Whole-slide Images Research Articles

Mesothelin expression prediction in pancreatic cancer based on multimodal stochastic configuration networks.

Predicting tumor biomarkers with high precision is essential for improving the diagnostic accuracy and developing more effective treatment strategies. This paper proposes a machine learning model that utilizes CT images and biopsy whole slide images (WSI) to classify mesothelin expression levels in pancreatic cancer. By combining multimodal learning and stochastic configuration networks, a radiopathomics mesothelin-prediction system named RPMSNet is developed. The system extracts radiomic and pathomic features from CT images and WSI, respectively, and sends them into stochastic configuration networks for the final prediction. Compared to traditional radiomics or pathomics, this system has the capability to capture more comprehensive image features, providing a multidimensional insight into tissue characteristics. The experiments and analyses demonstrate the accuracy and effectiveness of the system, with an area under the curve of 81.03%, an accuracy of 73.67%, a sensitivity of 71.54%, a precision of 76.78%, and a F1-score of 72.61%, surpassing both single-modality and dual-modality models. RPMSNet highlights its potential for early diagnosis and personalized treatment in precision medicine.

Diagnostic value of artificial intelligence-based pathology diagnosis system in lymphatic metastasis of gastric cancer.

Introduction Gastric cancer remains one of the leading causes of cancer-related mortality worldwide, with lymph node metastasis (LNM) being an independent prognostic factor. However, there are still challenges in the pathological diagnosis of LNM in gastric cancer (GC). The aim of this meta-analysis is to systematically evaluate the accuracy of artificial intelligence (AI) in detecting LNM in GC from whole-slide pathological images.. Methods As of March 24, 2024, a comprehensive search for studies on the pathological diagnosis of GC LNM AI was performed in the databases of PubMed, Web of Science, Cochrane Library, and CNKI. Meta-analysis of the included data was performed using Meta-Disc 1.4, Review Manager 5.4, and Stata SE 17.0 software to calculate diagnostic metrics such as overall sensitivity and specificity. The overall diagnostic performance of the AI was assessed. Meta-regression analysis explored sources of heterogeneity. Results A total of 7 articles involving 1,669 GC patients were included. The analysis showed that AI had a sensitivity of 0.90 (95% CI: 0.84-0.94) and a specificity of 0.95 (95% CI: 0.91-0.98) for the diagnosis of GC LNM, with significant heterogeneity across studies. The area under the curve was 0.97, indicating an excellent diagnostic value. Meta-regression analysis showed that the sample size and the number of study centers contributed to the heterogeneity. Conclusion AI for diagnosing LNM in GC from whole-slide pathological images demonstrates high accuracy, offering significant clinical implications for improving diagnosis and treatment strategies.

A histopathology-based artificial intelligence system assisting the screening of genetic alteration in intrahepatic cholangiocarcinoma.

Targeted therapy for intrahepatic cholangiocarcinoma (ICC) shows superior survival outcomes but patients with certain targetable alterations are no more than 20%. Genetic alteration screening for all ICC patients is of high cost and not routinely performed. This study intends to develop a histopathology-based artificial intelligence (AI)-assisted system for predicting genetic alteration of ICC. We constructed a Genetic Alteration Prediction (GAP) system based on multi-instance learning and self-supervised learning to predict genetic alterations using whole-slide images (WSIs) of H&E-stained slides. A total of 2069 WSIs from 232 ICC patients underwent surgery of the FAH-SYSU dataset were used for model construction and adjustment by five-fold cross-validation. Another 150 patients from three medical centres were used as independent external validations. We also compared the cost-effectiveness of GAP-assisted precise treatment and all-sequencing strategy to non-sequencing strategy. The GAP was able to predict actionable genetic alterations of ICC, including FGFR2 and IDH. The area under the receiver operating characteristic curves (AUC) for FGFR2 and IDH were 0.754 and 0.713 in the internal dataset, and 0.724 and 0.656 in the external dataset, respectively. Furthermore, compared to giving chemotherapy without sequencing for every patient, GAP-assisted precise treatment could increase 1 progression-free quality-adjusted life month with a cost of $13871.72, the co-responding figure for all-sequencing strategy is $44538.93. Decision curve analysis showed that AI-assisted strategy provides better clinical benefits. We constructed an AI-assisted genetic alteration screening system which is predictable to ICC actionable targets and has potential to assist precise targeted treatment of advanced ICC.

