Abstract Polarisation microscopy is a label-free technique whose tissue architecture profiling through anisotropy remains underinvestigated. In histology, bright-field microscopy and special stains remain the standard for investigating extracellular matrix (ECM) proteins. However, these approaches are qualitative and observer-dependent. By measuring birefringence parameters, quantitative polarisation microscopy (QPM) could offer a more objective alternative. Using dual photoelastic modulators and full Stokes parameter acquisition, QPM was applied to Congo red and picrosirius red-stained sections of human placenta, normal skin, and keloid scars. From the Stokes vectors (I, Q, U, V), polarisation azimuth, ellipticity, phase retardation, and depolarisation maps were derived, enabling quantitative characterisation of collagen organisation. QPM revealed distinct anisotropic signatures corresponding to ECM microarchitecture. Picrosirius red-stained sections demonstrated a three/four-fold in phase retardation increase compared to Congo red, confirming its collagen-specific birefringent enhancement. In placenta, spatially heterogeneous birefringence highlighted perivascular collagen arrangements. In skin, stronger phase retardation and depolarisation patterns were observed in dermal collagen bundles, with keloid scars showing markedly increased phase retardation (~ 1.4 radians) and depolarisation (~ 0.96), reflecting altered collagen density and disorganisation. QPM provides objective, spatially-resolved tissue anisotropy metrics, overcoming the qualitative limitations of traditional histological techniques. This approach offers a robust framework for assessing collagen remodelling in various pathological contexts.

PROBLEM:Gestational diabetes mellitus (GDM) increases the risk of large-for-gestational-age (LGA) birth and long-term cardiometabolic complications in offspring, particularly in males. These outcomes are associated with altered placental vascularisation, but the underlying mechanisms remain poorly defined. Hofbauer cells (HBCs) are fetal-origin macrophages located in the villous stroma with established roles in immune regulation and vascularisation. METHOD OF STUDY:This study investigated whether HBC abundance and phenotype are associated with fetal growth, fetal sex, and placental vascularisation in term placentae from non-GDM and GDM pregnancies. Pan-macrophage (CD14, CD68), HBC-enriched (FOLR2, VSIG4), M1 (CD86), and M2 (CD163, MRC1) markers were assessed by RT-qPCR and quantitative immunohistochemistry. RESULTS:In both non-GDM and GDM placentae, all markers, except CD86 were detected, supporting an M2-like HBC phenotype. In GDM placentae, the number of pan-macrophage (CD68), HBC-enriched (FOLR2), and M2-associated (CD163, MRC1) cells were reduced in terminal villi compared with non-GDM controls (p < 0.05; n = 13 non-GDM; n = 12 GDM), indicating reduced HBC abundance without phenotypic switching. Reduced expression of HBC-enriched (FOLR2, VSIG4) and M2-associated (CD163) transcripts supported these findings (p < 0.05; n = 18 non-GDM; n = 19 GDM). No further differences were observed following stratification by fetal growth or sex. HBC-related gene expression correlated positively with the endothelial marker PECAM1/CD31, in both non-GDM and GDM placentae (r ≥ 0.5, p < 0.05). CONCLUSIONS:HBCs abundance is reduced in GDM placentae independently of fetal growth or sex, whilst HBC phenotype is preserved. Reduced HBC abundance may contribute to placental vascular alterations that are characteristic of GDM.

