Journal of Pathology Informatics

Background: General-purpose large language models (LLMs) are increasingly evaluated in diagnostic pathology, but prior studies have largely emphasized diagnostic accuracy rather than how models fail. We evaluated four LLMs for diagnostic performance, pathology-relevant errors and hallucinations, their burden, and potential clinical impact across multi-organ pathology cases. Design: In this retrospective multicenter study, 153 pathology cases from two institutions spanning 20 organs were evaluated using ChatGPT-5.3 (LLM1), Gemini 3 (LLM2), Grok 4.20 (LLM3), and Claude Opus 4.6 (LLM4). Each LLM received multi-magnification histologic images with clinical context and generated a microscopic description and diagnosis. No data splitting, training, or fine-tuning was performed. Twenty-one pathologists assessed 612 outputs for diagnostic correctness, error and hallucination type and burden, clinical impact (0-4), and overall performance (1-5). Results: Strict diagnostic accuracy was 48.9% overall (60.1% including partially correct diagnoses) and ranged from 36.6% to 58.2% across LLMs. Errors occurred in 82.0% of outputs and hallucinations in 76.6%; 90.2% contained at least one error or hallucination. Misinterpretation was the most frequent error (72.1%), while fabricated histologic features were the dominant hallucination type (74.5%). LLM2 had significantly lower misinterpretation rates than the other three LLMs, while LLM3 had significantly higher fabricated-feature hallucination rates than LLM1 and LLM2. Errors were more frequent in incorrect than correct diagnoses (97.5% vs 66.2%), as were hallucinations (95.1% vs 59.9%; both p < 0.001). Every strictly incorrect diagnosis contained an error and/or hallucination, while 79.9% of strictly correct diagnoses also contained at least one. In multivariable analysis, LLM3 was independently associated with higher odds of an incorrect diagnosis. Diagnostic correctness was the strongest determinant of high clinical impact; each one-point increase in hallucination burden increased the odds by 63% (adjusted OR, 1.63). Conclusion: Diagnostic accuracy alone substantially underestimates the safety limitations of general-purpose LLMs in histopathology. Errors and hallucinations were common even when the final diagnosis was correct, and their burden was independently associated with clinical impact. Evaluation frameworks should therefore assess both diagnostic correctness and the reliability and potential consequences of accompanying generated content.

Foundation models (FMs) have rapidly become dominant in artificial intelligence and are increasingly being adopted in computational pathology. Numerous pathology-specific FMs have been developed and evaluated for a variety of downstream tasks, most commonly using frozen image embeddings with linear probes. While a pathology FM, at least implicitly suggests broad reusability across tasks, the transferability of these models to neurodegenerative disease-related tasks remains largely unexplored. In this study, we evaluated fourteen frozen feature extractors, including general-vision and pathology FMs, across four pathology image classification datasets spanning two specialized neurodegenerative disease immuno-histochemistry (IHC) tasks (Tau neurofibrillary tangle (NFT) and amyloid-{beta} plaque classification) and two cancer-related hematoxylin and eosin (H&E) tasks (the breast tissue BACH dataset and the multi-tissue TIL dataset). The cancer-related H&E datasets represent tasks more closely aligned with the predominant pretraining domain of many current pathology FMs, whereas the neurodegenerative IHC datasets represent a more specialized domain with limited representation in existing FM pretraining cohorts. Frozen embedding linear probes were compared against a conventional supervised ResNet-50 convolutional neural network (CNN) trained directly on image tiles using identical train, validation, and test splits. Across both neurodegenerative IHC datasets, the supervised CNN substantially outperformed all frozen FM linear probes. In contrast, pathology FMs achieved performance comparable to, and in some cases exceeding, the supervised CNN across the two cancer-related H&E datasets, with UNI2-h achieving the highest performance on BACH and several pathology FMs performing on par with the CNN on the larger TIL dataset. Furthermore, a supervised CNN trained using only 1% of the Tau NFT training data (1,938 tiles) still exceeded the performance of the best frozen FM linear probe trained on the complete dataset. Together, these results suggest the transferability of frozen pathology FMs may depend strongly on how well the downstream task is represented by their pretraining domain. These findings demonstrate frozen pathology FMs transfer effectively to the cancer-related H&E tasks evaluated here but may be less effective for specialized neurodegenerative IHC tasks less well represented in current FM pretraining cohorts. Expanding pathology FM pretraining datasets to include a broader range of disease domains and staining modalities may therefore improve transferability to specialized pathology applications. Our findings also highlight the continued importance of conventional supervised learning and motivate future work investigating nonlinear probes and end-to-end FM fine-tuning.

