Whole-slide Histopathology Images Research Articles

Ensemble transformer-based multiple instance learning to predict pathological subtypes and tumor mutational burden from histopathological whole slide images of endometrial and colorectal cancer

In endometrial cancer (EC) and colorectal cancer (CRC), in addition to microsatellite instability, tumor mutational burden (TMB) has gradually gained attention as a genomic biomarker that can be used clinically to determine which patients may benefit from immune checkpoint inhibitors. High TMB is characterized by a large number of mutated genes, which encode aberrant tumor neoantigens, and implies a better response to immunotherapy. Hence, a part of EC and CRC patients associated with high TMB may have higher chances to receive immunotherapy. TMB measurement was mainly evaluated by whole-exome sequencing or next-generation sequencing, which was costly and difficult to be widely applied in all clinical cases. Therefore, an effective, efficient, low-cost and easily accessible tool is urgently needed to distinguish the TMB status of EC and CRC patients. In this study, we present a deep learning framework, namely Ensemble Transformer-based Multiple Instance Learning with Self-Supervised Learning Vision Transformer feature encoder (ETMIL-SSLViT), to predict pathological subtype and TMB status directly from the H&E stained whole slide images (WSIs) in EC and CRC patients, which is helpful for both pathological classification and cancer treatment planning. Our framework was evaluated on two different cancer cohorts, including an EC cohort with 918 histopathology WSIs from 529 patients and a CRC cohort with 1495 WSIs from 594 patients from The Cancer Genome Atlas. The experimental results show that the proposed methods achieved excellent performance and outperforming seven state-of-the-art (SOTA) methods in cancer subtype classification and TMB prediction on both cancer datasets. Fisher’s exact test further validated that the associations between the predictions of the proposed models and the actual cancer subtype or TMB status are both extremely strong (p<0.001). These promising findings show the potential of our proposed methods to guide personalized treatment decisions by accurately predicting the EC and CRC subtype and the TMB status for effective immunotherapy planning for EC and CRC patients.

BreasTDLUSeg: A coarse-to-fine framework for segmentation of breast terminal duct lobular units on histopathological whole-slide images

Automatic segmentation of breast terminal duct lobular units (TDLUs) on histopathological whole-slide images (WSIs) is crucial for the quantitative evaluation of TDLUs in the diagnostic and prognostic analysis of breast cancer. However, TDLU segmentation remains a great challenge due to its highly heterogeneous sizes, structures, and morphologies as well as the small areas on WSIs. In this study, we propose BreasTDLUSeg, an efficient coarse-to-fine two-stage framework based on multi-scale attention to achieve localization and precise segmentation of TDLUs on hematoxylin and eosin (H&E)-stained WSIs. BreasTDLUSeg consists of two networks: a superpatch-based patch-level classification network (SPPC-Net) and a patch-based pixel-level segmentation network (PPS-Net). SPPC-Net takes a superpatch as input and adopts a sub-region classification head to classify each patch within the superpatch as TDLU positive or negative. PPS-Net takes the TDLU positive patches derived from SPPC-Net as input. PPS-Net deploys a multi-scale CNN-Transformer as an encoder to learn enhanced multi-scale morphological representations and an upsampler to generate pixel-wise segmentation masks for the TDLU positive patches. We also constructed two breast cancer TDLU datasets containing a total of 530 superpatch images with patch-level annotations and 2,322 patch images with pixel-level annotations to enable the development of TDLU segmentation methods. Experiments on the two datasets demonstrate that BreasTDLUSeg outperforms other state-of-the-art methods with the highest Dice similarity coefficients of 79.97% and 92.93%, respectively. The proposed method shows great potential to assist pathologists in the pathological analysis of breast cancer. An open-source implementation of our approach can be found at https://github.com/Dian-kai/BreasTDLUSeg.

