Banff Digital Pathology Working Group: Image Bank, Artificial Intelligence Algorithm, and Challenge Trial Developments

The Banff Digital Pathology Working Group (DPWG) was established with the goal to establish a digital pathology repository; develop, validate, and share models for image analysis; and foster collaborations using regular videoconferencing. During the calls, a variety of artificial intelligence (AI)-based support systems for transplantation pathology were presented. Potential collaborations in a competition/trial on AI applied to kidney transplant specimens, including the DIAGGRAFT challenge (staining of biopsies at multiple institutions, pathologists' visual assessment, and development and validation of new and pre-existing Banff scoring algorithms), were also discussed. To determine the next steps, a survey was conducted, primarily focusing on the feasibility of establishing a digital pathology repository and identifying potential hosts. Sixteen of the 35 respondents (46%) had access to a server hosting a digital pathology repository, with 2 respondents that could serve as a potential host at no cost to the DPWG. The 16 digital pathology repositories collected specimens from various organs, with the largest constituent being kidney (n = 12,870 specimens). A DPWG pilot digital pathology repository was established, and there are plans for a competition/trial with the DIAGGRAFT project. Utilizing existing resources and previously established models, the Banff DPWG is establishing new resources for the Banff community.

Erratum: 89 Bridging Cell Biology and Engineering Sciences: Interdisciplinary Team-based Training in Computational Pathology - ERRATUM

[This corrects the article DOI: 10.1017/cts.2023.172.].

Discovery of Novel Digital Biomarkers for Type 2 Diabetic Nephropathy Classification via Integration of Urinary Proteomics and Pathology

Background

The heterogeneous phenotype of diabetic nephropathy (DN) from type 2 diabetes complicates appropriate treatment approaches and outcome prediction. Kidney histology helps diagnose DN and predict its outcomes, and an artificial intelligence (AI)-based approach will maximize clinical utility of histopathological evaluation. Herein, we addressed whether AI-based integration of urine proteomics and image features improves DN classification and its outcome prediction, altogether augmenting and advancing pathology practice.

Methods

We studied whole slide images (WSIs) of periodic acid-Schiff-stained kidney biopsies from 56 DN patients with associated urinary proteomics data. We identified urinary proteins differentially expressed in patients who developed end-stage kidney disease (ESKD) within two years of biopsy. Extending our previously published human-AI-loop pipeline, six renal sub-compartments were computationally segmented from each WSI. Hand-engineered image features for glomeruli and tubules, and urinary protein measurements, were used as inputs to deep-learning frameworks to predict ESKD outcome. Differential expression was correlated with digital image features using the Spearman rank sum coefficient.

Results

A total of 45 urinary proteins were differentially detected in progressors, which was most predictive of ESKD (AUC=0.95), while tubular and glomerular features were less predictive (AUC=0.71 and AUC=0.63, respectively). Accordingly, a correlation map between canonical cell-type proteins, such as epidermal growth factor and secreted phosphoprotein 1, and AI-based image features was obtained, which supports previous pathobiological results.

Conclusions

Computational method-based integration of urinary and image biomarkers may improve the pathophysiological understanding of DN progression as well as carry clinical implications in histopathological evaluation.

Integrating image analysis with single cell RNA-seq data to study podocyte-specific changes in diabetic kidney disease

Podocyte injury plays a crucial role in the progression of diabetic kidney disease (DKD). Injured podocytes demonstrate variations in nuclear shape and chromatin distribution. These morphometric changes have not yet been quantified in podocytes. Furthermore, the molecular mechanisms underlying these variations are poorly understood. Recent advances in omics have shed new lights into the biological mechanisms behind podocyte injury. However, there currently exists no study analyzing the biological mechanisms underlying podocyte morphometric variations during DKD. First, to study the importance of nuclear morphometrics, we performed morphometric quantification of podocyte nuclei from whole slide images of renal tissue sections obtained from murine models of DKD. Our results indicated that podocyte nuclear textural features demonstrate statistically significant difference in diabetic podocytes when compared to control. Additionally, the morphometric features demonstrated the existence of multiple subpopulations of podocytes suggesting a potential cause for their varying response to injury. Second, to study the underlying pathophysiology, we employed single cell RNA sequencing data from the murine models. Our results again indicated five subpopulations of podocytes in control and diabetic mouse models, validating the morphometrics-based results. Additionally, gene set enrichment analysis revealed epithelial to mesenchymal transition and apoptotic pathways in a subgroup of podocytes exclusive to diabetic mice, suggesting the molecular mechanism behind injury. Lastly, our results highlighted two distinct lineages of podocytes in control and diabetic cases suggesting a phenotypical change in podocytes during DKD. These results suggest that textural variations in podocyte nuclei may be key to understanding the pathophysiology behind podocyte injury.

HistoLens: A generalizable tool for increasing accessibility and interpretability of quantitative analyses in digital pathology

The incorporation of automated computational tools has a great amount of potential to positively influence the field of pathology. However, pathologists and regulatory agencies are reluctant to trust the output of complex models such as Convolutional Neural Networks (CNNs) due to their usual implementation as black-box tools. Increasing the interpretability of quantitative analyses is a critical line of research in order to increase the adoption of modern Machine Learning (ML) pipelines in clinical environments. Towards that goal, we present HistoLens, a Graphical User Interface (GUI) designed to facilitate quantitative assessments of datasets of annotated histological compartments. Additionally, we introduce the use of hand-engineered feature visualizations to highlight regions within each structure that contribute to particular feature values. These feature visualizations can then be paired with feature hierarchy determinations in order to view which regions within an image are significant to a particular sub-group within the dataset. As a use case, we analyzed a dataset of old and young mouse kidney sections with glomeruli annotated. We highlight some of the functional components within HistoLens that allow non-computational experts to efficiently navigate a new dataset as well as allowing for easier transition to downstream computational analyses.

PodoSighter: A Cloud-Based Tool for Label-Free Podocyte Detection in Kidney Whole-Slide Images

BACKGROUND

Podocyte depletion precedes progressive glomerular damage in several kidney diseases. However, the current standard of visual detection and quantification of podocyte nuclei from brightfield microscopy images is laborious and imprecise.

METHODS

We have developed PodoSighter, an online cloud-based tool, to automatically identify and quantify podocyte nuclei from giga-pixel brightfield whole-slide images (WSIs) using deep learning. Ground-truth to train the tool used immunohistochemically or immunofluorescence-labeled images from a multi-institutional cohort of 122 histologic sections from mouse, rat, and human kidneys. To demonstrate the generalizability of our tool in investigating podocyte loss in clinically relevant samples, we tested it in rodent models of glomerular diseases, including diabetic kidney disease, crescentic GN, and dose-dependent direct podocyte toxicity and depletion, and in human biopsies from steroid-resistant nephrotic syndrome and from human autopsy tissues.

RESULTS

The optimal model yielded high sensitivity/specificity of 0.80/0.80, 0.81/0.86, and 0.80/0.91, in mouse, rat, and human images, respectively, from periodic acid-Schiff-stained WSIs. Furthermore, the podocyte nuclear morphometrics extracted using PodoSighter were informative in identifying diseased glomeruli. We have made PodoSighter freely available to the general public as turnkey plugins in a cloud-based web application for end users.

CONCLUSIONS

Our study demonstrates an automated computational approach to detect and quantify podocyte nuclei in standard histologically stained WSIs, facilitating podocyte research, and enabling possible future clinical applications.