Cervical cytology screening relies on the visual assessment of nuclear and cellular morphology across thousands of cells per slide, a labor-intensive task that could benefit from quantitative computational support. Here we present CytoLens, a modular deep learning system that detects and counts nuclei, delineates nuclei and whole cells, measures the nuclear-to-cell area ratio (N:C), classifies cells from multifocal images and scores candidate abnormality. We trained and tested each module on a public dataset matched to its task, without pooling datasets. CytoLens detected nuclei with an F1 score of 0.931 (95% confidence interval (CI), 0.914-0.946) and counted 75 of 100 fields to within one nucleus. Point-prompted segmentation achieved mean Dice coefficients of 0.901 for nuclei and 0.847 for whole cells and, without retraining, transferred to a second dataset in which measured N:C increased with lesion grade in parallel with expert outlines. Multifocal hierarchical classification reached a mean accuracy of 0.947 across four Bethesda-aligned categories, and abnormality scores ranked annotated abnormal candidates with an area under the receiver operating characteristic curve (AUROC) of 0.865. These results support the evaluation of CytoLens on patient-linked clinical specimens.

Current state of the art computational pathology foundation models attain satisfying accuracy most general pathology tasks including detection of pancreatic ductal adenocarcinoma (PDAC) but fail to provide sufficient explainability, operating as "black boxes". Some interpretability effort has been made, with models providing attention maps that project back on the slide the models high attended areas that pushed for the given prediction result, without further naming or reasoning explanation which can limit pathologists trust toward the prediction. We developed C3PRO, a cell-centric framework attempting to provide deeper understanding and explainability, by using embeddings extracted using a pathology foundation model, from cell centered tiles containing both the cell and its close neighborhood, which were then clustered into recurrent morphological phenotypes. A spatial graph was additionally constructed on top of the back-projected vocabulary to account for recurrent motifs. The evaluation of the model performance involved a cohort of 809 patients (825 diagnostic biopsies) using nested cross validation. C3PRO was benchmarked against four different multiple instance learning frameworks and achieved on-par performance for diagnostic (0.958 AUC), survival (0.617) and resectability (0.696) prediction, while providing additional insights compared to the strongest baseline models. Each clustered phenotype was probed and extracted as a representative tile mosaic and annotated by two expert pathologists, constituting a phenotype vocabulary available for statistical analysis. These phenotypes were scored by pathologists with physical brightfield microscopy and replicated the independent statistical significance impact on overall survival prediction from diagnostic biopsies.

Objectives To assess the effectiveness of our proposed urinary segmentation method based upon image processing, and to contrast its performance against various approaches. Subjects and Methods Non-contrast-enhanced computed tomography (NCCT) scans of instances with stone disease were collected. An experienced urologist and a senior radiology resident generated ground truths by manually drawing the regions of interest (ROIs) of stone samples. The proposed method took loosely defined ROIs as input and included three steps: (1) finding mean_HU_rim, the mean Hounsfield unit (HU) of the stone rim, on each NCCT slice by an edge detection operator; (2) considering pixels with HU higher than the minimum value of all the mean_HU_rim; and (3) removing noise. The entire data was divided into a developing set of 406 samples to evaluate the performance of the proposed method as well as to fine-tune a nnUNetv2 model and a comparison test set of 125 samples to compare the performance and inference time of various segmentation methods. In addition, the reproducibility of our method was tested on the 30 samples randomly selected from the entire data. Results A total of 531 stone samples from 287 instances were included. Our method showed a high level of agreement with the ground truth in the developing set, with the median (interquartile range) Dice coefficient of 0.86 (0.81 - 0.89). The reproducibility of our method was remarkably high with the median (interquartile range) Dice coefficient of 1.0 (0.991 - 1.0). On the comparison test set, our semi-automatic segmentation outperformed the fixed thresholding and deep-learning-based methods. Lastly, the inference time of the proposed method was less than a second. Conclusion The proposed semi-automatic approach provided a consistently reliable, simple, and robust method to segment urinary stones.