Histopathologic Differential Diagnosis and Estrogen Receptor/Progesterone Receptor Immunohistochemical Evaluation of Breast Carcinoma Using a Deep Learning–Based Artificial Intelligence Architecture

In breast carcinoma, invasive ductal carcinoma (IDC) is the most common histopathological subtype, and ductal carcinoma in situ (DCIS) is a precursor of IDC. They are often concomitant. The immunohistochemical staining of estrogen receptor (ER)/progesterone receptor (PR) in IDC/DCIS on whole-slide histopathological images (WSIs) can predict the prognosis of patients. However, the inter-observer variability among pathologists in reading WSIs is inevitable. Thus, artificial intelligence (AI) technology is crucial. Herein, IDC/DCIS detection was conducted by deep learning approach, including Faster R-CNN, RetinaNet, SSD300, YOLOv3, YOLOv5, YOLOv7, YOLOv8, and Swin transformer. Their performance was estimated by mean average precision (mAP) values. Cell recognition and counting were performed using AI technology to evaluate the intensity and proportion of ER/PR-immunostained cancer cells in IDC/DCIS. A three-round ring study (RS) was conducted to assess WSIs. A database for modelling the underlying probability distribution of a dataset with labels was established. YOLOv8 exhibits the highest detection performance with an mAP@0.5 of 0.944 and an mAP@0.5-0.95 of 0.790. With the assistance of YOLOv8, the scoring concordance across all pathologists was boosted to excellent in RS3 (0.970) from moderate in RS1 (0.724) and good in RS2 (0.812). Deep learning detection can be applied in clinicopathological field. To facilitate the histopathological diagnosis of IDC/DCIS and immunostaining scoring of ER/PR, a novel AI architecture and well-organized dataset were developed.

Pathology diagnosis of intraoperative frozen thyroid lesions assisted by deep learning

BackgroundThyroid cancer is a common thyroid malignancy. The majority of thyroid lesion needs intraoperative frozen pathology diagnosis, which provides important information for precision operation. As digital whole slide images (WSIs) develop, deep learning methods for histopathological classification of the thyroid gland (paraffin sections) have achieved outstanding results. Our current study is to clarify whether deep learning assists pathology diagnosis for intraoperative frozen thyroid lesions or not.MethodsWe propose an artificial intelligence-assisted diagnostic system for frozen thyroid lesions that applies prior knowledge in tandem with a dichotomous judgment of whether the lesion is cancerous or not and a quadratic judgment of the type of cancerous lesion to categorize the frozen thyroid lesions into five categories: papillary thyroid carcinoma, medullary thyroid carcinoma, anaplastic thyroid carcinoma, follicular thyroid tumor, and non-cancerous lesion. We obtained 4409 frozen digital pathology sections (WSI) of thyroid from the First Affiliated Hospital of Sun Yat-sen University (SYSUFH) to train and test the model, and the performance was validated by a six-fold cross validation, 101 papillary microcarcinoma sections of thyroid were used to validate the system’s sensitivity, and 1388 WSIs of thyroid were used for the evaluation of the external dataset. The deep learning models were compared in terms of several metrics such as accuracy, F1 score, recall, precision and AUC (Area Under Curve).ResultsWe developed the first deep learning-based frozen thyroid diagnostic classifier for histopathological WSI classification of papillary carcinoma, medullary carcinoma, follicular tumor, anaplastic carcinoma, and non-carcinoma lesion. On test slides, the system had an accuracy of 0.9459, a precision of 0.9475, and an AUC of 0.9955. In the papillary carcinoma test slides, the system was able to accurately predict even lesions as small as 2 mm in diameter. Tested with the acceleration component, the cut processing can be performed in 346.12 s and the visual inference prediction results can be obtained in 98.61 s, thus meeting the time requirements for intraoperative diagnosis. Our study employs a deep learning approach for high-precision classification of intraoperative frozen thyroid lesion distribution in the clinical setting, which has potential clinical implications for assisting pathologists and precision surgery of thyroid lesions.

Sequential Patching Lattice for Image Classification and Enquiry: Streamlining Digital Pathology Image Processing

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), there’s a growing demand 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 paper, 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, demonstrating improved accuracy, reduced computation time, and storage requirements compared to 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.