A novel AI-based score for assessing the prognostic value of intra-epithelial lymphocytes in oral epithelial dysplasia.

Oral epithelial dysplasia (OED) poses a significant clinical challenge due to its potential for malignant transformation and the lack of reliable prognostic markers. Current OED grading systems do not reliably predict transformation and suffer from considerable observer variability. Recent studies have highlighted that peri-epithelial lymphocytes may play an important role in OED malignant transformation, with indication that intra-epithelial lymphocytes (IELs) may also be important. We propose a novel artificial intelligence (AI) based IEL score from Haematoxylin and Eosin (H&E) stained Whole Slide Images (WSIs) of OED tissue slides. We determine the prognostic value of our IEL score on a digital dataset of 219 OED WSIs (acquired using three different scanners), compared to pathologist-led clinical grading. Our IEL scores demonstrated significant prognostic value (C-index = 0.67, p < 0.001) and were shown to improve both the binary/WHO grading systems in multivariate analyses (p < 0.001). Nuclear analyses confirmed the positive association between higher IEL scores, more severe OED and malignant transformation (p < 0.05). This underscores the potential importance of IELs, and by extension our IEL score, as prognostic indicators in OED. Further validation through prospective multi-centric studies is warranted to confirm the clinical utility of IELs.

Multiple-Instance Learning for thyroid gland disease classification: A hands-on experience

The morphological diagnosis of thyroid gland neoplasms presents a dual challenge: it requires the expertise of highly trained specialists and considerable time, particularly when evaluating multiple whole slide images (WSIs) from a single patient. The integration of artificial intelligence (AI) techniques into the diagnostic workflow is a hot area of research. However, most studies rely on meticulously curated datasets, the preparation of which is both costly and fraught with complexities. This paper investigates the development of machine learning models using weakly-annotated “real-world” data, devoid of the selective preprocessing typical in common research datasets. Our study demonstrates that a Multiple-Instance Learning (MIL) model, trained on a weak patient-level annotations of 1102 patients encompassing 5104 WSIs, successfully discriminates between benign and malignant conditions at the patient level, achieving an average test set F1-Score of 0.85 with a standard deviation of 0.05. This study is, to our knowledge, the first to report findings from an AI model trained on patient-level data without prior labeling refinement. Additionally, we identify potential pitfalls in data quality that could induce model overfitting, such as the inadvertent inclusion of dye used to highlight resection margins, which correlates with the target variable. We also assessed the impact of detailed slide-level versus coarse patient-level annotations on classification accuracy using a smaller, more precisely annotated dataset of 36 laboratory cases (91 WSIs). The results indicate that detailed annotations substantially enhance classification performance in smaller datasets.

Deciphering cell to cell spatial relationship for pathology images using SpatialQPFs

Understanding spatial dynamics within tissue microenvironments is crucial for deciphering cellular interactions and molecular signaling in living systems. These spatial characteristics govern cell distribution, extracellular matrix components, and signaling molecules, influencing local biochemical and biophysical conditions. Despite significant progress in analyzing digital pathology images, current methods for capturing spatial relationships are limited. They often rely on specific spatial features that only partially describe the complex spatial distributions of cells and are frequently tied to particular outcomes within predefined model frameworks. Furthermore, these methods are typically limited to field of view analysis, which restricts their capacity to capture spatial patterns across whole-slide images, thereby limiting their ability to fully address the complexities of tissue architecture. To address these limitations, we present SpatialQPFs (Spatial Quantitative Pathology Features), an R package designed to extract interpretable spatial features from cell imaging data using spatial statistical methodologies. Leveraging segmented cell information, our package offers a comprehensive toolkit for applying a range of spatial statistical methods within a stochastic process framework, including analyses of point process data, areal data, and geostatistical data. By decoupling feature extraction from specific outcome models, SpatialQPFs enables thorough large-scale spatial analyses applicable across diverse clinical and biological contexts. This approach enhances the depth and accuracy of spatial insights derived from tissue data, empowering researchers to conduct comprehensive spatial analyses efficiently and reproducibly. By providing a flexible and robust framework for spatial feature extraction, SpatialQPFs facilitates advanced spatial analyses, paving the way for new discoveries in tissue biology and pathology. SpatialQPFs code and documentation are publicly available at https://github.com/Genentech/SpatialQPFs.