Background: Artificial intelligence (AI) models for mammography can achieve high diagnostic performance when training and test data originate from similar populations and imaging environments, but performance often deteriorates under cross- cohort domain shift. Differences in acquisition systems, image characteristics, preprocessing, population composition, and disease prevalence can introduce distributional variation that is poorly captured by conventional within- dataset validation. Recent studies have further shown that Foundation Model representations can retain substantial dataset-specific information. However, it remains unclear how image representation influences diagnostic transfer to completely unseen cohorts and whether domain-adversarial learning provides comparable benefits across different representation types. Methods: We systematically evaluated cross-cohort mammography classification using seven independent datasets spanning diverse geographic, institutional, scanner, and imaging environments. Three image representations were compared: handcrafted radiomic features, EfficientNet-B0-derived features, and embeddings from the medical vision-language model MedSigLIP-448. Each was evaluated under three preprocessing conditions: unprocessed images, Otsu-based breast-region extraction, and Otsu extraction combined with Contrast Limited Adaptive Histogram Equalization (CLAHE). Patient-level classification was performed using a mean-pooled multilayer perceptron (MLP) baseline and an attention-based Domain-Adversarial Neural Network (DANN). Generalization was evaluated using a multi-source Leave-One-Domain-Out (LODO) framework in which six datasets were used for model development and the seventh was completely withheld as an unseen test cohort, iteratively across all seven datasets. Performance was primarily assessed by area under the receiver operating characteristic curve (AUC-ROC). Results: Cross-cohort performance depended strongly on image representation and model architecture. MedSigLIP consistently provided the highest performance on unseen cohorts. With MedSigLIP features, mean LODO AUC-ROC increased from 0.598 with MLP to 0.685 with DANN for unprocessed images, from 0.607 to 0.678 after Otsu preprocessing, and from 0.603 to 0.659 after CLAHE+Otsu preprocessing. When DANN-MLP differences were evaluated across held-out datasets and preprocessing conditions, a significant gain was observed for MedSigLIP after correction for multiple comparisons, whereas corresponding gains were not significant for Radiomics or EfficientNet-B0. A mixed-effects analysis similarly showed a positive MedSigLIP X DANN interaction, although this narrowly missed conventional statistical significance. Unprocessed images produced the highest numerical mean performance for MedSigLIP-DANN, but preprocessing itself had no significant overall effect. Notably, linear probing showed strong dataset discriminability in MedSigLIP and EfficientNet representations but little linearly recoverable dataset information in Radiomics, indicating that low dataset separability alone did not predict better diagnostic generalization. Conclusion: Cross-cohort mammography generalization depends strongly on the choice of image representation and its interaction with the classification strategy. MedSigLIP provided the most transferable representation in our multi-source unseen-domain evaluation, and the performance gain associated with DANN was concentrated in MedSigLIP rather than consistently observed across representation types. These findings suggest that the effectiveness of domain-adversarial learning is representation-dependent and that neither conventional preprocessing nor low dataset discriminability alone ensures robust transfer to unseen clinical cohorts.

Purpose: To quantify the sampling error of conventional 2D regions of interest (ROIs) compared with whole-organ 3D volumetric CT attenuation for opportunistic hepatic steatosis screening, and to evaluate its dependency on intraparenchymal spatial heterogeneity. Materials and Methods: In this retrospective computational study (CLAIM-compliant), 971 abdominal CT scans were analyzed across a multicenter derivation cohort (TotalSegmentator v2, n = 841) and an external validation cohort (Medical Segmentation Decathlon Task03, n = 130). Automated 3D liver segmentation was performed using nnU-Net, followed by an 8-mm spherical 3D erosion to eliminate peripheral partial volume effects and major hilar vessels. Three clinical sampling paradigms (1, 3, and 5 axial 2D ROIs of 15 mm diameter) were modeled through 500 stochastic Monte Carlo iterations per scan (485,500 total simulations). Absolute sampling error (|Delta HU| = |HU_ROI - HU_3D|) and diagnostic misclassification rates at the standard <= 40 HU steatosis threshold were computed. Results: In the derivation cohort, the conventional 3-ROI approach yielded a mean absolute error of 6.61 +/- 7.83 HU (median: 2.92 HU), significantly underperforming compared to the 5-ROI strategy (5.21 +/- 6.00 HU; Wilcoxon paired test, p < 0.001) but improving on the single-ROI approach (11.32 +/- 14.16 HU; p < 0.001). Sampling error correlated strongly with parenchymal spatial heterogeneity (Pearson r = 0.850, 95% CI: [0.830-0.868], p < 0.001). In borderline attenuation zones (35-45 HU), diagnostic misclassification reached 45.2% in heterogeneous livers. Findings were corroborated on external validation, confirming the reproducible decay of sampling error (|Delta HU| = 7.38 HU for 1 ROI vs. 5.14 HU for 3 ROI, p < 0.001). Conclusion: Manual 2D ROI sampling exhibits an intrinsic metrological uncertainty exceeding clinically relevant thresholds (5 HU) in heterogeneous livers, misclassifying nearly half of borderline cases. Opportunistic screening requires fully automated 3D volumetric extraction embedded into clinical PACS workflows.

