Deep learning (DL) can accelerate the prediction of prognostic biomarkers from routine pathology slides in colorectal cancer (CRC). However, current approaches rely on convolutional neural networks (CNNs) and have mostly been validated on small patient cohorts. Here, we develop a new transformer-based pipeline for end-to-end biomarker prediction from pathology slides by combining a pre-trained transformer encoder with a transformer network for patch aggregation. Our transformer-based approach substantially improves the performance, generalizability, data efficiency, and interpretability as compared with current state-of-the-art algorithms. After training and evaluating on a large multicenter cohort of over 13,000 patients from 16 colorectal cancer cohorts, we achieve a sensitivity of 0.99 with a negative predictive value of over 0.99 for prediction of microsatellite instability (MSI) on surgical resection specimens. We demonstrate that resection specimen-only training reaches clinical-grade performance on endoscopic biopsy tissue, solving a long-standing diagnostic problem.

Cryo-electron tomography (cryo-ET) provides unique insights into macromolecular complexes in their native environments, yet membrane analysis remains a major bottleneck due to low signal-to-noise ratios, missing wedge artifacts, and the complexity of membrane-associated proteins. Existing tools often require extensive manual annotation, struggle with generalization across datasets, and lack integrated solutions for segmentation, protein localization, and quantitative analysis. We introduce MemBrain v2, a deep learning-enabled framework that unifies these tasks into a streamlined pipeline. MemBrain-seg leverages a diverse, collaboratively generated training dataset and specialized model training strategies to achieve generalizable membrane segmentation across variable tomographic conditions. MemBrain-pick enables data-efficient localization of membrane-bound proteins by integrating geometric constraints with deep learning, reducing the need for extensive manual annotation. MemBrain-stats provides quantitative insights into protein distributions, computing spatial metrics to analyze intra-membrane particle organization. MemBrain v2 integrates seamlessly into cryo-ET workflows, providing an accessible and structured approach to membrane analysis. The full package is available at https://github.com/CellArchLab/MemBrain-v2 .

Cryo-electron tomography (cryo-ET) is an imaging technique that enables 3D visualization of the native cellular environment at sub-nanometer resolution, providing unpreceded insights into the molecular organization of cells. However, cryo-electron tomograms suffer from low signal-to-noise ratios and anisotropic resolution, which makes subsequent image analysis challenging. In particular, the efficient detection of membrane-embedded proteins is a problem still lacking satisfactory solutions. We present MemBrain - a new deep learning-aided pipeline that automatically detects membrane-bound protein complexes in cryo-electron tomograms. After subvolumes are sampled along a segmented membrane, each subvolume is assigned a score using a convolutional neural network (CNN), and protein positions are extracted by a clustering algorithm. Incorporating rotational subvolume normalization and using a tiny receptive field simplify the task of protein detection and thus facilitate the network training. MemBrain requires only a small quantity of training labels and achieves excellent performance with only a single annotated membrane (F1 score: 0.88). A detailed evaluation shows that our fully trained pipeline outperforms existing classical computer vision-based and CNN-based approaches by a large margin (F1 score: 0.92 vs. max. 0.63). Furthermore, in addition to protein center positions, MemBrain can determine protein orientations, which has not been implemented by any existing CNN-based method to date. We also show that a pre-trained MemBrain program generalizes to tomograms acquired using different cryo-ET methods and depicting different types of cells. MemBrain is a powerful and annotation-efficient tool for the detection of membrane protein complexes in cryo-ET data, with the potential to be used in a wide range of biological studies. It is generalizable to various kinds of tomograms, making it possible to use pretrained models for different tasks. Its efficiency in terms of required annotations also allows rapid training and fine-tuning of models. The corresponding code, pretrained models, and instructions for operating the MemBrain program can be found at: https://github.com/CellArchLab/MemBrain.

Histopathology is the reference standard for diagnosing the presence and nature of many diseases, including cancer. However, analyzing tissue samples under a microscope and summarizing the findings in a comprehensive pathology report is time-consuming, labor-intensive, and non-standardized. To address this problem, we present HistoGPT, a vision language model that generates pathology reports from a patient’s multiple full-resolution histology images. It is trained on 15,129 whole slide images from 6705 dermatology patients with corresponding pathology reports. The generated reports match the quality of human-written reports for common and homogeneous malignancies, as confirmed by natural language processing metrics and domain expert analysis. We evaluate HistoGPT in an international, multi-center clinical study and show that it can accurately predict tumor subtypes, tumor thickness, and tumor margins in a zero-shot fashion. Our model demonstrates the potential of artificial intelligence to assist pathologists in evaluating, reporting, and understanding routine dermatopathology cases.