Deep learning algorithm on H&E whole slide images to characterize TP53 alterations frequency and spatial distribution in breast cancer

The tumor suppressor TP53 is frequently mutated in hormone receptor-negative, HER2-positive breast cancer (BC), contributing to tumor aggressiveness. Traditional ancillary methods like immunohistochemistry (IHC) to assess TP53 functionality face pre- and post-analytical challenges. This proof-of-concept study employed a deep learning (DL) algorithm to predict TP53 mutational status from H&E-stained whole slide images (WSIs) of BC tissue. Using a pre-trained convolutional neural network, the model identified tumor areas and predicted TP53 mutations with a Dice coefficient score of 0.82. Predictions were validated through IHC and next-generation sequencing (NGS), confirming TP53 aberrant expression in 92 % of the tumor area, closely matching IHC findings (90 %). The DL model exhibited high accuracy in tissue quantification and TP53 status prediction, outperforming traditional methods in terms of precision and efficiency. DL-based approaches offer significant promise for enhancing biomarker testing and precision oncology by reducing intra- and inter-observer variability, but further validation is required to optimize their integration into real-world clinical workflows. This study underscores the potential of DL algorithms to predict key genetic alterations, such as TP53 mutations, in BC. DL-based histopathological analysis represents a valuable tool for improving patient management and tailoring treatment approaches based on molecular biomarker status.

Multiple Instance Bagging and Risk Histogram for Survival Time Analysis Based on Whole Slide Images of Brain Cancer Patients

This study tackles the challenges in computer-aided prognosis for glioblastoma multiforme, a highly aggressive brain cancer, using only whole slide images (WSIs) as input. Unlike traditional methods that rely on random selection or region-of-interest (ROI) extraction to choose meaningful subsets of patches representing the whole slide, we propose a multiple instance bagging approach. This method utilizes all patches extracted from the whole slide, employing different subsets in each training epoch, thereby leveraging information from the entire slide while keeping the training computationally feasible. Additionally, we developed a two-stage framework based on the ResNet-CBAM model which estimates not just the usual survival risk, but also predicts the actual survival time. Using risk scores of patches estimated from the risk estimation stage, a risk histogram can be constructed and used as input to train a survival time prediction model. A censor hinge loss based on root mean square error was also developed to handle censored data when training the regression model. Tests using the Cancer Genome Atlas Program’s glioblastoma public database yielded a concordance index of 73.16±2.15%, surpassing existing models. Log-rank testing on predicted high- and low-risk groups using the Kaplan–Meier method revealed a p-value of 3.88×10−9, well below the usual threshold of 0.005, indicating the model’s ability to significantly differentiate between the two groups. We also implemented a heatmap visualization method that provides interpretable risk assessments at the patch level, potentially aiding clinicians in identifying high-risk regions within WSIs. Notably, these results were achieved using 98% fewer parameters compared to state-of-the-art models.

Prognostic and predictive value of pathohistological features in gastric cancer and identification of SLITRK4 as a potential biomarker for gastric cancer

The aim of this study was to develop a quantitative feature-based model from histopathologic images to assess the prognosis of patients with gastric cancer. Whole slide image (WSI) images of H&E-stained histologic specimens of gastric cancer patients from The Cancer Genome Atlas were included and randomly assigned to training and test groups in a 7:3 ratio. A systematic preprocessing approach was employed as well as a non-overlapping segmentation method that combined patch-level prediction with a multi-instance learning approach to integrate features across the slide images. Subjects were categorized into high- or low-risk groups based on the median risk score derived from the model, and the significance of this stratification was assessed using a log-rank test. In addition, combining transcriptomic data from patients and data from other large cohort studies, we further searched for genes associated with pathological features and their prognostic value. A total of 165 gastric cancer patients were included for model training, and a total of 26 features were integrated through multi-instance learning, with each process generating 11 probabilistic features and 2 predictive labeling features. We applied a 10-fold Lasso-Cox regression model to achieve dimensionality reduction of these features. The predictive accuracy of the model was verified using Kaplan-Meyer (KM) curves for stratification with a consistency index of 0.741 for the training set and 0.585 for the test set. Deep learning-based resultant supervised pathohistological features have the potential for superior prognostic stratification of gastric cancer patients, transforming image pixels into an effective and labor-saving tool to optimize the clinical management of gastric cancer patients. Also, SLITRK4 was identified as a prognostic marker for gastric cancer.

