Artificial Intelligence in Toxicologic Pathology: Quantitative Evaluation of Compound-Induced Hepatocellular Hypertrophy in Rats

The Use of Artificial Intelligence in the Liver Histopathology Field: A Systematic Review

Digital pathology (DP) has begun to play a key role in the evaluation of liver specimens. Recent studies have shown that a workflow that combines DP and artificial intelligence (AI) applied to histopathology has potential value in supporting the diagnosis, treatment evaluation, and prognosis prediction of liver diseases. Here, we provide a systematic review of the use of this workflow in the field of hepatology. Based on the PRISMA 2020 criteria, a search of the PubMed, SCOPUS, and Embase electronic databases was conducted, applying inclusion/exclusion filters. The articles were evaluated by two independent reviewers, who extracted the specifications and objectives of each study, the AI tools used, and the results obtained. From the 266 initial records identified, 25 eligible studies were selected, mainly conducted on human liver tissues. Most of the studies were performed using whole-slide imaging systems for imaging acquisition and applying different machine learning and deep learning methods for image pre-processing, segmentation, feature extractions, and classification. Of note, most of the studies selected demonstrated good performance as classifiers of liver histological images compared to pathologist annotations. Promising results to date bode well for the not-too-distant inclusion of these techniques in clinical practice.

A Weakly Supervised Deep Learning Framework for Whole Slide Classification to Facilitate Digital Pathology in Animal Study

The pathology of animal studies is crucial for toxicity evaluations and regulatory assessments, but the manual examination of slides by pathologists remains time-consuming and requires extensive training. One inherent challenge in this process is the interobserver variability, which can compromise the consistency and accuracy of a study. Artificial intelligence (AI) has demonstrated its ability to automate similar examinations in clinical applications with enhanced efficiency, consistency, and accuracy. However, training AI models typically relies on costly pixel-level annotation of injured regions and is often not available for animal pathology. To address this, we developed the PathologAI system, a "weakly" supervised approach for WSI classification in rat images without explicit lesion annotation at the pixel level. Using rat liver imaging data from the Open TG-GATEs system, PathologAI was applied to predict necrosis of n = 816 WSIs (377 controls). TG-GATEs studied 170 compounds at three dose levels (low, middle, and high) for four time points (3, 7, 14, and 28 days). PathologAI first preprocessed WSIs at the tile level to generate a high-level representation with a Generative Adversarial Network architecture. The prediction of liver necrosis relied on an ensemble model of 5 CNN classifiers trained on 335 WSIs. The ensemble model achieved notable classification accuracy on the holdout test set: 87% among 87 control slides free of findings, 83% among 120 controls with spontaneous necrosis, 67% among 147 treated animals with spontaneous minimal or slight necrosis, and 59% among 127 treated animals with minimal or slight necrosis caused by the treatment. Importantly, PathologAI was able to discriminate WSIs with spontaneous necrosis from those with treatment related necrosis and discriminated mild lesion level findings (slight vs minimal) and between treatment dose levels. PathologAI could provide an inexpensive and rapid screening tool to assist the digital pathology analysis in preclinical applications and general toxicological studies.

A comparative study on the implementation of deep learning algorithms for detection of hepatic necrosis in toxicity studies

Deep learning has recently become one of the most popular methods of image analysis. In non-clinical studies, several tissue slides are generated to investigate the toxicity of a test compound. These are converted into digital image data using a slide scanner, which is then studied by researchers to investigate abnormalities, and the deep learning method has been started to adopt in this study. However, comparative studies evaluating different deep learning algorithms for analyzing abnormal lesions are scarce. In this study, we applied three algorithms, SSD, Mask R-CNN, and DeepLabV3+, to detect hepatic necrosis in slide images and determine the best deep learning algorithm for analyzing abnormal lesions. We trained each algorithm on 5750 images and 5835 annotations of hepatic necrosis including validation and test, augmented with 500 image tiles of 448 × 448 pixels. Precision, recall, and accuracy were calculated for each algorithm based on the prediction results of 60 test images of 2688 × 2688 pixels. The two segmentation algorithms, DeepLabV3+ and Mask R-CNN, showed over 90% of accuracy (0.94 and 0.92, respectively), whereas SSD, an object detection algorithm, showed lower accuracy. The trained DeepLabV3+ outperformed all others in recall while also successfully separating hepatic necrosis from other features in the test images. It is important to localize and separate the abnormal lesion of interest from other features to investigate it on a slide level. Therefore, we suggest that segmentation algorithms are more appropriate than object detection algorithms for use in the pathological analysis of images in non-clinical studies.

Supplementary Information

The online version contains supplementary material available at 10.1007/s43188-023-00173-5.

