer-extracted features to distinguish each of the benign classes (benign prostatic hyperplasia (BPH), inflammation, atrophy or prostatic intra-epithelial neoplasia (PIN). In this study we tried to (1) calculate different mathematical representations of the MRI parameters which more clearly express subtle differences between different classes, (2) learn which of the MRI image features will allow to distinguish specific benign confounders from prostate cancer, and (2) find the combination of computer-extracted MRI features to best discriminate cancer from the confounding classes using a cascaded classifier. One of the most important requirements for identifying MRI signatures for adenocarcinoma, BPH, atrophy, inflammation, and PIN is accurate mapping of the location and spatial extent of the confounder and cancer categories from ex vivo histopathology to MRI. Towards this end we employed an annotated prostatectomy data set of 31 patients, all of whom underwent a multi-parametric 3 Tesla MRI prior to radical prostatectomy. The prostatectomy slides were carefully co-registered to the corresponding MRI slices using an elastic registration technique. We extracted texture features from the T2-weighted imaging, pharmacokinetic features from the dynamic contrast enhanced imaging and diffusion features from the diffusion-weighted imaging for each of the confounder classes and prostate cancer. These features were selected because they form the mainstay of clinical diagnosis. Relevant features for each of the classes were selected using maximum relevance minimum redundancy feature selection, allowing us to perform classifier independent feature selection. The selected features were then incorporated in a cascading classifier, which can focus on easier sub-tasks at each stage, leaving the more difficult classification tasks for later stages. Results show that distinct features are relevant for each of the benign classes, for example the fraction of extra-vascular, extra-cellular space in a voxel is a clear discriminator for inflammation. Furthermore, the cascaded classifier outperforms both multi-class and one-shot classifiers in overall accuracy for discriminating confounders from cancer: 0.76 versus 0.71 and 0.62.

Proceedings Article | 13 March 2014 Paper

Supervised multi-view canonical correlation analysis: fused multimodal prediction of disease diagnosis and prognosis

Asha Singanamalli, Haibo Wang, George Lee, Natalie Shih, Mark Rosen, Stephen Master, John Tomaszewski, Michael Feldman, Anant Madabhushi

Proceedings Volume 9038, 903805 (2014) https://doi.org/10.1117/12.2043762

KEYWORDS: Magnetic resonance imaging, Data fusion, Principal component analysis, Canonical correlation analysis, Alzheimer's disease, Simulation of CCA and DLA aggregates, Tumors, Proteins, Prostate cancer, Biomedical optics

Read Abstract +

While the plethora of information from multiple imaging and non-imaging data streams presents an opportunity for discovery of fused multimodal, multiscale biomarkers, they also introduce multiple independent sources of noise that hinder their collective utility. The goal of this work is to create fused predictors of disease diagnosis and prognosis by combining multiple data streams, which we hypothesize will provide improved performance as compared to predictors from individual data streams. To achieve this goal, we introduce supervised multiview canonical correlation analysis (sMVCCA), a novel data fusion method that attempts to find a common representation for multiscale, multimodal data where class separation is maximized while noise is minimized. In doing so, sMVCCA assumes that the different sources of information are complementary and thereby act synergistically when combined. Although this method can be applied to any number of modalities and to any disease domain, we demonstrate its utility using three datasets. We fuse (i) 1.5 Tesla (T) magnetic resonance imaging (MRI) features with cerbrospinal fluid (CSF) proteomic measurements for early diagnosis of Alzheimer’s disease (n = 30), (ii) 3T Dynamic Contrast Enhanced (DCE) MRI and T2w MRI for in vivo prediction of prostate cancer grade on a per slice basis (n = 33) and (iii) quantitative histomorphometric features of glands and proteomic measurements from mass spectrometry for prediction of 5 year biochemical recurrence postradical prostatectomy (n = 40). Random Forest classifier applied to the sMVCCA fused subspace, as compared to that of MVCCA, PCA and LDA, yielded the highest classification AUC of 0.82 +/- 0.05, 0.76 +/- 0.01, 0.70 +/- 0.07, respectively for the aforementioned datasets. In addition, sMVCCA fused subspace provided 13.6%, 7.6% and 15.3% increase in AUC as compared with that of the best performing individual view in each of the three datasets, respectively. For the biochemical recurrence dataset, Kaplan-Meier curves generated from classifier prediction in the fused subspace reached the significance threshold (p = 0.05) for distinguishing between patients with and without 5 year biochemical recurrence, unlike those generated from classifier predictions of the individual modalities.

