Quantitative imaging biomarkers (QIBs) hold enormous potential to improve the efficiency of clinical trials that use standard-of-care CT imaging. Examples of QIBs include size, shape, intensity histogram characteristics, texture, radiomics, and more. There is, however, a well-recognized gap between discovery and the translation to practice of QIBs, which is driven in part by concerns about their repeatability and reproducibility in the diverse clinical environment. Our goal is to characterize QIB repeatability and reproducibility by using virtual imaging clinical trials (VICTs) to simulate the full data pathway. We start by estimating the probability distribution functions (PDFs) for patient-, disease-, treatment- , and imaging-related sources of variability. These are used to forward-model sinograms that are reconstructed and then analyzed by the QIB under evaluation in a virtual imaging pipeline. By repeatedly sampling from the variability PDFs, estimates of the bias, variance, repeatability and reproducibility of the QIB can be generated by comparison with the known ground truth. These estimates of QIB performance can be used as evidence of the utility of QIBs in clinical trials of new therapies.
There is a tremendous potential for AI-based quantitative imaging biomarkers to make clinical trials with standardof- care CT more efficient. There is, however, a well-recognized gap between discovery and the translation to practice for AI-based imaging biomarkers. Our goal is to enable more efficient and effective imaging clinical trials by characterizing the repeatability and reproducibility AI-based imaging biomarkers. We used virtual imaging clinical trials (VCTs) to simulate the data pathway by estimating the probability distributions functions for patient-, disease-, and imaging-related sources of variability. We evaluated the bias and variance in estimating the volume of liver lesions and the variance of an algorithm, that has shown success in predicting mortality risk for NSCLC patients. We used the volumetric XCAT anthropomorphic simulated phantom with inserted lesions with varied shape, size, and location. For CT acquisition and reconstruction we used the CatSim package and varied acquisition mAs and image reconstruction kernel. For each combination of parameters we generated 20 independent realizations with quantum and electronic noise. The resulting images were analyzed with the two AI-based imaging biomarkers described above, and from that we computed the mean and standard deviation of the results. Mean values and/or bias results were counter-intuitive in some cases, e.g. lower mean bias in scans with lower mAs. Addition of variations in lesion size, shape and location increased variance of the estimated parameters more than the mAs effects. These results indicate the feasibility of using VCTs to estimate the repeatability and reproducibility of AI-based biomarkers used in clinical trials with standard-of-care CT.
Radiomic features characterize tumor imaging phenotype. Nonsmall cell lung cancer (NSCLC) tumors are known for their complexity in shape and wide range in density. We explored the effects of variable tumor contouring on the prediction of epidermal growth factor receptor (EGFR) mutation status by radiomics in NSCLC patients treated with a targeted therapy (Gefitinib). Forty-six early stage NSCLC patients (EGFR mutant:wildtype = 20:26) were included. Three experienced radiologists independently delineated the tumors using a semiautomated segmentation software on a noncontrast-enhanced baseline and three-week post-therapy CT scan images that were reconstructed using 1.25-mm slice thickness and lung kernel. Eighty-nine radiomic features were computed on both scans and their changes (radiomic delta-features) were calculated. The highest area under the curves (AUCs) were 0.87, 0.85, and 0.80 for the three radiologists and the number of significant features (AUC>0.8) was 3, 5, and 0, respectively. The AUCs of a single feature significantly varied among radiologists (e.g., 0.88, 0.75, and 0.73 for run-length primitive length uniformity). We conclude that a three-week change in tumor imaging phenotype allows identifying the EGFR mutational status of NSCLC. However, interobserver variability in tumor contouring translates into a significant variability in radiomic metrics accuracy.
Tumor volume measured from computed tomography images is considered a biomarker for disease progression or treatment response. The estimation of the tumor volume depends on the imaging system parameters selected, as well as lesion characteristics. In this study, we examined how different image reconstruction methods affect the measurement of lesions in an anthropomorphic liver phantom with a non-uniform background. Iterative statistics-based and model-based reconstructions, as well as filtered back-projection, were evaluated and compared in this study. Statistics-based and filtered back-projection yielded similar estimation performance, while model-based yielded higher precision but lower accuracy in the case of small lesions. Iterative reconstructions exhibited higher signal-to-noise ratio but slightly lower contrast of the lesion relative to the background. A better understanding of lesion volumetry performance as a function of acquisition parameters and lesion characteristics can lead to its incorporation as a routine sizing tool.
