High-throughput biomarker segmentation on ovarian cancer tissue microarrays via hierarchical normalized cuts

Artificial intelligence in ovarian cancer histopathology: a systematic review

This study evaluates the quality of published research using artificial intelligence (AI) for ovarian cancer diagnosis or prognosis using histopathology data. A systematic search of PubMed, Scopus, Web of Science, Cochrane CENTRAL, and WHO-ICTRP was conducted up to May 19, 2023. Inclusion criteria required that AI was used for prognostic or diagnostic inferences in human ovarian cancer histopathology images. Risk of bias was assessed using PROBAST. Information about each model was tabulated and summary statistics were reported. The study was registered on PROSPERO (CRD42022334730) and PRISMA 2020 reporting guidelines were followed. Searches identified 1573 records, of which 45 were eligible for inclusion. These studies contained 80 models of interest, including 37 diagnostic models, 22 prognostic models, and 21 other diagnostically relevant models. Common tasks included treatment response prediction (11/80), malignancy status classification (10/80), stain quantification (9/80), and histological subtyping (7/80). Models were developed using 1-1375 histopathology slides from 1-776 ovarian cancer patients. A high or unclear risk of bias was found in all studies, most frequently due to limited analysis and incomplete reporting regarding participant recruitment. Limited research has been conducted on the application of AI to histopathology images for diagnostic or prognostic purposes in ovarian cancer, and none of the models have been demonstrated to be ready for real-world implementation. Key aspects to accelerate clinical translation include transparent and comprehensive reporting of data provenance and modelling approaches, and improved quantitative evaluation using cross-validation and external validations. This work was funded by the Engineering and Physical Sciences Research Council.

Computational Analysis of Routine Biopsies Improves Diagnosis and Prediction of Cardiac Allograft Vasculopathy

Background: Cardiac allograft vasculopathy (CAV) is a leading cause of morbidity and mortality for heart transplant recipients. While clinical risk factors for CAV have been established, no personalized prognostic test exists to confidently identify patients at high vs. low risk of developing aggressive CAV. The aim of this investigation was to leverage computational methods for analyzing digital pathology images from routine endomyocardial biopsies (EMB) to develop a precision medicine tool for predicting CAV years before overt clinical presentation. Methods: Clinical data from 1-year post-transplant was collected on 302 transplant recipients from the University of Pennsylvania, including 53 'early CAV' patients and 249 'no-CAV' controls. This data was used to generate a 'clinical model' (ClinCAV-Pr) for predicting future CAV development. From this cohort, n=183 archived EMBs were collected for CD31 and modified trichrome staining and then digitally scanned. These included 1-year post-transplant EMBs from 50 'early CAV' patients and 82 no-CAV patients, as well as 51 EMBs from 'disease control' patients obtained at the time of definitive coronary angiography confirming CAV. Using biologically-inspired, hand-crafted features extracted from digitized EMBs, quantitative histologic models for differentiating no-CAV from disease controls (HistoCAV-Dx), and for predicting future CAV from 1-year post-transplant EMBs were developed (HistoCAV-Pr). The performance of histologic and clinical models for predicting future CAV (i.e. HistoCAV-Pr and ClinCAV-Pr, respectively) were compared in a held-out validation set, before being combined to assess the added predictive value of an integrated predictive model (iCAV-Pr). Results: ClinCAV-Pr achieved modest performance on the independent test set, with area under the receiver operating curve (AUROC) of 0.70. The HistoCAV-Dx model for diagnosing CAV achieved excellent discrimination, with an AUROC of 0.91, while HistoCAV-Pr model for predicting CAV achieved good performance with an AUROC of 0.80. The integrated iCAV-Pr model achieved excellent predictive performance, with an AUROC of 0.93 on the held-out test set. Conclusions: Prediction of future CAV development is greatly improved by incorporation of computationally extracted histologic features. These results suggest morphologic details contained within regularly obtained biopsy tissue have the potential to enhance precision and personalization of treatment plans for post-heart transplant patients.

Deep learning-based image analysis methods for brightfield-acquired multiplex immunohistochemistry images

BACKGROUND

Multiplex immunohistochemistry (mIHC) permits the labeling of six or more distinct cell types within a single histologic tissue section. The classification of each cell type requires detection of the unique colored chromogens localized to cells expressing biomarkers of interest. The most comprehensive and reproducible method to evaluate such slides is to employ digital pathology and image analysis pipelines to whole-slide images (WSIs). Our suite of deep learning tools quantitatively evaluates the expression of six biomarkers in mIHC WSIs. These methods address the current lack of readily available methods to evaluate more than four biomarkers and circumvent the need for specialized instrumentation to spectrally separate different colors. The use case application for our methods is a study that investigates tumor immune interactions in pancreatic ductal adenocarcinoma (PDAC) with a customized mIHC panel.