BACKGROUND:As the histopathology workforce continues to struggle and service demand continues to increase, it has become prudent to consider viable avenues to try to alleviate diagnostic workload burden. One such avenue is computer-based technologies (CBTs). Breast cancer (BC) is the most common malignant neoplasm in the United Kingdom and requires additional testing for estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor-2 (HER2) status at the time of histological diagnosis. This makes BC diagnostics a promising candidate for the application of an efficient CBT. However, for clinical acceptance, these technologies must prove that they work within a real-life diagnostic environment. OBJECTIVE:We present a study protocol for a prospective clinical service evaluation aimed to validate a UK Conformity Assessed-marked CBT's ability to provide ER, PR, and HER2 results for invasive BCs from scanned hematoxylin and eosin-stained whole slide images. METHODS:This protocol has been designed to use and mimic a preexisting digital pathology workflow within a National Health Service tertiary referral cancer center without disrupting normal patient care. Eligible cases are identified prospectively through the laboratory information management system, and their whole slide images are extracted from the clinical digital workflow. After verification of national data opt-out status and the exclusion of appropriate cases (N=400 analyzable cases), these cases are analyzed on a dedicated computer in parallel to the existing clinical workflow by a UK Conformity Assessed-marked deep learning-based CBT in a separate environment, providing results for ER, PR, and HER2 status. These results are compared to the ER, PR, and HER2 status reported on the corresponding pathology report. To evaluate the CBT's performance, a range of accepted concordance measures will be applied, including specificity, sensitivity, false-positive rate, false-negative rate, positive predictive value, and negative predictive value. Moreover, time stamps representing the duration of image analysis will also be collected. RESULTS:This study started in April 2025. There are no results to present, as this paper focuses on study design, and results have yet to be generated. As of March 2026, overall, 366 potentially analyzable cases have been collected. The anticipated end date of the study is May 2026 (400-case target). Results will be presented in a separate publication. CONCLUSIONS:This design assesses a CBT within a clinical environment while effectively eliminating any unwanted effects on patient care. This type of service evaluation provides a useful step to establish confidence in a CBT before trialing its effect on patient care. It also offers the opportunity to support interventional randomized controlled trials, health economic evaluations, and usability studies. This protocol will hopefully prove useful to others who wish to conduct a similar service evaluation at their own institution. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID):DERR1-10.2196/76785.

3520 Background: Mismatch repair (MMR) deficiency and microsatellite instability (MSI) testing is integral to colorectal cancer management. Despite guideline recommendations, routine testing remains limited by cost, turnaround time, and pathology resources. PANProfiler Colorectal (PPC) is an artificial intelligence (AI) system that infers MSI/MMR status directly from H&E-stained whole slide images (WSIs), offering a rapid, resource-efficient alternative. This study reports blinded validation of PPC, specifically evaluating performance across clinically relevant subgroups. Methods: A total of 2,636 WSIs from St. James’s University Hospital (Leeds, UK) were retrospectively analyzed, with the dataset representing a broad range of clinicopathological characteristics including age ( < 50 to > 75 years), gender, tumor stage, differentiation, and histological subtypes. PPC returned proficient MMR ( pMMR ), deficient MMR ( dMMR ) or indeterminate (no definitive result), with results evaluated for agreement against immunohistochemistry. Results: PPC generated definitive results for 2,109 WSIs, achieving a test replacement rate (TRR) of 80%. Overall positive percent agreement (PPA) was 97.9% and negative percent agreement (NPA) 93.8% (Table). Performance was consistent across all age groups and genders. PPA and NPA were mostly robust in all cancer stages, with PPA exceeding 99% in Stage II disease, where MMR status primarily informs adjuvant therapy decisions. In Stage III/IV disease, PPA reduced to 82.6%, which may reflect greater histological heterogeneity in advanced tumors. In mucinous and poorly differentiated tumors, PPA remained high (98.7-100%), supporting reliable detection of dMMR samples, while NPA ranged from 75.4-80%, indicating more conservative classification of pMMR tumors that would require lab tests. Conclusions: PPC demonstrated a high overall performance, providing definitive results for the majority of cases. PPA and NPA were consistent in key clinical groups, including younger patients and early stage disease. In more challenging cases like mucinous and poorly differentiated tumors, PPA remained robust despite reductions in NPA, supporting safe guidance of subsequent testing. These findings suggest PPC could streamline MSI/MMR workflows, reducing reliance on conventional testing while maintaining diagnostic safety across diverse clinicopathological profiles. Performance across diverse subgroups. Overall Age <50 Age 50-65 Age 65-75 Age >75 Male Female Stage I Stage II Stage III/IV Well Diff. Moderately Diff. Poorly Diff. Adenocarcinoma Mucinous Definitive (n) 2109 155 159 698 703 1165 944 395 1015 694 245 1655 187 1879 210 PPA (%) 97.9 100 100 92.1 100 95.5 99.4 97.8 99.5 82.6 100 96 100 99.5 98.7 NPA (%) 93.8 91.7 98 91.3 94.1 95.5 91.5 95.1 91.8 95.5 92.5 95.6 80 95.3 75.4 TRR (%) 80 74.5 76.4 81.2 82.2 81.1 78.7 74.5 81 81.8 76.1 80.8 80.3 82.4 63.6

