Dr. Germán Corredor Profile

Dr. Germán Corredor

Instructor at Emory University

SPIE Involvement:

Author

Publications (22)

Proceedings Article | 7 April 2023 Presentation + Paper

Transformer as a spatially-aware multi-instance learning framework to predict the risk of death for early-stage non-small cell lung cancer

Yufei Zhou, Can Koyuncu, Cristian ‪Barrera, Germán Corredor, Xiangxue Wang, Cheng Lu, Anant Madabhushi

Proceedings Volume 12471, 124710V (2023) https://doi.org/10.1117/12.2654498

KEYWORDS: Transformers, Spatial learning, Lung cancer, Tumors, Medical research, Cancer, Tissues, Feature extraction

Read Abstract +

In computational pathology, training and inference of conventional deep convolutional neural networks (CNN) are usually limited to patches of small sizes (e.g., 256 × 256) sampled from whole slide images. In practice, however, diagnostic and prognostic information could lie within the context of tumor microenvironment across multiple regions, far beyond the scope of individual patches. For instance, the spatial relationship of tumor-infiltrating lymphocytes (TIL) across regions of interest might be prognostic for non-small cell lung cancer (NSCLC). This poses a multi-instance learning (MIL) problem, and a single-patch-driven CNN typically fails to learn spatial information and context between multiple patches, especially their spatial relationship. In this work, we present a cell graph-based MIL framework to predict the risk of death for early-stage NSCLC by aggregating feature representation of TIL-enclosing patches according to their spatial relationship. Inspired by PATCHY-SAN, a graph-embedding framework for CNNs, we use graph kernel-based approaches to embed a bag of patches into a sequence with their spatial information encoded into the sequence order. A transformer model was then trained to aggregate patch-level features based on spatial information. We demonstrate the capability of this framework to predict the likelihood of the patient with NSCLC in two cohorts (n=240) to survive for more than 5 years. The training cohort (n=195) comprised hematoxylin and eosin (H&E)-stained whole slide images (WSI), while the testing cohort (n=45) comprised H&E-stained tumor microarrays (TMA). We show that, with the spatial context of multiple patches encoded as an ordered patch sequence, the performance in the testing cohort of our approach achieves an area under the receiver operating characteristic curve (AUC) of 0.836 (p=0.009; HR=5.62), as opposed to a baseline conventional CNN with an AUC of 0.542 (p=0.105; HR=1.66). The results suggest that the Transformer is a generic spatial information aware MIL framework that can learn the spatial relationship of multiple TIL-enclosing patches from the graph representation of immune cells.

Proceedings Article | 7 April 2023 Presentation + Paper

Spatial connectivity of tumor and associated cells (SpaCell): a novel computational pathology biomarker

Germán Corredor, Can Koyuncu, Andrew Janowczyk, Paula Toro, Sepideh Azarianpour, James Lewis, Anant Madabhushi

Proceedings Volume 12471, 124710U (2023) https://doi.org/10.1117/12.2653950

KEYWORDS: Tumors, Cancer, Lung cancer, Image segmentation, Deep learning, Lung, Education and training, Pulmonary disorders, Medical research, Tumor growth modeling

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Computer extracted features of tumor-infiltrating lymphocytes (TILs) architecture are prognostic of progression-free survival in stage III colon cancer

Aya Aqeel, Germán Corredor, Vidya Sankar Viswanathan, Chuheng Chen, Mogjan Mokhtari, Pingfu Fu, Joseph Willis, Anant Madabhushi

Proceedings Volume 12039, 120390V (2022) https://doi.org/10.1117/12.2613161

KEYWORDS: Colorectal cancer, Tumors, Feature extraction, Cancer, Image segmentation, Data modeling, Medical research