Prediction of Epidermal Growth Factor Receptor Mutation Subtypes in Non–Small Cell Lung Cancer From Hematoxylin and Eosin–Stained Slides Using Deep Learning

Accurate assessment of epidermal growth factor receptor (EGFR) mutation status and subtype is critical for the treatment of non–small cell lung cancer patients. Conventional molecular testing methods for detecting EGFR mutations have limitations. In this study, an artificial intelligence–powered deep learning framework was developed for the weakly supervised prediction of EGFR mutations in non–small cell lung cancer from hematoxylin and eosin–stained histopathology whole-slide images. The study cohort was partitioned into training and validation subsets. Foreground regions containing tumor tissue were extracted from whole-slide images. A convolutional neural network employing a contrastive learning paradigm was implemented to extract patch-level morphologic features. These features were aggregated using a vision transformer-based model to predict EGFR mutation status and classify patient cases. The established prediction model was validated on unseen data sets. In internal validation with a cohort from the University of Science and Technology of China (n = 172), the model achieved patient-level areas under the receiver-operating characteristic curve (AUCs) of 0.927 and 0.907, sensitivities of 81.6% and 83.3%, and specificities of 93.0% and 92.3%, for surgical resection and biopsy specimens, respectively, in EGFR mutation subtype prediction. External validation with cohorts from the Second Affiliated Hospital of Anhui Medical University and the First Affiliated Hospital of Wannan Medical College (n = 193) yielded patient-level AUCs of 0.849 and 0.867, sensitivities of 79.2% and 80.7%, and specificities of 91.7% and 90.7% for surgical and biopsy specimens, respectively. Further validation with The Cancer Genome Atlas data set (n = 81) showed an AUC of 0.861, a sensitivity of 84.6%, and a specificity of 90.5%. Deep learning solutions demonstrate potential advantages for automated, noninvasive, fast, cost-effective, and accurate inference of EGFR alterations from histomorphology. Integration of such artificial intelligence frameworks into routine digital pathology workflows could augment existing molecular testing pipelines.

Prognostic prediction of ovarian cancer based on hierarchical sampling & fine-grained recognition convolution neural network

Ovarian cancer ranks among the deadliest gynecological malignancies, with high-grade serous adenocarcinoma (HGSA) constituting 75 % of ovarian cancer cases and accounting for 80 %–90 % of ovarian cancer-related fatalities. Accurate prognosis prediction for ovarian HGSA is of critical clinical significance. However, existing prognostic analysis methods exhibit suboptimal performance in identifying prognostically relevant pathological markers, making it challenging, even for experienced pathologists, to forecast the prognosis of ovarian HGSA patients accurately. Deep learning holds promise in enhancing prognostic prediction accuracy. However, a significant challenge in this field arises from the impracticality of directly inputting histopathology whole-slide images with millions to billions of pixels into existing deep learning networks for training and inference. To address this issue, we propose a prognostic analysis network for ovarian cancer based on hierarchical sampling and fine-grained recognition. This network comprises a two-stage hierarchical sampling sub-network, a fine-grained image recognition sub-network, and a prognostic analysis sub-network. We assess the system's performance using a pathological dataset of 450 cases of ovarian HGSA diagnosed and treated at the Pathology Department of the West China Second University Hospital of Sichuan University. Results indicate that: (1) The proposed prognostic analysis network based on two-stage hierarchical sampling sub-network can effectively analyze the histopathology whole-slide image; (2) the use of fine-grained image recognition and the introduction of clinical information can improve the performance of HGSA prognosis analysis method, with an improvement range of 4.77–10.66%; and (3) the proposed method can be used for the model analysis of pathological datasets of HGSA. Moreover, this method can be used to explore effective characteristics from the multi-modal dataset through automatic learning with prediction recall, accuracy, and precision rates of 80.0%, 81.1%, and 81.8%, respectively, underscoring its clinical potential. This study reveals the reliability and effectiveness of the proposed prognosis evaluation method of HGCA. Conclusions can help clinicians precisely evaluate the recurrence risk of patients, take the initiative to master the diagnosis and treatment, and increase the long-term survival rate of patients.

Survival outcome prediction of breast carcinomas on whole-slide histopathology images using deep learning.

