ABSTRACT
Digital pathology and the integration of artificial intelligence (AI) models have revolutionized histopathology, opening new opportunities. With the increasing availability of whole-slide images (WSIs), demand is growing for efficient retrieval, processing, and analysis of relevant images from vast biomedical archives. However, processing WSIs presents challenges due to their large size and content complexity. Full computer digestion of WSIs is impractical, and processing all patches individually is prohibitively expensive. In this article, we propose an unsupervised patching algorithm, Sequential Patching Lattice for Image Classification and Enquiry (SPLICE). This novel approach condenses a histopathology WSI into a compact set of representative patches, forming a collage of WSI while minimizing redundancy. SPLICE prioritizes patch quality and uniqueness by sequentially analyzing a WSI and selecting nonredundant representative features. We evaluated SPLICE for search and match applications, showing its improved accuracy, reduced computation time, and storage requirements compared with existing state-of-the-art methods. As an unsupervised method, SPLICE effectively reduces storage requirements for representing tissue images by 50%. This reduction enables numerous algorithms in computational pathology to operate much more efficiently, paving the way for accelerated adoption of digital pathology.
ABSTRACT
Steatohepatitis with diverse etiologies is the most common histological manifestation in patients with liver disease. However, there are currently no specific histopathological features pathognomonic for metabolic dysfunction-associated steatotic liver disease, alcohol-associated liver disease, or metabolic dysfunction-associated steatotic liver disease with increased alcohol intake. Digitizing traditional pathology slides has created an emerging field of digital pathology, allowing for easier access, storage, sharing, and analysis of whole-slide images. Artificial intelligence (AI) algorithms have been developed for whole-slide images to enhance the accuracy and speed of the histological interpretation of steatohepatitis and are currently employed in biomarker development. Spatial biology is a novel field that enables investigators to map gene and protein expression within a specific region of interest on liver histological sections, examine disease heterogeneity within tissues, and understand the relationship between molecular changes and distinct tissue morphology. Here, we review the utility of digital pathology (using linear and nonlinear microscopy) augmented with AI analysis to improve the accuracy of histological interpretation. We will also discuss the spatial omics landscape with special emphasis on the strengths and limitations of established spatial transcriptomics and proteomics technologies and their application in steatohepatitis. We then highlight the power of multimodal integration of digital pathology augmented by machine learning (ML)algorithms with spatial biology. The review concludes with a discussion of the current gaps in knowledge, the limitations and premises of these tools and technologies, and the areas of future research.
ABSTRACT
Histopathology is the reference standard for pathology diagnosis, and has evolved with the digitization of glass slides [ie, whole slide images (WSIs)]. While trained histopathologists are able to diagnose diseases by examining WSIs visually, this process is time consuming and prone to variability. To address these issues, artificial intelligence models are being developed to generate slide-level representations of WSIs, summarizing the entire slide as a single vector. This enables various computational pathology applications, including interslide search, multimodal training, and slide-level classification. Achieving expressive and robust slide-level representations hinges on patch feature extraction and aggregation steps. This study proposed an additional binary patch grouping (BPG) step, a plugin that can be integrated into various slide-level representation pipelines, to enhance the quality of slide-level representation in bone marrow histopathology. BPG excludes patches with less clinical relevance through minimal interaction with the pathologist; a one-time human intervention for the entire process. This study further investigated domain-general versus domain-specific feature extraction models based on convolution and attention and examined two different feature aggregation methods, with and without BPG, showing BPG's generalizability. The results showed that using BPG boosts the performance of WSI retrieval (mean average precision at 10) by 4% and improves WSI classification (weighted-F1) by 5% compared to not using BPG. Additionally, domain-general large models and parameterized pooling produced the best-quality slide-level representations.