METHODS

Six different colored chromogens were utilized to label T-cells (CD3, CD4, CD8), B-cells (CD20), macrophages (CD16), and tumor cells (K17) in formalin-fixed paraffin-embedded (FFPE) PDAC tissue sections. We leveraged pathologist annotations to develop complementary deep learning-based methods: (1) ColorAE is a deep autoencoder which segments stained objects based on color; (2) U-Net is a convolutional neural network (CNN) trained to segment cells based on color, texture and shape; and ensemble methods that employ both ColorAE and U-Net, collectively referred to as (3) ColorAE:U-Net. We assessed the performance of our methods using: structural similarity and DICE score to evaluate segmentation results of ColorAE against traditional color deconvolution; F1 score, sensitivity, positive predictive value, and DICE score to evaluate the predictions from ColorAE, U-Net, and ColorAE:U-Net ensemble methods against pathologist-generated ground truth. We then used prediction results for spatial analysis (nearest neighbor).

RESULTS

We observed that (1) the performance of ColorAE is comparable to traditional color deconvolution for single-stain IHC images (note: traditional color deconvolution cannot be used for mIHC); (2) ColorAE and U-Net are complementary methods that detect 6 different classes of cells with comparable performance; (3) combinations of ColorAE and U-Net into ensemble methods outperform using either ColorAE and U-Net alone; and (4) ColorAE:U-Net ensemble methods can be employed for detailed analysis of the tumor microenvironment (TME). We developed a suite of scalable deep learning methods to analyze 6 distinctly labeled cell populations in mIHC WSIs. We evaluated our methods and found that they reliably detected and classified cells in the PDAC tumor microenvironment. We also present a use case, wherein we apply the ColorAE:U-Net ensemble method across 3 mIHC WSIs and use the predictions to quantify all stained cell populations and perform nearest neighbor spatial analysis. Thus, we provide proof of concept that these methods can be employed to quantitatively describe the spatial distribution immune cells within the tumor microenvironment. These complementary deep learning methods are readily deployable for use in clinical research studies.

Histo-genomics: digital pathology at the forefront of precision medicine

The toughest challenge OMICs face is that they provide extremely high molecular resolution but poor spatial information. Understanding the cellular/histological context of the overwhelming genetic data is critical for a full understanding of the clinical behavior of a malignant tumor. Digital pathology can add an extra layer of information to help visualize in a spatial and microenvironmental context the molecular information of cancer. Thus, histo-genomics provide a unique chance for data integration. In the era of a precision medicine, a four-dimensional (4D) (temporal/spatial) analysis of cancer aided by digital pathology can be a critical step to understand the evolution/progression of different cancers and consequently tailor individual treatment plans. For instance, the integration of molecular biomarkers expression into a three-dimensional (3D) image of a digitally scanned tumor can offer a better understanding of its subtype, behavior, host immune response and prognosis. Using advanced digital image analysis, a larger spectrum of parameters can be analyzed as potential predictors of clinical behavior. Correlation between morphological features and host immune response can be also performed with therapeutic implications. Radio-histomics, or the interface of radiological images and histology is another emerging exciting field which encompasses the integration of radiological imaging with digital pathological images, genomics, and clinical data to portray a more holistic approach to understating and treating disease. These advances in digital slide scanning are not without technical challenges, which will be addressed carefully in this review with quick peek at its future.

Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images

Pathological evaluation of tumor tissue is pivotal for diagnosis in cancer patients and automated image analysis approaches have great potential to increase precision of diagnosis and help reduce human error. In this study, we utilize several computational methods based on convolutional neural networks (CNN) and build a stand-alone pipeline to effectively classify different histopathology images across different types of cancer. In particular, we demonstrate the utility of our pipeline to discriminate between two subtypes of lung cancer, four biomarkers of bladder cancer, and five biomarkers of breast cancer. In addition, we apply our pipeline to discriminate among four immunohistochemistry (IHC) staining scores of bladder and breast cancers. Our classification pipeline includes a basic CNN architecture, Google's Inceptions with three training strategies, and an ensemble of two state-of-the-art algorithms, Inception and ResNet. Training strategies include training the last layer of Google's Inceptions, training the network from scratch, and fine-tunning the parameters for our data using two pre-trained version of Google's Inception architectures, Inception-V1 and Inception-V3. We demonstrate the power of deep learning approaches for identifying cancer subtypes, and the robustness of Google's Inceptions even in presence of extensive tumor heterogeneity. On average, our pipeline achieved accuracies of 100%, 92%, 95%, and 69% for discrimination of various cancer tissues, subtypes, biomarkers, and scores, respectively. Our pipeline and related documentation is freely available at https://github.com/ih-_lab/CNN_Smoothie.