Lupus podocytopathy superimposed on diabetic glomerulosclerosis: A case report

RATIONALE

Lupus podocytopathy (LP) is an entity that is increasingly being reported in the literature on systemic lupus erythematosus (SLE). LP is characterized by nephrotic syndrome in SLE patients with diffuse glomerular podocyte foot process effacement and no immune complex deposits along the capillary loops. Histologically, LP typically mimics minimal change disease or primary focal segmental glomerulosclerosis (FSGS) on a background of ISN/RPS class I or II lupus nephritis. In situations where there are coexistent glomerular diseases, however, LP may be easily masked by background lesions and overlapping clinical symptoms.

PATIENT CONCERNS

We report the case of a 24-year-old woman with type I diabetes, hypertension, psoriasis/rash, and intermittent arthritis who presented with abrupt onset of severe nephrotic proteinuria and renal insufficiency. Renal biopsy revealed nodular glomerulosclerosis and FSGS. Immune deposits were not identified by immunofluorescence or electron microscopy. Ultrastructurally, there was diffuse glomerular basement membrane thickening and over 90% podocyte foot process effacement. With no prior established diagnosis of SLE, the patient was initially diagnosed with diabetic nephropathy with coexistent FSGS, and the patient was started on angiotensin-converting enzyme inhibitors (ACEI) and diuretics. However, nephrotic proteinuria persisted and renal function deteriorated. The patient concurrently developed hemolytic anemia with pancytopenia.

DIAGNOSES

Subsequent to the biopsy, serologic results showed positive autoantibodies against double strand DNA (dsDNA), Smith antigen, ribonucleoprotein (RNP), and Histone. A renal biopsy was repeated, revealing essentially similar findings to those of the previous biopsy. Integrating serology and clinical presentation, SLE was favored. The pathology findings were re-evaluated and considered to be most consistent with LP and coexistent diabetic nephropathy, with superimposed FSGS either as a component of LP or as a lesion secondary to diabetes or hypertension.

INTERVENTIONS

The patient was started on high-dose prednisone at 60 mg/day, with subsequent addition of mycophenolate mofetil and ACEI, while prednisone was gradually tapered.

OUTCOMES

The patient's proteinuria, serum creatinine, complete blood counts, skin rash, and arthritis were all significantly improved.

CONCLUSION

The diagnosis of LP when confounded by other glomerular diseases that may cause nephrotic syndrome can be challenging. Sufficient awareness of this condition is necessary for the appropriate diagnosis and treatment.

A Distributed System Improves Inter-Observer and AI Concordance in Annotating Interstitial Fibrosis and Tubular Atrophy

Histologic examination of interstitial fibrosis and tubular atrophy (IFTA) is critical to determine the extent of irreversible kidney injury in renal disease. The current clinical standard involves pathologist's visual assessment of IFTA, which is prone to inter-observer variability. To address this diagnostic variability, we designed two case studies (CSs), including seven pathologists, using HistomicsTK- a distributed system developed by Kitware Inc. (Clifton Park, NY). Twenty-five whole slide images (WSIs) were classified into a training set of 21 and a validation set of four. The training set was composed of seven unique subsets, each provided to an individual pathologist along with four common WSIs from the validation set. In CS 1, all pathologists individually annotated IFTA in their respective slides. These annotations were then used to train a deep learning algorithm to computationally segment IFTA. In CS 2, manual and computational annotations from CS 1 were first reviewed by the annotators to improve concordance of IFTA annotation. Both the manual and computational annotation processes were then repeated as in CS1. The inter-observer concordance in the validation set was measured by Krippendorff's alpha (KA). The KA for the seven pathologists in CS1 was 0.62 with CI [0.57, 0.67], and after reviewing each other's annotations in CS2, 0.66 with CI [0.60, 0.72]. The respective CS1 and CS2 KA were 0.58 with CI [0.52, 0.64] and 0.63 with CI [0.56, 0.69] when including the deep learner as an eighth annotator. These results suggest that our designed annotation framework refines agreement of spatial annotation of IFTA and demonstrates a human-AI approach to significantly improve the development of computational models.

The New York State SARS-CoV-2 Testing Consortium: Regional Communication in Response to the COVID-19 Pandemic

The COVID-19 pandemic, caused by severe acute respiratory syndrome coronavirus 2, created an unprecedented need for comprehensive laboratory testing of populations, in order to meet the needs of medical practice and to guide the management and functioning of our society. With the greater New York metropolitan area as an epicenter of this pandemic beginning in March 2020, a consortium of laboratory leaders from the assembled New York academic medical institutions was formed to help identify and solve the challenges of deploying testing. This report brings forward the experience of this consortium, based on the real-world challenges which we encountered in testing patients and in supporting the recovery effort to reestablish the health care workplace. In coordination with the Greater New York Hospital Association and with the public health laboratory of New York State, this consortium communicated with state leadership to help inform public decision-making addressing the crisis. Through the length of the pandemic, the consortium has been a critical mechanism for sharing experience and best practices in dealing with issues including the following: instrument platforms, sample sources, test performance, pre- and post-analytical issues, supply chain, institutional testing capacity, pooled testing, biospecimen science, and research. The consortium also has been a mechanism for staying abreast of state and municipal policies and initiatives, and their impact on institutional and laboratory operations. The experience of this consortium may be of value to current and future laboratory professionals and policy-makers alike, in dealing with major events that impact regional laboratory services.

Neutrophil Extracellular Traps (NETs): An unexplored territory in renal pathobiology, a pilot computational study

In the age of modern medicine and artificial intelligence, image analysis and machine learning have revolutionized diagnostic pathology, facilitating the development of computer aided diagnostics (CADs) which circumvent prevalent diagnostic challenges. Although CADs will expedite and improve the precision of clinical workflow, their prognostic potential, when paired with clinical outcome data, remains indeterminate. In high impact renal diseases, such as diabetic nephropathy and lupus nephritis (LN), progression often occurs rapidly and without immediate detection, due to the subtlety of structural changes in transient disease states. In such states, exploration of quantifiable image biomarkers, such as Neutrophil Extracellular Traps (NETs), may reveal alternative progression measures which correlate with clinical data. NETs have been implicated in LN as immunogenic cellular structures, whose occurrence and dysregulation results in excessive tissue damage and lesion manifestation. We propose that renal biopsy NET distribution will function as a discriminate, predictive biomarker in LN, and will supplement existing classification schemes. We have developed a computational pipeline for segmenting NET-like structures in LN biopsies. NET-like structures segmented from our biopsies warrant further study as they appear pathologically distinct, and resemble non-lytic, vital NETs. Examination of corresponding H&E regions predominantly placed NET-like structures in glomeruli, including globally and segmentally sclerosed glomeruli, and tubule lumina. Our work continues to explore NET-like structures in LN biopsies by: 1.) revising detection and analytical methods based on evolving NETs definitions, and 2.) cataloguing NET morphology in order to implement supervised classification of NET-like structures in histopathology images.

The Presence and Location of Podocytes in Glomeruli as Affected by Diabetes Mellitus

The primary purpose of the kidney, specifically the glomerulus, is filtration. Filtration is accomplished through the glomerular filtration barrier, which consists of the fenestrated endothelium, glomerular basement membrane, and specialized epithelial cells called podocytes. In pathologic states, such as Diabetes Mellitus (DM) and diabetic kidney disease (DKD), variable glomerular conditions result in podocyte injury and depletion, followed by progressive glomerular injury and DKD progression. In this work we quantified glomerulus and podocyte structural changes in histopathology image data derived from a murine model of DM. Using a variety of image processing techniques, we studied changes in podocyte morphology and intra-glomerular distribution across healthy, mild DM, and DM glomeruli. Our feature analysis provided feature trends which we believe are reflective of DKD pathology; while glomerular area peaked in mild DM, average podocyte number and distance from the urinary pole continued to decrease and increase, respectively, throughout DM. Ultimately, this study aims to augment the set of quantifiable image biomarkers used for evaluation of DKD progression in digital pathology, as well as underscore the importance of engineering biologically-inspired image features.