Dual attention model with reinforcement learning for classification of histology whole-slide images

Digital whole slide images (WSIs) are generally captured at microscopic resolution and encompass extensive spatial data (several billions of pixels per image). Directly feeding these images to deep learning models is computationally intractable due to memory constraints, while downsampling the WSIs risks incurring information loss. Alternatively, splitting the WSIs into smaller patches (or tiles) may result in a loss of important contextual information. In this paper, we propose a novel dual attention approach, consisting of two main components, both inspired by the visual examination process of a pathologist: The first soft attention model processes a low magnification view of the WSI to identify relevant regions of interest (ROIs), followed by a custom sampling method to extract diverse and spatially distinct image tiles from the selected ROIs. The second component, the hard attention classification model further extracts a sequence of multi-resolution glimpses from each tile for classification. Since hard attention is non-differentiable, we train this component using reinforcement learning to predict the location of the glimpses. This approach allows the model to focus on essential regions instead of processing the entire tile, thereby aligning with a pathologist’s way of diagnosis. The two components are trained in an end-to-end fashion using a joint loss function to demonstrate the efficacy of the model. The proposed model was evaluated on two WSI-level classification problems: Human epidermal growth factor receptor 2 (HER2) scoring on breast cancer histology images and prediction of Intact/Loss status of two Mismatch Repair (MMR) biomarkers from colorectal cancer histology images. We show that the proposed model achieves performance better than or comparable to the state-of-the-art methods while processing less than 10% of the WSI at the highest magnification and reducing the time required to infer the WSI-level label by more than 75%. The code is available at github.

Generating and evaluating synthetic data in digital pathology through diffusion models

Synthetic data is becoming a valuable tool for computational pathologists, aiding in tasks like data augmentation and addressing data scarcity and privacy. However, its use necessitates careful planning and evaluation to prevent the creation of clinically irrelevant artifacts.This manuscript introduces a comprehensive pipeline for generating and evaluating synthetic pathology data using a diffusion model. The pipeline features a multifaceted evaluation strategy with an integrated explainability procedure, addressing two key aspects of synthetic data use in the medical domain.The evaluation of the generated data employs an ensemble-like approach. The first step includes assessing the similarity between real and synthetic data using established metrics. The second step involves evaluating the usability of the generated images in deep learning models accompanied with explainable AI methods. The final step entails verifying their histopathological realism through questionnaires answered by professional pathologists. We show that each of these evaluation steps are necessary as they provide complementary information on the generated data’s quality.The pipeline is demonstrated on the public GTEx dataset of 650 Whole Slide Images (WSIs), including five different tissues. An equal number of tiles from each tissue are generated and their reliability is assessed using the proposed evaluation pipeline, yielding promising results.In summary, the proposed workflow offers a comprehensive solution for generative AI in digital pathology, potentially aiding the community in their transition towards digitalization and data-driven modeling.

NACNet: A histology context-aware transformer graph convolution network for predicting treatment response to neoadjuvant chemotherapy in Triple Negative Breast Cancer

Neoadjuvant chemotherapy (NAC) response prediction for triple negative breast cancer (TNBC) patients is a challenging task clinically as it requires understanding complex histology interactions within the tumor microenvironment (TME). Digital whole slide images (WSIs) capture detailed tissue information, but their giga-pixel size necessitates computational methods based on multiple instance learning, which typically analyze small, isolated image tiles without the spatial context of the TME. To address this limitation and incorporate TME spatial histology interactions in predicting NAC response for TNBC patients, we developed a histology context-aware transformer graph convolution network (NACNet). Our deep learning method identifies the histopathological labels on individual image tiles from WSIs, constructs a spatial TME graph, and represents each node with features derived from tissue texture and social network analysis. It predicts NAC response using a transformer graph convolution network model enhanced with graph isomorphism network layers. We evaluate our method with WSIs of a cohort of TNBC patient (N=105) and compared its performance with multiple state-of-the-art machine learning and deep learning models, including both graph and non-graph approaches. Our NACNet achieves 90.0% accuracy, 96.0% sensitivity, 88.0% specificity, and an AUC of 0.82, through eight-fold cross-validation, outperforming baseline models. These comprehensive experimental results suggest that NACNet holds strong potential for stratifying TNBC patients by NAC response, thereby helping to prevent overtreatment, improve patient quality of life, reduce treatment cost, and enhance clinical outcomes, marking an important advancement toward personalized breast cancer treatment.

