Papers by Anant Madabhushi
American Society of Clinical Oncology Educational Book
Cancer therapeutics cause various treatment-related changes that may impact patient follow-up and... more Cancer therapeutics cause various treatment-related changes that may impact patient follow-up and disease monitoring. Although atypical responses such as pseudoprogression may be misinterpreted as treatment nonresponse, other changes, such as hyperprogressive disease seen with immunotherapy, must be recognized early for timely management. Radiation necrosis in the brain is a known response to radiotherapy and must be distinguished from local tumor recurrence. Radiotherapy can also cause adverse effects such as pneumonitis and local tissue toxicity. Systemic therapies, like chemotherapy and targeted therapies, are known to cause long-term cardiovascular effects. Thus, there is a need for robust biomarkers to identify, distinguish, and predict cancer treatment–related changes. Radiomics, which refers to the high-throughput extraction of subvisual features from radiologic images, has been widely explored for disease classification, risk stratification, and treatment-response prediction...
Computer extracted texture features on T2w MRI to predict
American Society of Clinical Oncology Educational Book, 2018
The current standard of Response Evaluation Criteria in Solid Tumors (RECIST)–based tumor respons... more The current standard of Response Evaluation Criteria in Solid Tumors (RECIST)–based tumor response evaluation is limited in its ability to accurately monitor treatment response. Radiomics, an approach involving computerized extraction of several quantitative imaging features, has shown promise in predicting as well as monitoring response to therapy. In this article, we provide a brief overview of radiomic approaches and the various analytical methods and techniques, specifically in the context of predicting and monitoring treatment response for non–small cell lung cancer (NSCLC). We briefly summarize some of the various types of radiomic features, including tumor shape and textural patterns, both within the tumor and within the adjacent tumor microenvironment. Additionally, we also discuss work in delta-radiomics or change in radiomic features (e.g., texture within the nodule) across longitudinally interspersed images in time for monitoring changes in therapy. We discuss the utility...
PloS one, 2018
Translation of radiomics into the clinic may require a more comprehensive understanding of the un... more Translation of radiomics into the clinic may require a more comprehensive understanding of the underlying morphologic tissue characteristics they reflect. In the context of prostate cancer (PCa), some studies have correlated gross histological measurements of gland lumen, epithelium, and nuclei with disease appearance on MRI. Quantitative histomorphometry (QH), like radiomics for radiologic images, is the computer based extraction of features for describing tumor morphology on digitized tissue images. In this work, we attempt to establish the histomorphometric basis for radiomic features for prostate cancer by (1) identifying the radiomic features from T2w MRI most discriminating of low vs. intermediate/high Gleason score, (2) identifying QH features correlated with the most discriminating radiomic features previously identified, and (3) evaluating the discriminative ability of QH features found to be correlated with spatially co-localized radiomic features. On a cohort of 36 patien...
BMC cancer, Jan 30, 2018
Gene-expression companion diagnostic tests, such as the Oncotype DX test, assess the risk of earl... more Gene-expression companion diagnostic tests, such as the Oncotype DX test, assess the risk of early stage Estrogen receptor (ER) positive (+) breast cancers, and guide clinicians in the decision of whether or not to use chemotherapy. However, these tests are typically expensive, time consuming, and tissue-destructive. In this paper, we evaluate the ability of computer-extracted nuclear morphology features from routine hematoxylin and eosin (H&E) stained images of 178 early stage ER+ breast cancer patients to predict corresponding risk categories derived using the Oncotype DX test. A total of 216 features corresponding to the nuclear shape and architecture categories from each of the pathologic images were extracted and four feature selection schemes: Ranksum, Principal Component Analysis with Variable Importance on Projection (PCA-VIP), Maximum-Relevance, Minimum Redundancy Mutual Information Difference (MRMR MID), and Maximum-Relevance, Minimum Redundancy - Mutual Information Quotie...
Radiation oncology (London, England), Jan 10, 2016
Radiomics or computer - extracted texture features have been shown to achieve superior performanc... more Radiomics or computer - extracted texture features have been shown to achieve superior performance than multiparametric MRI (mpMRI) signal intensities alone in targeting prostate cancer (PCa) lesions. Radiomics along with deformable co-registration tools can be used to develop a framework to generate targeted focal radiotherapy treatment plans. The Rad-TRaP framework comprises three distinct modules. Firstly, a module for radiomics based detection of PCa lesions on mpMRI via a feature enabled machine learning classifier. The second module comprises a multi-modal deformable co-registration scheme to map tissue, organ, and delineated target volumes from MRI onto CT. Finally, the third module involves generation of a radiomics based dose plan on MRI for brachytherapy and on CT for EBRT using the target delineations transferred from the MRI to the CT. Rad-TRaP framework was evaluated using a retrospective cohort of 23 patient studies from two different institutions. 11 patients from the...