Generative modeling for renal microanatomy

Generative adversarial networks (GANs) have received immense attention in the field of machine learning for their potential to learn high-dimensional and real data distribution. These methods do not rely on any assumptions about the data distribution of the input sample and can generate real-like samples from latent vector space based on unsupervised learning. In the medical field, particularly, in digital pathology expert annotation and availability of a large set of training data is costly and the study of manifestations of various diseases is based on visual examination of stained slides. In clinical practice, various staining information is required to improve the pathological diagnosis process. But when the sampled tissue to be examined is limited, the final diagnosis made by the pathologist is based on limited stain styles. These limitations can be overcome by studying the usability and reliability of generative models in the field of digital pathology. To understand the usability of the generative models, we synthesize in an unsupervised manner, high resolution renal microanatomical structures like renal glomerulus in thin tissue histology images using state-of-art architectures like Deep Convolutional Generative Adversarial Network (DCGAN) and Enhanced Super-Resolution Generative Adversarial Network (ESRGAN). Successful generation of such structures will lead to obtaining a large set of labeled data for further developing supervised algorithms for disease classification and understanding progression. Our study suggests while GAN is able to attain formalin fixed and paraffin embedded tissue image quality, GAN requires further prior knowledge as input to model intrinsic micro-anatomical details, such as capillary wall, urinary pole, nuclei placement, suggesting developing semi-supervised architectures by using these above details as prior information. Also, the generative models can be used to create an artificial effect of staining without physically tampering the histopathological slide. To demonstrate this, we use a CycleGAN network to transform Hematoxylin and eosin (H&E) stain to Periodic acid-Schiff (PAS) stain and Jones methenamine silver (JMS) stain to PAS stain. In this way GAN can be employed to translate different renal pathology stain styles when the relevant staining information is not available in the clinical settings.

Quantitative Image Analysis of Human Epidermal Growth Factor Receptor 2 Immunohistochemistry for Breast Cancer: Guideline From the College of American Pathologists

CONTEXT.—

Advancements in genomic, computing, and imaging technology have spurred new opportunities to use quantitative image analysis (QIA) for diagnostic testing.

OBJECTIVE.—

To develop evidence-based recommendations to improve accuracy, precision, and reproducibility in the interpretation of human epidermal growth factor receptor 2 (HER2) immunohistochemistry (IHC) for breast cancer where QIA is used.

DESIGN.—

The College of American Pathologists (CAP) convened a panel of pathologists, histotechnologists, and computer scientists with expertise in image analysis, immunohistochemistry, quality management, and breast pathology to develop recommendations for QIA of HER2 IHC in breast cancer. A systematic review of the literature was conducted to address 5 key questions. Final recommendations were derived from strength of evidence, open comment feedback, expert panel consensus, and advisory panel review.

RESULTS.—

Eleven recommendations were drafted: 7 based on CAP laboratory accreditation requirements and 4 based on expert consensus opinions. A 3-week open comment period received 180 comments from more than 150 participants.

CONCLUSIONS.—

To improve accurate, precise, and reproducible interpretation of HER2 IHC results for breast cancer, QIA and procedures must be validated before implementation, followed by regular maintenance and ongoing evaluation of quality control and quality assurance. HER2 QIA performance, interpretation, and reporting should be supervised by pathologists with expertise in QIA.

Computational Segmentation and Classification of Diabetic Glomerulosclerosis

BACKGROUND

Pathologists use visual classification of glomerular lesions to assess samples from patients with diabetic nephropathy (DN). The results may vary among pathologists. Digital algorithms may reduce this variability and provide more consistent image structure interpretation.

METHODS

We developed a digital pipeline to classify renal biopsies from patients with DN. We combined traditional image analysis with modern machine learning to efficiently capture important structures, minimize manual effort and supervision, and enforce biologic prior information onto our model. To computationally quantify glomerular structure despite its complexity, we simplified it to three components consisting of nuclei, capillary lumina and Bowman spaces; and Periodic Acid-Schiff positive structures. We detected glomerular boundaries and nuclei from whole slide images using convolutional neural networks, and the remaining glomerular structures using an unsupervised technique developed expressly for this purpose. We defined a set of digital features which quantify the structural progression of DN, and a recurrent network architecture which processes these features into a classification.

RESULTS

Our digital classification agreed with a senior pathologist whose classifications were used as ground truth with moderate Cohen's kappa κ = 0.55 and 95% confidence interval [0.50, 0.60]. Two other renal pathologists agreed with the digital classification with κ₁ = 0.68, 95% interval [0.50, 0.86] and κ₂ = 0.48, 95% interval [0.32, 0.64]. Our results suggest computational approaches are comparable to human visual classification methods, and can offer improved precision in clinical decision workflows. We detected glomerular boundaries from whole slide images with 0.93±0.04 balanced accuracy, glomerular nuclei with 0.94 sensitivity and 0.93 specificity, and glomerular structural components with 0.95 sensitivity and 0.99 specificity.

CONCLUSIONS

Computationally derived, histologic image features hold significant diagnostic information that may augment clinical diagnostics.

Examining Structural Patterns and Causality in Diabetic Nephropathy using inter-Glomerular Distance and Bayesian Graphical Models

In diabetic nephropathy (DN), hyperglycemia drives a progressive thickening of glomerular filtration surfaces, increased cell proliferation as well as mesangial expansion and a constriction of capillary lumens. This leads to progressive structural changes inside the Glomeruli. In this work, we make a study of structural glomerular changes in DN from a graph-theoretic standpoint, using features extracted from Minimal Spanning Trees (MSTs) constructed over intercellular distances in order to classify the "packing signatures" of different DN stages. We further investigate the significance of the competing effects of Volume change measured here in 2Dimensional Pixel span area (Area) on one hand and increased cell proliferation on the other in determining the packing patterns. Towards that we formulate the problem as Dynamic Bayesian Network (DBN). From our preliminary results we do postulate that volume expansion caused by internal pressure as capillary lumens constriction has perhaps has a greater effect in the early stages.

An integrated iterative annotation technique for easing neural network training in medical image analysis

Neural networks promise to bring robust, quantitative analysis to medical fields. However, their adoption is limited by the technicalities of training these networks and the required volume and quality of human-generated annotations. To address this gap in the field of pathology, we have created an intuitive interface for data annotation and the display of neural network predictions within a commonly used digital pathology whole-slide viewer. This strategy used a 'human-in-the-loop' to reduce the annotation burden. We demonstrate that segmentation of human and mouse renal micro compartments is repeatedly improved when humans interact with automatically generated annotations throughout the training process. Finally, to show the adaptability of this technique to other medical imaging fields, we demonstrate its ability to iteratively segment human prostate glands from radiology imaging data.