Proceedings Article | 12 March 2014 Paper

Distinguishing benign confounding treatment changes from residual prostate cancer on MRI following laser ablation

G. Litjens, H. Huisman, R. Elliott, N. Shih, M. Feldman, S. Viswanath, J. Fütterer, J. Bomers, A. Madabhushi

Proceedings Volume 9036, 90361D (2014) https://doi.org/10.1117/12.2043819

KEYWORDS: Magnetic resonance imaging, Tissues, Prostate cancer, Prostate, Cancer, Feature extraction, Laser ablation, Laser therapeutics, Scanners, Image registration

Read Abstract +

Laser interstitial thermotherapy (LITT) is a relatively new focal therapy technique for the ablation of localized prostate cancer. However, very little is known about the specific effects of LITT within the ablation zone and the surrounding normal tissue regions. For instance, it is important to be able to assess the extent of residual cancer within the prostate following LITT, which may be masked by thermally induced benign necrotic changes. Fortunately LITT is MRI compatible and hence this allows for quantitatively assessing LITT induced changes via multi-parametric MRI. Of course definite validation of any LITT induced changes on MRI requires confirmation via histopathology. The aim of this study was to quantitatively assess and distinguish the imaging characteristics of prostate cancer and benign confounding treatment changes following LITTon 3 Tesla multi-parametric MRI by carefully mapping the treatment related changes from the ex vivo surgically resected histopathologic specimens onto the pre-operative in vivo imaging. A better understanding of the imaging characteristics of residual disease and successfully ablated tissue might lead to improved treatment monitoring and as such patient prognosis. A unique clinical trial at the Radboud University Medical Center, in which 3 patients underwent a prostatectomy after LITT treatment, yielded ex-vivo histopathologic specimens along with pre- and post-LITT MRI. Using this data we (1) identified the computer extracted MRI signatures associated with treatment effects including benign necrotic changes and residual disease and (2) subsequently evaluated the computer extracted MRI features previously identified in distinguishing LITT induced changes in the ablated area relative to the residual disease. Towards this end first a pathologist annotated the ablated area and the residual disease on the ex-vivo histology and then we transferred the annotations to the post-LITT MRI using semi-automatic elastic registration. The pre- and post-LITT MRI were subsequently registered and computer-derived multi-parametric MRI features extracted to determine differences in feature values between residual disease and successfully ablated tissue to assess treatment response. A scoring metric allowed us to identify those specific computer-extracted MRI features that maximally and differentially expressed between the ablated regions and the residual cancer, on a voxel- by voxel basis. Finally, we used a Fuzzy C-Means algorithm to assess the discriminatory power of these selected features. Our results show that specific computer-extracted features from multi-parametric MRI differentially express within the ablated and residual cancer regions, as evidenced by our ability to, on a voxel-by-voxel basis, classify tissue as residual disease. Additionally, we show that change of feature values between pre- and post-LITT MRI may be useful as a quantitative marker for treatment response (T2-weighted texture and DCE MRI features showed largest differences between residual disease and successfully ablated tissue). Finally, a clustering approach to separate treatment effects and residual disease incorporating both (1) and (2) yielded a maximum area under the ROC curve of 0.97 on a voxel basis across 3 studies.

Proceedings Article | 29 March 2013 Paper

Identifying in vivo DCE MRI parameters correlated with ex vivo quantitative microvessel architecture: A radiohistomorphometric approach

Asha Singanamalli, Rachel Sparks, Mirabela Rusu, Natalie Shih, Amy Ziober, John Tomaszewski, Mark Rosen, Michael Feldman, Anant Madabhushi

Proceedings Volume 8676, 867604 (2013) https://doi.org/10.1117/12.2008136

KEYWORDS: Tumors, Magnetic resonance imaging, Feature extraction, Tissues, Image segmentation, Targeting Task Performance metric, In vivo imaging, Prostate cancer, Prostate, Pathology