Read Abstract +

Stage III Colorectal cancer (CRC) is treated with surgery followed by chemotherapy. Yet >20% of clinically low-risk patients develop recurrence. It is critical to identify high-risk stage III patients who can benefit from closer monitoring and escalation of therapy. Previous studies showed promising results in predicting risk from H&E slides in CRC using deep learning based algorithms. One biomarker which was heavily studied and showed good results in predicting risk is Tumor Infiltrating Lymphocytes (TILs). In CRC, TIL density has been shown to be significantly and independently associated with overall patient survival¹. Furthermore, additional studies have demonstrated that analyzing spatial organization of TILs could be more informative than density alone². Hence, our study aimed to stratify stage III CRC patients into distinct risk groups based on features derived from TILs and to determine if this classification could have independent prognostic significance. The training set (D₁) included 50 patients and validation set (D₂) consisted of 70 patients from an independent site. A survival model was trained to predict the risk of recurrence in stage III CRC patients. First, a deep learning (DL) model was used to segment TILs on WSIs. Next, 1036 features related to spatial architecture (SpaTIL) and density of TILs (DenTIL) were extracted. A Cox proportional hazards regression model in conjunction with the least absolute shrinkage and selection operator (Lasso) was used to find top 5 features and the feature coefficients associated with progression free survival (PFS) and provide risk scores to each patient. The risk scores for the training dataset were computed using the selected features with their respective coefficients. A cut-off value was determined according to these risk scores, above which patients were labelled high-risk and below was low risk. In the validation set, the median PFS for the high-risk group was 15.1mos and in the low-risk group was 27mos. The model was able to accurately predict higher incidence of progression in patients in the high-risk group (HR = 3.76, 95% CI 1.3-10.9, p-value=0.0053, c-index=0.687) in the validation set. Future work will entail additional multi-site, multi-institutional validation of our biomarker to further understand its strengths and applications.

Proceedings Article | 4 April 2022 Presentation + Paper

Selecting training samples for ovarian cancer classification via a semi-supervised clustering approach

Jennifer Salguero L., Prateek Prasanna, Germán Corredor, Angel Cruz-Roa, David Becerra, Eduardo Romero

Proceedings Volume 12039, 1203906 (2022) https://doi.org/10.1117/12.2612984

KEYWORDS: Ovarian cancer, Cancer, Statistical modeling, Pathology, Feature extraction, Diagnostics, Machine learning, Statistical analysis

Read Abstract +

SPIE Journal Paper | 13 July 2021 Open Access

Computational pathology reveals unique spatial patterns of immune response in H&E images from COVID-19 autopsies: preliminary findings

Paula Toro, Kaustav Bera, Pingfu Fu, Lisa Barton, Hannah Gilmore, Sanjay Mukhopadhyay, Anant Madabhushi, Germán Corredor, Dylan Rasmussen, Vidya Sankar Viswanathan, Christina Buzzy, Edana Stroberg, Eric Duval

JMI, Vol. 8, Issue S1, 017501, (July 2021) https://doi.org/10.1117/12.10.1117/1.JMI.8.S1.017501

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 16 March 2020 Presentation + Paper

Compactness measures of tumor infiltrating lymphocytes in lung adenocarcinoma are associated with overall patient survival and immune scores

Ruiwen Ding, Prateek Prasanna, Germán Corredor, Cheng Lu, Priya Velu, Khoi Le, Patrick Leo, Niha Beig, Vamsidhar Velcheti, David Rimm, Kurt Schalper, Anant Madabhushi

Proceedings Volume 11320, 1132003 (2020) https://doi.org/10.1117/12.2549588

KEYWORDS: Tumors, Tissues, Feature extraction, Lung, Lung cancer, Biological research, Cancer, Data modeling, Principal component analysis, Statistical analysis

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Computer extracted features related to the spatial arrangement of tumor-infiltrating lymphocytes predict overall survival in epithelial ovarian cancer receiving adjuvant chemotherapy

Sepideh Azarianpour, Germán Corredor, Kaustav Bera, Patrick Leo, Nathaniel Braman, Pingfu Fu, Haider Mahdi, Anant Madabhushi

Proceedings Volume 11320, 113200Q (2020) https://doi.org/10.1117/12.2550188

KEYWORDS: Tumors, Ovarian cancer, Cancer, Feature extraction, Lung cancer, Statistical analysis, Tumor growth modeling, Tissues, Data modeling, Medical research