1070 Background: Breast cancer is the most common cancer among women with 2 million new cases and 627,000 deaths in 2020. Early diagnosis and effective treatment are crucial for improved outcomes. Prognosis mainly depends on histopathological features, among them grade. As whole slide histopathology image (WSI) of tumor tissue contains a huge amount of hidden morphological features unexploited by pathologists, we investigate the potential of Artificial Intelligence (AI)-based analysis on WSI to predict prognosis in terms of 5-year overall survival in breast cancer patients. Methods: We used a novel deep neural network (DNN), DiaDeepBreastPRS, designed specifically for predicting a survival risk score in breast cancer patients based on H&amp;E-stained whole slide images (WSI) of tumor tissues. The model incorporates two distinct viewpoints, one capturing cellular details and the other the tissue-level information. DiaDeepBreastPRS was trained and evaluated on a multi-centric discovery cohort of 1,027 patients (1,095 H&amp;E WSI) from the TCGA-BRCA dataset using a cross-testing and cross-validation technique. It was evaluated on an external cohort, comprising 232 patients (247 H&amp;E WSI). A statistical analysis with a multivariate Cox regression model was carried out on clinico-pathological data. AI scores and the concordance index (c-index) serves as the metric for assessing the performance. The predicted risk scores were used for effective risk stratification of breast carcinomas. Results: On the TCGA-BRCA dataset, the model achieved an average c-index of 67%, which reaches 78% by adding the pTNM stage and age at diagnosis. On the external dataset, the model achieved a c-index of 66% and 75% when including some histopathological prognosis factors (pTNM stage, age at diagnosis, HER2 and HR status and mitosis). The AI score was independently associated with the survival of breast cancer patients with the highest hazard ratio (HR 2.46, p&lt;0.005). Furthermore, the model was able to significantly discriminate between the 2 groups of patients, with a good and a poor prognosis in terms of overall survival (p&lt;0.005). Conclusions: In this study, we showcased that the algorithm was able to instantly extract prognostic morphological features from H&amp;E whole slide images (WSI) and could be included in the pathology report. This could potentially enhance clinical decision-making, elevating the standard of care. Compared to commonly used molecular signatures, the AI algorithm enables a reduction in response time and cost savings. However, further investigations using additional independent cohorts are essential to consolidate the algorithm's performance and allow its generalizability, establish its superiority over existing prognostic markers, and provide insights into its interpretability.

Artificial intelligence to predict homologous recombination deficiency in ovarian cancer from whole-slide histopathological images.

Artificial intelligence to predict homologous recombination deficiency in ovarian cancer from whole-slide histopathological images.

Artificial Intelligence-Based Quality Assessment of Histopathology Whole-Slide Images within a Clinical Workflow: Assessment of 'PathProfiler' in a Diagnostic Pathology Setting.

Digital pathology continues to gain momentum, with the promise of artificial intelligence to aid diagnosis and for assessment of features which may impact prognosis and clinical management. Successful adoption of these technologies depends upon the quality of digitised whole-slide images (WSI); however, current quality control largely depends upon manual assessment, which is inefficient and subjective. We previously developed PathProfiler, an automated image quality assessment tool, and in this feasibility study we investigate its potential for incorporation into a diagnostic clinical pathology setting in real-time. A total of 1254 genitourinary WSI were analysed by PathProfiler. PathProfiler was developed and trained on prostate tissue and, of the prostate biopsy WSI, representing 46% of the WSI analysed, 4.5% were flagged as potentially being of suboptimal quality for diagnosis. All had concordant subjective issues, mainly focus-related, 54% severe enough to warrant remedial action which resulted in improved image quality. PathProfiler was less reliable in assessment of non-prostate surgical resection-type cases, on which it had not been trained. PathProfiler shows potential for incorporation into a digitised clinical pathology workflow, with opportunity for image quality improvement. Whilst its reliability in the current form appears greatest for assessment of prostate specimens, other specimen types, particularly biopsies, also showed benefit.

Image-based consensus molecular subtyping in rectal cancer biopsies and response to neoadjuvant chemoradiotherapy