Background: Clinical registries and institutional quality control (QC) in pathology heavily depend on complex histopathological data. However, critical tumor characteristics are mostly locked in unstructured free-text reports. We hypothesize that locally deployed, resource-efficient language models operating within a secure institutional network can reliably extract relevant variables from German reports of hepatocellular carcinoma (HCC), thereby enabling automated data curation without transferring sensitive patient data. Methods: We developed a local, privacy-preserving open-weight Large Language Model (LLM) pipeline consisting of two consecutive stages: Stage 1 utilizes a lightweight gatekeeper model to isolate the target cohort of confirmed Hepatocellular Carcinoma cases from a screening pool of N = 2,864 reports. Stage 2 deploys a high-capacity model to extract 15 predefined histopathological variables, including tumor-node-metastasis staging, histological grading, vascular invasion, and selected immunohistochemical features into structured JSON format. For both Stages, pipeline performance was evaluated using Accuracy, Macro F1-scores, and Cohen's kappa compared to expert-curated reference annotations. Results: The top-performing Stage 1 gatekeeper isolated the target patient cohort with zero classification errors, effectively reaching complete agreement with the reference standard (ground truth) and correcting inaccurate administrative metadata. For Stage 2 feature extraction, current-generation models demonstrated robust structural reliability, reducing the burden of manual post-processing. The 31B model configuration (Gemma 4) virtually eliminated objective factual errors, achieving near-perfect agreement with the reference standard (Macro F1 > 0.99). Conclusion: Local two-stage pipelines offer a highly accurate, resource-efficient, and secure solution for clinical text processing. This framework serves as a privacy-preserving engine for institutional quality control and the scalable curation of pathology registries.

Objective: To study the prevalence of co-occurring endometriosis and polyendocrine metabolic ovarian syndrome (PMOS), estimate infertility odds, and characterize menstrual symptom profiles associated with this combined phenotype in a population cohort. Design: Prospective digital cohort in the United States (US). Subjects: 90,714 consented participants enrolled between November 2019 and June 2025 who completed relevant surveys; a subset of 25,152 participants with menstrual cycle logs linked to monthly surveys contributed to symptom analyses. Exposure: Participants were classified by self-reported physician diagnosis into four groups: endometriosis alone, PMOS alone, co-occurring endometriosis and PMOS (endometriosis+PMOS), or neither condition (reference group). Main Outcome Measures: (1) Odds of self-reported physician-diagnosed infertility (ever/never, cross-sectional), estimated using multivariable logistic regression adjusted for age, race/ethnicity, and subjective socioeconomic status; (2) number of adverse menstrual symptoms logged per cycle, assessed using negative binomial mixed-effects models adjusted for age, race/ethnicity, and hormonal contraceptive use. Results: Among 90,714 participants, the mean age was 35.1 years (standard deviation: 11.6) and the majority identified as non-Hispanic White (72%). Prevalence estimates were 11% for PMOS alone, 6% for endometriosis alone, and 2% for endometriosis+PMOS. Individuals with endometriosis+PMOS more frequently reported unemployment, low socioeconomic status, active smoking, poorer subjective health, early menarche, current irregular cycles, and a broad range of comorbidities. Infertility odds were highest for endometriosis+PMOS (odds ratio: 12.49 [95% confidence interval: 11.13-13.99]), followed by PMOS alone (6.12 [5.69-6.59]) and endometriosis alone (4.31 [3.93-4.72]), with the combined effect exceeding additive expectations (relative excess risk due to interaction: 3.05 [1.65-4.46]). Individuals with endometriosis+PMOS logged 11% more symptoms per cycle than those with neither condition (incidence rate ratio: 1.11 [1.04-1.19]) and had the highest odds of logging pelvic pain, fatigue, and sleep changes, among other symptoms. Conclusion: In this large US digital cohort, co-occurring endometriosis and PMOS affected 1 in 50 participants and was associated with markedly elevated infertility odds exceeding additive expectations, and a heightened menstrual symptom burden. Several risk factors and health impacts characteristic of each condition appeared amplified in individuals with both conditions, suggesting a subgroup with compounded clinical complexity and greater care needs.

