Nicolas Michel Orsi

Background: The release of Large Language Models (LLMs) has introduced numerous benefits across the healthcare domain. This study evaluated the responses of 11 LLMs from the Claude, Mistral, Llama, and GPT families to Frequently Asked Questions (FAQs) regarding ovarian cancer with regards to three domains: (a) ease of understanding, (b) accuracy, and (c) empathy. Methods: Fifteen FAQs were sourced from the Ovarian Cancer Action (OCA) website comprising (a) anticipated questions and (b) actual questions. Responses from each of the 11 LLMs were blinded and then evaluated by three Gynaecological Oncology Surgical Fellows using a 5-point Likert scale. Inter-observer agreement was calculated for each response, and LLMs were compared across the three domains using Friedman’s test (p<0.05). Finally, all LLM responses were compared with the ones from the OCA website using the same evaluation criteria. Results: Varying levels of inter-observer agreement were observed. Claude 3 Opus produced the easiest-to-understand answers (average score 4.38), followed by Mistral Large (4.36) and GPT-4o (4.33). GPT-4o scored highest for accuracy (average score 4.24) and showed strongest performance in empathy (average of 3.87). Compared with the OCA responses, GPT-4o outperformed all models in accuracy (4.24) and empathy (3.87), with 50% of its responses rated more accurate and 70% more empathetic than the OCA content. Claude 3 Opus, Mistral Large, and Mixtral 8x7B surpassed OCA in clarity for one-third of responses, while Claude 3 Sonnet achieved the highest readability gains (40%). Conclusion: The study informs the development of LLMs suitable for patient-facing ovarian cancer communication with Claude 3 Opus and GPT-4o excelling in different metrics. While improvements in emotional intelligence remain necessary, our findings pave the way for developing a specialized LLM for ovarian cancer, using domain-specific text to provide comprehensive and empathetic information.

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 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.

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.

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.

AT-rich interaction domain 1 (ARID1A) is a pivotal gene with a significant role in gastrointestinal tumors which encodes a protein referred to as BAF250a or SMARCF1, an integral component of the SWI/SNF (SWItch/sucrose non-fermentable) chromatin remodeling complex. This complex is instrumental in regulating gene expression by modifying the structure of chromatin to affect the accessibility of DNA. Mutations in ARID1A have been identified in various gastrointestinal cancers, including colorectal, gastric, and pancreatic cancers. These mutations have the potential to disrupt normal SWI/SNF complex function, resulting in aberrant gene expression and potentially contributing to the initiation and progression of these malignancies. ARID1A mutations are relatively common in gastric cancer, particularly in specific adenocarcinoma subtypes. Moreover, such mutations are more frequently observed in specific molecular subtypes, such as microsatellite stable (MSS) cancers and those with a diffuse histological subtype. Understanding the presence and implications of ARID1A mutations in GC is of paramount importance for tailoring personalized treatment strategies and assessing prognosis, particularly given their potential in predicting patient response to novel treatment strategies including immunotherapy, poly(ADP) ribose polymerase (PARP) inhibitors, mammalian target of rapamycin (mTOR) inhibitors, and enhancer of zeste 2 polycomb repressive complex 2 subunit (EZH2) inhibitors.