Background/Objectives: Surgical pathology of tubo-ovarian and peritoneal cancer carries a well-recognised diagnostic workload, partly due to the large amount of non-primary tumour-related tissue requiring assessment for the presence of metastatic disease. The lymph nodes and omentum are almost universally included in such resection cases and contribute considerably to this burden, principally due to volume rather than task complexity. To date, artificial intelligence (AI)-based studies have reported good success rates in identifying nodal spread in other malignancies, but the development of such time-saving assistive digital solutions has been neglected in ovarian cancer. This study aimed to detect the presence or absence of metastatic ovarian carcinoma in the lymph nodes and omentum. Methods: We used attention-based multiple-instance learning (ABMIL) with a vision-transformer foundation model to classify whole-slide images (WSIs) as either containing ovarian carcinoma metastases or not. Training and validation were conducted with a total of 855 WSIs of surgical resection specimens collected from 404 patients at Leeds Teaching Hospitals NHS Trust. Results: Ensembled classification from hold-out testing reached an AUROC of 0.998 (0.985-1.0) and a balanced accuracy of 100% (100.0-100.0%) in the lymph node set, and an AUROC of 0.963 (0.911-0.999) and a balanced accuracy of 98.0% (94.8-100.0%) in the omentum set. Conclusions: This model shows great potential in the identification of ovarian carcinoma nodal and omental metastases, and could provide clinical utility through its ability to pre-screen WSIs prior to histopathologist review. In turn, this could offer significant time-saving benefits and streamline clinical diagnostic workflows, helping to address the chronic staffing shortages in histopathology.

Computer vision models are increasingly capable of classifying ovarian epithelial cancer subtypes, but they differ from pathologists by independently processing small single-resolution tissue patches. Multi-resolution graph models leverage the spatial relationships of patches at multiple magnifications, learning the context for each patch. In this study, we conduct the most thorough validation of graph models for ovarian cancer subtyping to date. Seven models were tuned and trained using five-fold cross-validation on a set of 1864 whole slide images (WSIs) from 434 patients treated at Leeds Teaching Hospitals NHS Trust. The cross-validation models were ensembled and evaluated using a balanced hold-out test set of 100 WSIs from 30 patients, and an external validation set of 80 WSIs from 80 patients in the Transcanadian Study. The best-performing model, a graph model using 10x + 20x magnification data, gave balanced accuracies of 73 https://github.com/scjjb/MultiscalePathGraph .

The Whitten effect is a widely used tool for manipulating the mouse estrous cycle and generating reproductively active females within the laboratory setting. Typically, peak numbers of sexually receptive mice occur following exposure to male pheromones, resulting in a higher number of successful copulations on the third day after exposure. Although this method has improved efficiencies, the percentage of females mated and subsequently deemed to be pregnant/pseudopregnant remains relatively low, around 50%. In experiment 1, we aimed to 1) further understand cyclicity; 2) determine whether the initial cycle stage plays an importance on day 3 receptivity; and 3) identify any repetitive patterns/cycle stabilization. Mice (n = 27) were assigned to group cages according to cycle stage (proestrus, estrus, metestrus, diestrus). Experiment 2 was developed to determine an optimum treatment to promote receptivity by exposure to various pheromone stimuli. Mice (n = 45) were randomly assigned to 5 treatment groups (PBS-treated sham soiled bedding, male soiled bedding, live male, pregnant females, and lactating females). In both experiments, daily vaginal cytology was performed for 21 days to determine the cycle stage. Results from experiment 1 indicate that the initial cycle stage did not contribute to day 3 receptivity, although synchronization within several groups/cages was noted, and that the greatest numbers of estrous animals were obtained on days 6 and 7. Experiment 2 revealed that exposure to live males and lactating females both significantly improved receptivity compared with the PBS, male soiled bedding, and pregnant female groups. These results indicate that current strategies used for routine synchronization could be further improved through alternative housing regimens without compromising animal welfare.