The development of deep learning (DL) models to predict the consensus molecular subtypes (CMS) from histopathology images (imCMS) is a promising and cost-effective strategy to support patient stratification. Here, we investigate whether imCMS calls generated from whole slide histopathology images (WSIs) of rectal cancer (RC) pre-treatment biopsies are associated with pathological complete response (pCR) to neoadjuvant long course chemoradiotherapy (LCRT) with single agent fluoropyrimidine. DL models were trained to classify WSIs of colorectal cancers stained with hematoxylin and eosin into one of the four CMS classes using a multi-centric dataset of resection and biopsy specimens (n = 1057 WSIs) with paired transcriptional data. Classifiers were tested on a held out RC biopsy cohort (ARISTOTLE) and correlated with pCR to LCRT in an independent dataset merging two RC cohorts (ARISTOTLE, n = 114 and SALZBURG, n = 55 patients). DL models predicted CMS with high classification performance in multiple comparative analyses. In the independent cohorts (ARISTOTLE, SALZBURG), cases with WSIs classified as imCMS1 had a significantly higher likelihood of achieving pCR (OR = 2.69, 95% CI 1.01–7.17, p = 0.048). Conversely, imCMS4 was associated with lack of pCR (OR = 0.25, 95% CI 0.07–0.88, p = 0.031). Classification maps demonstrated pathologist-interpretable associations with high stromal content in imCMS4 cases, associated with poor outcome. No significant association was found in imCMS2 or imCMS3. imCMS classification of pre-treatment biopsies is a fast and inexpensive solution to identify patient groups that could benefit from neoadjuvant LCRT. The significant associations between imCMS1/imCMS4 with pCR suggest the existence of predictive morphological features that could enhance standard pathological assessment.

Abstract 4938: Prediction of gene mutation from colorectal adenocarcinoma whole slide images via integrated deep learning pipeline

Abstract Colorectal cancer (CRC) stands as one of the deadliest cancer types worldwide. Identifying specific gene mutations crucial for targeted therapy is pivotal for CRC treatment. However, the current genetic testing method involves liquid biopsy, which is often cumbersome and cost-intensive. Histopathological whole-slide images (WSIs) are routinely generated for diagnostic purposes and can offer valuable insights into cellular heterogeneity. In this study, we aim to develop an integrated deep learning pipeline for predicting TP53 mutations in CRC, one of the most frequently mutated genes in CRC. We commenced by collecting 424 diagnostic WSIs from the TCGA-COAD cohorts. Each WSI was split as small patches at a resolution of 0.5 micrometers per pixel for following analyses. Quality control was implemented using Otsu thresholding and Gaussian blur filtering, both at the slide-level masking and patch-level filtering stages. Additionally, we applied the Macenko algorithm for color normalization to eliminate systematic errors. Following image preprocessing, we constructed a tissue-type classification model based on VGG19, which was trained and tested using the NCT-CRC-HE-100K and CRC-VAL-HE-7K datasets, both containing pixels with tissue types labeled by human experts. The trained classifier was then used to identify adenocarcinoma epithelium patches from TCGA-COAD. Subsequently, we applied multiple pre-trained Convolutional Neural Network (CNN) models, including ResNet-101, DenseNet-201, and Inception-ResNet-v2, to predict TP53 mutations for the identified adenocarcinoma epithelium patches from TCGA-COAD. A novel integration approach was employed to aggregate patch-level predictions into slide-level outcomes. We evaluated the trained models using various metrics, including accuracy, precision, recall, F1 score, AUC (Area Under the Curve), and Cohen's Kappa coefficient. The tissue-type classification model exhibited robust performance, achieving an overall accuracy of 94.7%, a Cohen's Kappa coefficient of 94%, a precision of 95.3%, a recall of 99.76%, and an F1 score of 97.48% for identifying adenocarcinoma epithelium patches. Regarding the TP53 mutation prediction models, ResNet-101, DenseNet-201, and Inception-ResNet-v2 exhibit the predictive ability to both patch level (AUC=65%) and slide level (AUC=70%). In summary, the proposed deep learning pipeline offers an efficient way to acquire gene mutation information from WSIs. Moreover, it demonstrates a capability to discover potential molecular aberration from the clinical images. Citation Format: Geng-Yun Tien, Liang-Chuan Lai, Tzu-Pin Lu, Mong-Hsun Tsai, Hsiang-Han Chen, Eric Y. Chuang. Prediction of gene mutation from colorectal adenocarcinoma whole slide images via integrated deep learning pipeline [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4938.

Deep learning-based accurate diagnosis and quantitative evaluation of microvascular invasion in hepatocellular carcinoma on whole-slide histopathology images.