Characterization of Breast Cancer Intra-Tumor Heterogeneity Using Artificial Intelligence.

Intra-tumor heterogeneity (ITH) is a fundamental characteristic of breast cancer (BC), influencing tumor progression, prognosis, and therapeutic responses. However, the complexity of ITH in BC makes its accurate characterization challenging. This study leverages deep learning (DL) techniques to comprehensively evaluate ITH in early-stage luminal BC and provide a nuanced understanding of its impact on tumor behavior and patient outcomes. A large cohort (n = 2561) of early-stage luminal BC was evaluated using whole slide images (WSIs) of hematoxylin and eosin-stained slides of excision specimens. Morphological features of both the tumor and stromal components were meticulously annotated by a panel of pathologists in a subset of cases. A DL model was applied to develop an algorithm to assess the degree of heterogeneity of various morphological features per individual case utilizing defined patches. The results of extracted features were used to generate an overall heterogeneity score that was correlated with the clinicopathological features and outcome. Overall, 162 features were quantified and a significant positive correlation between these features was identified. Specifically, there was a significant association between a high degree of intra-tumor heterogeneity and larger tumor size, poorly differentiated tumors, highly proliferative tumors, tumors of no special type (NST), and those with low estrogen receptor (ER) expression. When all features are considered in combination, a high overall heterogeneity score was significantly associated with parameters characteristic of aggressive tumor behavior, and it was an independent predictor of poor patient outcome. In conclusion, DL models can be used to accurately decipher the complexity of ITH and provide extra information for outcome prediction.

Improved DeTraC Binary Coyote Net-Based Multiple Instance Learning for Predicting Lymph Node Metastasis of Breast Cancer From Whole-Slide Pathological Images.

Early detection of lymph node metastasis in breast cancer is vital for improving treatment outcomes and prognosis. This study introduces an Improved Decompose, Transfer, and Compose Binary Coyote Net-based Multiple Instance Learning (ImDeTraC-BCNet-MIL) method for predicting lymph node metastasis from Whole Slide Images (WSIs) using multiple instance learning. The method involves segmenting WSIs into patches using Otsu and double-dimensional clustering techniques. The developed multiple instance learning approach introduces a paradigm into computational pathology by shaping pathological data and constructing features. ImDeTraC-BCNet-MIL was utilised for feature generation during both training and testing to differentiate lymph node metastasis in WSIs. The proposed model achieves the highest accuracy of 95.3% and 99.8%, precision values of 98% and 99.8%, and recall rates of 92.9% and 99.8% on the Camelyon16 and Camelyon17 datasets. These findings underscore the effectiveness of ImDeTraC-BCNet-MIL in enhancing the early detection of lymph node metastasis in breast cancer.

Development of CytoAcademy: a new web- and mobile-based E-learning platform for cytopathologists and cytotechnologists by the Korean Society for Cytopathology in the post-pandemic era.