Age and sex estimation from dental radiographs supports forensic identification and age-dependent legal assessment. Multi-input models may combine global and regional representations, but when these inputs are derived from the same radiograph, they may repeat anatomical information rather than provide complementary signals. We developed HMA-Net, a hierarchical multi-stream anatomical network, together with a task-specific input audit that evaluates whether each candidate representation improves at least one prediction task without materially degrading the other. The model was developed using a retrospective single-centre cohort of 4,293 panoramic radiographs from individuals aged 3-18 years and combined a panoramic-image stream with graph-linked tooth representations. On the held-out test set, the final panoramic-plus-permanent-tooth model achieved a mean absolute age error of 0.51 years and a sex-classification accuracy of 85.2%; 99.4% of age estimates were within 2 years of chronological age. Across three independent training runs, removing the jaw-region stream reduced mean absolute age error from 0.68 +/- 0.01 to 0.52 +/- 0.01 years and increased sex accuracy from 81.3+/- 1.7% to 85.8 +/- 0.8%. Adding 20 deciduous-tooth classes provided no age benefit and reduced sex accuracy by 7.9% relative to the permanent-only representation. The mandibular first molars received the greatest tooth-level attention, and their occlusion impaired both prediction tasks. These findings show that anatomically plausible inputs do not necessarily provide incremental predictive value. Task-specific input auditing can improve joint model performance, reduce input redundancy and preserve anatomically traceable predictions. More broadly, this framework provides a testable approach for selecting correlated inputs in medical-imaging systems in which regional views re-present anatomy already contained in the whole image. Keywords: Forensic odontology; Dental age estimation; Sex classification; Panoramic radiography; Multi-input learning; Anatomical input auditing

Background Artificial intelligence computer-aided diagnosis (AI CAD) algorithms for screening mammography have shown promise, but independent head-to-head comparisons of commercial algorithms on large, diverse cohorts remain limited. Methods 786,124 mammography screening exam performed from January 1 2022 to December 31 2023 were identified from electronic medical records. Three FDA-cleared commercial algorithms (A, B, D) and the open-source academic model Mirai (C), were applied to the four standard screening views. Breast cancer within 12 months was ascertained through cancer registry linkage. Algorithms were compared by AUROC; sensitivity, specificity, and PPV at matched AI-positive rates of 5%, 10%, 15%, 20%, 25%; and the proportion of false negatives classified as AI-positive. Results Of 707,922 examinations with complete data, 4,436 were associated with cancer. Radiologists recalled 6.8% of examinations, with a sensitivity of 67.2%. Algorithm D had the highest AUROC (0.849), followed by algorithm B (0.818), Mirai (0.817), and algorithm A (0.815). Algorithm D also had the highest sensitivity at every AI-positive rate, from 55.3% (95% CI: 54.1, 56.6) at 5% to 77.9% (95% CI: 76.9, 79.0) at 25%, with CIs that did not overlap those of the other algorithms. No algorithm matched radiologist sensitivity at AI-positive rates of 10% or less. Algorithm B flagged a proportion of radiologist false negatives similar to that of algorithm D from 5% through 20% (20.8% vs 20.5% at 5%), despite its lower standalone sensitivity. Conclusions AI CAD algorithms differed meaningfully in performance on the same large, diverse screening examination cohort, and an open-source academic model performed comparably to two of the three commercial products. Independent local validation at clinically relevant operating points should precede adoption of mammography AI, and algorithm choice and threshold should be matched to the intended workflow.