Microvascular invasion (MVI) is an independent prognostic factor that is associated with early recurrence and poor survival after resection of hepatocellular carcinoma (HCC). However, the traditional pathology approach is relatively subjective, time-consuming, and heterogeneous in the diagnosis of MVI. The aim of this study was to develop a deep-learning model that could significantly improve the efficiency and accuracy of MVI diagnosis. We collected H&E-stained slides from 753 patients with HCC at the First Affiliated Hospital of Zhejiang University. An external validation set with 358 patients was selected from The Cancer Genome Atlas database. The deep-learning model was trained by simulating the method used by pathologists to diagnose MVI. Model performance was evaluated with accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve. We successfully developed a MVI artificial intelligence diagnostic model (MVI-AIDM) which achieved an accuracy of 94.25% in the independent external validation set. The MVI positive detection rate of MVI-AIDM was significantly higher than the results of pathologists. Visualization results demonstrated the recognition of micro MVIs that were difficult to differentiate by the traditional pathology. Additionally, the model provided automatic quantification of the number of cancer cells and spatial information regarding MVI. We developed a deep learning diagnostic model, which performed well and improved the efficiency and accuracy of MVI diagnosis. The model provided spatial information of MVI that was essential to accurately predict HCC recurrence after surgery.

A multi-class brain tumor grading system based on histopathological images using a hybrid YOLO and RESNET networks

Gliomas are primary brain tumors caused by glial cells. These cancers’ classification and grading are crucial for prognosis and treatment planning. Deep learning (DL) can potentially improve the digital pathology investigation of brain tumors. In this paper, we developed a technique for visualizing a predictive tumor grading model on histopathology pictures to help guide doctors by emphasizing characteristics and heterogeneity in forecasts. The proposed technique is a hybrid model based on YOLOv5 and ResNet50. The function of YOLOv5 is to localize and classify the tumor in large histopathological whole slide images (WSIs). The suggested technique incorporates ResNet into the feature extraction of the YOLOv5 framework, and the detection results show that our hybrid network is effective for identifying brain tumors from histopathological images. Next, we estimate the glioma grades using the extreme gradient boosting classifier. The high-dimensional characteristics and nonlinear interactions present in histopathology images are well-handled by this classifier. DL techniques have been used in previous computer-aided diagnosis systems for brain tumor diagnosis. However, by combining the YOLOv5 and ResNet50 architectures into a hybrid model specifically designed for accurate tumor localization and predictive grading within histopathological WSIs, our study presents a new approach that advances the field. By utilizing the advantages of both models, this creative integration goes beyond traditional techniques to produce improved tumor localization accuracy and thorough feature extraction. Additionally, our method ensures stable training dynamics and strong model performance by integrating ResNet50 into the YOLOv5 framework, addressing concerns about gradient explosion. The proposed technique is tested using the cancer genome atlas dataset. During the experiments, our model outperforms the other standard ways on the same dataset. Our results indicate that the proposed hybrid model substantially impacts tumor subtype discrimination between low-grade glioma (LGG) II and LGG III. With 97.2% of accuracy, 97.8% of precision, 98.6% of sensitivity, and the Dice similarity coefficient of 97%, the proposed model performs well in classifying four grades. These results outperform current approaches for identifying LGG from high-grade glioma and provide competitive performance in classifying four categories of glioma in the literature.

Federated Learning for Decentralized Artificial Intelligence in Melanoma Diagnostics

The development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where classifier development is distributed across hospitals. To investigate whether a more privacy-preserving federated learning approach can achieve comparable diagnostic performance to a classical centralized (ie, single-model) and ensemble learning approach for AI-based melanoma diagnostics. This multicentric, single-arm diagnostic study developed a federated model for melanoma-nevus classification using histopathological whole-slide images prospectively acquired at 6 German university hospitals between April 2021 and February 2023 and benchmarked it using both a holdout and an external test dataset. Data analysis was performed from February to April 2023. All whole-slide images were retrospectively analyzed by an AI-based classifier without influencing routine clinical care. The area under the receiver operating characteristic curve (AUROC) served as the primary end point for evaluating the diagnostic performance. Secondary end points included balanced accuracy, sensitivity, and specificity. The study included 1025 whole-slide images of clinically melanoma-suspicious skin lesions from 923 patients, consisting of 388 histopathologically confirmed invasive melanomas and 637 nevi. The median (range) age at diagnosis was 58 (18-95) years for the training set, 57 (18-93) years for the holdout test dataset, and 61 (18-95) years for the external test dataset; the median (range) Breslow thickness was 0.70 (0.10-34.00) mm, 0.70 (0.20-14.40) mm, and 0.80 (0.30-20.00) mm, respectively. The federated approach (0.8579; 95% CI, 0.7693-0.9299) performed significantly worse than the classical centralized approach (0.9024; 95% CI, 0.8379-0.9565) in terms of AUROC on a holdout test dataset (pairwise Wilcoxon signed-rank, P < .001) but performed significantly better (0.9126; 95% CI, 0.8810-0.9412) than the classical centralized approach (0.9045; 95% CI, 0.8701-0.9331) on an external test dataset (pairwise Wilcoxon signed-rank, P < .001). Notably, the federated approach performed significantly worse than the ensemble approach on both the holdout (0.8867; 95% CI, 0.8103-0.9481) and external test dataset (0.9227; 95% CI, 0.8941-0.9479). The findings of this diagnostic study suggest that federated learning is a viable approach for the binary classification of invasive melanomas and nevi on a clinically representative distributed dataset. Federated learning can improve privacy protection in AI-based melanoma diagnostics while simultaneously promoting collaboration across institutions and countries. Moreover, it may have the potential to be extended to other image classification tasks in digital cancer histopathology and beyond.