Application of convolutional neural network for analyzing hepatic fibrosis in mice

Recently, with the development of computer vision using artificial intelligence (AI), clinical research on diagnosis and prediction using medical image data has increased. In this study, we applied AI methods to analyze hepatic fibrosis in mice to determine whether an AI algorithm can be used to analyze lesions. Whole slide image (WSI) Sirius Red staining was used to examine hepatic fibrosis. The Xception network, an AI algorithm, was used to train normal and fibrotic lesion identification. We compared the results from two analyses, that is, pathologists' grades and researchers' annotations, to observe whether the automated algorithm can support toxicological pathologists efficiently as a new apparatus. The accuracies of the trained model computed from the training and validation datasets were greater than 99%, and that obtained by testing the model was 100%. In the comparison between analyses, all analyses showed significant differences in the results for each group. Furthermore, both normalized fibrosis grades inferred from the trained model annotated the fibrosis area, and the grades assigned by the pathologists showed significant correlations. Notably, the deep learning algorithm derived the highest correlation with the pathologists' average grade. Owing to the correlation outcomes, we conclude that the trained model might produce results comparable to those of the pathologists' grading of the Sirius Red-stained WSI fibrosis. This study illustrates that the deep learning algorithm can potentially be used for analyzing fibrotic lesions in combination with Sirius Red-stained WSIs as a second opinion tool in non-clinical research.

MMO-Net (Multi-Magnification Organ Network): A use case for Organ Identification using Multiple Magnifications in Preclinical Pathology Studies

Identifying organs within histology images is a fundamental and non-trivial step in toxicological digital pathology workflows as multiple organs often appear on the same whole slide image (WSI). Previous works in automated tissue classification have investigated the use of single magnifications, and demonstrated limitations when attempting to identify small and contiguous organs at low magnifications. In order to overcome these shortcomings, we present a multi-magnification convolutional neural network (CNN), called MMO-Net, which employs context and cellular detail from different magnifications to facilitate the recognition of complex organs. Across N=320 WSI from 3 contract research organization (CRO) laboratories, we demonstrate state-of-the-art organ detection and segmentation performance of 7 rat organs with and without lesions: liver, kidney, thyroid gland, parathyroid gland, urinary bladder, salivary gland, and mandibular lymph node (AUROC=0.99–1.0 for all organs, Dice≥0.9 except parathyroid (0.73)). Evaluation takes place at both inter- and intra CRO levels, suggesting strong generalizability performance. Results are qualitatively reviewed using visualization masks to ensure separation of organs in close proximity (e.g., thyroid vs parathyroid glands). MMO-Net thus offers organ localization that serves as a potential quality control tool to validate WSI metadata and as a preprocessing step for subsequent organ-specific artificial intelligence (AI) use cases. To facilitate research in this area, all associated WSI and metadata used for this study are being made freely available, forming a first of its kind dataset for public use.

Deep Learning Approaches and Applications in Toxicologic Histopathology: Current Status and Future Perspectives

Whole slide imaging enables the use of a wide array of digital image analysis tools that are revolutionizing pathology. Recent advances in digital pathology and deep convolutional neural networks have created an enormous opportunity to improve workflow efficiency, provide more quantitative, objective, and consistent assessments of pathology datasets, and develop decision support systems. Such innovations are already making their way into clinical practice. However, the progress of machine learning - in particular, deep learning (DL) - has been rather slower in nonclinical toxicology studies. Histopathology data from toxicology studies are critical during the drug development process that is required by regulatory bodies to assess drug-related toxicity in laboratory animals and its impact on human safety in clinical trials. Due to the high volume of slides routinely evaluated, low-throughput, or narrowly performing DL methods that may work well in small-scale diagnostic studies or for the identification of a single abnormality are tedious and impractical for toxicologic pathology. Furthermore, regulatory requirements around good laboratory practice are a major hurdle for the adoption of DL in toxicologic pathology. This paper reviews the major DL concepts, emerging applications, and examples of DL in toxicologic pathology image analysis. We end with a discussion of specific challenges and directions for future research.

The Teaching Pattern of Law Majors Using Artificial Intelligence and Deep Neural Network Under Educational Psychology

With the increasing attention to the cultivation of legal talents, a new teaching model has been explored through artificial intelligence (AI) technology under educational psychology, which focuses on improving learning initiative, teaching methods, and teaching quality of students. First, the application of AI and deep neural network (DNN) algorithms are reviewed in education, and the advantages and disadvantages of traditional learning material recommendation algorithms are summarized. Then, a personalized learning material recommendation algorithm is put forward based on DNN, together with an adaptive learning system based on DNN. Finally, the traditional user-based collaborative filtering (UserCF) model and lifelong topic modeling (LTM) algorithm are introduced as the control group to verify the performance of the proposed recommendation system. The results show that the best learning rate of model training is 0.0001, the best dropout value is 0.5, and the best batch size is 32. The proposed personalized learning resource recommendation method based on deep learning (DL) still has good stability under various training data scales. The personalized test questions of recommended students are moderately difficult. It is easier to recommend materials according to the acquisition of knowledge points and the practicability of the recommended test questions of students. Personalized learning material recommendation algorithm based on AI can timely feedback needs of students, thereby improving the effect of classroom teaching. Using the combination of AI and DL algorithms in teaching design, students can complete targeted personalized learning assignments, which is of great significance to cultivate high-level legal professionals.