Mismatch repair (MMR) deficiency occurs in 10-20% of colorectal cancer (CRC) cases, leading to microsatellite instability (MSI). Although MSI/MMR testing is critical for CRC management, high costs and long turnaround times limit testing rates and clinical utility, highlighting the need for more accessible, cost-effective alternatives. PANProfiler Colorectal (PPC) is an artificial intelligence (AI)-based biomarker test that determines MSI/MMR status directly from haematoxylin and eosin (H&E)-stained slides. We conducted a blinded, multi-centred validation to assess PPC's performance against standard testing. The study included 3,576 whole slide images from 1,243 CRC patients across three United Kingdom institutions. PPC produced definitive results for 86.55% of slides, achieving an overall agreement of 93.83%, positive agreement of 92.54%, and negative agreement of 94.02%. PPC accurately determined MSI/MMR status from routine H&E slides, offering a rapid, scalable alternative to conventional diagnostic methods.

BACKGROUND:PANProfiler Breast is a UKCA-marked, deep-learning image analysis tool. It provides oestrogen and progesterone receptor (ER/PR) status and identifies human epidermal growth factor receptor-2 (HER2) negativity from whole slide images (WSIs) of haematoxylin and eosin (H&E)-stained breast cancer (BC) tissue. This study blindly validated PANProfiler's prediction of ER/PR status and identification of HER2 negative status. MATERIALS AND METHODS:Three cohorts of WSIs of H&E-stained BC specimens were used for calibration (200 cases, 344 WSIs) and blind validation (200 cases, 348 WSIs). For the blind validation, PANProfiler analysed WSIs to provide results for ER, PR ("Positive," "Negative," or "Indeterminate") and HER2 ("Negative" or "Indeterminate"). These were compared to the corresponding pathology reports. To discern PANProfiler's performance, concordance and other metrics were calculated, including test replacement rate (TRR) (cases PANProfiler produced a definitive result for) and complete test replacement rate (CTTR) (cases with definitive results for all markers). RESULTS:Following blind validation, concordance for ER and PR status across the cohorts was 90%-93% and 86%-91%, respectively. The TRR for ER was 70%-84% and 55%-84% for PR. For HER2 negative cases, concordance across cohorts was 91%-100%, with a TRR ranging from 22% to 27%. CTTRs for the cohorts were between 18% and 20%. CONCLUSION:PANProfiler Breast showed high concordance for ER and PR status and identified HER2 negativity from WSIs of H&E-stained BCs. For HER2 negativity, whilst the TRR was lower than that of ER and PR, the high level of concordance indicated its reliability in identifying negative cases.

In brief:Superovulation is widely used in reproductive technologies, but its impact on ovarian vascular development and oocyte quality remains poorly understood. This study provides the first 3D quantitative analysis of perifollicular vasculature in superovulated mice, revealing dose-dependent vascular changes and offering a novel imaging approach for reproductive research. Abstract:Superovulation is widely used to maximise oocyte/embryo yield in animal models. However, it has been implicated in disrupting normal follicular development, potentially affecting perifollicular angiogenesis. This study investigated the impact of superovulation on ovarian perifollicular neoangiogenesis using light sheet fluorescence microscopy (LSFM), and by quantitatively profiling the three-dimensional (3D) perifollicular capillary bed in murine antral follicles. Dioestrus CD1 mice received 2.5, 5.0 or 7.5 IU pregnant mare serum gonadotrophin (PMSG) intraperitoneally, and ovaries were collected 24 and 48 h later, with those from normal cycling females (dioestrus, proestrus or oestrus) as controls. Ovaries were fixed and labelled with fluorescently tagged wheat germ agglutinin lectin and anti-CD34 to visualise the oocyte zona pellucida and thecal vasculature, respectively. Optically cleared samples were imaged using LSFM, and 3D volume rendering, vessel segmentation and image analysis were performed using Arivis Vision 4D and Fiji. Quantitative metrics including vessel volume, length, branching, density, spatial arrangement and oocyte characteristics were profiled. Statistical analysis was based on Kruskal-Wallis tests. PMSG-induced superovulation showed dose-dependent effects on perifollicular vasculature, causing premature (24 h) neoangiogenesis at 7.5 IU (increase in total vessel volume, length and number of branches, and decrease in average branch length; P < 0.05 for all), and reduced final (48 h) vessel density at 2.5 IU compared to naturally cycling animals (P < 0.05). The early angiogenesis observed at 7.5 IU may reflect a compensatory mechanism, while the reduced density at 2.5 IU suggests an insufficient angiogenic response. By contrast, intrafollicular metrics were largely unaffected. This study provides the first comprehensive quantitative 3D analysis of thecal vasculature and oocytes in murine ovaries, and highlights its potential applications in other areas of reproductive biology.