Since the late 1990s, online e-learning has offered unparalleled convenience and affordability, becoming increasingly popular among pathologists. Traditional learning theories have been successfully applied to web/mobile-based learning systems, with mobile technologies even enhancing conventional offline education. In cytopathology, hands-on microscope training has traditionally been paramount, complemented by real-case presentations and lectures. However, the coronavirus disease 2019 (COVID-19) pandemic disrupted regular academic activities, making online e-learning platforms essential. We designed a web/mobile-based learning platform to enhance continued medical education in cytopathology at various levels, particularly during the era of COVID-19 and beyond. Since 2021, we have integrated curriculum materials, virtual education files, and whole-slide images (WSIs) of cytopathology, submitted from over 200 institutions across Korea, with the support of numerous instructors. We develop a new e-learning platform named "CytoAcademy" composed of a basic session for each organ and level across the range of morphologic findings; on-demand lectures to enhance cytopathologic knowledge; WSI archives that allow users to explore various histologically confirmed cases; and a self-assessment test to help organize diagnostic knowledge acquired through the web/mobile-friendly learning system. The platform provides not just an opportunity to achieve a correct diagnosis, but also a learning experience based on problem-solving point. Members interact, identify their deficiencies, and focus on specific educational materials. In this manner, all participants can actively engage in creating and maintaining knowledge and foster a proactive approach to learning.

Digital profiling of gene expression from histology images with linearized attention

Cancer is a heterogeneous disease requiring costly genetic profiling for better understanding and management. Recent advances in deep learning have enabled cost-effective predictions of genetic alterations from whole slide images (WSIs). While transformers have driven significant progress in non-medical domains, their application to WSIs lags behind due to high model complexity and limited dataset sizes. Here, we introduce SEQUOIA, a linearized transformer model that predicts cancer transcriptomic profiles from WSIs. SEQUOIA is developed using 7584 tumor samples across 16 cancer types, with its generalization capacity validated on two independent cohorts comprising 1368 tumors. Accurately predicted genes are associated with key cancer processes, including inflammatory response, cell cycles and metabolism. Further, we demonstrate the value of SEQUOIA in stratifying the risk of breast cancer recurrence and in resolving spatial gene expression at loco-regional levels. SEQUOIA hence deciphers clinically relevant information from WSIs, opening avenues for personalized cancer management.

Dual-Attention Multiple Instance Learning Framework for Pathology Whole-Slide Image Classification

Conventional methods for tumor diagnosis suffer from two inherent limitations: they are time-consuming and subjective. Computer-aided diagnosis (CAD) is an important approach for addressing these limitations. Pathology whole-slide images (WSIs) are high-resolution tissue images that have made significant contributions to cancer diagnosis and prognosis assessment. Due to the complexity of WSIs and the availability of only slide-level labels, multiple instance learning (MIL) has become the primary framework for WSI classification. However, most MIL methods fail to capture the interdependence among image patches within a WSI, which is crucial for accurate classification prediction. Moreover, due to the weak supervision of slide-level labels, overfitting may occur during the training process. To address these issues, this paper proposes a dual-attention-based multiple instance learning framework (DAMIL). DAMIL leverages the spatial relationships and channel information between WSI patches for classification prediction, without detailed pixel-level tumor annotations. The output of the model preserves the semantic variations in the latent space, enhances semantic disturbance invariance, and provides reliable class identification for the final slide-level representation. We validate the effectiveness of DAMIL on the most commonly used public dataset, Camelyon16. The results demonstrate that DAMIL outperforms the state-of-the-art methods in terms of classification accuracy (ACC), area under the curve (AUC), and F1-Score. Our model also allows for the examination of its interpretability by visualizing the dual-attention weights. To the best of our knowledge, this is the first attempt to use a dual-attention mechanism, considering both spatial and channel information, for whole-slide image classification.

Lymph Node Metastasis Prediction From In Situ Lung Squamous Cell Carcinoma Histopathology Images Using Deep Learning

Lung squamous cell carcinoma (LUSC), a subtype of non–small cell lung cancer, represents a significant portion of lung cancer cases with distinct histologic patterns impacting prognosis and treatment. The current pathological assessment methods face limitations such as interobserver variability, necessitating more reliable techniques. This study seeks to predict lymph node metastasis in LUSC using deep learning models applied to histopathology images of primary tumors, offering a more accurate and objective method for diagnosis and prognosis. Whole slide images (WSIs) from the Outdo-LUSC and the cancer genome atlas cohorts were used to train and validate deep learning models. Multiinstance learning was applied, with patch-level predictions aggregated into WSI-level outcomes. The study employed the ResNet-18 network, transfer learning, and rigorous data preprocessing. To represent WSI features, innovative techniques like patch likelihood histogram and bag of words were used, followed by training of machine learning classifiers, including the ExtraTrees algorithm. The diagnostic model for lymph node metastasis showed strong performance, particularly using the ExtraTrees algorithm, as demonstrated by receiver operating characteristic curves and gradient-weighted class activation mapping visualizations. The signature generated by the ExtraTrees algorithm, named lymph node status-related in situ LUSC histopathology (LN_ISLUSCH), achieved an area under the curve of 0.941 (95% CI: 0.926-0.955) in the training set and 0.788 (95% CI: 0.748-0.827) in the test set. Kaplan-Meier analyses confirmed that the LN_ISLUSCH model was a significant prognostic factor (P = .02). This study underscores the potential of artificial intelligence in enhancing diagnostic precision in pathology. The LN_ISLUSCH model stands out as a promising tool for predicting lymph node metastasis and prognosis in LUSC. Future studies should focus on larger and more diverse cohorts and explore the integration of additional omics data to further refine predictive accuracy and clinical utility.