Deep Multi-Dictionary Learning for Survival Prediction With Multi-Zoom Histopathological Whole Slide Images.

Survival prediction based on histopathological whole slide images (WSIs) is of great significance for risk-benefit assessment and clinical decision. However, complex microenvironments and heterogeneous tissue structures in WSIs bring challenges to learning informative prognosis-related representations. Additionally, previous studies mainly focus on modeling using mono-scale WSIs, which commonly ignore useful subtle differences existed in multi-zoom WSIs. To this end, we propose a deep multi-dictionary learning framework for cancer survival prediction with multi-zoom histopathological WSIs. The framework can recognize and learn discriminative clusters (i.e., microenvironments) based on multi-scale deep representations for survival analysis. Specifically, we learn multi-scale features based on multi-zoom tiles from WSIs via stacked deep autoencoders network followed by grouping different microenvironments by cluster algorithm. Based on multi-scale deep features of clusters, a multi-dictionary learning method with a post-pruning strategy is devised to learn discriminative representations from selected prognosis-related clusters in a task-driven manner. Finally, a survival model (i.e., EN-Cox) is constructed to estimate the risk index of an individual patient. The proposed model is evaluated on three datasets derived from The Cancer Genome Atlas (TCGA), and the experimental results demonstrate that it outperforms several state-of-the-art survival analysis approaches.

Machine Learning of Histopathological Images Predicts Recurrences of Resected Pancreatic Ductal Adenocarcinoma With Adjuvant Treatment.

Pancreatic ductal adenocarcinoma is an intractable disease with frequent recurrence after resection and adjuvant therapy. The present study aimed to clarify whether artificial intelligence-assisted analysis of histopathological images can predict recurrence in patients with pancreatic ductal adenocarcinoma who underwent resection and adjuvant chemotherapy with tegafur/5-chloro-2,4-dihydroxypyridine/potassium oxonate. Eighty-nine patients were enrolled in the study. Machine-learning algorithms were applied to 10-billion-scale pixel data of whole-slide histopathological images to generate key features using multiple deep autoencoders. Areas under the curve were calculated from receiver operating characteristic curves using a support vector machine with key features alone and by combining with clinical data (age and carbohydrate antigen 19-9 and carcinoembryonic antigen levels) for predicting recurrence. Supervised learning with pathological annotations was conducted to determine the significant features for predicting recurrence. Areas under the curves obtained were 0.73 (95% confidence interval, 0.59-0.87) by the histopathological data analysis and 0.84 (95% confidence interval, 0.73-0.94) by the combinatorial analysis of histopathological data and clinical data. Supervised learning model demonstrated that poor tumor differentiation was significantly associated with recurrence. Results indicate that machine learning with the integration of artificial intelligence-driven evaluation of histopathological images and conventional clinical data provides relevant prognostic information for patients with pancreatic ductal adenocarcinoma.