Background: The advent of artificial intelligence (AI) has revolutionised many fields in healthcare. More recently, it has garnered interest in terms of its potential applications in histopathology, where algorithms are increasingly being explored as adjunct technologies that can support pathologists in diagnosis, molecular typing and prognostication. While many research endeavours have focused on solid tumours, gynaecological malignancies have nevertheless been relatively overlooked. The aim of this review was therefore to provide a summary of the status quo in the field of AI in gynaecological pathology by encompassing malignancies throughout the entirety of the female reproductive tract rather than focusing on individual cancers. Methods: This narrative/scoping review explores the potential application of AI in whole slide image analysis in gynaecological histopathology, drawing on both findings from the research setting (where such technologies largely remain confined), and highlights any findings and/or applications identified and developed in other cancers that could be translated to this arena. Results: A particular focus is given to ovarian, endometrial, cervical and vulval/vaginal tumours. This review discusses different algorithms, their performance and potential applications. Conclusions: The effective application of AI tools is only possible through multidisciplinary co-operation and training.

44 Background: Testing for microsatellite instability (MSI) or mismatch repair deficiency (dMMR) is part of the diagnosis and clinical management of patients with colorectal cancer (CRC). Healthcare services recommend MSI or dMMR testing for all CRC patients to guide therapeutic choices and assist in identifying Lynch Syndrome. However, in clinical practice, high costs and the demand for timely test results, combined with the rising prevalence of CRC and a shrinking pathology workforce, present a barrier to universal adoption. This highlights the need for rapid and affordable alternatives. PANProfiler CRC (PPC) is a deep learning-based solution for detecting MSI/dMMR in CRC tumors that only requires whole slide images (WSIs) of haematoxylin and eosin (H&E)-stained tissue to provide test results. Using only WSIs, PPC offers an efficient alternative to standard testing. This study evaluates PPC's performance in a multi-site blinded setting. Methods: Blinded validation was performed using 3246 WSIs of H&E-stained CRC specimens. PPC provided outputs as "Stable", "Unstable", or "Indeterminate", with "Unstable" indicating dMMR or MSI-High, and "Stable" indicating proficient mismatch repair or non-MSI-High. "Indeterminate" was returned when PPC did not have a definitive result. PPC was evaluated by comparison to standard MSI/dMMR tests. Validation data spanned three cohorts from two sites (Table). St James’s University Hospital (SJUH), Leeds, UK, supplied Cohorts 1 and 2; Cohort 3 was sourced from Wales Cancer Biobank (WCB), UK. Blinded analysis was performed at SJUH. Results: Results are given (Table). PPC demonstrated an overall percent agreement of 93.91%, a positive percent agreement of 92.17%, and a negative percent agreement of 94.15%, returning a definitive result for 88.05% of WSIs. Conclusions: This real-world, multi-site, blinded validation study demonstrates PPC’s remarkable performance, comparable to standard tests for detecting MSI/dMMR in CRC, with high test replacement rates. In the clinical setting, PPC could significantly accelerate testing and enable timely delivery of stratified treatment plans. This accurate and cost-effective diagnostic solution promises to revolutionize MSI/dMMR testing in CRC. Blinded validation results of PPC with confidence intervals (CI) at 95%. Site Cohort Sample Size (Unstable; Stable) Overall Percent Agreement % (CI) Positive Percent Agreement % (CI) Negative Percent Agreement %(CI) Test Replacement Rate % SJUH 1 488 (78; 410) 92.79 (89.86-95.08) 90.16 (79.81-96.30) 93.24(90.11-95.62) 85.25 SJUH 2 2704 (318; 2386) 94.31(93.31-95.21) 92.31(88.48-95.18) 94.57(93.52-95.50) 88.42 WCB 3 54 (11; 43) 84.31 (71.41-92.98) 100.00(71.51-100.00) 80.00(64.35-90.95) 94.44 All 3246 (407; 2839) 93.91 (92.97-94.76) 92.17(88.82-94.78) 94.15(93.16-95.04) 88.05