Artificial Intelligence in Toxicological Pathology: Quantitative Evaluation of Compound-Induced Follicular Cell Hypertrophy in Rat Thyroid Gland Using Deep Learning Models

Digital pathology has recently been more broadly deployed, fueling artificial intelligence (AI) application development and more systematic use of image analysis. Here, two different AI models were developed to evaluate follicular cell hypertrophy in hematoxylin and eosin-stained whole-slide-images of rat thyroid gland, using commercial AI-based-software. In the first, mean cytoplasmic area measuring approach (MCA approach), mean cytoplasmic area was calculated via several sequential deep learning (DL)-based algorithms including segmentation in microanatomical structures (separation of colloid and stroma from thyroid follicular epithelium), nuclear detection, and area measurements. With our additional second, hypertrophy area fraction predicting approach (HAF approach), we present for the first time DL-based direct detection of the histopathological change follicular cell hypertrophy in the thyroid gland with similar results. For multiple studies, increased output parameters (mean cytoplasmic area and hypertrophic area fraction) were shown in groups given different hypertrophy-inducing reference compounds in comparison to control groups. Quantitative results correlated with the gold standard of board-certified veterinary pathologists' diagnoses and gradings as well as thyroid hormone dependent gene expressions. Accuracy and repeatability of diagnoses and grading by pathologists are expected to be improved by additional evaluation of mean cytoplasmic area or direct detection of hypertrophy, combined with standard histopathological observations.

Whole-slide imaging, tissue image analysis, and artificial intelligence in veterinary pathology: An updated introduction and review

Since whole-slide imaging has been commercially available for over 2 decades, digital pathology has become a constantly expanding aspect of the pathology profession that will continue to significantly impact how pathologists conduct their craft. While some aspects, such as whole-slide imaging for archiving, consulting, and teaching, have gained broader acceptance, other facets such as quantitative tissue image analysis and artificial intelligence-based assessments are still met with some reservations. While most vendors in this space have focused on diagnostic applications, that is, viewing one or few slides at a time, some are developing solutions tailored more specifically to the various aspects of veterinary pathology including updated diagnostic, discovery, and research applications. This has especially advanced the use of digital pathology in toxicologic pathology and drug development, for primary reads as well as peer reviews. It is crucial that pathologists gain a deeper understanding of digital pathology and tissue image analysis technology and their applications in order to fully use these tools in a way that enhances and improves the pathologist's assessment as well as work environment. This review focuses on an updated introduction to the basics of digital pathology and image analysis and introduces emerging topics around artificial intelligence and machine learning.

Mini Review: The Last Mile-Opportunities and Challenges for Machine Learning in Digital Toxicologic Pathology

The 2019 manuscript by the Special Interest Group on Digital Pathology and Image Analysis of the Society of Toxicologic pathology suggested that a synergism between artificial intelligence (AI) and machine learning (ML) technologies and digital toxicologic pathology would improve the daily workflow and future impact of toxicologic pathologists globally. Now 2 years later, the authors of this review consider whether, in their opinion, there is any evidence that supports that thesis. Specifically, we consider the opportunities and challenges for applying ML (the study of computer algorithms that are able to learn from example data and extrapolate the learned information to unseen data) algorithms in toxicologic pathology and how regulatory bodies are navigating this rapidly evolving field. Although we see similarities with the "Last Mile" metaphor, the weight of evidence suggests that toxicologic pathologists should approach ML with an equal dose of skepticism and enthusiasm. There are increasing opportunities for impact in our field that leave the authors cautiously excited and optimistic. Toxicologic pathologists have the opportunity to critically evaluate ML applications with a "call-to-arms" mentality. Why should we be late adopters? There is ample evidence to encourage engagement, growth, and leadership in this field.

Deep learning-based image-analysis algorithm for classification and quantification of multiple histopathological lesions in rat liver

Artificial intelligence (AI)-based image analysis is increasingly being used for preclinical safety-assessment studies in the pharmaceutical industry. In this paper, we present an AI-based solution for preclinical toxicology studies. We trained a set of algorithms to learn and quantify multiple typical histopathological findings in whole slide images (WSIs) of the livers of young Sprague Dawley rats by using a U-Net-based deep learning network. The trained algorithms were validated using 255 liver WSIs to detect, classify, and quantify seven types of histopathological findings (including vacuolation, bile duct hyperplasia, and single-cell necrosis) in the liver. The algorithms showed consistently good performance in detecting abnormal areas. Approximately 75% of all specimens could be classified as true positive or true negative. In general, findings with clear boundaries with the surrounding normal structures, such as vacuolation and single-cell necrosis, were accurately detected with high statistical scores. The results of quantitative analyses and classification of the diagnosis based on the threshold values between “no findings” and “abnormal findings” correlated well with diagnoses made by professional pathologists. However, the scores for findings ambiguous boundaries, such as hepatocellular hypertrophy, were poor. These results suggest that deep learning-based algorithms can detect, classify, and quantify multiple findings simultaneously on rat liver WSIs. Thus, it can be a useful supportive tool for a histopathological evaluation, especially for primary screening in rat toxicity studies.