Medical physics, 2017
Distinguishing between benign granulmoas and adenocarcinomas is confounded by their similar visua... more Distinguishing between benign granulmoas and adenocarcinomas is confounded by their similar visual appearance on routine CT scans. Unfortunately, owing to the inability to discriminate these lesions radigraphically, many patients with benign granulomas are subjected to unnecessary surgical wedge resections and biopsies for pathologic confirmation of cancer presence or absence. This suggests the need for improved computerized characterization of these nodules in order to distinguish between these two classes of lesions on CT scans. While there has been substantial interest in the use of textural analysis for radiomic characterization of lung nodules, relatively less work has been done in shape based characterization of lung nodules, particularly with respect to granulmoas and adenocarcinomas. The primary goal of this study is to evaluate the role of 3D shape features for discrimination of benign granulomas from malignant adenocarcinomas on lung CT images. Towards this end we present ...
Scientific reports, Jan 15, 2017
The introduction of mild cognitive impairment (MCI) as a diagnostic category adds to the challeng... more The introduction of mild cognitive impairment (MCI) as a diagnostic category adds to the challenges of diagnosing Alzheimer's Disease (AD). No single marker has been proven to accurately categorize patients into their respective diagnostic groups. Thus, previous studies have attempted to develop fused predictors of AD and MCI. These studies have two main limitations. Most do not simultaneously consider all diagnostic categories and provide suboptimal fused representations using the same set of modalities for prediction of all classes. In this work, we present a combined framework, cascaded multiview canonical correlation (CaMCCo), for fusion and cascaded classification that incorporates all diagnostic categories and optimizes classification by selectively combining a subset of modalities at each level of the cascade. CaMCCo is evaluated on a data cohort comprising 149 patients for whom neurophysiological, neuroimaging, proteomic and genomic data were available. Results suggest t...
Scientific reports, Jan 6, 2016
Content-based image retrieval (CBIR) retrieves database images most similar to the query image by... more Content-based image retrieval (CBIR) retrieves database images most similar to the query image by (1) extracting quantitative image descriptors and (2) calculating similarity between database and query image descriptors. Recently, manifold learning (ML) has been used to perform CBIR in a low dimensional representation of the high dimensional image descriptor space to avoid the curse of dimensionality. ML schemes are computationally expensive, requiring an eigenvalue decomposition (EVD) for every new query image to learn its low dimensional representation. We present out-of-sample extrapolation utilizing semi-supervised ML (OSE-SSL) to learn the low dimensional representation without recomputing the EVD for each query image. OSE-SSL incorporates semantic information, partial class label, into a ML scheme such that the low dimensional representation co-localizes semantically similar images. In the context of prostate histopathology, gland morphology is an integral component of the Gle...
PLOS ONE, 2015
Clinical trials increasingly employ medical imaging data in conjunction with supervised classifie... more Clinical trials increasingly employ medical imaging data in conjunction with supervised classifiers, where the latter require large amounts of training data to accurately model the system. Yet, a classifier selected at the start of the trial based on smaller and more accessible datasets may yield inaccurate and unstable classification performance. In this paper, we aim to address two common concerns in classifier selection for clinical trials: (1) predicting expected classifier performance for large datasets based on error rates calculated from smaller datasets and (2) the selection of appropriate classifiers based on expected performance for larger datasets. We present a framework for comparative evaluation of classifiers using only limited amounts of training data by using random repeated sampling (RRS) in conjunction with a cross-validation sampling strategy. Extrapolated error rates are subsequently validated via comparison with leave-one-out cross-validation performed on a larger dataset. The ability to predict error rates as dataset size increases is demonstrated on both synthetic data as well as three different computational imaging tasks: detecting cancerous image regions in prostate histopathology, differentiating high and low grade cancer in breast histopathology, and detecting cancerous metavoxels in prostate magnetic resonance spectroscopy. For each task, the relationships between 3 distinct classifiers (k-nearest neighbor, naive Bayes, Support Vector Machine) are explored. Further quantitative evaluation in terms of interquartile range (IQR) suggests that our approach consistently yields error rates with lower variability (mean IQRs of 0.0070, 0.0127, and 0.0140) than a traditional RRS approach (mean IQRs of 0.0297, 0.0779, and 0.305) that does not employ cross-validation sampling for all three datasets.