Read Abstract +

We introduce a novel radiohistomorphometric method for quantitative correlation and subsequent discovery of imaging markers for aggressive prostate cancer (CaP). While this approach can be employed in the context any imaging modality and disease domain, we seek to identify quantitative dynamic contrast enhanced (DCE) magnetic resonance imaging (MRI) attributes that are highly correlated with density and architecture of tumor microvessels, surrogate markers of CaP aggressiveness. This retrospective study consisted of five Gleason score matched patients who underwent 3 Tesla multiparametric MRI prior to radical prostatectomy (RP). The excised gland was sectioned and quartered with a rotary knife. For each serial section, digitized images of individual quadrants were reconstructed into pseudo whole mount sections via previously developed stitching program. The individual quadrants were stained with vascular marker CD31 and annotated for CaP by an expert pathologist. The stained microvessel regions were quantitatively characterized in terms of density and architectural arrangement via graph algorithms, yielding a series of quantitative histomorphometric features. The reconstructed pseudo whole mount histologic sections were non-linearly co-registered with DCE MRI to identify tumor extent on MRI on a voxel-by-voxel basis. Pairwise correlations between kinetic and microvessel features within CaP annotated regions on the two modalities were computed to identify highly correlated attributes. Preliminary results of the radiohistomorphometric correlation identified 8 DCE MRI kinetic features that were highly and significantly (p<0.05) correlated with a number of microvessel parameters. Most of the identified imaging features were related to rate of washout (Rwo) and initial area under the curve (IAUC). Association of those attributes with Gleason patterns showed that the identified imaging features clustered most of the tumors with primary Gleason pattern of 3 together. These results suggest that Rwo and IAUC may be promising candidate imaging markers for identification of aggressive CaP in vivo.

Proceedings Article | 23 February 2012 Paper

Incorporating the whole-mount prostate histology reconstruction program Histostitcher into the extensible imaging platform (XIP) framework

Robert Toth, Jonathan Chappelow, Christoph Vetter, Oliver Kutter, Christoph Russ, Michael Feldman, John Tomaszewski, Natalie Shih, Anant Madabhushi

Proceedings Volume 8315, 83151K (2012) https://doi.org/10.1117/12.912938

KEYWORDS: Visualization, Magnetic resonance imaging, Human-machine interfaces, In vivo imaging, MATLAB, Prostate, Reconstruction algorithms, Computer aided diagnosis and therapy, Prostate cancer, Medical imaging

Read Abstract +

There is a need for identifying quantitative imaging (e.g. MRI) signatures for prostate cancer (CaP), so that computer-aided diagnostic methods can be trained to detect disease extent in vivo. Determining CaP extent on in vivo MRI is difficult to do; however, with the availability of ex vivo surgical whole mount histological sections (WMHS) for CaP patients undergoing radical prostatectomy, co-registration methods can be applied to align and map disease extent onto pre-operative MR imaging from the post-operative histology. Yet obtaining digitized images of WHMS for co-registration with the pre-operative MRI is cumbersome since (a) most digital slide scanners are unable to accommodate the entire section, and (b) significant technical expertise is required for whole mount slide preparation. Consequently, most centers opt to construct quartered sections of each histology slice. Prior to co-registration with MRI, however, these quartered sections need to be digitally stitched together to reconstitute a digital, pseudo WMHS. Histostitcher© is an interactive software program that uses semi-automatic registration tools to digitally stitch quartered sections into pseudo WMHS. Histostitcher© was originally developed using the GUI tools provided by the Matlab programming interface, but the clinical use was limited due to the inefficiency of the interface. The limitations of the Matlab based GUI include (a) an inability to edit the fiducials, (b) the rendering being extremely slow, and (c) lack of interactive and rapid visualization tools. In this work, Histostitcher© has been integrated into the eXtensible Imaging Platform (XIP ^TM ) framework (a set of libraries containing functionalities for analyzing and visualizing medical image data). XIP ^TM lends the stitching tool much greater flexibility and functionality by (a) allowing interactive and seamless navigation through the full resolution histology images, (b) the ability to easily add, edit, or remove fiducials and annotations in order to register the quadrants and map the disease extent. In this work, we showcase examples of digital stitching of quartered histological sections into pseudo-WHMS using Histostitcher © via the new XIP ^TM interface. This tool will be particularly useful in clinical trials and large cohort studies where a quick, interactive way of digitally reconstructing pseudo WMHS is required.