Subject(s)
Artificial Intelligence , Bone Marrow , Humans , Dietary Supplements , PathologistsABSTRACT
Breast cancer is one of the most common cancers affecting women worldwide. It includes a group of malignant neoplasms with a variety of biological, clinical, and histopathologic characteristics. There are more than 35 different histologic forms of breast lesions that can be classified and diagnosed histologically according to cell morphology, growth, and architecture patterns. Recently, deep learning, in the field of artificial intelligence, has drawn a lot of attention for the computerized representation of medical images. Searchable digital atlases can provide pathologists with patch-matching tools, allowing them to search among evidently diagnosed and treated archival cases, a technology that may be regarded as computational second opinion. In this study, we indexed and analyzed the World Health Organization breast taxonomy (Classification of Tumors fifth ed.) spanning 35 tumor types. We visualized all tumor types using deep features extracted from a state-of-the-art deep-learning model, pretrained on millions of diagnostic histopathology images from the Cancer Genome Atlas repository. Furthermore, we tested the concept of a digital "atlas" as a reference for search and matching with rare test cases. The patch similarity search within the World Health Organization breast taxonomy data reached >88% accuracy when validating through "majority vote" and >91% accuracy when validating using top n tumor types. These results show for the first time that complex relationships among common and rare breast lesions can be investigated using an indexed digital archive.
Subject(s)
Artificial Intelligence , Breast Neoplasms , Female , Humans , Breast/pathology , Breast Neoplasms/pathologyABSTRACT
An increasing number of machine learning applications are being developed and applied to digital pathology, including hematopathology. The goal of these modern computerized tools is often to support diagnostic workflows by extracting and summarizing information from multiple data sources, including digital images of human tissue. Hematopathology is inherently multimodal and can serve as an ideal case study for machine learning applications. However, hematopathology also poses unique challenges compared to other pathology subspecialities when applying machine learning approaches. By modeling the pathologist workflow and thinking process, machine learning algorithms may be designed to address practical and tangible problems in hematopathology. In this article, we discuss the current trends in machine learning in hematopathology. We review currently available machine learning enabled medical devices supporting hematopathology workflows. We then explore current machine learning research trends of the field with a focus on bone marrow cytology and histopathology, and how adoption of new machine learning tools may be enabled through the transition to digital pathology.
Subject(s)
Algorithms , Machine Learning , Humans , Pathologists , WorkflowABSTRACT
Purpose: The latest generation of scanners can digitize histopathology glass slides for computerized image analysis. These images contain valuable information for diagnostic and prognostic purposes. Consequently, the availability of high digital magnifications like 20 × and 40 × is commonly expected in scanning the slides. Thus, the image acquisition typically generates gigapixel high-resolution images, times as large as 100,000 × 100,000 pixels . Naturally, the storage and processing of such huge files may be subject to severe computational bottlenecks. As a result, the need for techniques that can operate on lower magnification levels but produce results on par with outcomes for high magnification levels is becoming urgent. Approach: Over the past decade, the digital solution of enhancing images resolution has been addressed by the concept of super resolution (SR). In addition, deep learning has offered state-of-the-art results for increasing the image resolution after acquisition. In this study, multiple deep learning networks designed for image SR are trained and assessed for the histopathology domain. Results: We report quantitative and qualitative comparisons of the results using publicly available cancer images to shed light on the benefits and challenges of deep learning for extrapolating image resolution in histopathology. Three pathologists evaluated the results to assess the quality and diagnostic value of generated SR images. Conclusions: Pixel-level information, including structures and textures in histopathology images, are learnable by deep networks; hence improving the resolution quantity of scanned slides is possible by training appropriate networks. Different SR networks may perform best for various cancer sites and subtypes.
ABSTRACT
This paper investigates the effect of magnification on content-based image search in digital pathology archives and proposes to use multi-magnification image representation. Image search in large archives of digital pathology slides provides researchers and medical professionals with an opportunity to match records of current and past patients and learn from evidently diagnosed and treated cases. When working with microscopes, pathologists switch between different magnification levels while examining tissue specimens to find and evaluate various morphological features. Inspired by the conventional pathology workflow, we have investigated several magnification levels in digital pathology and their combinations to minimize the gap between AI-enabled image search methods and clinical settings. The proposed searching framework does not rely on any regional annotation and potentially applies to millions of unlabelled (raw) whole slide images. This paper suggests two approaches for combining magnification levels and compares their performance. The first approach obtains a single-vector deep feature representation for a digital slide, whereas the second approach works with a multi-vector deep feature representation. We report the search results of 20×, 10×, and 5× magnifications and their combinations on a subset of The Cancer Genome Atlas (TCGA) repository. The experiments verify that cell-level information at the highest magnification is essential for searching for diagnostic purposes. In contrast, low-magnification information may improve this assessment depending on the tumor type. Our multi-magnification approach achieved up to 11% F1-score improvement in searching among the urinary tract and brain tumor subtypes compared to the single-magnification image search.
