New Technologies to Image Tumors.

The premise of this book is the importance of the tumor microenvironment (TME). Until recently, most research on and clinical attention to cancer biology, diagnosis, and prognosis were focused on the malignant (or premalignant) cellular compartment that could be readily appreciated using standard morphology-based imaging.

High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection.

Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200 × 200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500 × 500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (∼6 million of samples in 24 hours) with far fewer samples (∼2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%.

Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent.

With the increasing ability to routinely and rapidly digitize whole slide images with slide scanners, there has been interest in developing computerized image analysis algorithms for automated detection of disease extent from digital pathology images. The manual identification of presence and extent of breast cancer by a pathologist is critical for patient management for tumor staging and assessing treatment response. However, this process is tedious and subject to inter- and intra-reader variability. For computerized methods to be useful as decision support tools, they need to be resilient to data acquired from different sources, different staining and cutting protocols and different scanners. The objective of this study was to evaluate the accuracy and robustness of a deep learning-based method to automatically identify the extent of invasive tumor on digitized images. Here, we present a new method that employs a convolutional neural network for detecting presence of invasive tumor on whole slide images. Our approach involves training the classifier on nearly 400 exemplars from multiple different sites, and scanners, and then independently validating on almost 200 cases from The Cancer Genome Atlas. Our approach yielded a Dice coefficient of 75.86%, a positive predictive value of 71.62% and a negative predictive value of 96.77% in terms of pixel-by-pixel evaluation compared to manually annotated regions of invasive ductal carcinoma.

Stain Normalization using Sparse AutoEncoders (StaNoSA): Application to digital pathology.

Digital histopathology slides have many sources of variance, and while pathologists typically do not struggle with them, computer aided diagnostic algorithms can perform erratically. This manuscript presents Stain Normalization using Sparse AutoEncoders (StaNoSA) for use in standardizing the color distributions of a test image to that of a single template image. We show how sparse autoencoders can be leveraged to partition images into tissue sub-types, so that color standardization for each can be performed independently. StaNoSA was validated on three experiments and compared against five other color standardization approaches and shown to have either comparable or superior results.

Predicting classifier performance with limited training data: applications to computer-aided diagnosis in breast and prostate cancer.

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.

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

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 ([Formula: see text] magnification) by several pathologists and 15 testing HPFs yielded an [Formula: see text]-measure of 0.7345. Our approach is accurate, fast, and requires fewer computing resources compared to existent methods, making this feasible for clinical use.

Multi-field-of-view framework for distinguishing tumor grade in ER+ breast cancer from entire histopathology slides.

Modified Bloom-Richardson (mBR) grading is known to have prognostic value in breast cancer (BCa), yet its use in clinical practice has been limited by intra- and interobserver variability. The development of a computerized system to distinguish mBR grade from entire estrogen receptor-positive (ER+) BCa histopathology slides will help clinicians identify grading discrepancies and improve overall confidence in the diagnostic result. In this paper, we isolate salient image features characterizing tumor morphology and texture to differentiate entire hematoxylin and eosin (H and E) stained histopathology slides based on mBR grade. The features are used in conjunction with a novel multi-field-of-view (multi-FOV) classifier--a whole-slide classifier that extracts features from a multitude of FOVs of varying sizes--to identify important image features at different FOV sizes. Image features utilized include those related to the spatial arrangement of cancer nuclei (i.e., nuclear architecture) and the textural patterns within nuclei (i.e., nuclear texture). Using slides from 126 ER+ patients (46 low, 60 intermediate, and 20 high mBR grade), our grading system was able to distinguish low versus high, low versus intermediate, and intermediate versus high grade patients with area under curve values of 0.93, 0.72, and 0.74, respectively. Our results suggest that the multi-FOV classifier is able to 1) successfully discriminate low, medium, and high mBR grade and 2) identify specific image features at different FOV sizes that are important for distinguishing mBR grade in H and E stained ER+ BCa histology slides.

Variable importance in nonlinear kernels (VINK): classification of digitized histopathology.

Quantitative histomorphometry is the process of modeling appearance of disease morphology on digitized histopathology images via image-based features (e.g., texture, graphs). Due to the curse of dimensionality, building classifiers with large numbers of features requires feature selection (which may require a large training set) or dimensionality reduction (DR). DR methods map the original high-dimensional features in terms of eigenvectors and eigenvalues, which limits the potential for feature transparency or interpretability. Although methods exist for variable selection and ranking on embeddings obtained via linear DR schemes (e.g., principal components analysis (PCA)), similar methods do not yet exist for nonlinear DR (NLDR) methods. In this work we present a simple yet elegant method for approximating the mapping between the data in the original feature space and the transformed data in the kernel PCA (KPCA) embedding space; this mapping provides the basis for quantification of variable importance in nonlinear kernels (VINK). We show how VINK can be implemented in conjunction with the popular Isomap and Laplacian eigenmap algorithms. VINK is evaluated in the contexts of three different problems in digital pathology: (1) predicting five year PSA failure following radical prostatectomy, (2) predicting Oncotype DX recurrence risk scores for ER+ breast cancers, and (3) distinguishing good and poor outcome p16+ oropharyngeal tumors. We demonstrate that subsets of features identified by VINK provide similar or better classification or regression performance compared to the original high dimensional feature sets.