Read Abstract +

Proceedings Article | 15 May 2019 Presentation + Paper

Phenotyping tumor infiltrating lymphocytes (PhenoTIL) on H&E tissue images: predicting recurrence in lung cancer

Cristian Barrera, Germán Corredor, Xiangxue Wang, Kurt Schalper, David Rimm, Vamsidhar Velcheti, Anant Madabhushi, Eduardo Romero Castro

Proceedings Volume 10956, 1095607 (2019) https://doi.org/10.1117/12.2513048

KEYWORDS: Tumors, Tissues, Lung cancer, Data modeling, Statistical analysis, Image segmentation, Cancer, Process modeling, Oncology, Image analysis

Read Abstract +

Proceedings Article | 21 December 2018 Paper

A visualization, navigation, and annotation system for dermatopathology training

Paula Toro, Germán Corredor, Eduardo Romero , Viviana Arias

Proceedings Volume 10975, 109750Z (2018) https://doi.org/10.1117/12.2511638

KEYWORDS: Navigation systems, Pathology, Visualization, Skin, Dermatology, Diagnostics, Scanners, Human-machine interfaces, Microscopy

Read Abstract +

Proceedings Article | 21 December 2018 Paper

A method to detect glands in histological gastric cancer images

Sunny Alfonso, Germán Corredor, Ricardo Moncayo, Cristian Barrera, Angel Sanchez, Paula Toro, Eduardo Romero

Proceedings Volume 10975, 109750X (2018) https://doi.org/10.1117/12.2511680

KEYWORDS: Cancer, Feature extraction, Image segmentation, Tissues, Pathology, Tumors, Prostate cancer, Monte Carlo methods, Binary data, Deconvolution

Read Abstract +

Proceedings Article | 6 March 2018 Paper

A watershed and feature-based approach for automated detection of lymphocytes on lung cancer images

Germán Corredor, Xiangxue Wang, Cheng Lu, Vamsidhar Velcheti, Eduardo Romero, Anant Madabhushi

Proceedings Volume 10581, 105810R (2018) https://doi.org/10.1117/12.2293147

KEYWORDS: Lung cancer, Image segmentation, Visualization, Data modeling, Feature extraction, Tumors, Image processing, Cancer, Visual process modeling, Pathology

Read Abstract +

Proceedings Article | 17 November 2017 Paper

A sparse representation of the pathologist's interaction with whole slide images to improve the assigned relevance of regions of interest

Daniel Santiago, Germán Corredor, Eduardo Romero

Proceedings Volume 10572, 1057204 (2017) https://doi.org/10.1117/12.2285906

KEYWORDS: Associative arrays, Microscopes, Image segmentation, Diagnostics, Chemical species, Skin, Biopsy, Pathology, Biomedical optics

Read Abstract +

Proceedings Article | 17 November 2017 Paper

Multi-channel non-invasive fetal electrocardiography detection using wavelet decomposition

Javier Almeida , Josué Ruano, Germán Corredor, David Romo-Bucheli, José Ricardo Navarro-Vargas, Eduardo Romero

Proceedings Volume 10572, 105720U (2017) https://doi.org/10.1117/12.2286749

KEYWORDS: Fetus, Signal detection, Wavelets, Electrocardiography, Electronic filtering, Independent component analysis, Discrete wavelet transforms, Detection and tracking algorithms, Data modeling, Signal to noise ratio

Read Abstract +

Proceedings Article | 17 November 2017 Paper

A lymphocyte spatial distribution graph-based method for automated classification of recurrence risk on lung cancer images

Juan Garciá-Arteaga, Germán Corredor, Xiangxue Wang, Vamsidhar Velcheti, Anant Madabhushi, Eduardo Romero

Proceedings Volume 10572, 1057203 (2017) https://doi.org/10.1117/12.2285653

KEYWORDS: Lung cancer, Pathology, Blood, Tumors, Image classification, Machine learning, Feature extraction, Biomedical optics

Read Abstract +

Proceedings Article | 17 November 2017 Paper

Quantifying expert diagnosis variability when grading tumor-infiltrating lymphocytes