Subject(s)
Image Processing, Computer-Assisted , Microscopy , Humans , Image Processing, Computer-Assisted/methods , Microscopy/methods , WorkflowABSTRACT
Background: Bone marrow cytology is required to make a hematological diagnosis, influencing critical clinical decision points in hematology. However, bone marrow cytology is tedious, limited to experienced reference centers and associated with inter-observer variability. This may lead to a delayed or incorrect diagnosis, leaving an unmet need for innovative supporting technologies. Methods: We develop an end-to-end deep learning-based system for automated bone marrow cytology. Starting with a bone marrow aspirate digital whole slide image, our system rapidly and automatically detects suitable regions for cytology, and subsequently identifies and classifies all bone marrow cells in each region. This collective cytomorphological information is captured in a representation called Histogram of Cell Types (HCT) quantifying bone marrow cell class probability distribution and acting as a cytological patient fingerprint. Results: Our system achieves high accuracy in region detection (0.97 accuracy and 0.99 ROC AUC), and cell detection and cell classification (0.75 mean average precision, 0.78 average F1-score, Log-average miss rate of 0.31). Conclusions: HCT has potential to eventually support more efficient and accurate diagnosis in hematology, supporting AI-enabled computational pathology.
ABSTRACT
The artificial intelligence revolution has been spurred forward by the availability of large-scale datasets. In contrast, the paucity of large-scale medical datasets hinders the application of machine learning in healthcare. The lack of publicly available multi-centric and diverse datasets mainly stems from confidentiality and privacy concerns around sharing medical data. To demonstrate a feasible path forward in medical image imaging, we conduct a case study of applying a differentially private federated learning framework for analysis of histopathology images, the largest and perhaps most complex medical images. We study the effects of IID and non-IID distributions along with the number of healthcare providers, i.e., hospitals and clinics, and the individual dataset sizes, using The Cancer Genome Atlas (TCGA) dataset, a public repository, to simulate a distributed environment. We empirically compare the performance of private, distributed training to conventional training and demonstrate that distributed training can achieve similar performance with strong privacy guarantees. We also study the effect of different source domains for histopathology images by evaluating the performance using external validation. Our work indicates that differentially private federated learning is a viable and reliable framework for the collaborative development of machine learning models in medical image analysis.
ABSTRACT
Although deep learning networks applied to digital images have shown impressive results for many pathology-related tasks, their black-box approach and limitation in terms of interpretability are significant obstacles for their widespread clinical utility. This study investigates the visualization of deep features (DFs) to characterize two lung cancer subtypes, adenocarcinoma and squamous cell carcinoma. It demonstrates that a subset of DFs, called prominent DFs, can accurately distinguish these two cancer subtypes. Visualization of such individual DFs allows for a better understanding of histopathologic patterns at both the whole-slide and patch levels, and discrimination of these cancer types. These DFs were visualized at the whole slide image level through DF-specific heatmaps and at tissue patch level through the generation of activation maps. In addition, these prominent DFs can distinguish carcinomas of organs other than the lung. This framework may serve as a platform for evaluating the interpretability of any deep network for diagnostic decision making.
Subject(s)
Adenocarcinoma of Lung/diagnosis , Carcinoma, Squamous Cell/diagnosis , Deep Learning , Lung Neoplasms/diagnosis , Adenocarcinoma of Lung/pathology , Carcinoma, Squamous Cell/pathology , Datasets as Topic , Diagnosis, Differential , Feasibility Studies , Female , Humans , Image Interpretation, Computer-Assisted/methods , Image Processing, Computer-Assisted/methods , Lung Neoplasms/pathology , Male , Neural Networks, Computer , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
One of the major obstacles in reaching diagnostic consensus is observer variability. With the recent success of artificial intelligence, particularly the deep networks, the question emerges as to whether the fundamental challenge of diagnostic imaging can now be resolved. This article briefly reviews the problem and how eventually both supervised and unsupervised AI technologies could help to overcome it.