Automated erythrocyte detection and classification from whole slide images

Blood smear is a crucial diagnostic aid. Quantification of both solitary and overlapping erythrocytes within these smears, directly from their whole slide images (WSIs), remains a challenge. Existing software designed to accomplish the computationally extensive task of hematological WSI analysis is too expensive and is widely unavailable. We have thereby developed a fully automated software targeted for erythrocyte detection and quantification from WSIs. We define an optimal region within the smear, which contains cells that are neither too scarce/damaged nor too crowded. We detect the optimal regions within the smear and subsequently extract all the cells from these regions, both solitary and overlapped, the latter of which undergoes a clump splitting before extraction. The performance was systematically tested on 28 WSIs of blood smears obtained from 13 different species from three classes of the subphylum vertebrata including birds, mammals, and reptiles. These data pose as an immensely variant erythrocyte database with diversity in size, shape, intensity, and textural features. Our method detected [Formula: see text] more cells than that detected from the traditional monolayer and resulted in a testing accuracy of 99.14% for the classification into their respective class (bird, mammal, or reptile) and a testing accuracy of 84.73% for the classification into their respective species. The results suggest the potential employment of this software for the diagnosis of hematological disorders, such as sickle cell anemia.

Outsourcing of Academic Clinical Laboratories: Experiences and Lessons From the Association of Pathology Chairs Laboratory Outsourcing Survey

American hospitals are increasingly turning to service outsourcing to reduce costs, including laboratory services. Studies of this practice have largely focused on nonacademic medical centers. In contrast, academic medical centers have unique practice environments and unique mission considerations. We sought to elucidate and analyze clinical laboratory outsourcing experiences in US academic medical centers. Seventeen chairs of pathology with relevant experience were willing to participate in in-depth interviews about their experiences. Anticipated financial benefits from joint venture arrangements often eroded after the initial years of the agreement, due to increased test pricing, management fees, duplication of services in support of inpatients, and lack of incentive for utilization control on the part of the for-profit partner. Outsourcing can preclude development of lucrative outreach programs; such programs were successfully launched in several cases after joint ventures were either avoided or terminated. Common complaints included poor test turnaround time and problems with test quality (especially in molecular pathology, microbiology, and flow cytometry), leading to clinician dissatisfaction. Joint ventures adversely affected retention of academically oriented clinical pathology faculty, with adverse effects on research and education, which further exacerbated clinician dissatisfaction due to lack of available consultative expertise. Resident education in pathology and in other disciplines (especially infectious disease) suffered both from lack of on-site laboratory capabilities and from lack of teaching faculty. Most joint ventures were initiated with little or no input from pathology leadership, and input from pathology leadership was seen to have been critical in those cases where such arrangements were declined or terminated.

Multi-radial LBP Features as a Tool for Rapid Glomerular Detection and Assessment in Whole Slide Histopathology Images

We demonstrate a simple and effective automated method for the localization of glomeruli in large (~1 gigapixel) histopathological whole-slide images (WSIs) of thin renal tissue sections and biopsies, using an adaptation of the well-known local binary patterns (LBP) image feature vector to train a support vector machine (SVM) model. Our method offers high precision (>90%) and reasonable recall (>70%) for glomeruli from WSIs, is readily adaptable to glomeruli from multiple species, including mouse, rat, and human, and is robust to diverse slide staining methods. Using 5 Intel(R) Core(TM) i7-4790 CPUs with 40 GB RAM, our method typically requires ~15 sec for training and ~2 min to extract glomeruli reproducibly from a WSI. Deploying a deep convolutional neural network trained for glomerular recognition in tandem with the SVM suffices to reduce false positives to below 3%. We also apply our LBP-based descriptor to successfully detect pathologic changes in a mouse model of diabetic nephropathy. We envision potential clinical and laboratory applications for this approach in the study and diagnosis of glomerular disease, and as a means of greatly accelerating the construction of feature sets to fuel deep learning studies into tissue structure and pathology.

Unsupervised labeling of glomerular boundaries using Gabor filters and statistical testing in renal histology

The glomerulus is the blood filtering unit of the kidney. Each human kidney contains [Formula: see text] glomeruli. Several renal conditions originate from structural damage to glomerular microcompartments, such as proteinuria, the excessive loss of blood proteins into urine. The gold standard for evaluating structural damage in renal pathology is histopathological and immunofluorescence examination of needle biopsies under a light microscope. This method is limited by qualitative or semiquantitative manual scoring approaches to the evaluation of glomerular structural features. Computational quantification of equivalent features promises to improve the precision of glomerular structural analysis. One large obstacle to the computational quantification of renal tissue is the identification of complex glomerular boundaries automatically. To mitigate this issue, we developed a computational pipeline capable of extracting and exactly defining glomerular boundaries. Our method, composed of Gabor filtering, Gaussian blurring, statistical [Formula: see text]-testing, and distance transform, is able to accurately identify glomerular boundaries with mean sensitivity/specificity of [Formula: see text] and accuracy of 0.92, on [Formula: see text] glomeruli images stained with standard renal histological stains. Our method will simplify computational partitioning of glomerular microcompartments hidden within dense textural boundaries. Automatic quantification of glomeruli will streamline structural analysis in clinic and can pioneer real-time diagnoses and interventions for renal care.

Identification of Epstein-Barr Virus Lytic and Latent RNA Transcripts in Post-transplant Lymphoproliferative Disorder

Thirty-three specimens from 25 transplant recipients with Epstein-Barr virus-associated lymphoproliferative disease were studied by in situ hybridization for 2 lytic and 4 latent Epstein-Barr virus transcripts. All specimens were found to contain at least 1 latent transcript while 28 were positive for at least 1 lytic transcript. The amount of Epstein-Barr virus infection and lytic activity varied with histopathology and number of involved sites. Patients with localized polymorphous disease contained the lowest number of infected cells with an almost equal lytic:latent ratio. Disseminated polymorphous and single and multisite monomorphous specimens showed a large latent cell population. Minimal lytic activity was seen in single site monomorphous specimens, but disseminated monomorphous specimens showed the highest levels of lytic transcripts. Most post-transplant lymphoproliferative disorder specimens demonstrate lytic Epstein-Barr virus transcripts, although the majority of cells contain latent Epstein-Barr virus. Lytic activity is highest in patients with disseminated disease. Lytic Epstein-Barr virus infection may aid in the development and maintenance of lymphoproliferative disorders in transplant recipients.

A Non-epithelial Pseudosarcomatous Mural Nodule in a Mucinous Cystic Neoplasm of the Pancreas

A mucinous cystic neoplasm of indeterminate malignant potential was found to have a well-circumscribed, 3.1 cm pseudosarcomatous mural nodule, similar to those previously described in the ovary. The nodule contained reactive giant cells and intermediate to large-sized tumor cells with bizarre mitotic figures and nuclear atypia. The tumor cells were found to be of non-epithelial origin, based on multiple negative stains for cytokeratins and ultrastructural demonstration of osteoclastic and osteoblastic differentiation and absent desmosomes. This case report is the only description of a pseudosarcomatous mural nodule in a mucinous cystic neoplasm with non-epithelial origins.

Computational Pathology: A Path Ahead

CONTEXT

We define the scope and needs within the new discipline of computational pathology, a discipline critical to the future of both the practice of pathology and, more broadly, medical practice in general.

OBJECTIVE

To define the scope and needs of computational pathology.

DATA SOURCES

A meeting was convened in Boston, Massachusetts, in July 2014 prior to the annual Association of Pathology Chairs meeting, and it was attended by a variety of pathologists, including individuals highly invested in pathology informatics as well as chairs of pathology departments.

CONCLUSIONS

The meeting made recommendations to promote computational pathology, including clearly defining the field and articulating its value propositions; asserting that the value propositions for health care systems must include means to incorporate robust computational approaches to implement data-driven methods that aid in guiding individual and population health care; leveraging computational pathology as a center for data interpretation in modern health care systems; stating that realizing the value proposition will require working with institutional administrations, other departments, and pathology colleagues; declaring that a robust pipeline should be fostered that trains and develops future computational pathologists, for those with both pathology and nonpathology backgrounds; and deciding that computational pathology should serve as a hub for data-related research in health care systems. The dissemination of these recommendations to pathology and bioinformatics departments should help facilitate the development of computational pathology.