BackgroundPremature ovarian insufficiency (POI) is a condition affecting female fertility e.g., in the context of autoimmune disease. A recent proof-of-concept study showed that B-cell depletion with rituximab (RTX) temporarily restored ovarian function in patients with autoimmune POI. However, the underlying immunological mechanisms behind this response is unknown. ObjectivesTo characterize B- and T-cell phenotypes before and after RTX therapy in the above-mentioned patients and associations with autoantibody levels and treatment response. MethodsCryopreserved cell samples were available from six autoimmune patients with POI, four of whom were positive for autoantibodies against steroidogenic enzymes (21OH, 17OH and/or SCC). Patients received RTX and blood samples were collected at baseline, second infusion (2 weeks), 3, 8 and 12 months. Peripheral B- and T-cell phenotypes were analysed using spectral flow cytometry and correlated with autoantibody levels. ResultsAt baseline, patients displayed signs of B-cell activation by alteration in subset composition compared to matched controls. Upon closer analysis, patients positive for steroidogenic enzyme autoantibodies had significantly increased frequency of CXCR3+switched memory (SWM) B-cells than autoantibody-negative patients, which correlated positively with anti-17OH and-SCC autoantibody levels. In parallel, increased Th1 cell frequencies were also observed in the same patient group. Longitudinal analyses showed expected B-cell depletion followed by repopulation after RTX. Changes in T-cell subsets were observed at 8 months with reduced frequencies of Th1 and Tfh cells. ConclusionAutoimmune POI displayed altered B- and T-cell subsets implicating cell crosstalk, immune cell infiltration to sites of inflammation such as ovaries, and presence of Th1-driven immunopathogenesis. Key messagesO_LIIncreased CXCR3+SWM B cells and Th1 cells were found in patients with autoimmune POI who were positive for autoantibodies against steroidogenic enzymes. C_LIO_LICXCR3 expression on SWM B cells positively associated with anti-17OH and anti-SCC autoantibody levels. C_LIO_LIRTX induced rapid B-cell depletion followed by repopulation and a delayed T-cell effect at 8 months with reduced Th1 and Tfh cell frequencies. C_LI Capsule summaryRTX has recently been shown to restore fertility in autoimmune POI. Lymphocyte profiling identified Th1 bias accompanied by CXCR3+memory B cells that correlate with autoantibody levels. B-cell depletion appears to temporarily alleviate ovarian autoimmunity and ameliorate physiological function.

Accurate classification of lung adenocarcinoma growth patterns from hematoxylin and eosin (H\&E)-stained whole-slide images is essential for treatment planning and prognosis. We develop and evaluate an exponentially weighted ensemble deep learning approach that combines five architectures (EfficientNet-B3, DeiT3, Swin Transformer, Vision Transformer, ConvNeXt) with weights determined by a softmax transformation of per-model Quadratic Weighted Kappa (QWK) scores. Using 25,545 image patches at 40x magnification from the Dartmouth-Hitchcock dataset, we evaluated performance with stratified 5-fold cross-validation. Individual model performance ranged from Cohen's kappa kappa = 0.5563 (ConvNeXt) to kappa = 0.9561 (EfficientNet-B3). The ensemble achieved 96.52% accuracy and kappa = 0.9648, exceeding the best individual model by delta kappa = +0.0087 with statistical significance (McNemar's test, chi^2 = 50.84, p < 10^-12; bootstrap 95% CI on delta kappa [+0.0056, +0.0117]. Pairwise disagreement rates of 16.6--43.2% between architectures indicate that the models capture different aspects of tissue morphology, and the framework automatically down-weights unreliable components, as illustrated by ConvNeXt receiving only 5.7% ensemble weight despite a single-fold training failure. The approach offers a clinically grounded method for ensemble aggregation in digital pathology.

Polyendocrine Metabolic Ovarian Syndrome (PMOS, formerly PCOS) is associated with chronic low-grade inflammation. This study aimed to characterize the peripheral cytokine landscape in women with PMOS and identify cytokines associated with disease pathogenesis and phenotypic variation. Plasma concentrations of 48 cytokines were quantified using a multiplex bead-based assay in 102 women with PMOS and 114 healthy controls. We performed receiver operating characteristic (ROC) analysis, odds ratio estimation, correlation analysis, and network analyses to characterise cytokine alterations and identify phenotype-associated inflammatory signatures. Fourteen cytokines were significantly elevated in PMOS compared with healthy controls: IL-18, IL-1Ra, IL-12p70, IL-13, IL-16, MCP-1, MCP-3, CTACK, Eotaxin, RANTES, IP-10, M-CSF, HGF, and {beta}-NGF. ROC analysis identified IL-16, CTACK, and IP-10 as potential discriminators of phenotype A, whereas IL-18, M-CSF, and HGF demonstrated promising discriminatory performance for phenotype B. Odds ratio analysis identified 11 cytokines with odds ratios greater than 1, with IL-16 showing the strongest association with PMOS. Correlation analysis revealed 10 strongly correlated cytokine pairs (r [&ge;] 0.7) in the PMOS group, suggesting coordinated regulation of inflammatory mediators. Gene ontology and network analysis highlighted alterations in chemotaxis and immune cell migration pathways, implicating these processes in PMOS-associated immune dysregulation. These findings reveal a distinct peripheral inflammatory cytokine signature and phenotype-associated differences in PMOS. IL-16 emerged as a prominent candidate for further investigation, given its strong association with PMOS. Peripheral cytokine profiling may provide a minimally invasive approach to characterising immune alterations and identifying candidate biomarkers for disease characterisation and phenotype stratification.