Subject(s)
Artificial Intelligence , Image Processing, Computer-Assisted , Observer Variation , Pathology , Humans , Natural Language Processing , Neural Networks, ComputerABSTRACT
Background: Pathology synopses consist of semi-structured or unstructured text summarizing visual information by observing human tissue. Experts write and interpret these synopses with high domain-specific knowledge to extract tissue semantics and formulate a diagnosis in the context of ancillary testing and clinical information. The limited number of specialists available to interpret pathology synopses restricts the utility of the inherent information. Deep learning offers a tool for information extraction and automatic feature generation from complex datasets. Methods: Using an active learning approach, we developed a set of semantic labels for bone marrow aspirate pathology synopses. We then trained a transformer-based deep-learning model to map these synopses to one or more semantic labels, and extracted learned embeddings (i.e., meaningful attributes) from the model's hidden layer. Results: Here we demonstrate that with a small amount of training data, a transformer-based natural language model can extract embeddings from pathology synopses that capture diagnostically relevant information. On average, these embeddings can be used to generate semantic labels mapping patients to probable diagnostic groups with a micro-average F1 score of 0.779 Â ± 0.025. Conclusions: We provide a generalizable deep learning model and approach to unlock the semantic information inherent in pathology synopses toward improved diagnostics, biodiscovery and AI-assisted computational pathology.
ABSTRACT
Within artificial intelligence and machine learning, a generative model is a powerful tool for learning any kind of data distribution. With the advent of deep learning and its success in image recognition, the field of deep generative models has clearly emerged as one of the promising fields for medical imaging. In a recent issue of The Journal of Pathology, Levine, Peng et al demonstrate the ability of generative models to synthesize high-quality pathology images. They suggested that generative models can serve as an unlimited source of images either for educating freshman pathologists or training machine learning models for diverse image analysis tasks, especially in scarce cases, while resolving patients' privacy and confidentiality concerns. © 2020 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.
Subject(s)
Artificial Intelligence , Pathologists , Humans , United KingdomABSTRACT
CONTEXT.: Pathologists may encounter extraneous pieces of tissue (tissue floaters) on glass slides because of specimen cross-contamination. Troubleshooting this problem, including performing molecular tests for tissue identification if available, is time consuming and often does not satisfactorily resolve the problem. OBJECTIVE.: To demonstrate the feasibility of using an image search tool to resolve the tissue floater conundrum. DESIGN.: A glass slide was produced containing 2 separate hematoxylin and eosin (H&E)-stained tissue floaters. This fabricated slide was digitized along with the 2 slides containing the original tumors used to create these floaters. These slides were then embedded into a dataset of 2325 whole slide images comprising a wide variety of H&E stained diagnostic entities. Digital slides were broken up into patches and the patch features converted into barcodes for indexing and easy retrieval. A deep learning-based image search tool was employed to extract features from patches via barcodes, hence enabling image matching to each tissue floater. RESULTS.: There was a very high likelihood of finding a correct tumor match for the queried tissue floater when searching the digital database. Search results repeatedly yielded a correct match within the top 3 retrieved images. The retrieval accuracy improved when greater proportions of the floater were selected. The time to run a search was completed within several milliseconds. CONCLUSIONS.: Using an image search tool offers pathologists an additional method to rapidly resolve the tissue floater conundrum, especially for those laboratories that have transitioned to going fully digital for primary diagnosis.