Supervised multi-view canonical correlation analysis (sMVCCA): integrating histologic and proteomic features for predicting recurrent prostate cancer

In this work, we present a new methodology to facilitate prediction of recurrent prostate cancer (CaP) following radical prostatectomy (RP) via the integration of quantitative image features and protein expression in the excised prostate. Creating a fused predictor from high-dimensional data streams is challenging because the classifier must 1) account for the "curse of dimensionality" problem, which hinders classifier performance when the number of features exceeds the number of patient studies and 2) balance potential mismatches in the number of features across different channels to avoid classifier bias towards channels with more features. Our new data integration methodology, supervised Multi-view Canonical Correlation Analysis (sMVCCA), aims to integrate infinite views of highdimensional data to provide more amenable data representations for disease classification. Additionally, we demonstrate sMVCCA using Spearman's rank correlation which, unlike Pearson's correlation, can account for nonlinear correlations and outliers. Forty CaP patients with pathological Gleason scores 6-8 were considered for this study. 21 of these men revealed biochemical recurrence (BCR) following RP, while 19 did not. For each patient, 189 quantitative histomorphometric attributes and 650 protein expression levels were extracted from the primary tumor nodule. The fused histomorphometric/proteomic representation via sMVCCA combined with a random forest classifier predicted BCR with a mean AUC of 0.74 and a maximum AUC of 0.9286. We found sMVCCA to perform statistically significantly (p < 0.05) better than comparative state-of-the-art data fusion strategies for predicting BCR. Furthermore, Kaplan-Meier analysis demonstrated improved BCR-free survival prediction for the sMVCCA-fused classifier as compared to histology or proteomic features alone.

Co-occurring gland angularity in localized subgraphs: predicting biochemical recurrence in intermediate-risk prostate cancer patients

Quantitative histomorphometry (QH) refers to the application of advanced computational image analysis to reproducibly describe disease appearance on digitized histopathology images. QH thus could serve as an important complementary tool for pathologists in interrogating and interpreting cancer morphology and malignancy. In the US, annually, over 60,000 prostate cancer patients undergo radical prostatectomy treatment. Around 10,000 of these men experience biochemical recurrence within 5 years of surgery, a marker for local or distant disease recurrence. The ability to predict the risk of biochemical recurrence soon after surgery could allow for adjuvant therapies to be prescribed as necessary to improve long term treatment outcomes. The underlying hypothesis with our approach, co-occurring gland angularity (CGA), is that in benign or less aggressive prostate cancer, gland orientations within local neighborhoods are similar to each other but are more chaotically arranged in aggressive disease. By modeling the extent of the disorder, we can differentiate surgically removed prostate tissue sections from (a) benign and malignant regions and (b) more and less aggressive prostate cancer. For a cohort of 40 intermediate-risk (mostly Gleason sum 7) surgically cured prostate cancer patients where half suffered biochemical recurrence, the CGA features were able to predict biochemical recurrence with 73% accuracy. Additionally, for 80 regions of interest chosen from the 40 studies, corresponding to both normal and cancerous cases, the CGA features yielded a 99% accuracy. CGAs were shown to be statistically signicantly () better at predicting BCR compared to state-of-the-art QH methods and postoperative prostate cancer nomograms.

Histostitcher™: An informatics software platform for reconstructing whole-mount prostate histology using the extensible imaging platform framework

CONTEXT

Co-registration of ex-vivo histologic images with pre-operative imaging (e.g., magnetic resonance imaging [MRI]) can be used to align and map disease extent, and to identify quantitative imaging signatures. However, ex-vivo histology images are frequently sectioned into quarters prior to imaging.

AIMS

This work presents Histostitcher™, a software system designed to create a pseudo whole mount histology section (WMHS) from a stitching of four individual histology quadrant images.

MATERIALS AND METHODS

Histostitcher™ uses user-identified fiducials on the boundary of two quadrants to stitch such quadrants. An original prototype of Histostitcher™ was designed using the Matlab programming languages. However, clinical use was limited due to slow performance, computer memory constraints and an inefficient workflow. The latest version was created using the extensible imaging platform (XIP™) architecture in the C++ programming language. A fast, graphics processor unit renderer was designed to intelligently cache the visible parts of the histology quadrants and the workflow was significantly improved to allow modifying existing fiducials, fast transformations of the quadrants and saving/loading sessions.

RESULTS

The new stitching platform yielded significantly more efficient workflow and reconstruction than the previous prototype. It was tested on a traditional desktop computer, a Windows 8 Surface Pro table device and a 27 inch multi-touch display, with little performance difference between the different devices.

CONCLUSIONS

Histostitcher™ is a fast, efficient framework for reconstructing pseudo WMHS from individually imaged quadrants. The highly modular XIP™ framework was used to develop an intuitive interface and future work will entail mapping the disease extent from the pseudo WMHS onto pre-operative MRI.

Computerized image analysis for identifying triple-negative breast cancers and differentiating them from other molecular subtypes of breast cancer on dynamic contrast-enhanced MR images: a feasibility study

PURPOSE

To determine the feasibility of using a computer-aided diagnosis (CAD) system to differentiate among triple-negative breast cancer, estrogen receptor (ER)-positive cancer, human epidermal growth factor receptor type 2 (HER2)-positive cancer, and benign fibroadenoma lesions on dynamic contrast material-enhanced (DCE) magnetic resonance (MR) images.

MATERIALS AND METHODS

This is a retrospective study of prospectively acquired breast MR imaging data collected from an institutional review board-approved, HIPAA-compliant study between 2002 and 2007. Written informed consent was obtained from all patients. The authors collected DCE MR images from 65 women with 76 breast lesions who had been recruited into a larger study of breast MR imaging. The women had triple-negative (n = 21), ER-positive (n = 25), HER2-positive (n = 18), or fibroadenoma (n = 12) lesions. All lesions were classified as Breast Imaging Reporting and Data System category 4 or higher on the basis of previous imaging. Images were subject to quantitative feature extraction, feed-forward feature selection by means of linear discriminant analysis, and lesion classification by using a support vector machine classifier. The area under the receiver operating characteristic curve (Az) was calculated for each of five lesion classification tasks involving triple-negative breast cancers.

RESULTS

For each pair-wise lesion type comparison, linear discriminant analysis helped identify the most discriminatory features, which in conjunction with a support vector machine classifier yielded an Az of 0.73 (95% confidence interval [CI]: 0.59, 0.87) for triple-negative cancer versus all non-triple-negative lesions, 0.74 (95% CI: 0.60, 0.88) for triple-negative cancer versus ER- and HER2-positive cancer, 0.77 (95% CI: 0.63, 0.91) for triple-negative versus ER-positive cancer, 0.74 (95% CI: 0.58, 0.89) for triple-negative versus HER2-positive cancer, and 0.97 (95% CI: 0.91, 1.00) for triple-negative cancer versus fibroadenoma.

CONCLUSION

Triple-negative cancers possess certain characteristic features on DCE MR images that can be captured and quantified with CAD, enabling good discrimination of triple-negative cancers from non-triple-negative cancers, as well as between triple-negative cancers and benign fibroadenomas. Such CAD algorithms may provide added diagnostic benefit in identifying the highly aggressive triple-negative cancer phenotype with DCE MR imaging in high-risk women.