BACKGROUND:The kynurenine pathway is a key immunosuppressive mechanism implicated in resistance to immune checkpoint inhibitors (ICIs). This study investigated expression of tryptophan-metabolising enzymes (IDO1, TDO2, IL4I1) and their relationship with the immune microenvironment across molecular subtypes of endometrial cancer (EC). METHODS:A cohort of 570 ECs was classified as mismatch repair-deficient (MMRd), p53-mutant (p53mut), or no specific molecular profile (NSMP). Expression of IDO1, TDO2, IL4I1, PD-L1, kynurenine, and immune markers (CD8, FOXP3, CD68, CD163) was assessed by immunohistochemistry and quantified in tumour and stromal compartments using QuPath. Associations with disease-specific survival (DSS) were analysed using correlation testing, Kaplan-Meier, and Cox regression. RESULTS:IDO1, TDO2, and IL4I1 correlated strongly with immune infiltrate density. High IDO1 tumour expression was linked to improved DSS in NSMP and p53mut tumours (p < 0.05), consistent with an "inflamed" phenotype. In contrast, high TDO2 stromal expression predicted reduced DSS in NSMP patients (p < 0.05). Elevated IL4I1 tumour expression was associated with improved DSS in MMRd tumours (p < 0.05). A high CD163:CD8 ratio independently predicted worse DSS in p53mut tumours (p < 0.05). Both TDO2 and IL4I1 were highly expressed high-risk tumours, particularly p53mut cases. CONCLUSIONS:Tryptophan-kynurenine enzymes shape the immune landscape of EC in a subtype-specific manner. High IDO1 was linked to favourable outcomes in p53mut and NSMP cases, whereas TDO2 predicted poor prognosis. The CD163:CD8 ratio emerged as an independent marker of poor survival. These findings support therapeutic strategies combining dual IDO1/TDO2 inhibition or targeting the IL4I1- aryl hydrocarbon receptor (AhR) axis to enhance immunotherapy efficacy in EC.

e15718 Background: Microsatellite instability (MSI) and mismatch repair (MMR) testing is critical for guiding therapeutic decisions in colorectal cancer (CRC). Despite their clinical importance, routine MSI/MMR testing faces significant challenges, including high costs, long turnaround times, and pathology workforce shortages. Artificial intelligence (AI) offers opportunities to overcome these barriers through data-driven solutions. To maximize the clinical utility and performance of AI-based approaches, it is crucial to identify and analyze the key predictors of MSI/MMR status. Such analysis not only aids in developing more accurate predictive models, but also supports efforts to adapt diagnostic tools to diverse patient populations. To this end, we conducted a comprehensive study with a real-world clinical dataset of retrospective CRC cases to identify the critical factors associated with MSI/MMR status. Methods: Clinical and histopathological data from 800 CRC cases at St James’s University Hospital (UK) were analyzed using a random forest (RF) classifier to identify the most important predictors for determining the overall MSI/MMR status. MSI/MMR testing was done as part of routine clinical care, with 11.9% of cases classified as MMR-deficient/MSI-high (n = 95). Normalized importance values were computed for each feature to quantify their contribution. Pairwise correlation analysis was conducted using Cramer's V and Chi-squared tests to evaluate interdependencies among features. The cohort included 308 patients (38.5%) under 65 years of age and 492 patients (61.5%) aged 65 or older, with a higher proportion of males (n = 453, 56.6%) compared to females (n = 347, 43.4%). The majority of patients were diagnosed with Stage II and III cancers (n = 557, 69.6%) and had tumors graded as moderately differentiated (n = 620, 78.6%). The primary tumor site was the colon (n = 528, 66.0%) and the most common histological subtype was adenocarcinoma (n = 686, 85.8%). Results: The classifier identified age as the most influential feature associated with MSI/MMR status, with an importance of 52.9%. Stage and grade were the next most significant contributors, accounting for 17.0% and 12.2%, respectively. Histological subtype and tumor site were less influential, with contributions of 7.8% and 6.0%, respectively. Gender was the least impactful factor, with an importance of 4.1%. Pairwise correlation analysis showed weak associations among individual features, with all Cramer's V values below 0.26 and Chi-squared tests indicating statistical significance (p < 0.001). Conclusions: Our analysis highlights the role of age, stage, and grade in determining MSI/MMR status, with minimal interdependencies among features. These results provide valuable insights for refining predictive models and advancing the development of reliable, generalizable diagnostic tools for diverse CRC patient populations.