Computer-aided prognosis: predicting patient and disease outcome via quantitative fusion of multi-scale, multi-modal data.

Computer-aided prognosis (CAP) is a new and exciting complement to the field of computer-aided diagnosis (CAD) and involves developing and applying computerized image analysis and multi-modal data fusion algorithms to digitized patient data (e.g. imaging, tissue, genomic) for helping physicians predict disease outcome and patient survival. While a number of data channels, ranging from the macro (e.g. MRI) to the nano-scales (proteins, genes) are now being routinely acquired for disease characterization, one of the challenges in predicting patient outcome and treatment response has been in our inability to quantitatively fuse these disparate, heterogeneous data sources. At the Laboratory for Computational Imaging and Bioinformatics (LCIB)(1) at Rutgers University, our team has been developing computerized algorithms for high dimensional data and image analysis for predicting disease outcome from multiple modalities including MRI, digital pathology, and protein expression. Additionally, we have been developing novel data fusion algorithms based on non-linear dimensionality reduction methods (such as Graph Embedding) to quantitatively integrate information from multiple data sources and modalities with the overarching goal of optimizing meta-classifiers for making prognostic predictions. In this paper, we briefly describe 4 representative and ongoing CAP projects at LCIB. These projects include (1) an Image-based Risk Score (IbRiS) algorithm for predicting outcome of Estrogen receptor positive breast cancer patients based on quantitative image analysis of digitized breast cancer biopsy specimens alone, (2) segmenting and determining extent of lymphocytic infiltration (identified as a possible prognostic marker for outcome in human epidermal growth factor amplified breast cancers) from digitized histopathology, (3) distinguishing patients with different Gleason grades of prostate cancer (grade being known to be correlated to outcome) from digitized needle biopsy specimens, and (4) integrating protein expression measurements obtained from mass spectrometry with quantitative image features derived from digitized histopathology for distinguishing between prostate cancer patients at low and high risk of disease recurrence following radical prostatectomy.

Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX.

In this paper, we attempt to quantify the prognostic information embedded in multi-parametric histologic biopsy images to predict disease aggressiveness in estrogen receptor-positive (ER+) breast cancers (BCa). The novel methodological contribution is in the use of a multi-field-of-view (multi-FOV) framework for integrating image-based information from differently stained histopathology slides. The multi-FOV approach involves a fixed image resolution while simultaneously integrating image descriptors from many FOVs corresponding to different sizes. For each study, the corresponding risk score (high scores reflecting aggressive disease and vice versa), predicted by a molecular assay (Oncotype DX), is available and serves as the surrogate ground truth for long-term patient outcome. Using the risk scores, a trained classifier is used to identify disease aggressiveness for each FOV size. The predictions for each FOV are then combined to yield the final prediction of disease aggressiveness (good, intermediate, or poor outcome). Independent multi-FOV classifiers are constructed for (1) 50 image features describing the spatial arrangement of cancer nuclei (via Voronoi diagram, Delaunay triangulation, and minimum spanning tree graphs) in H and E stained histopathology and (2) one image feature describing the vascular density in CD34 IHC stained histopathology. In a cohort of 29 patients, the multi-FOV classifiers obtained by combining information from the H and E and CD34 IHC stained channels were able to distinguish low- and high-risk patients with an accuracy of 0.91 ± 0.02 and a positive predictive value of 0.94 ± 0.10, suggesting that a purely image-based assay could potentially replace more expensive molecular assays for making disease prognostic predictions.

Integrated diagnostics: a conceptual framework with examples.

With the advent of digital pathology, imaging scientists have begun to develop computerized image analysis algorithms for making diagnostic (disease presence), prognostic (outcome prediction), and theragnostic (choice of therapy) predictions from high resolution images of digitized histopathology. One of the caveats to developing image analysis algorithms for digitized histopathology is the ability to deal with highly dense, information rich datasets; datasets that would overwhelm most computer vision and image processing algorithms. Over the last decade, manifold learning and non-linear dimensionality reduction schemes have emerged as popular and powerful machine learning tools for pattern recognition problems. However, these techniques have thus far been applied primarily to classification and analysis of computer vision problems (e.g., face detection). In this paper, we discuss recent work by a few groups in the application of manifold learning methods to problems in computer aided diagnosis, prognosis, and theragnosis of digitized histopathology. In addition, we discuss some exciting recent developments in the application of these methods for multi-modal data fusion and classification; specifically the building of meta-classifiers by fusion of histological image and proteomic signatures for prostate cancer outcome prediction.

Expectation-maximization-driven geodesic active contour with overlap resolution (EMaGACOR): application to lymphocyte segmentation on breast cancer histopathology.