Foundation models for fast, label-free detection of glioma infiltration.

A critical challenge in glioma treatment is detecting tumour infiltration during surgery to achieve safe maximal resection1-3. Unfortunately, safely resectable residual tumour is found in the majority of patients with glioma after surgery, causing early recurrence and decreased survival4-6. Here we present FastGlioma, a visual foundation model for fast (<10 s) and accurate detection of glioma infiltration in fresh, unprocessed surgical tissue. FastGlioma was pretrained using large-scale self-supervision (around 4 million images) on rapid, label-free optical microscopy, and fine-tuned to output a normalized score that indicates the degree of tumour infiltration within whole-slide optical images. In a prospective, multicentre, international testing cohort of patients with diffuse glioma (n = 220), FastGlioma was able to detect and quantify the degree of tumour infiltration with an average area under the receiver operating characteristic curve of 92.1 ± 0.9%. FastGlioma outperformed image-guided and fluorescence-guided adjuncts for detecting tumour infiltration during surgery by a wide margin in a head-to-head, prospective study (n = 129). The performance of FastGlioma remained high across diverse patient demographics, medical centres and diffuse glioma molecular subtypes as defined by the World Health Organization. FastGlioma shows zero-shot generalization to other adult and paediatric brain tumour diagnoses, demonstrating the potential for our foundation model to be used as a general-purpose adjunct for guiding brain tumour surgeries. These findings represent the transformative potential of medical foundation models to unlock the role of artificial intelligence in the care of patients with cancer.

Deep-Learning-Based Approach in Cancer-Region Assessment from HER2-SISH Breast Histopathology Whole Slide Images.

Fluorescence in situ hybridization (FISH) is widely regarded as the gold standard for evaluating human epidermal growth factor receptor 2 (HER2) status in breast cancer; however, it poses challenges such as the need for specialized training and issues related to signal degradation from dye quenching. Silver-enhanced in situ hybridization (SISH) serves as an automated alternative, employing permanent staining suitable for bright-field microscopy. Determining HER2 status involves distinguishing between "Amplified" and "Non-Amplified" regions by assessing HER2 and centromere 17 (CEN17) signals in SISH-stained slides. This study is the first to leverage deep learning for classifying Normal, Amplified, and Non-Amplified regions within HER2-SISH whole slide images (WSIs), which are notably more complex to analyze compared to hematoxylin and eosin (H&E)-stained slides. Our proposed approach consists of a two-stage process: first, we evaluate deep-learning models on annotated image regions, and then we apply the most effective model to WSIs for regional identification and localization. Subsequently, pseudo-color maps representing each class are overlaid, and the WSIs are reconstructed with these mapped regions. Using a private dataset of HER2-SISH breast cancer slides digitized at 40× magnification, we achieved a patch-level classification accuracy of 99.9% and a generalization accuracy of 78.8% by applying transfer learning with a Vision Transformer (ViT) model. The robustness of the model was further evaluated through k-fold cross-validation, yielding an average performance accuracy of 98%, with metrics reported alongside 95% confidence intervals to ensure statistical reliability. This method shows significant promise for clinical applications, particularly in assessing HER2 expression status in HER2-SISH histopathology images. It provides an automated solution that can aid pathologists in efficiently identifying HER2-amplified regions, thus enhancing diagnostic outcomes for breast cancer treatment.