An Image Analysis Resource for Cancer Research: PIIP-Pathology Image Informatics Platform for Visualization, Analysis, and Management

Pathology Image Informatics Platform (PIIP) is an NCI/NIH sponsored project intended for managing, annotating, sharing, and quantitatively analyzing digital pathology imaging data. It expands on an existing, freely available pathology image viewer, Sedeen. The goal of this project is to develop and embed some commonly used image analysis applications into the Sedeen viewer to create a freely available resource for the digital pathology and cancer research communities. Thus far, new plugins have been developed and incorporated into the platform for out of focus detection, region of interest transformation, and IHC slide analysis. Our biomarker quantification and nuclear segmentation algorithms, written in MATLAB, have also been integrated into the viewer. This article describes the viewing software and the mechanism to extend functionality by plugins, brief descriptions of which are provided as examples, to guide users who want to use this platform. PIIP project materials, including a video describing its usage and applications, and links for the Sedeen Viewer, plug-ins, and user manuals are freely available through the project web page: http://pathiip.org Cancer Res; 77(21); e83-86. ©2017 AACR.

A resolution adaptive deep hierarchical (RADHicaL) learning scheme applied to nuclear segmentation of digital pathology images

Deep learning (DL) has recently been successfully applied to a number of image analysis problems. However, DL approaches tend to be inefficient for segmentation on large image data, such as high-resolution digital pathology slide images. For example, typical breast biopsy images scanned at 40× magnification contain billions of pixels, of which usually only a small percentage belong to the class of interest. For a typical naïve deep learning scheme, parsing through and interrogating all the image pixels would represent hundreds if not thousands of hours of compute time using high performance computing environments. In this paper, we present a resolution adaptive deep hierarchical (RADHicaL) learning scheme wherein DL networks at lower resolutions are leveraged to determine if higher levels of magnification, and thus computation, are necessary to provide precise results. We evaluate our approach on a nuclear segmentation task with a cohort of 141 ER+ breast cancer images and show we can reduce computation time on average by about 85%. Expert annotations of 12,000 nuclei across these 141 images were employed for quantitative evaluation of RADHicaL. A head-to-head comparison with a naïve DL approach, operating solely at the highest magnification, yielded the following performance metrics: .9407 vs .9854 Detection Rate, .8218 vs .8489 F-score, .8061 vs .8364 true positive rate and .8822 vs 0.8932 positive predictive value. Our performance indices compare favourably with state of the art nuclear segmentation approaches for digital pathology images.

A robust nonlinear tissue-component discrimination method for computational pathology

Advances in digital pathology, specifically imaging instrumentation and data management, have allowed for the development of computational pathology tools with the potential for better, faster, and cheaper diagnosis, prognosis, and prediction of disease. Images of tissue sections frequently vary in color appearance across research laboratories and medical facilities because of differences in tissue fixation, staining protocols, and imaging instrumentation, leading to difficulty in the development of robust computational tools. To address this challenge, we propose a novel nonlinear tissue-component discrimination (NLTD) method to register automatically the color space of histopathology images and visualize individual tissue components, independent of color differences between images. Our results show that the NLTD method could effectively discriminate different tissue components from different types of tissues prepared at different institutions. Further, we demonstrate that NLTD can improve the accuracy of nuclear detection and segmentation algorithms, compared with using conventional color deconvolution methods, and can quantitatively analyze immunohistochemistry images. Together, the NLTD method is objective, robust, and effective, and can be easily implemented in the emerging field of computational pathology.