Paula Toro, Germán Corredor, Xiangxue Wang, Viviana Arias, Vamsidhar Velcheti, Anant Madabhushi, Eduardo Romero

Proceedings Volume 10572, 1057202 (2017) https://doi.org/10.1117/12.2286717

KEYWORDS: Tumors, Pathology, Lung cancer, Oncology, Solids, Cancer, Human-machine interfaces, Software, Image quality, Statistical analysis

Read Abstract +

SPIE Journal Paper | 11 March 2017

Training a cell-level classifier for detecting basal-cell carcinoma by combining human visual attention maps with low-level handcrafted features

Germán Corredor, Jon Whitney, Viviana Arias Pedroza, Anant Madabhushi, Eduardo Romero Castro

JMI, Vol. 4, Issue 02, 021105, (March 2017) https://doi.org/10.1117/12.10.1117/1.JMI.4.2.021105

KEYWORDS: Visualization, Cancer, Tumor growth modeling, Diagnostics, Visual process modeling, Information visualization, Pathology, Image segmentation, Feature extraction, Medical imaging

Read Abstract +

Proceedings Article | 26 January 2017 Paper

Nuclei graph local features for basal cell carcinoma classification in whole slide images

David Romo-Bucheli, Germán Corredor, Juan García-Arteaga, Viviana Arias, Eduardo Romero

Proceedings Volume 10160, 101600Q (2017) https://doi.org/10.1117/12.2257386

KEYWORDS: Skin, Tissues, Image classification, Medicine, Cancer, Feature extraction, Data modeling, Image segmentation, Tumor growth modeling, Visualization

Read Abstract +

Proceedings Article | 26 January 2017 Paper

A radiology image retrieval system based on user preferences

Lina Guzmán, Germán Corredor, Eduardo Romero

Proceedings Volume 10160, 1016018 (2017) https://doi.org/10.1117/12.2257305

KEYWORDS: Radiology, Picture Archiving and Communication System, Information visualization, Image retrieval, Visualization, Databases, Brain, Image visualization, Medicine, Neuroimaging

Read Abstract +

Proceedings Article | 22 December 2015 Paper

A low dimensional entropy-based descriptor of several tissues in skin cancer histopathology samples

Pablo Álvarez, Germán Corredor, Juan García-Arteaga, Eduardo Romero

Proceedings Volume 9681, 968102 (2015) https://doi.org/10.1117/12.2211528

KEYWORDS: Skin cancer, Feature extraction, Tissues, Pathology, Visualization, Image segmentation, Statistical analysis, Image retrieval, Cancer, Databases

Read Abstract +

Proceedings Article | 28 January 2015 Paper

Registration of cardiac magnetic resonance images using SURF points and matching

Braian Moreno, Angélica Atehortúa, Germán Corredor, Eduardo Romero

Proceedings Volume 9287, 92870U (2015) https://doi.org/10.1117/12.2073527

KEYWORDS: Image registration, Heart, Magnetism, Image segmentation, Pathology, Diagnostics, Sensors, Image processing, Medical imaging, Image analysis

Read Abstract +

Proceedings Article | 28 January 2015 Paper

A statistical model for characterization of histopathology images

Pablo Álvarez, Guatizalema Castro, Germán Corredor, Eduardo Romero

Proceedings Volume 9287, 92870H (2015) https://doi.org/10.1117/12.2073530

KEYWORDS: Image processing, Statistical analysis, Tissues, Systems modeling, Error analysis, Statistical modeling, Data modeling, Image understanding, Image retrieval, Mechanics

Read Abstract +

Proceedings Article | 19 November 2013 Paper

Concurrent access to a virtual microscope using a web service oriented architecture

Germán Corredor, Marcela Iregui, Viviana Arias, Eduardo Romero

Proceedings Volume 8922, 89220T (2013) https://doi.org/10.1117/12.2035424

KEYWORDS: Visualization, Microscopy, Web services, Image resolution, Microscopes, Image quality, Databases, Image compression, Solids, Computer architecture

Read Abstract +

Showing 5 of 22 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years