Subject(s)
Algorithms , Artifacts , Carcinoma, Renal Cell/pathology , Diagnostic Errors/prevention & control , Kidney Neoplasms/pathology , Pathology, Clinical , Carcinoma, Renal Cell/diagnosis , Databases, Factual , Eosine Yellowish-(YS) , Feasibility Studies , Hematoxylin , Humans , Image Processing, Computer-Assisted , Kidney Neoplasms/diagnosis , Pathologists , Staining and LabelingABSTRACT
In this paper, we introduce a new dataset for cancer research containing somatic mutation states of 536 genes of the Cancer Gene Census (CGC). We used somatic mutation information from the Cancer Genome Atlas (TCGA) projects to create this dataset. As preliminary investigations, we employed machine learning techniques, including k-Nearest Neighbors, Decision Tree, Random Forest, and Artificial Neural Networks (ANNs) to evaluate the potential of these somatic mutations for classification of cancer types. We compared our models on accuracy, precision, recall, and F1-score. We observed that ANNs outperformed the other models with F1-score of 0.36 and overall classification accuracy of 40%, and precision ranging from 12% to 92% for different cancer types. The 40% accuracy is significantly higher than random guessing which would have resulted in 3% overall classification accuracy. Although the model has relatively low overall accuracy, it has an average classification specificity of 98%. The ANN achieved high precision scores (> 0.7) for 5 of the 33 cancer types. The introduced dataset can be used for research on TCGA data, such as survival analysis, histopathology image analysis and content-based image retrieval. The dataset is available online for download: https://kimialab.uwaterloo.ca/kimia/.
Subject(s)
Neoplasms , Neural Networks, Computer , Humans , Machine Learning , Mutation , Neoplasms/genetics , Sensitivity and SpecificityABSTRACT
This paper introduces the "encoded local projections" (ELP) as a new dense-sampling image descriptor for search and classification problems. The gradient changes of multiple projections in local windows of gray-level images are encoded to build a histogram that captures spatial projection patterns. Using projections is a conventional technique in both medical imaging and computer vision. Furthermore, powerful dense-sampling methods, such as local binary patterns and the histogram of oriented gradients, are widely used for image classification and recognition. Inspired by many achievements of such existing descriptors, we explore the design of a new class of histogram-based descriptors with particular applications in medical imaging. We experiment with three public datasets (IRMA, Kimia Path24, and CT Emphysema) to comparatively evaluate the performance of ELP histograms. In light of the tremendous success of deep architectures, we also compare the results with deep features generated by pretrained networks. The results are quite encouraging as the ELP descriptor can surpass both conventional and deep descriptors in performance in several experimental settings.
Subject(s)
Image Interpretation, Computer-Assisted/methods , Image Processing, Computer-Assisted/methods , Information Storage and Retrieval/methods , Algorithms , Databases, Factual , Deep Learning , Diagnostic Imaging/classification , HumansABSTRACT
The level set approach to segmentation of medical images has received considerable attention in recent years. Evolving an initial contour to converge to anatomical boundaries of an organ or tumor is a very appealing method, especially when it is based on a well-defined mathematical foundation. However, one drawback of such evolving method is its high computation time. It is desirable to design and implement algorithms that are not only accurate and robust but also fast in execution. Bresson et al. have proposed a variational model using both boundary and region information as well as shape priors. The latter can be a significant factor in medical image analysis. In this work, we combine the variational model of level set with a multi-resolution approach to accelerate the processing. The question is whether a multi-resolution context can make the segmentation faster without affecting the accuracy. As well, we investigate the question whether a premature convergence, which happens in a much shorter time, would reduce accuracy. We examine multiple semiautomated configurations to segment the prostate gland in T2W MR images. Comprehensive experimentation is conducted using a data set of a 100 patients (1,235 images) to verify the effectiveness of the multi-resolution level set with shape priors. The results show that the convergence speed can be increased by a factor of ≈ 2.5 without affecting the segmentation accuracy. Furthermore, a premature convergence approach drastically increases the segmentation speed by a factor of ≈ 17.9.