Immunohistochemical Studies of Metastatic Germ-Cell Tumors in Retroperitoneal Dissection Specimens

Germ-cell tumors (GCTs) are the most common malignancies in adolescent and young men. These tumors are highly treatable, even at an advanced stage; therefore, accurate diagnosis is imperative. In this study, we evaluated immunohistochemical stains for SALL4, NANOG, glypican-3 (GPC3), D2-40, and CD30 with adequate control in retroperitoneal dissection specimens under the same laboratory conditions. The study groups included 31 cases of metastatic testicular GCTs with the following components: 11 seminomas, 14 embryonal carcinoma (ECs), 12 yolk sac tumor (YSTs), 8 teratomas, 10 cases of metastatic melanomas, 14 cases of malignant lymphomas, and 11 cases of metastatic, poorly differentiated carcinoma. SALL4 showed diffuse nuclear labeling for all seminomas, ECs, and YSTs. NANOG showed diffuse nuclear positivity in all seminomas and ECs. Metastatic carcinomas, melanomas, and malignant lymphomas were negative for these 2 markers. Gypican-3, D2-40, and CD30 showed sensitive staining for YSTs, seminomas, and ECs, respectively. In conclusion, SALL4 and NANOG are sensitive and specific markers for GCTs. GPC3, D2-40, and CD30 are sensitive but not specific for individual components of GCTs and may be useful in aiding in the differential diagnosis for the individual component of GCTs when the identity of GCT is established.

Microsatellite instability and TARBP2 mutation study in upper urinary tract urothelial carcinoma

Microsatellite instability (MSI) contributes to the tumorigenesis of upper urinary tract urothelial carcinomas (UUT-UCs). In this study, we first used MLH1 and MSH2 immunohistochemistry to identify patients with loss of expression of either or both of these proteins in 132 UUT-UCs. We found a total loss of MSH2 expression in 4 patients. MSI was evaluated using 5 markers in these 4 cases. All of the tumors had high MSI (MSI-H) status. Trans-activation responsive RNA-binding protein 2, an integral component of DICER1-containing complex, was a putative target of DNA mismatch repair deficiency. Truncating mutation has been identified in gastrointestinal cancers with MSI. No previous study has evaluated the mutation status of this gene in MSI UUT-UCs. In this study, we analyze the mutation of TARBP2 in MSI-H UUT-UCs with reverse transcription polymerase chain reaction. No truncating mutations were identified in the MSI-H UUT-UCs.

Fluorescence in situ hybridization study of chromosome abnormalities of upper urinary tract urothelial carcinoma in paraffin-embedded tissue

Urothelial carcinomas arising from the upper urinary tract (renal pelvis and ureter) are rare and few molecular genetic studies of these tumors have been conducted to date. We investigated hyperploidy at chromosomes 3, 7, and 17 using a multitarget fluorescence in situ hybridization system to identify genetic alterations in patients with urothelial carcinomas of the upper urinary tract. Chromosomal aberrations are seen most frequently in the high-grade tumors. A highly significant relationship was found between an increase in the percentage of hyperdiploidy and high grade for each chromosome (chromosome 3, P = 6 × 10(-4); chromosome 7, P = 2 × 10(-4); chromosome 17, P = 6 × 10(-5)). To determine whether these associations were independent for each chromosome, the correlation between percentage of hyperdiploidy for each pair of chromosomes was examined. In each case, the correlation was highly significant (R = 0.89-0.91). No statistically significant association was found between percentage of hyperdiploidy and tumor stage for any chromosome.

Supervised regularized canonical correlation analysis: integrating histologic and proteomic data for predicting biochemical failures

Multimodal data, especially imaging and non-imaging data, is being routinely acquired in the context of disease diagnostics; however computational challenges have limited the ability to quantitatively integrate imaging and non-imaging data channels with different dimensionalities for making diagnostic and prognostic predictions. The objective of this work is to create a common subspace to simultaneously accommodate both the imaging and non-imaging data, called a metaspace. This metaspace can be used to build a meta-classifier that produces better classification results than a classifier that is based on a single modality alone. In this paper, we present a novel Supervised Regularized Canonical Correlation Analysis (SRCCA) algorithm that (1) enables the quantitative integration of data from multiple modalities using a feature selection scheme, (2) is regularized, and (3) is computationally cheap. We leverage this SRCCA framework towards the fusion of proteomic and histologic image signatures for identifying prostate cancer patients at risk for biochemical recurrence following radical prostatectomy. For a cohort of 19 prostate cancer patients, SRCCA was able to yield a lower fused dimensional metaspace comprising both the histological and proteomic attributes. In conjunction with SRCCA, a random forest classifier was able to identify patients at risk for biochemical failure with a maximum accuracy of 93%. The classifier performance in the SRCCA space was statistically significantly higher compared to the fused data representations obtained either with Canonical Correlation Analysis (CCA) or Regularized CCA.

Accumulation of intrahepatic islet amyloid in a nonhuman primate transplant model

Islet amyloid is hypothesized to play a role in nonimmunologic transplanted islet graft loss. We performed a quantitative histologic analysis of liver biopsies from intrahepatic islet grafts transplanted in streptozotocin-induced diabetic cynomolgus macaques. Seven animals treated with antithymocyte globulin (ATG) and rapamycin or ATG and rituximab experienced islet graft rejection with lymphocytic infiltrates present on islet graft biopsies. Except for one case involving the oldest and largest donor where amyloid was present on initial biopsy 1 month after transplant, none of the six other cases with rejection contained amyloid, including one case biopsied serially to 25 months. In contrast, four out of six animals treated with ATG and rituximab and rapamycin had no evidence of rejection at the time of biopsy (two animals that discontinued rapamycin had mild periislet lymphocytes), and all four cases followed more than 4 months demonstrated amyloid deposition at subsequent time points. Amyloid severity increased with time after transplant (r = 0.68; P < 0.05) and with decreasing islet β-cell area (r = -0.68; P < 0.05). In two islet recipients with no evidence of rejection and still normoglycemic and insulin independent at the first detection of amyloid, β-cell secretory capacity declined over time coincident with increasing amyloid severity and decreasing β-cell area, with both animals eventually becoming hyperglycemic and insulin dependent. Transplanted islet amyloid also developed in autologous islets placed sc. These results indicate that in cynomolgus macaques, transplanted islets may accumulate amyloid over time associated with subsequent decline in β-cell mass and function and support the development of intrahepatic islet amyloid as a potential mechanism for nonimmunologic islet graft loss.

p53 in Pure Epithelioid PEComa

Pure epithelioid PEComa (PEP; so-called epithelioid angiomyolipoma) is rare and is more often associated with aggressive behaviors. The pathogenesis of PEP has been poorly understood. The authors studied p53 expression and gene mutation in PEPs by immunohistochemistry, single-strand conformation polymorphism, and direct sequencing in paraffin material from 8 PEPs. A group of classic angiomyolipomas (AMLs) were also analyzed for comparison. Five PEPs were from kidneys and 1 each from the heart, the liver, and the uterus. PEPs showed much stronger p53 nuclear staining (Allred score 6.4 ± 2.5) than the classic AML (2.3 ± 2.9) ( P < .01). There was no p53 single-strand conformation polymorphism identified in either the PEPs or the 8 classic AMLs. p53 mutation analyses by direct sequencing of exons 5 to 9 showed 4 mutations in 3 of 8 PEPs but none in any of the 8 classic AMLs. The mutations included 2 missense mutations in a hepatic PEComa and 2 silent mutations in 2 renal PEPs. Both the missense mutations in the hepatic PEComa involved the exon 5, one involving codon 165, with change from CAG to CAC (coding amino acid changed from glutamine to histidine), and the other involving codon 182, with change from TGC to TAC (coding amino acid changed from cysteine to tyrosine). The finding of stronger p53 expression and mutations in epithelioid angiomyolipomas might have contributed to their less predictable behavior. However, the abnormal p53 expression cannot be entirely explained by p53 mutations in the exons examined in the PEPs.