2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2009
Triple-negative (TN) breast cancer has gained much interest recently due to its lack of response ... more Triple-negative (TN) breast cancer has gained much interest recently due to its lack of response to receptor-targeted therapies and its aggressive clinical nature. In this study, we evaluate the ability of a computer-aided diagnosis (CAD) system to not only distinguish benign from malignant lesions on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), but also to quantitatively distinguish triple negative breast cancers from other molecular subtypes of breast cancer. 41 breast lesions (24 malignant, 17 benign) as imaged on DCE-MRI were included in the dataset. Of the 24 malignant cases, 13 were of the TN phenotype. Using the dynamic signal intensity information from the DCE-MRIs, an Expectation Maximization-driven active contours scheme is used to automatically segment the breast lesions. Following quantitative morphological, textural, and kinetic feature extraction, a support vector machine classifier was employed to distinguish (a) benign from malignant lesions and (b) TN from non-TN cancers. In the former case, the classifier yielded an accuracy of 83%, sensitivity of 79%, and specificity of 88%. In distinguishing TN from non-TN cases, the classifier had an accuracy of 92%, sensitivity of 92%, and specificity of 91%. The results suggest that the TN phenotype has distinct and quantifiable signatures on DCE-MRI that will be instrumental in the early detection of this aggressive breast cancer subtype.
SPIE Proceedings, 2014
In this study we explore the ability of a novel machine learning approach, in conjunction with co... more In this study we explore the ability of a novel machine learning approach, in conjunction with computer-extracted features describing prostate cancer morphology on pre-treatment MRI, to predict whether a patient will develop biochemical recurrence within ten years of radiation therapy. Biochemical recurrence, which is characterized by a rise in serum prostate-specific antigen (PSA) of at least 2 ng/mL above the nadir PSA, is associated with increased risk of metastasis and prostate cancer-related mortality. Currently, risk of biochemical recurrence is predicted by the Kattan nomogram, which incorporates several clinical factors to predict the probability of recurrence-free survival following radiation therapy (but has limited prediction accuracy). Semantic attributes on T2w MRI, such as the presence of extracapsular extension and seminal vesicle invasion and surrogate measurements of tumor size, have also been shown to be predictive of biochemical recurrence risk. While the correlation between biochemical recurrence and factors like tumor stage, Gleason grade, and extracapsular spread are welldocumented, it is less clear how to predict biochemical recurrence in the absence of extracapsular spread and for small tumors fully contained in the capsule. Computer-extracted texture features, which quantitatively describe tumor micro-architecture and morphology on MRI, have been shown to provide clues about a tumor's aggressiveness. However, while computer-extracted features have been employed for predicting cancer presence and grade, they have not been evaluated in the context of predicting risk of biochemical recurrence. This work seeks to evaluate the role of computer-extracted texture features in predicting risk of biochemical recurrence on a cohort of sixteen patients who underwent pre-treatment 1.5 Tesla (T) T2w MRI. We extract a combination of first-order statistical, gradient, co-occurrence, and Gabor wavelet features from T2w MRI. To identify which of these T2w MRI texture features are potential independent prognostic markers of PSA failure, we implement a partial least squares (PLS) method to embed the data in a low-dimensional space and then use the variable importance in projections (VIP) method to quantify the contributions of individual features to classification on the PLS embedding. In spite of the poor resolution of the 1.5 T MRI data, we are able to identify three Gabor wavelet features that, in conjunction with a logistic regression classifier, yield an area under the receiver operating characteristic curve of 0.83 for predicting the probability of biochemical recurrence following radiation therapy. In comparison to both the Kattan nomogram and semantic MRI attributes, the ability of these three computer-extracted features to predict biochemical recurrence risk is demonstrated.