Introduction: Thyroid diseases are major health problems and among the most common endocrine disorders worldwide, including in Ethiopia. They are characterized by alterations in hormone secretion, enlargement of the thyroid gland, or both. Fine needle aspiration cytology is an important initial screening tool, and histopathologic examination is essential for the definitive diagnosis of thyroid disease. This study aimed to compare the diagnostic accuracy of fine needle aspiration cytology with histopathology in identifying thyroid diseases. Methods: A cross-sectional study was conducted at three health facilities in Hawassa City, Ethiopia, involving 304 patients who underwent both thyroid fine needle aspiration cytology and histopathologic examination of the same site between 30th October 2024 and 29th October 2025. FNAC results were classified using the Bethesda system, with histopathology as the gold standard. Data were entered into Kobo Toolbox, exported to SPSS version 27, and analyzed using cross-tabulation and chi-square ({chi}{superscript 2}) tests to determine diagnostic accuracy. Result: 304 patient records were included in the study. The fine needle aspiration cytology was determinate/diagnostic in 81.6% of cases. The study revealed the sensitivity and specificity of fine needle aspiration cytology to be 88.2% (CI 77.6-95.1%) and 94.4% (CI 90.6-97.1%), respectively. The false negative and false positive rates in this study were 2.4% and 4.4%, respectively. The positive predictive value was 80.3% (CI 68.7-89.3%), and the negative predictive value was 96.8% (CI 93.8-98.7%). The accuracy of fine needle aspiration cytology in differentiating benign from malignant thyroid lesions was 93.1%. Conclusion: FNAC demonstrated strong agreement with histopathology and remains a reliable, cost-effective first-line diagnostic tool for thyroid disease, particularly in resource-limited settings. Strengthening sample handling, ultrasound guidance, and adherence to Bethesda criteria may further improve diagnostic precision

In this work, we investigate the homogeneity of performance in binary classification between the Rotterdam phenotypes and phenotype prediction. For this purpose, a multi-task neural network architecture is designed to improve the prediction accuracy of phenotypes while maintaining the accuracy of binary classification. Using a clinical PCOS dataset which contains unlabeled samples of patients that cannot be attributed to any of the known phenotypes, three models are evaluated: optimized binary Random Forest (RF), six-class weighted class RF, and multi-task neural network (with a common hidden layer and two heads for binary and six-class classifications) optimized by a genetic algorithm. Techniques used for evaluation include ten-fold out-of-fold predictions, paired McNemar tests, bootstrap tests, ablation study, and clustering (Adjusted Rand Index, ARI). Binary RF model reached 90.2% accuracy; however, recall of different phenotypes was significantly unbalanced - from 75.0% of phenotype B to 97.8% of phenotype A. This difference of 22.8 % points was observed (23.3 points) even after excluding phenotype-specific features. While direct phenotype prediction improved recall for common phenotypes, it decreased recall for phenotype B to 43.8% and unclassified cases to 31.5%. Our multi-task model preserved 90.2% binary accuracy and significantly recovered phenotype B recall to 87.5% and unclassified cases to 79.6% (p<0.05). The cluster analysis confirmed the weak correlation between the results and labels (ARI=0.045). The ablation analysis demonstrates that feature selection and class weighting drive this improvement, isolating the specific components responsible for performance gains. We establish that aggregate binary accuracy does not reflect the heterogeneous detection of PCOS phenotypes. Direct phenotype prediction alone redistributes the classification errors, but the multi-task architecture successfully improves the detection of rare phenotypes without compromising binary accuracy. Phenotype-disaggregated evaluations, supported by significance testing and ablation, are essential for clinical classifier research.