Integration of architectural and cytologic driven image algorithms for prostate adenocarcinoma identification

INTRODUCTION

The advent of digital slides offers new opportunities within the practice of pathology such as the use of image analysis techniques to facilitate computer aided diagnosis (CAD) solutions. Use of CAD holds promise to enable new levels of decision support and allow for additional layers of quality assurance and consistency in rendered diagnoses. However, the development and testing of prostate cancer CAD solutions requires a ground truth map of the cancer to enable the generation of receiver operator characteristic (ROC) curves. This requires a pathologist to annotate, or paint, each of the malignant glands in prostate cancer with an image editor software - a time consuming and exhaustive process. Recently, two CAD algorithms have been described: probabilistic pairwise Markov models (PPMM) and spatially-invariant vector quantization (SIVQ). Briefly, SIVQ operates as a highly sensitive and specific pattern matching algorithm, making it optimal for the identification of any epithelial morphology, whereas PPMM operates as a highly sensitive detector of malignant perturbations in glandular lumenal architecture.

METHODS

By recapitulating algorithmically how a pathologist reviews prostate tissue sections, we created an algorithmic cascade of PPMM and SIVQ algorithms as previously described by Doyle el al. [1] where PPMM identifies the glands with abnormal lumenal architecture, and this area is then screened by SIVQ to identify the epithelium.

RESULTS

The performance of this algorithm cascade was assessed qualitatively (with the use of heatmaps) and quantitatively (with the use of ROC curves) and demonstrates greater performance in the identification of malignant prostatic epithelium.

CONCLUSION

This ability to semi-autonomously paint nearly all the malignant epithelium of prostate cancer has immediate applications to future prostate cancer CAD development as a validated ground truth generator. In addition, such an approach has potential applications as a pre-screening/quality assurance tool.

Supervised regularized canonical correlation analysis: integrating histologic and proteomic measurements for predicting biochemical recurrence following prostate surgery

BACKGROUND

Multimodal data, especially imaging and non-imaging data, is being routinely acquired in the context of disease diagnostics; however, computational challenges have limited the ability to quantitatively integrate imaging and non-imaging data channels with different dimensionalities and scales. To the best of our knowledge relatively few attempts have been made to quantitatively fuse such data to construct classifiers and none have attempted to quantitatively combine histology (imaging) and proteomic (non-imaging) measurements for making diagnostic and prognostic predictions. The objective of this work is to create a common subspace to simultaneously accommodate both the imaging and non-imaging data (and hence data corresponding to different scales and dimensionalities), called a metaspace. This metaspace can be used to build a meta-classifier that produces better classification results than a classifier that is based on a single modality alone. Canonical Correlation Analysis (CCA) and Regularized CCA (RCCA) are statistical techniques that extract correlations between two modes of data to construct a homogeneous, uniform representation of heterogeneous data channels. In this paper, we present a novel modification to CCA and RCCA, Supervised Regularized Canonical Correlation Analysis (SRCCA), that (1) enables the quantitative integration of data from multiple modalities using a feature selection scheme, (2) is regularized, and (3) is computationally cheap. We leverage this SRCCA framework towards the fusion of proteomic and histologic image signatures for identifying prostate cancer patients at the risk of 5 year biochemical recurrence following radical prostatectomy.

RESULTS

A cohort of 19 grade, stage matched prostate cancer patients, all of whom had radical prostatectomy, including 10 of whom had biochemical recurrence within 5 years of surgery and 9 of whom did not, were considered in this study. The aim was to construct a lower fused dimensional metaspace comprising both the histological and proteomic measurements obtained from the site of the dominant nodule on the surgical specimen. In conjunction with SRCCA, a random forest classifier was able to identify prostate cancer patients, who developed biochemical recurrence within 5 years, with a maximum classification accuracy of 93%.

CONCLUSIONS

The classifier performance in the SRCCA space was found to be statistically significantly higher compared to the fused data representations obtained, not only from CCA and RCCA, but also two other statistical techniques called Principal Component Analysis and Partial Least Squares Regression. These results suggest that SRCCA is a computationally efficient and a highly accurate scheme for representing multimodal (histologic and proteomic) data in a metaspace and that it could be used to construct fused biomarkers for predicting disease recurrence and prognosis.

Image microarrays (IMA): Digital pathology's missing tool

Introduction:

The increasing availability of whole slide imaging (WSI) data sets (digital slides) from glass slides offers new opportunities for the development of computer-aided diagnostic (CAD) algorithms. With the all-digital pathology workflow that these data sets will enable in the near future, literally millions of digital slides will be generated and stored. Consequently, the field in general and pathologists, specifically, will need tools to help extract actionable information from this new and vast collective repository.

Methods:

To address this limitation, we designed and implemented a tool (dCORE) to enable the systematic capture of image tiles with constrained size and resolution that contain desired histopathologic features.

Results:

In this communication, we describe a user-friendly tool that will enable pathologists to mine digital slides archives to create image microarrays (IMAs). IMAs are to digital slides as tissue microarrays (TMAs) are to cell blocks. Thus, a single digital slide could be transformed into an array of hundreds to thousands of high quality digital images, with each containing key diagnostic morphologies and appropriate controls. Current manual digital image cut-and-paste methods that allow for the creation of a grid of images (such as an IMA) of matching resolutions are tedious.

Conclusion:

The ability to create IMAs representing hundreds to thousands of vetted morphologic features has numerous applications in education, proficiency testing, consensus case review, and research. Lastly, in a manner analogous to the way conventional TMA technology has significantly accelerated in situ studies of tissue specimens use of IMAs has similar potential to significantly accelerate CAD algorithm development.

HistoStitcher(©): an interactive program for accurate and rapid reconstruction of digitized whole histological sections from tissue fragments

We present an interactive program called HistoStitcher(©) for accurate and rapid reassembly of histology fragments into a pseudo-whole digitized histological section. HistoStitcher(©) provides both an intuitive graphical interface to assist the operator in performing the stitch of adjacent histology fragments by selecting pairs of anatomical landmarks, and a set of computational routines for determining and applying an optimal linear transformation to generate the stitched image. Reconstruction of whole histological sections from images of slides containing smaller fragments is required in applications where preparation of whole sections of large tissue specimens is not feasible or efficient, and such whole mounts are required to facilitate (a) disease annotation and (b) image registration with radiological images. Unlike manual reassembly of image fragments in a general purpose image editing program (such as Photoshop), HistoStitcher(©) provides memory efficient operation on high resolution digitized histology images and a highly flexible stitching process capable of producing more accurate results in less time. Further, by parameterizing the series of transformations determined by the stitching process, the stitching parameters can be saved, loaded at a later time, refined, or reapplied to multi-resolution scans, or quickly transmitted to another site. In this paper, we describe in detail the design of HistoStitcher(©) and the mathematical routines used for calculating the optimal image transformation, and demonstrate its operation for stitching high resolution histology quadrants of a prostate specimen to form a digitally reassembled whole histology section, for 8 different patient studies. To evaluate stitching quality, a 6 point scoring scheme, which assesses the alignment and continuity of anatomical structures important for disease annotation, is employed by three independent expert pathologists. For 6 studies compared with this scheme, reconstructed sections generated via HistoStitcher(©) scored higher than reconstructions generated by an expert pathologist using Photoshop.