SPIE Proceedings, 2011
Active contours and active shape models (ASM) have been widely employed in image segmentation. A ... more Active contours and active shape models (ASM) have been widely employed in image segmentation. A major limitation of active contours, however, is in their (a) inability to resolve boundaries of intersecting objects and to (b) handle occlusion. Multiple overlapping objects are typically segmented out as a single object. On the other hand, ASMs are limited by point correspondence issues since object landmarks need to be identified across multiple objects for initial object alignment. ASMs are also are constrained in that they can usually only segment a single object in an image. In this paper, we present a novel synergistic boundary and region-based active contour model that incorporates shape priors in a level set formulation. We demonstrate an application of these synergistic active contour models using multiple level sets to segment nuclear and glandular structures on digitized histopathology images of breast and prostate biopsy specimens. Unlike previous related approaches, our model is able to resolve object overlap and separate occluded boundaries of multiple objects simultaneously. The energy functional of the active contour is comprised of three terms. The first term comprises the prior shape term, modeled on the object of interest, thereby constraining the deformation achievable by the active contour. The second term, a boundary based term detects object boundaries from image gradients. The third term drives the shape prior and the contour towards the object boundary based on region statistics. The results of qualitative and quantitative evaluation on 100 prostate and 14 breast cancer histology images for the task of detecting and segmenting nuclei, lymphocytes, and glands reveals that the model easily outperforms two state of the art segmentation schemes (Geodesic Active Contour (GAC) and Roussons shape based model) and resolves up to 92% of overlapping/occluded lymphocytes and nuclei on prostate and breast cancer histology images.
SPIE Proceedings, 2011
Content-based image retrieval (CBIR) systems, in the context of medical image analysis, allow for... more Content-based image retrieval (CBIR) systems, in the context of medical image analysis, allow for a user to compare a query image to previously archived database images in terms of diagnostic and/or prognostic similarity. CBIR systems can therefore serve as a powerful computerized decision support tool for clinical diagnostics and also serve as a useful learning tool for medical students, residents, and fellows. An accurate CBIR system relies on two components, (1) image descriptors which are related to a previously defined notion of image similarity and (2) quantification of image descriptors in order to accurately characterize and capture the a priori defined image similarity measure. In many medical applications, the morphology of an object of interest (e.g. breast lesions on DCE-MRI or glands on prostate histopathology) may provide important diagnostic and prognostic information regarding the disease being investigated. Morphological attributes can be broadly categorized as being (a) model-based (MBD) or (b) non-model based (NMBD). Most computerized decision support tools leverage morphological descriptors (e.g. area, contour variation, and compactness) which belong to the latter category in that they do not explicitly model morphology for the object of interest. Conversely, descriptors such as Fourier descriptors (FDs) explicitly model the object of interest. In this paper, we present a CBIR system that leverages a novel set of MBD called Explicit Shape Descriptors (ESDs) which accurately describe the similarity between the morphology of objects of interest. ESDs are computed by: (a) fitting shape models to objects of interest, (b) pairwise comparison between shape models, and (c) a nonlinear dimensionality reduction scheme to extract a concise set of morphological descriptors in a reduced dimensional embedding space. We utilized our ESDs in the context of CBIR in three datasets: (1) the synthetic MPEG-7 Set B containing 1400 silhouette images, (2) DCE-MRI of 91 breast lesions, (3) and digitized prostate histopathology dataset comprised of 888 glands. For each dataset, each image was sequentially selected as a query image and the remaining images in the database were ranked according to how similar they were to the query image based on the ESDs. From this ranking, area under the precision-recall curve (AUPRC) was calculated and averaged over all possible query images, for each of the three datasets. For the MPEG-7 dataset bull's eye accuracy for our CBIR system is 78.65%, comparable to several state of the art shape modeling approaches. For the breast DCE-MRI dataset, ESDs outperforms a set of NMBDs with an AUPRC of 0.55 ± 0.02. For the prostate histopathology dataset, ESDs and FDs perform equivalently with an AUPRC of 0.40 ± .01, but outperform NMBDs.
Annual Review of Pathology: Mechanisms of Disease, 2013
Digital imaging in pathology has undergone an exponential period of growth and expansion catalyze... more Digital imaging in pathology has undergone an exponential period of growth and expansion catalyzed by changes in imaging hardware and gains in computational processing. Today, digitization of entire glass slides at near the optical resolution limits of light can occur in 60 s. Whole slides can be imaged in fluorescence or by use of multispectral imaging systems. Computational algorithms have been developed for cytometric analysis of cells and proteins in subcellular locations by use of multiplexed antibody staining protocols. Digital imaging is unlocking the potential to integrate primary image features into high-dimensional genomic assays by moving microscopic analysis into the digital age. This review highlights the emerging field of digital pathology and explores the methods and analytic approaches being developed for the application and use of these methods in clinical care and research settings.
