Chaima Ben Rabah

Foundation models (FMs) are increasingly proposed as general-purpose solutions for computational pathology, with the potential to simplify clinical artificial intelligence deployment by reducing the need for task-specific architectures. However, their reliability across cancer domains with distinct morphological characteristics remains unclear, limiting confidence in real-world clinical use. We benchmarked seven general-purpose pathology FMs and three domain-specific FMs across eleven patch-level datasets spanning three clinically relevant domains: pediatric hematology, prostate cancer, and breast cancer, using both linear probing and last-layer fine-tuning adaptation strategies. By jointly evaluating pediatric leukemia, male-predominant prostate cancer, and female-predominant breast cancer, this study is, to our knowledge, the first to explicitly examine specialist-versus-generalist FM behavior across age- and sex-stratified cancer populations. Performance differences were strongly domain dependent. In hematology, the specialist FM DINOBloom matched and, in several datasets, marginally exceeded leading generalist models (AUC 0.990–0.999 vs. GigaPath 0.981–1.000), suggesting advantages for highly distinctive cellular morphology. In prostate cancer grading, the generalist FM UNI2-h consistently outperformed the specialist HistoEncoder (AUC 0.956–0.977 vs. 0.908–0.964). In breast cancer, UNI2-h achieved the best overall performance across all tasks. No publicly available breast-cancer-specific FM currently exists for direct comparison; therefore, breast cancer results characterize general FM transferability rather than specialist-versus-generalist differences. Importantly, cross-dataset experiments revealed substantial performance degradation under dataset shift in both prostate and breast cancer, indicating that current FMs are not yet robust enough for heterogeneous multi-site clinical use. These findings support the use of generalist FMs as efficient backbones for well-characterized single-site, patch-level tasks, while challenging the assumption that high benchmark performance necessarily reflects true clinical readiness and demonstrating that pathology FMs are not uniformly superior to specialist models.

Objective: Peripheral neuropathies contribute to patient disability but may be diagnosed late or missed altogether due to late referral, limitation of current diagnostic methods and lack of specialized testing facilities. To address this clinical gap, we developed NeuropathAI, an interpretable deep learning–based multiclass classification system for rapid, automated diagnosis and differentiation of 88 patients with diabetic peripheral neuropathy (DPN), chemotherapy‐induced peripheral neuropathy (CIPN), chronic inflammatory demyelinating polyneuropathy (CIDP), and human immunodeficiency virus‐associated sensory neuropathy (HIV‐SN). Methods: A deep learning–based multiclass system was developed to analyze corneal nerve images. These images were preprocessed to train and validate the proposed model and the diagnostic utility was evaluated from the accuracy, F1 ‐score and area under the curve to derive sensitivity, specificity and precision. Results: NeuropathAI achieved excellent results: AUC—96.75%, sensitivity—83.87%, specificity—95.07%, and demonstrated excellent discrimination for CIDP, CIPN, HIV‐SN and DPN with one‐vs‐all AUC scores of 97%, 93.1%, 99.7% and 96.9%, respectively. Explainability visualization through heatmaps demonstrated that regions of decision making by the model localized to areas with nerve fiber loss, enhancing interpretability. Interpretation: NeuropathAI achieved rapid and accurate diagnosis of four of the most prevalent peripheral neuropathies globally, underscoring the potential of artificial intelligence–driven corneal image analysis for the rapid diagnosis and differentiation of peripheral neuropathies.

Background: Breast cancer is a heterogeneous disease with distinct molecular subtypes, each requiring tailored therapeutic strategies. Accurate classification of these subtypes is crucial for optimizing treatment and improving patient outcomes. While immunohistochemistry remains the gold standard for subtyping, it is invasive and may not fully capture tumor heterogeneity. Artificial Intelligence (AI), particularly Deep Learning (DL), offers a promising non-invasive alternative by analyzing medical imaging data. Methods: In this study, we propose a multimodal DL model that integrates mammography images with clinical metadata to classify breast lesions into five categories: benign, luminal A, luminal B, HER2-enriched, and triple-negative. Using the publicly available Chinese Mammography Database (CMMD), our model was trained and evaluated on a dataset of 4056 images from 1775 patients. Results: The proposed multimodal approach significantly outperformed a unimodal model based solely on mammography images, achieving an AUC of 88.87% for multiclass classification of these five categories, compared to 61.3% AUC for the unimodal model. Conclusions: These findings highlight the potential of multimodal AI-driven approaches for non-invasive breast cancer subtype classification, paving the way for improved diagnostic precision and personalized treatment strategies.