Association of HLA polymorphisms with post-transplant lymphoproliferative disorder in solid-organ transplant recipients

The association between HLA polymorphisms and PTLD was investigated in a case-control study, comparing 110 predominantly adult solid-organ transplant recipients who developed PTLD to 5601 who did not. Donor and recipient HLA were analyzed. We detected a significant association between recipient HLA-A26 and the development of PTLD (OR 2.74; p = 0.0007). In Caucasian recipients, both recipient and donor HLA-A26 were independently associated with development of PTLD (recipient A26 OR 2.99; p = 0.0004, donor A26 OR 2.81; p = 0.002). Analysis of HLA-A and -B haplotypes revealed that recipient HLA-A26, B38 haplotype was strongly correlated with a higher incidence of EBV-positive PTLD (OR 3.99; p = 0.001). The common ancestral haplotype HLA-A1, B8, DR3, when carried by the donor, was protective against PTLD (OR 0.41; p = 0.05). Several other HLA specificities demonstrated associations with clinical and pathological characteristics as well as survival. These findings demonstrate the importance of HLA polymorphisms in modulating the risk for PTLD, and may be useful in risk stratification and development of monitoring and prophylaxis strategies.

Repeat prostate biopsy and the incremental risk of clinically insignificant prostate cancer

OBJECTIVES

To determine the incremental risk of diagnosis of clinically insignificant prostate cancer with serial prostate biopsies.

METHODS

We reviewed our institutional radical prostatectomy (RP) database comprising 2411 consecutive patients undergoing RP. We then stratified patients by the prostate biopsy on which their cancer was diagnosed and correlated biopsy number with the risk of clinically insignificant disease and adverse pathology at radical prostatectomy.

RESULTS

A total of 1867 (77.4%), 281 (11.9%), and 175 (7.3%) patients underwent 1, 2, and 3 or more prostate biopsies, respectively, before RP. Increasing number of prostate biopsies was associated with increasing prostate volume (P <.01), prostate-specific antigen (P <.01), associated prostate intraepithelial neoplasia (P <.01), and increased likelihood of clinical Gleason 6 or less disease (P <.01). On pathologic analysis, increasing number of prostate biopsies was associated with increased risk of low-volume (P <.01), organ-confined (P <.01) disease. The risk of clinically insignificant disease was found to be 31.1%, 43.8%, and 46.8% in those undergoing 1, 2, and 3+ prostate biopsies, respectively. Conversely, the risk of adverse pathology was found to be 64.6%, 53.0%, and 52.0% in those undergoing 1, 2, and 3+ prostate biopsies, respectively.

CONCLUSIONS

Patients undergoing multiple prostate biopsies before RP are more likely to harbor clinically insignificant prostate cancer than those who only undergo 1 biopsy before resection. Nonetheless, the risk of adverse pathology in patients undergoing serial biopsies remains significant. The increased risk of prostate cancer overdiagnosis and overtreatment must be balanced with the continued risk of clinically significant disease when counseling patients regarding serial biopsies.

Impact of adjuvant chemotherapy on patients with lymph node metastasis at the time of radical cystectomy

INTRODUCTION

Radical cystectomy (RC) remains the gold standard treatment for patients with muscle-invasive bladder cancer. Unfortunately, a significant proportion of patients will have lymph node involvement at the time of RC. We set out to determine the impact of adjuvant cisplatin-based chemotherapy (AC) in a cohort of lymph node positive patients following RC.

PATIENTS AND METHODS

We reviewed our RC database and isolated patients with lymph node positive disease at the time of RC. Univariate and multivariable analysis was performed to identify predictors of poor outcome in patients receiving AC. Overall survival (OS), disease specific survival (DSS) and recurrence free survival (RFS) were calculated for those patients who received AC compared to those who did not.

RESULTS

Of the 316 patients, we identified 85 patients with metastatic lymph node involvement at the time of RC. Fifty-five (65%) of these patients received AC. Median follow up was 46 months. On multivariable analysis lymph node positive patients receiving AC had significantly improved OS, DSS and RFS compared to patients who did not receive AC (p = 0.031, p = 0.028, p = 0.004). The delivery of AC conferred the greatest recurrence-free, disease-specific, and overall survival advantages to those with lymph node densities (LND) of < 20% with (p = 0.016, p = 0.011, p = 0.007, respectively).

CONCLUSION

AC administered to patients with known lymph node metastasis conferred a significant survival advantage compared to observation. Furthermore, a LND of < 20% predicts of a more favorable response to AC. Further studies in larger patient populations are warranted to reveal the exact impact of AC in this subset of patients.

High-throughput detection of prostate cancer in histological sections using probabilistic pairwise Markov models

In this paper we present a high-throughput system for detecting regions of carcinoma of the prostate (CaP) in HSs from radical prostatectomies (RPs) using probabilistic pairwise Markov models (PPMMs), a novel type of Markov random field (MRF). At diagnostic resolution a digitized HS can contain 80Kx70K pixels - far too many for current automated Gleason grading algorithms to process. However, grading can be separated into two distinct steps: (1) detecting cancerous regions and (2) then grading these regions. The detection step does not require diagnostic resolution and can be performed much more quickly. Thus, we introduce a CaP detection system capable of analyzing an entire digitized whole-mount HS (2x1.75cm(2)) in under three minutes (on a desktop computer) while achieving a CaP detection sensitivity and specificity of 0.87 and 0.90, respectively. We obtain this high-throughput by tailoring the system to analyze the HSs at low resolution (8microm per pixel). This motivates the following algorithm: (Step 1) glands are segmented, (Step 2) the segmented glands are classified as malignant or benign, and (Step 3) the malignant glands are consolidated into continuous regions. The classification of individual glands leverages two features: gland size and the tendency for proximate glands to share the same class. The latter feature describes a spatial dependency which we model using a Markov prior. Typically, Markov priors are expressed as the product of potential functions. Unfortunately, potential functions are mathematical abstractions, and constructing priors through their selection becomes an ad hoc procedure, resulting in simplistic models such as the Potts. Addressing this problem, we introduce PPMMs which formulate priors in terms of probability density functions, allowing the creation of more sophisticated models. To demonstrate the efficacy of our CaP detection system and assess the advantages of using a PPMM prior instead of the Potts, we alternately incorporate both priors into our algorithm and rigorously evaluate system performance, extracting statistics from over 6000 simulations run across 40 RP specimens. Perhaps the most indicative result is as follows: at a CaP sensitivity of 0.87 the accompanying false positive rates of the system when alternately employing the PPMM and Potts priors are 0.10 and 0.20, respectively.

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.

CDX2 Expression in Yolk Sac Component of Testicular Germ Cell Tumors

CDX2 has been detected in the majority of colorectal adenocarcinoma cases and may be useful in determining the sites of origin of tumors. In this study, the authors evaluated CDX2 expression in germ cell tumors (GCTs) by immunohistochemistry. Forty cases of testicular GCTs and 8 cases of metastatic GCTs were retrieved for study. In the 40 cases of testicular GCTs, 13 were pure seminomas and 27 mixed GCTs. Yolk sac tumor (YST) was identified by morphology and glypican 3 staining in 20 testicular mixed GCTs. Of these 20 cases, 8 cases showed 1+ positivity for CDX2. Other primitive components of GCTs were negative. For the 6 cases of metastatic mixed GCT with YST, 4 cases were positive, 2+ in 2 cases and 1+ in 2 cases. The positivity of CDX2 in GCTs warrants including YST in the differential diagnosis of adenocarcinoma of unknown origin.