Colorectal cancer is one of the most common malignancies and the third leading cause of cancer-related mortality worldwide. Identifying KRAS, NRAS, and BRAF mutations and estimating MSI status is closely related to the individualized therapeutic judgment and oncologic prognosis of CRC patients. In this study, we introduce a cascaded network framework with an average voting ensemble strategy to sequentially identify the tumor regions and predict gene mutations & MSI status from whole-slide H&E images. Experiments on a colorectal cancer dataset indicate that the proposed method can achieve higher fidelity in both gene mutation prediction and MSI status estimation. In the testing set, our method achieves 0.792, 0.886, 0.897, and 0.764 AUCs for KRAS, NRAS, BRAF, and MSI, respectively. The results suggest that the deep convolutional networks have the potential to provide diagnostic insight and clinical guidance directly from pathological H&E slides.

Thyroid cancer is the most common form of endocrine malignancy and fine needle aspiration (FNA) cytology is a reliable method for clinical diagnosis. Identification of genetic mutation status has been proved efficient for accurate diagnosis and prognostic risk stratification. In this study, a dataset with thyroid cytological images of 310 indeterminate (TBS3 or 4) and 392 PTC (TBS5 or 6) was collected. We introduced a multimodal cascaded network framework to estimate BARF V600E and RAS mutations directly from thyroid cytological slides. The area under the curve in the external testing set achieved 0.902 ± 0.063 and 0.801 ± 0.137 AUCs for BRAF, and RAS, respectively. The results demonstrated that deep neural networks have the potential in cytologically predicting valuable diagnosis and comprehensive genetic status.

Background: Helicobacter pylori (H. pylori) eradication is increasingly compromised by antibiotic resistance, particularly to clarithromycin (CLA) and fluoroquinolones (FQs). Culture-based and molecular susceptibility testing remain resource-intensive and inaccessible in many settings. Whether routine hematoxylin and eosin (H&E) histopathology encodes indirect signatures of resistance has not been explored. Materials and Methods: We developed a weakly supervised deep learning framework to predict phenotypic H. pylori resistance directly from gastric biopsy whole-slide images (WSIs). Patches were filtered using vision-language models (VLMs; Qwen3-VL and MedGemma) performing two zero-shot classification tasks—grading patch image quality and identifying gastric surface or gland-neck epithelium—based solely on visible histo-morphological features. Retained patches were encoded with VIRCHOW2, a histopathology-specific vision foundation model (ViT-H/14, pretrained on 3.1 million WSIs), and aggregated via cross-attention for slide-level prediction. Polymerase chain reaction (PCR)-confirmed resistance phenotypes served as ground truth in a multicenter cohort of 755 patients. Results: In the independent test set (n = 151), the framework achieved an area under the receiver operating characteristic curve (AUC) of 0.903 for CLA resistance and 0.959 for FQs resistance. At the default threshold (0.5), sensitivity was 85.2% for CLA and 98.1% for FQs, supporting use as a screening tool. Threshold optimization by the Youden index improved specificity to 95.9% for CLA and 93.9% for FQs, enabling rule-in risk stratification. Decision curve analysis confirmed net clinical benefit across a broad range of threshold probabilities. Conclusion: Routine H&E-stained gastric biopsies contain probabilistic morphological correlates of H. pylori resistance phenotypes that deep learning can exploit. This approach provides complementary decision support for resistance risk stratification, particularly in resource-limited settings, pending prospective validation.