Proceedings Article | 14 March 2011 Paper

Local morphologic scale: application to segmenting tumor infiltrating lymphocytes in ovarian cancer TMAs

Andrew Janowczyk, Sharat Chandran, Michael Feldman, Anant Madabhushi

Proceedings Volume 7962, 79622N (2011) https://doi.org/10.1117/12.878415

KEYWORDS: Particles, Tumors, Ovarian cancer, Biopsy, RGB color model, Image segmentation, Image processing, Image classification, Tissues, Principal component analysis

Read Abstract +

In this paper we present the concept and associated methodological framework for a novel locally adaptive scale notion called local morphological scale (LMS). Broadly speaking, the LMS at every spatial location is defined as the set of spatial locations, with associated morphological descriptors, which characterize the local structure or heterogeneity for the location under consideration. More specifically, the LMS is obtained as the union of all pixels in the polygon obtained by linking the final location of trajectories of particles emanating from the location under consideration, where the path traveled by originating particles is a function of the local gradients and heterogeneity that they encounter along the way. As these particles proceed on their trajectory away from the location under consideration, the velocity of each particle (i.e. do the particles stop, slow down, or simply continue around the object) is modeled using a physics based system. At some time point the particle velocity goes to zero (potentially on account of encountering (a) repeated obstructions, (b) an insurmountable image gradient, or (c) timing out) and comes to a halt. By using a Monte-Carlo sampling technique, LMS is efficiently determined through parallelized computations. LMS is different from previous local scale related formulations in that it is (a) not a locally connected sets of pixels satisfying some pre-defined intensity homogeneity criterion (generalized-scale), nor is it (b) constrained by any prior shape criterion (ball-scale, tensor-scale). Shape descriptors quantifying the morphology of the particle paths are used to define a tensor LMS signature associated with every spatial image location. These features include the number of object collisions per particle, average velocity of a particle, and the length of the individual particle paths. These features can be used in conjunction with a supervised classifier to correctly differentiate between two different object classes based on local structural properties. In this paper, we apply LMS to the specific problem of classifying regions of interest in Ovarian Cancer (OCa) histology images as either tumor or stroma. This approach is used to classify lymphocytes as either tumor infiltrating lymphocytes (TILs) or non-TILs; the presence of TILs having been identified as an important prognostic indicator for disease outcome in patients with OCa. We present preliminary results on the tumor/stroma classification of 11,000 randomly selected locations of interest, across 11 images obtained from 6 patient studies. Using a Probabilistic Boosting Tree (PBT), our supervised classifier yielded an area under the receiver operation characteristic curve (AUC) of 0.8341 ±0.0059 over 5 runs of randomized cross validation. The average LMS computation time at every spatial location for an image patch comprising 2000 pixels with 24 particles at every location was only 18s.

Proceedings Article | 4 March 2011 Paper

Incorporating domain knowledge for tubule detection in breast histopathology using O'Callaghan neighborhoods

Ajay Basavanhally, Elaine Yu, Jun Xu, Shridar Ganesan, Michael Feldman, John Tomaszewski, Anant Madabhushi

Proceedings Volume 7963, 796310 (2011) https://doi.org/10.1117/12.878092

KEYWORDS: Cancer, Spatial analysis, Image segmentation, RGB color model, Feature extraction, Deconvolution, Breast cancer, Tissues, Breast, Data modeling