The presence of lymphocytic infiltration (LI) has been correlated with nodal metastasis and tumor recurrence in HER2+ breast cancer (BC). The ability to automatically detect and quantify extent of LI on histopathology imagery could potentially result in the development of an image based prognostic tool for human epidermal growth factor receptor-2 (HER2+) BC patients. Lymphocyte segmentation in hematoxylin and eosin (H&E) stained BC histopathology images is complicated by the similarity in appearance between lymphocyte nuclei and other structures (e.g., cancer nuclei) in the image. Additional challenges include biological variability, histological artifacts, and high prevalence of overlapping objects. Although active contours are widely employed in image segmentation, they are limited in their ability to segment overlapping objects and are sensitive to initialization. In this paper, we present a new segmentation scheme, expectation-maximization (EM) driven geodesic active contour with overlap resolution (EMaGACOR), which we apply to automatically detecting and segmenting lymphocytes on HER2+ BC histopathology images. EMaGACOR utilizes the expectation-maximization algorithm for automatically initializing a geodesic active contour (GAC) and includes a novel scheme based on heuristic splitting of contours via identification of high concavity points for resolving overlapping structures. EMaGACOR was evaluated on a total of 100 HER2+ breast biopsy histology images and was found to have a detection sensitivity of over 86% and a positive predictive value of over 64%. By comparison, the EMaGAC model (without overlap resolution) and GAC model yielded corresponding detection sensitivities of 42% and 19%, respectively. Furthermore, EMaGACOR was able to correctly resolve over 90% of overlaps between intersecting lymphocytes. Hausdorff distance (HD) and mean absolute distance (MAD) for EMaGACOR were found to be 2.1 and 0.9 pixels, respectively, and significantly better compared to the corresponding performance of the EMaGAC and GAC models. EMaGACOR is an efficient, robust, reproducible, and accurate segmentation technique that could potentially be applied to other biomedical image analysis problems.

Computerized image-based detection and grading of lymphocytic infiltration in HER2+ breast cancer histopathology.

The identification of phenotypic changes in breast cancer (BC) histopathology on account of corresponding molecular changes is of significant clinical importance in predicting disease outcome. One such example is the presence of lymphocytic infiltration (LI) in histopathology, which has been correlated with nodal metastasis and distant recurrence in HER2+ BC patients. In this paper, we present a computer-aided diagnosis (CADx) scheme to automatically detect and grade the extent of LI in digitized HER2+ BC histopathology. Lymphocytes are first automatically detected by a combination of region growing and Markov random field algorithms. Using the centers of individual detected lymphocytes as vertices, three graphs (Voronoi diagram, Delaunay triangulation, and minimum spanning tree) are constructed and a total of 50 image-derived features describing the arrangement of the lymphocytes are extracted from each sample. A nonlinear dimensionality reduction scheme, graph embedding (GE), is then used to project the high-dimensional feature vector into a reduced 3-D embedding space. A support vector machine classifier is used to discriminate samples with high and low LI in the reduced dimensional embedding space. A total of 41 HER2+ hematoxylin-and-eosin-stained images obtained from 12 patients were considered in this study. For more than 100 three-fold cross-validation trials, the architectural feature set successfully distinguished samples of high and low LI levels with a classification accuracy greater than 90%. The popular unsupervised Varma-Zisserman texton-based classification scheme was used for comparison and yielded a classification accuracy of only 60%. Additionally, the projection of the 50 image-derived features for all 41 tissue samples into a reduced dimensional space via GE allowed for the visualization of a smooth manifold that revealed a continuum between low, intermediate, and high levels of LI. Since it is known that extent of LI in BC biopsy specimens is a prognostic indicator, our CADx scheme will potentially help clinicians determine disease outcome and allow them to make better therapy recommendations for patients with HER2+ BC.

Towards improved cancer diagnosis and prognosis using analysis of gene expression data and computer aided imaging.

With the increasing cost effectiveness of whole slide digital scanners, gene expression microarray and SNP technologies, tissue specimens can now be analyzed using sophisticated computer aided image and data analysis techniques for accurate diagnoses and identification of prognostic markers and potential targets for therapeutic intervention. Microarray analysis is routinely able to identify biomarkers correlated with survival and reveal pathways underlying pathogenesis and invasion. In this paper we describe how microarray profiling of tumor samples combined with simple but powerful methods of analysis can identify biologically distinct disease subclasses of breast cancer with distinct molecular signatures, differential recurrence rates and potentially, very different response to therapy. Image analysis methods are also rapidly finding application in the clinic, complementing the pathologist in quantitative, reproducible, detection, staging, and grading of disease. We will describe novel computerized image analysis techniques and machine learning tools for automated cancer detection from digitized histopathology and how they can be employed for disease diagnosis and prognosis for prostate and breast cancer.

In vivo gated 4D imaging of the embryonic heart using optical coherence tomography.

We demonstrate the first in vivo gated 4D images of avian embryonic hearts by use of optical coherence tomography (OCT). We present a gated 4D dataset of an in vivo beating quail heart consisting of approximately 864,000 A-scans accumulated over multiple heartbeats. Generation of a gating trigger from a laser Doppler velocimetry (LDV) signal, collected from an outlying vitelline vessel, enabled us to gate image acquisition to the cardiac cycle. To fully characterize the genesis and mechanisms of cardiac defects, a tool capable of assessing structure and function simultaneously at early stages of development is needed, and gated OCT has the capability to become such a tool.