Measuring Blood Glucose Concentrations in Photometric Glucometers Requiring Very Small Sample Volumes

Glucometers present an important self-monitoring tool for diabetes patients and, therefore, must exhibit high accuracy as well as good usability features. Based on an invasive photometric measurement principle that drastically reduces the volume of the blood sample needed from the patient, we present a framework that is capable of dealing with small blood samples, while maintaining the required accuracy. The framework consists of two major parts: 1) image segmentation; and 2) convergence detection. Step 1 is based on iterative mode-seeking methods to estimate the intensity value of the region of interest. We present several variations of these methods and give theoretical proofs of their convergence. Our approach is able to deal with changes in the number and position of clusters without any prior knowledge. Furthermore, we propose a method based on sparse approximation to decrease the computational load, while maintaining accuracy. Step 2 is achieved by employing temporal tracking and prediction, herewith decreasing the measurement time, and, thus, improving usability. Our framework is tested on several real datasets with different characteristics. We show that we are able to estimate the underlying glucose concentration from much smaller blood samples than is currently state of the art with sufficient accuracy according to the most recent ISO standards and reduce measurement time significantly compared to state-of-the-art methods.

High-throughput histopathological image analysis via robust cell segmentation and hashing

Computer-aided diagnosis of histopathological images usually requires to examine all cells for accurate diagnosis. Traditional computational methods may have efficiency issues when performing cell-level analysis. In this paper, we propose a robust and scalable solution to enable such analysis in a real-time fashion. Specifically, a robust segmentation method is developed to delineate cells accurately using Gaussian-based hierarchical voting and repulsive balloon model. A large-scale image retrieval approach is also designed to examine and classify each cell of a testing image by comparing it with a massive database, e.g., half-million cells extracted from the training dataset. We evaluate this proposed framework on a challenging and important clinical use case, i.e., differentiation of two types of lung cancers (the adenocarcinoma and squamous carcinoma), using thousands of lung microscopic tissue images extracted from hundreds of patients. Our method has achieved promising accuracy and running time by searching among half-million cells .

Identifying in vivo DCE MRI markers associated with microvessel architecture and gleason grades of prostate cancer

BACKGROUND

To identify computer extracted in vivo dynamic contrast enhanced (DCE) MRI markers associated with quantitative histomorphometric (QH) characteristics of microvessels and Gleason scores (GS) in prostate cancer.

METHODS

This study considered retrospective data from 23 biopsy confirmed prostate cancer patients who underwent 3 Tesla multiparametric MRI before radical prostatectomy (RP). Representative slices from RP specimens were stained with vascular marker CD31. Tumor extent was mapped from RP sections onto DCE MRI using nonlinear registration methods. Seventy-seven microvessel QH features and 18 DCE MRI kinetic features were extracted and evaluated for their ability to distinguish low from intermediate and high GS. The effect of temporal sampling on kinetic features was assessed and correlations between those robust to temporal resolution and microvessel features discriminative of GS were examined.

RESULTS

A total of 12 microvessel architectural features were discriminative of low and intermediate/high grade tumors with area under the receiver operating characteristic curve (AUC) > 0.7. These features were most highly correlated with mean washout gradient (WG) (max rho = -0.62). Independent analysis revealed WG to be moderately robust to temporal resolution (intraclass correlation coefficient [ICC] = 0.63) and WG variance, which was poorly correlated with microvessel features, to be predictive of low grade tumors (AUC = 0.77). Enhancement ratio was the most robust (ICC = 0.96) and discriminative (AUC = 0.78) kinetic feature but was moderately correlated with microvessel features (max rho = -0.52).

CONCLUSION

Computer extracted features of prostate DCE MRI appear to be correlated with microvessel architecture and may be discriminative of low versus intermediate and high GS.

Sparse Non-negative Matrix Factorization (SNMF) based color unmixing for breast histopathological image analysis

Color deconvolution has emerged as a popular method for color unmixing as a pre-processing step for image analysis of digital pathology images. One deficiency of this approach is that the stain matrix is pre-defined which requires specific knowledge of the data. This paper presents an unsupervised Sparse Non-negative Matrix Factorization (SNMF) based approach for color unmixing. We evaluate this approach for color unmixing of breast pathology images. Compared to Non-negative Matrix Factorization (NMF), the sparseness constraint imposed on coefficient matrix aims to use more meaningful representation of color components for separating stained colors. In this work SNMF is leveraged for decomposing pure stained color in both Immunohistochemistry (IHC) and Hematoxylin and Eosin (H&E) images. SNMF is compared with Principle Component Analysis (PCA), Independent Component Analysis (ICA), Color Deconvolution (CD), and Non-negative Matrix Factorization (NMF) based approaches. SNMF demonstrated improved performance in decomposing brown diaminobenzidine (DAB) component from 36 IHC images as well as accurately segmenting about 1400 nuclei and 500 lymphocytes from H & E images.