Read Abstract +

An important criterion for identifying complicated objects with multiple attributes is the use of domain knowledge which reflects the precise spatial linking of the constituent attributes. Hence, simply detecting the presence of the low-level attributes that constitute the object, even in cases where these attributes might be detected in spatial proximity to each other is usually not a robust strategy. The O'Callaghan neighborhood is an ideal vehicle for characterizing objects comprised of multiple attributes spatially connected to each other in a precise fashion because it allows for modeling and imposing spatial distance and directional constraints on the object attributes. In this work we apply the O'Callaghan neighborhood to the problem of tubule identification on hematoxylin and eosin (H & E) stained breast cancer (BCa) histopathology, where a tubule is characterized by a central lumen surrounded by cytoplasm and a ring of nuclei around the cytoplasm. The detection of tubules is important because tubular density is an important predictor in cancer grade determination. In the context of ER+ BCa, grade has been shown to be strongly linked to disease aggressiveness and patient outcome. The more standard pattern recognition approaches to detection of complex objects typically involve training classifiers for low-level attributes individually. For tubule detection, the spatial proximity of lumen, cytoplasm, and nuclei might suggest the presence of a tubule. However such an approach could also suffer from false positive errors due to the presence of fat, stroma, and other lumen-like areas that could be mistaken for tubules. In this work, tubules are identified by imposing spatial and distance constraints using O'Callaghan neighborhoods between the ring of nuclei around each lumen. In this work, cancer nuclei in each image are found via a color deconvolution scheme, which isolates the hematoxylin stain, thereby enabling automated detection of individual cell nuclei. The potential lumen areas are segmented using a Hierarchical Normalized Cut (HNCut) initialized Color Gradient based Active Contour model (CGAC). The HNCut algorithm detects lumen-like areas within the image via pixel clustering across multiple image resolutions. The pixel clustering provides initial contours for the CGAC. From the initial contours, the CGAC evolves to segment the boundaries of the potential lumen areas. A set of 22 graph-based image features characterizing the spatial linking between the tubular attributes is extracted from the O'Callaghan neighborhood in order to distinguish true from false lumens. Evaluation on 1226 potential lumen areas from 14 patient studies produces an area under the receiver operating characteristic curve (AUC) of 0.91 along with the ability to classify true lumen with 86% accuracy. In comparison to manual grading of tubular density over 105 images, our method is able to distinguish histopathology images with low and high tubular density at 89% accuracy (AUC = 0.94).

Proceedings Article | 27 February 2010 Paper

Computer-assisted targeted therapy (CATT) for prostate radiotherapy planning by fusion of CT and MRI

Jonathan Chappelow, Stefan Both, Satish Viswanath, Stephen Hahn, Michael Feldman, Mark Rosen, John Tomaszewski, Neha Vapiwala, Pratik Patel, Anant Madabhushi

Proceedings Volume 7625, 76252C (2010) https://doi.org/10.1117/12.844653

KEYWORDS: Magnetic resonance imaging, Prostate, Diagnostics, Computed tomography, Cancer, Image registration, Tumors, Radiotherapy, Printed circuit board testing, Computer aided diagnosis and therapy

Read Abstract +

Proceedings Article | 27 March 2009 Paper

Probabilistic pairwise Markov models: application to prostate cancer detection

James Monaco, John Tomaszewski, Michael Feldman, Mehdi Moradi, Parvin Mousavi, Alexander Boag, Chris Davidson, Purang Abolmaesumi, Anant Madabhushi

Proceedings Volume 7259, 725903 (2009) https://doi.org/10.1117/12.812462

KEYWORDS: Image segmentation, Solid modeling, Tumor growth modeling, CAD systems, Computer aided design, Magnetorheological finishing, Prostate, Prostate cancer, Computer aided diagnosis and therapy, Chromium

Read Abstract +

Proceedings Article | 3 March 2009 Paper

A boosted distance metric: application to content based image retrieval and classification of digitized histopathology

Jay Naik, Scott Doyle, Ajay Basavanhally, Shridar Ganesan, Michael Feldman, John Tomaszewski, Anant Madabhushi

Proceedings Volume 7260, 72603F (2009) https://doi.org/10.1117/12.813931

KEYWORDS: Tissues, Databases, Feature extraction, Breast, Image classification, Cancer, Image retrieval, Breast cancer, Content based image retrieval, Lithium