Neurologic autoantibody cell-based assay images are difficult to interpret when fluorescence is weak, focal or dominated by background signal. We developed a visual artificial intelligence overlay that transfers detected cell boundaries from the structural channel to the antibody-staining image and evaluated standalone model concordance and its association with reader classifications. The analysis used 2 763 records for model development and 499 held-out records spanning 14 antibody targets. Four readers assessed the held-out records first without assistance and then with the boundary overlay and model category available. The selected model agreed with the reader-derived three-class reference in 85.2% of records, but recall was lowest for weak-positive or equivocal records. Reader agreement increased in the assisted session, and almost all revised ratings moved towards the model category. The combined display may support consistent visual review while also creating a risk of model-directed anchoring; its role as a second-read aid requires independent validation.

Abstract Polycystic ovarian syndrome and Type 2 diabetes mellitus are complex multivariate diseases that share well-established clinical pathophysiology, yet the molecular basis of their overlap is unknown. Prior bioinformatics studies have identified common differentially expressed genes between these two conditions. However, they have not accounted for the directionality of the gene expression changes observed, potentially obscuring any biological distinctions they may have. This study applied a direction-aware approach to classify molecular signatures between PCOS and T2DM as concordant or discordant. Transcriptomic analysis of GEO datasets GSE138518 (ovarian granulosa tissue, PCOS) and GSE25724 (pancreatic islet tissue, T2DM) identified 225 and 1,302 DEGs, respectively. Venn diagram analysis showed that only three genes (SLC6A8, RGS4, and SORL1) were shared between PCOS and T2DM from the total of 1,527 genes, and all 3 genes were regulated in opposing directions. Disease gene retrieval from the Comparative Toxicogenomics Database, Online Mendelian Inheritance in Man database, and GeneCards showed 214 shared disease-associated genes, with 311 genes unique to PCOS and 496 genes unique to T2DM. Protein-protein interaction construction using STRING (version 12.0) identified 70 interacting nodes. CytoHubba analysis across 6 scoring methods identified 18 high-confidence hub genes, including INS, BCL2, MTOR, LEP, MFN2, and PIK3CD. Functional enrichment analysis identified biological processes including immune activation, apoptosis, and insulin signaling, which were confirmed as the main pathways in KEGG pathway analysis. These findings show that while PCOS and T2DM share limited DEGs, they share common pathogenic pathways.

The -Bonacci weighted sequence space {ell}(,) is introduced for [&ge;] 2, 1 [&le;] < {infty}, and > 0). It is proved to be a Banach space which is isometrically isomorphic to {ell}, with an unconditional Schauder basis. The space is also reflexive and uniformly convex. Its strict inclusion chain, continuous dual, and asymptotic truncation estimate of order - / are also established. Based on this framework, Scaled &#119898-BonacciNet is proposed as a lightweight CNN that rescales Fibonacci-Net channels using the dominant &#119898-Bonacci root and employs depth wise separable convolutions. Tribonacci-Net achieved 96.09% accuracy and a 0.9581 macro F1-score on the 15-class Brain MRI dataset using 0.85 million parameters and 0.366 GFLOPs. Pentanacci-Net attained 95.87% accuracy on the 44-class dataset while reducing parameters and FLOPs by 47.10% and 44.48%, respectively. On the CKD ultrasound dataset, Hexanacci-Net achieved 83.75% accuracy and a 0.7941 macro F1-score, with corresponding reductions of 50.37% and 45.10%. These findings support dominant-root scaling as a structured approach to lightweight CNN design.

Embryo implantation remains a major limitation of assisted reproductive technology, with failure occurring in approximately 30% of euploid embryo transfers. Implantation requires a synchronized dialogue between the blastocyst and receptive endometrium during the window of implantation (WOI), yet minimally invasive approaches to characterize the structural and molecular features of receptivity remain limited. We analyzed paired sonohysterogram images and uterine lavage samples collected during the proliferative and mid-secretory phases from subjects with regular ovulatory cycles and proven fertility. Endometrial folds were quantified, and lavage samples were analyzed by Luminex multiplex immunoassay. Folds were present in both phases but were significantly more abundant during the mid-secretory WOI, independent of imaging view and endometrial thickness. Folding correlated strongly with circulating estradiol level during the proliferative phase but not the mid-secretory phase, and folding patterns between phases were not correlated, suggesting distinct regulatory mechanisms. Consistent with these structural patterns, uterine lavage demonstrated phase-specific differences in expression of factors associated with endometrial receptivity and implantation, with glandular epithelium, and myeloid-lineage cells emerging as major contributors. Together, these findings identify coordinated structural and secretory processes during the WOI and support further evaluation of endometrial folding and uterine lavage as complementary, minimally invasive markers of endometrial receptivity.