Background Endometrial carcinoma (EC) is the most common uterine cancer in the USA with rising incidence and mortality rates. Microcephalin 1 (MCPH1) and Bromodomain Containing 4 (BRD4) are DNA repair proteins involved in maintaining genomic stability and chromatin regulation. Dysregulated expression of these genes has been linked to poorer patient outcomes in EC. Immunotherapy, particularly immune checkpoint inhibitors (ICIs), has emerged as a promising treatment for EC. However, response rates are variable, indicating the need to identify novel biomarkers to improve patient stratification for immunotherapy. This study assessed the association between MCPH1 and BRD4 mRNA and protein expression and EC clinical and molecular biomarkers, particularly immune markers. Methods Immunohistochemistry was performed on 403 ECs. Nuclear staining was quantified using Qu-Path software to generate H Scores. Both continuous and categorised data analysis were performed for clinical parameters, p53 mutational status, mismatch repair deficiency and ICI related markers PD-1, PD-L1 and CD8. Statistical analysis included Chi-squared, Fisher’s exact, Mann-Whitney U, Kruskal Willis, Kaplan-Meier and Cox regression. Results High MCPH1 (p=0.034) and BRD4 (p=0.044) protein expression levels were both significantly associated with reduced disease specific survival (DSS). High MCPH1 protein levels were also an independent predictor of DSS. MCPH1 protein expression showed no significant association with clinical parameters. By contrast, high BRD4 protein expression was significantly associated with non-endometrioid EC (p=0.003), high tumour grade (p=0.052) and lymphovascular space invasion (p=0.052). MCPH1 protein upregulation correlated significantly with CD8 infiltrate, PD-L1, PD-1, and mismatch repair proficiency (MMRp). In addition, BRD4 protein expression correlated with p53 mutation, CD8 infiltrate, PD-L1 and PD-1 expression. Conclusions High MCPH1 and BRD4 protein expression was associated with immune activation markers and worse survival in EC, suggesting their potential as prognostic biomarkers. Both MCPH1 and BRD4 may also represent potential predictive markers for response to ICI therapy in EC.

Histopathology foundation models show great promise across many tasks, but analyses have been limited by arbitrary hyperparameters. We report the most rigorous single-task validation study to date, specifically in the context of ovarian carcinoma morphological subtyping. Attention-based multiple instance learning classifiers were compared using three ImageNet-pretrained encoders and fourteen foundation models, each trained with 1864 whole slide images and validated through hold-out testing and two external validations (the Transcanadian Study and OCEAN Challenge). The best-performing classifier used the H-optimus-0 foundation model, with balanced accuracies of 89%, 97%, and 74%, though UNI achieved similar results at a quarter of the computational cost. Hyperparameter tuning the classifiers improved performance by a median 1.9% balanced accuracy, with many improvements being statistically significant. Foundation models improve classification performance and may allow for clinical utility, with models providing a second opinion in challenging cases and potentially improving the accuracy and efficiency of diagnoses.