Detection and subtyping of basal cell carcinoma in whole-slide histopathology using weakly-supervised learning

The frequency of basal cell carcinoma (BCC) cases is putting an increasing strain on dermatopathologists. BCC is the most common type of skin cancer, and its incidence is increasing rapidly worldwide. AI can play a significant role in reducing the time and effort required for BCC diagnostics and thus improve the overall efficiency of the process. To train such an AI system in a fully-supervised fashion however, would require a large amount of pixel-level annotation by already strained dermatopathologists. Therefore, in this study, our primary objective was to develop a weakly-supervised for the identification of basal cell carcinoma (BCC) and the stratification of BCC into low-risk and high-risk categories within histopathology whole-slide images (WSI). We compared Clustering-constrained Attention Multiple instance learning (CLAM) with StreamingCLAM and hypothesized that the latter would be the superior approach. A total of 5147 images were used to train and validate the models, which were subsequently tested on an internal set of 949 images and an external set of 183 images. The labels for training were automatically extracted from free-text pathology reports using a rule-based approach. All data has been made available through the COBRA dataset. The results showed that both the CLAM and StreamingCLAM models achieved high performance for the detection of BCC, with an area under the ROC curve (AUC) of 0.994 and 0.997, respectively, on the internal test set and 0.983 and 0.993 on the external dataset. Furthermore, the models performed well on risk stratification, with AUC values of 0.912 and 0.931, respectively, on the internal set, and 0.851 and 0.883 on the external set. In every single metric the StreamingCLAM model outperformed the CLAM model or is on par. The performance of both models was comparable to that of two pathologists who scored 240 BCC positive slides. Additionally, in the public test set, StreamingCLAM demonstrated a comparable AUC of 0.958, markedly superior to CLAM’s 0.803. This difference was statistically significant and emphasized the strength and better adaptability of the StreamingCLAM approach.

Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (GPT-4).

Deep learning applied to whole-slide histopathology images (WSIs) has the potential to enhance precision oncology and alleviate the workload of experts. However, developing these models necessitates large amounts of data with ground truth labels, which can be both time-consuming and expensive to obtain. Pathology reports are typically unstructured or poorly structured texts, and efforts to implement structured reporting templates have been unsuccessful, as these effortslead to perceived extra workload. In this study, we hypothesised that large language models (LLMs), such as the generative pre-trained transformer 4 (GPT-4), can extract structured data from unstructured plain language reports using a zero-shot approach without requiring any re-training. We tested this hypothesis by utilising GPT-4 to extract information from histopathological reports, focusing on two extensive sets of pathology reports for colorectal cancer and glioblastoma. We found a high concordance between LLM-generated structured data and human-generated structured data. Consequently, LLMs could potentially be employed routinely to extract ground truth data for machine learning from unstructured pathology reports in the future. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Feed-forward networks using logistic regression and support vector machine for whole-slide breast cancer histopathology image classification

The performance of an image classification depends on the efficiency of the feature learning process. This process is a challenging task that traditionally requires prior knowledge from domain experts. Recently, representation learning was introduced to extract features directly from the raw images without any prior knowledge. Deep learning using a Convolutional Neural Network (CNN) has gained massive attention for performing image classification, as it achieves remarkable accuracy that sometimes exceeds human performance. But this type of network learns features by using a back-propagation approach. This approach requires a huge amount of training data and suffers from the vanishing gradient problem that deteriorates the feature learning. The forward-propagation approach uses predefined filters or filters learned outside the model and applied in a feed-forward manner. This approach is proven to achieve good results with small size labeled datasets. In this work, we investigate the suitability of using two feed-forward methods such as Convolutional Logistic Regression Network (CLR), and Convolutional Support Vector Machine Network for Histopathology Images (CSVM-H). The experiments we have conducted on two small breast cancer datasets (Sultan Qaboos University Hospital (SQUH) and BreaKHis dataset) demonstrate the advantage of using feed-forward approaches over the traditional back-propagation ones. On those datasets, the proposed models CLR and CSVM-H were faster to train and achieved better classification performance than the traditional back-propagation methods (VggNet-16 and ResNet-50) on the SQUH dataset. Importantly, our proposed approach CLR and CSVM-H efficiently learn representations from small amounts of breast cancer whole-slide images and achieve an AUC of 0.83 and 0.84, respectively, on the SQUH dataset. Moreover, the proposed models reduce memory footprint in the classification of Whole-Slide histopathology images since their training time is significantly reduced compared to the traditional CNN on the SQUH and BreaKHis datasets.