Subject(s)
Image Processing, Computer-Assisted/methods , Magnetic Resonance Imaging/methods , Prostate/pathology , Prostatic Neoplasms/diagnosis , Algorithms , Contrast Media , Humans , Image Enhancement/methods , Male , Pattern Recognition, Automated/methods , Reproducibility of ResultsABSTRACT
PURPOSE: Accurate segmentation and volume estimation of the prostate gland in magnetic resonance (MR) and computed tomography (CT) images are necessary steps in diagnosis, treatment, and monitoring of prostate cancer. This paper presents an algorithm for the prostate gland volume estimation based on the semiautomated segmentation of individual slices in T2-weighted MR and CT image sequences. METHODS: The proposed Inter-Slice Bidirectional Registration-based Segmentation (iBRS) algorithm relies on interslice image registration of volume data to segment the prostate gland without the use of an anatomical atlas. It requires the user to mark only three slices in a given volume dataset, i.e., the first, middle, and last slices. Next, the proposed algorithm uses a registration algorithm to autosegment the remaining slices. We conducted comprehensive experiments to measure the performance of the proposed algorithm using three registration methods (i.e., rigid, affine, and nonrigid techniques). RESULTS: The results with the proposed technique were compared with manual marking using prostate MR and CT images from 117 patients. Manual marking was performed by an expert user for all 117 patients. The median accuracies for individual slices measured using the Dice similarity coefficient (DSC) were 92% and 91% for MR and CT images, respectively. The iBRS algorithm was also evaluated regarding user variability, which confirmed that the algorithm was robust to interuser variability when marking the prostate gland. CONCLUSIONS: The proposed algorithm exploits the interslice data redundancy of the images in a volume dataset of MR and CT images and eliminates the need for an atlas, minimizing the computational cost while producing highly accurate results which are robust to interuser variability.
Subject(s)
Image Processing, Computer-Assisted/methods , Magnetic Resonance Imaging/methods , Prostate/diagnostic imaging , Tomography, X-Ray Computed/methods , Algorithms , Humans , Male , Organ Size , Prostate/pathology , Prostatic Neoplasms/diagnostic imaging , Prostatic Neoplasms/pathologyABSTRACT
Detecting objects, a significant task in computer vision, is accompanied with many challenges. When we focus on medical images, the challenges of detecting an organ or a tumour exhibit their own specific difficulties. Automatic finding of the prostate gland in magnetic resonance (MR) images, for instance, is a needed task in some clinical procedures. In this paper we propose a novel method for detection of the prostate gland in MR images. We use a multi-stage intra-patient approach to the template matching which is based on a trained dataset. We conduct experiments with the images of 100 patients and report preliminary results that seem to be promising.
Subject(s)
Algorithms , Magnetic Resonance Imaging , Prostate/anatomy & histology , Databases as Topic , Humans , Male , Organ SizeABSTRACT
PURPOSE: To perform a rigorous technological assessment and statistical validation of a software technology for anatomic delineations of the prostate on MRI datasets. METHODS AND MATERIALS: A 3-phase validation strategy was used. Phase I consisted of anatomic atlas building using 100 prostate cancer MRI data sets to provide training data sets for the segmentation algorithms. In phase II, 2 experts contoured 15 new MRI prostate cancer cases using 3 approaches (manual, N points, and region of interest). In phase III, 5 new physicians with variable MRI prostate contouring experience segmented the same 15 phase II datasets using 3 approaches: manual, N points with no editing, and full autosegmentation with user editing allowed. Statistical analyses for time and accuracy (using Dice similarity coefficient) endpoints used traditional descriptive statistics, analysis of variance, analysis of covariance, and pooled Student t test. RESULTS: In phase I, average (SD) total and per slice contouring time for the 2 physicians was 228 (75), 17 (3.5), 209 (65), and 15 seconds (3.9), respectively. In phase II, statistically significant differences in physician contouring time were observed based on physician, type of contouring, and case sequence. The N points strategy resulted in superior segmentation accuracy when initial autosegmented contours were compared with final contours. In phase III, statistically significant differences in contouring time were observed based on physician, type of contouring, and case sequence again. The average relative timesaving for N points and autosegmentation were 49% and 27%, respectively, compared with manual contouring. The N points and autosegmentation strategies resulted in average Dice values of 0.89 and 0.88, respectively. Pre- and postedited autosegmented contours demonstrated a higher average Dice similarity coefficient of 0.94. CONCLUSION: The software provided robust contours with minimal editing required. Observed time savings were seen for all physicians irrespective of experience level and baseline manual contouring speed.