Read Abstract +

Distance metrics are often used as a way to compare the similarity of two objects, each represented by a set of features in high-dimensional space. The Euclidean metric is a popular distance metric, employed for a variety of applications. Non-Euclidean distance metrics have also been proposed, and the choice of distance metric for any specific application or domain is a non-trivial task. Furthermore, most distance metrics treat each dimension or object feature as having the same relative importance in determining object similarity. In many applications, such as in Content-Based Image Retrieval (CBIR), where images are quantified and then compared according to their image content, it may be beneficial to utilize a similarity metric where features are weighted according to their ability to distinguish between object classes. In the CBIR paradigm, every image is represented as a vector of quantitative feature values derived from the image content, and a similarity measure is applied to determine which of the database images is most similar to the query. In this work, we present a boosted distance metric (BDM), where individual features are weighted according to their discriminatory power, and compare the performance of this metric to 9 other traditional distance metrics in a CBIR system for digital histopathology. We apply our system to three different breast tissue histology cohorts - (1) 54 breast histology studies corresponding to benign and cancerous images, (2) 36 breast cancer studies corresponding to low and high Bloom-Richardson (BR) grades, and (3) 41 breast cancer studies with high and low levels of lymphocytic infiltration. Over all 3 data cohorts, the BDM performs better compared to 9 traditional metrics, with a greater area under the precision-recall curve. In addition, we performed SVM classification using the BDM along with the traditional metrics, and found that the boosted metric achieves a higher classification accuracy (over 96%) in distinguishing between the tissue classes in each of 3 data cohorts considered. The 10 different similarity metrics were also used to generate similarity matrices between all samples in each of the 3 cohorts. For each cohort, each of the 10 similarity matrices were subjected to normalized cuts, resulting in a reduced dimensional representation of the data samples. The BDM resulted in the best discrimination between tissue classes in the reduced embedding space.

Proceedings Article | 17 March 2008 Paper

Improving supervised classification accuracy using non-rigid multimodal image registration: detecting prostate cancer

Jonathan Chappelow, Satish Viswanath, James Monaco, Mark Rosen, John Tomaszewski, Michael Feldman, Anant Madabhushi

Proceedings Volume 6915, 69150V (2008) https://doi.org/10.1117/12.770703

KEYWORDS: Magnetic resonance imaging, Image registration, Curium, Cancer, Prostate, Computer aided diagnosis and therapy, Prostate cancer, Image segmentation, Independent component analysis, Image classification

Read Abstract +

Computer-aided diagnosis (CAD) systems for the detection of cancer in medical images require precise labeling of training data. For magnetic resonance (MR) imaging (MRI) of the prostate, training labels define the spatial extent of prostate cancer (CaP); the most common source for these labels is expert segmentations. When ancillary data such as whole mount histology (WMH) sections, which provide the gold standard for cancer ground truth, are available, the manual labeling of CaP can be improved by referencing WMH. However, manual segmentation is error prone, time consuming and not reproducible. Therefore, we present the use of multimodal image registration to automatically and accurately transcribe CaP from histology onto MRI following alignment of the two modalities, in order to improve the quality of training data and hence classifier performance. We quantitatively demonstrate the superiority of this registration-based methodology by comparing its results to the manual CaP annotation of expert radiologists. Five supervised CAD classifiers were trained using the labels for CaP extent on MRI obtained by the expert and 4 different registration techniques. Two of the registration methods were affi;ne schemes; one based on maximization of mutual information (MI) and the other method that we previously developed, Combined Feature Ensemble Mutual Information (COFEMI), which incorporates high-order statistical features for robust multimodal registration. Two non-rigid schemes were obtained by succeeding the two affine registration methods with an elastic deformation step using thin-plate splines (TPS). In the absence of definitive ground truth for CaP extent on MRI, classifier accuracy was evaluated against 7 ground truth surrogates obtained by different combinations of the expert and registration segmentations. For 26 multimodal MRI-WMH image pairs, all four registration methods produced a higher area under the receiver operating characteristic curve compared to that obtained from expert annotation. These results suggest that in the presence of additional multimodal image information one can obtain more accurate object annotations than achievable via expert delineation despite vast differences between modalities that hinder image registration.

Proceedings Article | 7 March 2007 Paper

Multimodal image registration of ex vivo 4 Tesla MRI with whole mount histology for prostate cancer detection

Jonathan Chappelow, Anant Madabhushi, Mark Rosen, John Tomaszeweski, Michael Feldman

Proceedings Volume 6512, 65121S (2007) https://doi.org/10.1117/12.710558

KEYWORDS: Magnetic resonance imaging, Cancer, Image registration, Prostate, Image segmentation, Computer aided diagnosis and therapy, Tissues, Visualization, Prostate cancer, Electronic filtering

Read Abstract +