Novel genotype-phenotype associations in human cancers enabled by advanced molecular platforms and computational analysis of whole slide images

Technological advances in computing, imaging, and genomics have created new opportunities for exploring relationships between histology, molecular events, and clinical outcomes using quantitative methods. Slide scanning devices are now capable of rapidly producing massive digital image archives that capture histological details in high resolution. Commensurate advances in computing and image analysis algorithms enable mining of archives to extract descriptions of histology, ranging from basic human annotations to automatic and precisely quantitative morphometric characterization of hundreds of millions of cells. These imaging capabilities represent a new dimension in tissue-based studies, and when combined with genomic and clinical endpoints, can be used to explore biologic characteristics of the tumor microenvironment and to discover new morphologic biomarkers of genetic alterations and patient outcomes. In this paper, we review developments in quantitative imaging technology and illustrate how image features can be integrated with clinical and genomic data to investigate fundamental problems in cancer. Using motivating examples from the study of glioblastomas (GBMs), we demonstrate how public data from The Cancer Genome Atlas (TCGA) can serve as an open platform to conduct in silico tissue-based studies that integrate existing data resources. We show how these approaches can be used to explore the relation of the tumor microenvironment to genomic alterations and gene expression patterns and to define nuclear morphometric features that are predictive of genetic alterations and clinical outcomes. Challenges, limitations, and emerging opportunities in the area of quantitative imaging and integrative analyses are also discussed.

Automatic Myonuclear Detection in Isolated Single Muscle Fibers Using Robust Ellipse Fitting and Sparse Representation

Accurate and robust detection of myonuclei in isolated single muscle fibers is required to calculate myonuclear domain size. However, this task is challenging because: 1) shape and size variations of the nuclei, 2) overlapping nuclear clumps, and 3) multiple z-stack images with out-of-focus regions. In this paper, we have proposed a novel automatic detection algorithm to robustly quantify myonuclei in isolated single skeletal muscle fibers. The original z-stack images are first converted into one all-in-focus image using multi-focus image fusion. A sufficient number of ellipse fitting hypotheses are then generated from the myonuclei contour segments using heteroscedastic errors-in-variables (HEIV) regression. A set of representative training samples and a set of discriminative features are selected by a two-stage sparse model. The selected samples with representative features are utilized to train a classifier to select the best candidates. A modified inner geodesic distance based mean-shift clustering algorithm is used to produce the final nuclei detection results. The proposed method was extensively tested using 42 sets of z-stack images containing over 1,500 myonuclei. The method demonstrates excellent results that are better than current state-of-the-art approaches.

Quantifying local heterogeneity via morphologic scale: Distinguishing tumoral from stromal regions

INTRODUCTION

The notion of local scale was introduced to characterize varying levels of image detail so that localized image processing tasks could be performed while simultaneously yielding a globally optimal result. In this paper, we have presented the methodological framework for a novel locally adaptive scale definition, morphologic scale (MS), which is different from extant local scale definitions in that it attempts to characterize local heterogeneity as opposed to local homogeneity.

METHODS

At every point of interest, the MS is determined as a series of radial paths extending outward in the direction of least resistance, navigating around obstructions. Each pixel can then be directly compared to other points of interest via a rotationally invariant quantitative feature descriptor, determined by the application of Fourier descriptors to the collection of these paths.

RESULTS

OUR GOAL IS TO DISTINGUISH TUMOR AND STROMAL TISSUE CLASSES IN THE CONTEXT OF FOUR DIFFERENT DIGITIZED PATHOLOGY DATASETS: prostate tissue microarrays (TMAs) stained with hematoxylin and eosin (HE) (44 images) and TMAs stained with only hematoxylin (H) (44 images), slide mounts of ovarian H (60 images), and HE breast cancer (51 images) histology images. Classification performance over 50 cross-validation runs using a Bayesian classifier produced mean areas under the curve of 0.88 ± 0.01 (prostate HE), 0.87 ± 0.02 (prostate H), 0.88 ± 0.01 (ovarian H), and 0.80 ± 0.01 (breast HE).

CONCLUSION

For each dataset listed in Table 3, we randomly selected 100 points per image, and using the procedure described in Experiment 1, we attempted to separate them as belonging to stroma or epithelium.