Type 2 diabetes (T2D) is a chronic disease currently affecting around 500 million people worldwide with often severe health consequences. Yet, histopathological analyses are still inadequate to infer the glycaemic state of a person based on morphological alterations linked to impaired insulin secretion and β-cell failure in T2D. Giga-pixel microscopy can capture subtle morphological changes, but data complexity exceeds human analysis capabilities. In response, we generate a dataset of pancreas whole-slide images from living donors with multiple chromogenic and multiplex immunofluorescence stainings and train deep learning models to predict the T2D status. Using explainable AI, we make the learned relationships interpretable, quantify them as biomarkers, and assess their association with T2D. Remarkably, the highest prediction performance is achieved by simultaneously focusing on islet α- and δ-cells and neuronal axons, alongside subtle pancreatic alterations in T2D donors such as larger adipocyte clusters, altered islet-adipocyte proximity and smaller islets. This data-driven approach provides a foundation for future research into relevant diagnostic and therapeutic targets, refining several hypotheses regarding tissue alterations associated with T2D.

Complete tumor resection is crucial in oncological liver surgery, and the evaluation of intraoperative resection margins is essential to prove R0 resection. This can be challenging for hepatocellular carcinoma (HCC) due to the heterogeneity of both the tumor and background liver tissue. Label-free multiphoton microscopy (MPM) enables tissue analysis based on endogenous optical signals, and has the potential for intraoperative real-time assessment of resection planes. Matched samples of human HCC and background liver tissue from 76 patients were imaged using a multimodal approach, including coherent anti-Stokes Raman scattering, two-photon autofluorescence, and second harmonic generation. The morphological information contained in each channel was reduced to 17 texture parameters that were used for classification. A neural network model was trained on approximately 25,000 images (35 patients) and used to classify a test set of approximately 27,000 images (38 patients) as well as create maps showing the tumor border (3 patients). Label-free MPM revealed HCC growth patterns as well as steatotic and desmoplastic features. Accurate tumor recognition was achieved on low-lateral-resolution MPM images, mimicking the use of endoscopes. The model achieved a test set correct rate of 97.3% (98.2% for liver and 96.5% for tumor). Analysis of the contribution of the different nonlinear signals to the classification showed that autofluorescence plays a key role in discriminating between neoplastic and non-neoplastic tissue. In conclusion, label-free intraoperative optical histopathology of HCC has the potential to improve tumor resection margins. By implementation in endoscopes, MPM may enable on-site tissue analysis for optimization of tumor identification or characterization of liver tissue.

Abstract Perturbation of cell polarity is a hallmark of pancreatic ductal adenocarcinoma (PDAC) progression. Scribble (SCRIB) is a well-characterized polarity regulator that has diverse roles in the pathogenesis of human neoplasms. To investigate the impact of SCRIB deficiency in PDAC development and progression, Scrib expression was genetically ablated in well-established mouse models of PDAC. Scrib loss in combination with KrasG12D did not influence development of pancreatic intraepithelial neoplasms in mice. However, Scrib deletion cooperated with KrasG12D and concomitant Trp53 heterozygous deletion to promote invasive PDAC and metastatic dissemination, leading to reduced overall survival. Immunohistochemical and transcriptome analyses revealed that Scrib-null tumors display a pronounced reduction of collagen content and an abundance of cancer-associated fibroblasts (CAF). Mechanistically, IL1α levels were reduced in Scrib-deficient tumors, and Scrib knockdown downregulated IL1α in mouse PDAC organoids (mPDO), which impaired CAF activation. Furthermore, Scrib loss increased YAP activation in mPDOs and established PDAC cell lines, enhancing cell survival. Clinically, SCRIB expression was decreased in human PDAC, and SCRIB mislocalization was associated with poorer patient outcome. These results indicate that SCRIB deficiency enhances cancer cell survival and remodels the tumor microenvironment to accelerate PDAC development and progression, establishing the tumor suppressor function of SCRIB in advanced pancreatic cancer. Significance: SCRIB loss promotes invasive pancreatic cancer development via both cell-autonomous and non–cell-autonomous processes and is associated with poorer outcomes, denoting SCRIB as a tumor suppressor and potential biomarker for the prediction of recurrence.

The differentiation between benign and malignant biliary strictures remains a significant clinical challenge. Recent studies have suggested that next generation sequencing (NGS) can improve the diagnostic accuracy. However, evidence on its performance in routine clinical practice is limited. Therefore, validation of the diagnostic value of NGS using real-world clinical data is warranted. We compared the performance of NGS analysis of cholangiocellular carcinoma (CCC)-associated mutations in endoscopic biopsies with that of histopathology, CA19-9 and cross-sectional imaging. NGS showed higher sensitivity for malignancy (65%) compared to histopathology (52%) at similar specificity (96% vs. 100%). The combination of NGS and histopathology further increased sensitivity for malignancy to 78% (p = 0.03) at similar specificity (96%). Our data provide support for the use of NGS in the diagnostic workup of biliary strictures.

The integration of immunohistochemical biomarkers like PRAME (Preferentially Expressed Antigen in Melanoma) into the histomorphological assessment of melanocytic lesions is gaining prominence. While PRAME’s diagnostic value is widely recognized, its independent weight compared directly to classical morphology remains underexplored in large, challenging cohorts. This retrospective study quantifies the diagnostic utility of PRAME alongside traditional histomorphology in a high-risk cohort of 954 primary melanocytic lesions (335 nevi, 215 melanomas in situ, 404 invasive melanomas) where PRAME was clinically requested to resolve diagnostic ambiguity. Using Firth’s penalized likelihood regression, a baseline diagnostic model utilizing 13 histomorphological features was established and subsequently integrated with PRAME expression. The pure morphology baseline model demonstrated a high cross-validated area under the curve (AUC) of 0.969. As a standalone marker, PRAME achieved an AUC of 0.895, with a diffuse expression score of 4+ yielding peak specificity (94.3%) and moderate sensitivity (77.9%). Integrating PRAME into the morphological model significantly enhanced diagnostic accuracy (AUC: 0.980; p < 0.001), establishing PRAME as a dominant independent predictor of malignancy alongside core features like junctional atypia and upward melanocytes (Odds Ratio 19.08 for Score 4+). Analysis of discordant cases revealed that completely PRAME-negative melanomas were morphologically indistinguishable from typical PRAME-positive melanomas. Conversely, diffusely PRAME-positive (4+) nevi exhibited significantly higher rates of upward migrating melanocytes, constituting a critical diagnostic pitfall. In conclusion, while classic histomorphology remains the indispensable gold standard in dermatopathology, PRAME functions as a highly objective, reproducible tie-breaker. The synergistic integration of PRAME with morphological assessment effectively resolves diagnostic ambiguity and maximizes diagnostic confidence in challenging melanocytic lesions.

Survival analyses for PD-1 and TIGIT co-expression in blood.