The purpose of this work was to estimate bias in measuring the size of spherical and non-spherical lesions by
radiologists using three sizing techniques under a variety of simulated lesion and reconstruction slice thickness
conditions. We designed a reader study in which six radiologists estimated the size of 10 synthetic nodules of various
sizes, shapes and densities embedded within a realistic anthropomorphic thorax phantom from CT scan data. In this
manuscript we report preliminary results for the first four readers (Reader 1-4). Two repeat CT scans of the phantom
containing each nodule were acquired using a Philips 16-slice scanner at a 0.8 and 5 mm slice thickness. The readers
measured the sizes of all nodules for each of the 40 resulting scans (10 nodules x 2 slice thickness x 2 repeat scans)
using three sizing techniques (1D longest in-slice dimension; 2D area from longest in-slice dimension and corresponding
longest perpendicular dimension; 3D semi-automated volume) in each of 2 reading sessions. The normalized size was
estimated for each sizing method and an inter-comparison of bias among methods was performed. The overall relative
biases (standard deviation) of the 1D, 2D and 3D methods for the four readers subset (Readers 1-4) were -13.4 (20.3),
-15.3 (28.4) and 4.8 (21.2) percentage points, respectively. The relative biases for the 3D volume sizing method was
statistically lower than either the 1D or 2D method (p<0.001 for 1D vs. 3D and 2D vs. 3D).
The calculation of standardized uptake values (SUVs) in tumors on serial [18F]2-fluoro-2-deoxy-D-glucose (18F-FDG)
positron emission tomography (PET) images is often used for the assessment of therapy response. We present a
computerized method that automatically detects lung tumors on 18F-FDG PET/Computed Tomography (CT) images
using both anatomic and metabolic information. First, on CT images, relevant organs, including lung, bone, liver and
spleen, are automatically identified and segmented based on their locations and intensity distributions. Hot spots (SUV
>= 1.5) on 18F-FDG PET images are then labeled using the connected component analysis. The resultant "hot objects"
(geometrically connected hot spots in three dimensions) that fall into, reside at the edges or are in the vicinity of the
lungs are considered as tumor candidates. To determine true lesions, further analyses are conducted, including reduction
of tumor candidates by the masking out of hot objects within CT-determined normal organs, and analysis of candidate
tumors' locations, intensity distributions and shapes on both CT and PET. The method was applied to 18F-FDG-PET/CT
scans from 9 patients, on which 31 target lesions had been identified by a nuclear medicine radiologist during a Phase II
lung cancer clinical trial. Out of 31 target lesions, 30 (97%) were detected by the computer method. However,
sensitivity and specificity were not estimated because not all lesions had been marked up in the clinical trial. The
method effectively excluded the hot spots caused by mediastinum, liver, spleen, skeletal muscle and bone metastasis.
In mesothelioma, response is usually assessed by computed tomography (CT). In current clinical practice the Response Evaluation Criteria in Solid Tumors (RECIST) or WHO, i.e., the uni-dimensional or the bi-dimensional measurements, is applied to the assessment of therapy response. However, the shape of the mesothelioma volume is very irregular and its longest dimension is almost never in the axial plane. Furthermore, the sections and the sites where radiologists measure the tumor are rather subjective, resulting in poor reproducibility of tumor size measurements. We are developing an objective three-dimensional (3D) computer algorithm to automatically identify and quantify tumor volumes that are associated with malignant pleural mesothelioma to assess therapy response. The algorithm first extracts the lung pleural surface from the volumetric CT images by interpolating the chest ribs over a number of adjacent slices and then forming a volume that includes the thorax. This volume allows a separation of mesothelioma from the chest wall. Subsequently, the structures inside the extracted pleural lung surface, including the mediastinal area, lung parenchyma, and pleural mesothelioma, can be identified using a multiple thresholding technique and morphological operations. Preliminary results have shown the potential of utilizing this algorithm to automatically detect and quantify tumor volumes on CT scans and thus to assess therapy response for malignant pleural mesothelioma.
The reproducible measurement of tumors is critical to assess therapy response in oncology patients. Our purpose was to develop an automated technique of measuring tumor burden and compare the results with radiologists. 15 patients with pulmonary metastases were evaluated by 3 independent, blinded radiologists. Each radiologist identified and measured the 5 largest pulmonary metastases for each patient. A computerized method for automated detection and measurement of pulmonary nodules was developed. This included automatic detection of lung nodules using a local density maximum algorithm and accurate delineation of the nodules with a multi-criterion automated algorithm. Five largest nodules from each patient were determined using this method. The cross-product measurement was calculated as the greatest diameter and greatest perpendicular for each of the nodules automatically and by each radiologist.
The mean cross-product size of the pulmonary metastases was 3.6 cm2 (range 0.6 to 12.2 cm2). All 3 Radiologists identified the identical 5 metastases as "largest" in only 5 (33%) of cases. They identified the same metastases 54/75 (72%) and at least 2 Radiologists identified the same metastases 66/75 (88%) of the time. Of the 54 metastases identified by all 3 Radiologists, the computer calculated 52 of these to be the largest. The difference in cross-product measurement was significant for 2 (p=.006, p= .003) of the 3 Radiologists. There was no significant difference in cross-product measurement for the automatic measurement as compared to any of the Radiologists. Automated measurement of tumor burden generates more reproducible measurements especially compared with the manual techniques used by one or more Radiologists.