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, Jan 12, 2014
Shape based active contours have emerged as a natural solution to overlap resolution. However, mo... more Shape based active contours have emerged as a natural solution to overlap resolution. However, most of these shape-based methods are computationally expensive. There are instances in an image where no overlapping objects are present and applying these schemes results in significant computational overhead without any accompanying, additional benefit. In this paper we present a novel adaptive active contour scheme (AdACM) that combines boundary and region based energy terms with a shape prior in a multi level set formulation. To reduce the computational overhead, the shape prior term in the variational formulation is only invoked for those instances in the image where overlaps between objects are identified; these overlaps being identified via a contour concavity detection scheme. By not having to invoke all three terms (shape, boundary, region) for segmenting every object in the scene, the computational expense of the integrated active contour model is dramatically reduced, a particu...
Lecture Notes in Computer Science, 2014
We introduce a novel biologically inspired feature descriptor, Co-occurrence of Local Anisotropic... more We introduce a novel biologically inspired feature descriptor, Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe), that captures higher order co-occurrence patterns of local gradient tensors at a pixel level to distinguish disease phenotypes that have similar morphologic appearances. A number of pathologies (e.g. subtypes of breast cancer) have different histologic phenotypes but similar radiographic appearances. While texture features have been previously employed for distinguishing subtly different pathologies, they attempt to capture differences in global intensity patterns. In this paper we attempt to model CoLlAGe to identify higher order co-occurrence patterns of gradient tensors at a pixel level. The assumption behind this new feature is that different pathologies, even though they may have very similar overall texture and appearance on imaging, at a local scale, will have different co-occurring patterns with respect to gradient orientations. We demonstrate the utility of CoLlAGe in distinguishing two subtly different types of pathologies on MRI in the context of brain tumors and breast cancer. In the first problem, we look at CoLlAGe for distinguishing radiation effects from recurrent brain tumors over a cohort of 40 studies, and in the second, discriminating different molecular subtypes of breast cancer over a cohort of 73 studies. For both these challenging cohorts, CoLlAGe was found to have significantly improved classification performance, as compared to the traditional texture features such as Haralick, Gabor, local binary patterns, and histogram of gradients.
Imaging in Medicine, 2009
The digital pathologist & computerized image analysis of histopathology Over the last decade, the... more The digital pathologist & computerized image analysis of histopathology Over the last decade, the nature of diagnostic healthcare has changed rapidly owing to an explosion in the availability of patient data for disease diagnosis. Traditional methods of analysis of cancer samples were limited to a few variables, usually stage, grade and the measurement of a few clinical markers, such as estrogen receptor, progesterone receptor, HER2 for breast cancer and prostatespecific antigen for prostate cancer (CaP). The pathologist was trained to synthesize this information into a diagnosis that would help the clinician determine the best course of therapy. These data were also used to try to understand the molecular basis of cancer with the goal of improving therapy.
SPIE Proceedings, 2013
Prostate cancer (CaP) is evidenced by profound changes in the spatial distribution of cells. Spat... more Prostate cancer (CaP) is evidenced by profound changes in the spatial distribution of cells. Spatial arrangement and architectural organization of nuclei, especially clustering of the cells, within CaP histopathology is known to be predictive of disease aggressiveness and potentially patient outcome. Traditionally, graph theory has been used to characterize the spatial arrangement of these cells by constructing a graph with cell/nuclei as the node. One disadvantage of this approach is the inability to extract local attributes from complex networks that emerges from large histopathology samples. In this paper, we define a cluster of cells as a node and construct a novel graph called Cell Cluster Graph (CCG). CCG is constructed by first identifying the cell clusters to use as nodes for graph construction. Pairwise spatial relation between nodes is translated to the edges (links) of CCG with a certain probability. We then extract global and local features from the CCG that best capture the tumor morphology. We evaluated the ability of the CCG to capture the characteristics of CaP morphology in order to predict 5 year biochemical failures in men with CaP and treated with radical prostatectomy. Extracted features from CCG constructed using nuclei as nodal centers on tissue microarray (TMA) images obtained from the surgical specimens allowed us to predict biochemical recurrence. A randomized 3-fold cross-validation via support Vector Machine classifier achieved an accuracy of 83.1 ± 1.2% in dataset of 80 patients with 20 cases of biochemical recurrence.
Uploads
Papers by Anant Madabhushi