Liver segmentation is critical for the development of algorithms to detect and define focal lesions. It is also helpful in presurgical planning for hepatic resection and to gauge the results of therapies. The purpose of this study was to develop a computerized method for extraction of liver contours on contrast-enhanced hepatic CT.
The method is based on a snake algorithm with Gradient Vector Flow (GVF) field as its external force, which uses an edge map and an initial contour as its starting point. A Canny edge algorithm is thus applied to obtain the initial edge map. To suppress edges inside liver parenchyma, a liver template determined by analyzing the histogram of the liver image is employed. Based on the modified edge map, the GVF field is then computed in an iterative manner. Due to the finite iteration step, an area uncovered by the GVF field in the liver can be extracted and serves as an initial contour for the snake algorithm. Preliminary results have shown the potential of separating the liver from its adjacent structures (e.g., kidney and stomach) of similar densities.
In this work, we present a computer-aided detection (CAD) algorithm for small lung nodules on low-dose MSCT
images. With this technique, identification of potential lung nodules is carried out with a local density maximum (LDM)
algorithm, followed by reduction of false positives from the nodule candidates using task-specific 2-D/3-D features along
with a knowledge-based nodule inclusion/exclusion strategy. Twenty-eight MSCT scans (40/80mAs, 120kVp, 5mm
collimation/2.5mm reconstruction) from our lung cancer screening program that included at least one lung nodule were
selected for this study. Two radiologists independently interpreted these cases. Subsequently, a consensus reading by
both radiologists and CAD was generated to define a “gold standard”. In total, 165 nodules were considered as the “gold
standard” (average: 5.9 nodules/case; range: 1-22 nodules/case). The two radiologists detected 146 nodules (88.5%) and
CAD detected 100 nodules (60.6%) with 8.7 false-positives/case. CAD detected an additional 19 nodules (6 nodules >
3mm and 13 nodules < 3mm) that had been missed by both radiologists. Preliminary results show that the CAD is
capable of detecting small lung nodules with acceptable number of false-positives on low-dose MSCT scans and it can
detect nodules that are otherwise missed by radiologists, though a majority are small nodules (< 3mm).
Assessing the image quality of display devices is becoming an important concern for radiology departments with large numbers of widely distributed image displays. Methods commonly used for laboratory measurements are too costly and cumbersome for routine quality assessment, however, methods that rely on visual assessment of currently available test targets may not have adequate sensitivity. The purpose of this paper is to quantify the sensitivity of commonly used test targets for visual assessment of medical display devices with well-defined changes in sharpness and nose. Two test targets methods were selected form those that have been used for visual assessment of image displays. For each, the assessment is a measure of the size and contrast of the smallest visible pattern in the target. Computer simulation was used to produce images of each of the targets having known sharpness and nose degradation. Viewers were trainee in the use of each target, then asked to score a randomly ordered set of simulation-degraded target images. These data were approximately analyzed for each method and the result evaluated with standard statistical methods. Assessments were found to correlate with sharpness and noise. However, the sensitivity of both targets for single-stimulus assessment was found to be adequate. The practical utility of these methods must therefore be questioned.
Nodule growth is a key characteristic of malignancy. The measurement of nodule diameter on chest radiographs has been unsatisfactory due to insufficient accuracy and reproducibility. Additionally, the frequent use of high resolution CT scanners has increased the detection rate of very small nodules. On one hand, the small nodules present even greater diagnostic difficulties and, on the other hand, are more frequently benign, resulting in higher rates of unnecessary surgery. In this paper we present a 3-D algorithm to improve the consistency of nodule segmentation on multiple scans. The multi-criterion, multi-scan segmentation algorithm has been developed based on the fact that a typical small pulmonary nodule has distinct difference in density at the boundary and relatively compact shape, and that other tissues in the lung do not change in size over time. Our preliminary results with in-vivo nodules have shown the potential of applying this practical 3-D segmentation algorithm to clinical settings.
Alternative strategies used for wavelet-based lossy image compression can affect lesion detection differently at higher compression ratios. These effects were studied using three variants of a wavelet-based image compression algorithm: (1) unified quantization, (2) truncation of all coefficients at all subbands, and (3) truncation of coefficients subband by subband. The nonprewhitening- matched-filter-derived da, a deductibility index, was used to quantify the changes in detection performance as a function of compression ratio for each strategy. Based on this approach, the optimal compression strategy was determined. Two classes of images were generated to simulate signal-present and signal-absent cases for a liver imaged by CT. For each strategy, the performance in discriminating between the signal-present class and signal-absent class was quantified by da for varying compression ratios. Among the three strategies studied, truncation of all coefficients is the least desirable strategy for preserving small, low contrast signals; truncation of coefficients subband by subband yields the best result for subtle signals, but distorts high frequency edges between tissues; unified quantization is the best strategy if both low contrast objects and high frequency edges are to be preserved.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.