Hasil untuk "Pathology"

G. Litjens, Thijs Kooi, B. Bejnordi et al.

Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year. We survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks. Concise overviews are provided of studies per application area: neuro, retinal, pulmonary, digital pathology, breast, cardiac, abdominal, musculoskeletal. We end with a summary of the current state-of-the-art, a critical discussion of open challenges and directions for future research.

C. Fletcher

W. Penfield

Zaid Al-Ishaq, Suad AlAghbari, Samiya Al Hattali et al.

Background: Phyllodes tumors (PT) are rare fibroepithelial neoplasms of the breast that represent 0.3% to 1% of all primary breast tumors and may occur in benign, borderline or malignant forms. Objectives: To describe the clinical characteristics, surgical management, and outcomes of PT treated at a tertiary center in Oman. Materials and Methods: A retrospective review of all PT cases managed between 2011 and 2024 at the Breast Program of Sultan Qaboos Comprehensive Cancer Care and Research Centre/University Medical City was conducted. Demographic, pathological, surgical, adjuvant treatment, and outcome data were analyzed. Results: Seventeen Omani women were identified. Histological subtypes included malignant in 9 patients (52.9%), borderline in 6 (35.2%), and benign in 2 (11.7%). Breast-conserving surgery was performed in 13 patients (76.4%); 9 required re-excision for margin clearance, and 1 declined further surgery. Axillary staging was performed in 8 patients (47.1%) due to clinically suspicious nodes, with no pathological involvement detected. Adjuvant radiotherapy was administered to 3 patients (17.6%) with malignant PT. During a mean follow-up of 5.4 years (range 1-13 years), local recurrence occurred in 2 patients (11.7%) and distant metastases in 4 patients (23.5%). Conclusions: PT in this cohort frequently required margin re-excision, highlighting the importance of maintaining a high index of suspicion, integrating oncoplastic surgical techniques, and adopting a multidisciplinary management approach. Selective axillary assessment based on preoperative evaluation and multidisciplinary discussion may help minimize unnecessary axillary surgery.

Rundong Wang, Wei Ba, Ying Zhou et al.

Recent methods for pathology report generation from whole-slide image (WSI) are capable of producing slide-level diagnostic descriptions but fail to ground fine-grained statements in localized visual evidence. Furthermore, they lack control over which diagnostic details to include and how to verify them. Inspired by emerging agentic analysis paradigms and the diagnostic workflow of pathologists,who selectively examine multiple fields of view, we propose QCAgent, an agentic framework for quality-controllable WSI report generation. The core innovations of this framework are as follows: (i) it incorporates a customized critique mechanism guided by a user-defined checklist specifying required diagnostic details and constraints; (ii) it re-identifies informative regions in the WSI based on the critique feedback and text-patch semantic retrieval, a process that iteratively enriches and reconciles the report. Experiments demonstrate that by making report requirements explicitly prompt-defined, constraint-aware, and verifiable through evidence-grounded refinement, QCAgent enables controllable generation of clinically meaningful and high-coverage pathology reports from WSI.

Aixin Chen, Tianhang Chen, Yu He et al.

Objective: This study aims to investigate the pharmacodynamic effects and underlying mechanisms of the Chinese herbal formula RuHaoDaShi (RHDS) granules against the influenza virus in experimental models. Methods: This study aims to employ network pharmacology to identify the active components of RHDS and its potential targets and mechanisms of action against H1N1. The molecular docking approach validated the interactions between the core targets and the RHDS compounds. In vitro, the antiviral activity of RHDS was assessed by therapeutic, prophylactic, and premixed administration to H1N1-infected A549 cells. An in vivo experiment was conducted using a mouse H1N1 pneumonia model. The model was treated with a dose of 1.04, 2.08, and 4.16 g/kg of RHDS, administered via gavage daily. The study’s objective was to evaluate the antiviral activity and mechanism of action of RHDS in mice. Mice were evaluated on day 6 by assessing survival, viral load (RT-qPCR), lung pathology (HE staining), inflammatory cytokines (ELISA, immunohistochemistry), and ferroptosis markers (WB, qPCR). Results: Network pharmacology identified 77 biologically active RHDS compounds (e.g., quercetin and kaempferol) and 32 core targets common to RHDS, H1N1, and ferroptosis. Molecular docking was used to verify a high affinity for binding between the core targets HIF-1α, MAPK3, and key RHDS compounds. In vitro studies demonstrated that RHDS exhibited protective properties against H1N1-infected cells, with the therapeutic delivery method proving the most efficacious. In vivo studies have shown that RHDS reduces mortality, lung index, and viral load in mice while attenuating histopathological damage. The study demonstrated a reduction in the release of inflammatory cytokines, including IL-6, IFN-γ, and IL-17A, and decreased expression levels of MPO and F4/80 proteins in lung tissue. Mechanistically, the administration of RHDS resulted in the up-regulation of the expression levels of GPX4, SLC7A11, and Nrf2 proteins while concomitantly inhibiting the expression of HIF-1α, COX2, and ACSL4. These findings confirm the modulatory effect of RHDS on the GPX4/SLC7A11/Nrf2 pathway. Conclusions: RHDS demonstrated a protective effect against H1N1-induced cytopathy in vitro and was effective in attenuating H1N1-induced pneumonia in murine models. The study suggests that RHDS has antiviral potential to treat H1N1 viral pneumonia by modulating inflammatory cytokines and the GPX4/SLC7A11/Nrf2 pathway.

Hao Wang, Xuan Wang, Yusheng Du et al.

Objectives: This study aimed to develop a predictive model for lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) patients by deep learning radiomic (DLRad) and clinical features. Methods: This study included 271 thyroid lobes from 228 PTC patients who underwent preoperative neck non-contrast CT at Center 1 (May 2021–April 2024). LNM status was confirmed via postoperative pathology, with each thyroid lobe labeled accordingly. The cohort was divided into training (n = 189) and validation (n = 82) cohorts, with additional temporal (n = 59 lobes, Center 1, May–August 2024) and external (n = 66 lobes, Center 2) test cohorts. Thyroid lobes were manually segmented from the isthmus midline, ensuring interobserver consistency (ICC ≥ 0.8). Deep learning and radiomics features were selected using LASSO algorithms to compute DLRad scores. Logistic regression identified independent predictors, forming DLRad, clinical, and combined models. Model performance was evaluated using AUC, calibration, decision curves, and the DeLong test, compared against radiologists' assessments. Results: Independent predictors of LNM included age, gender, multiple nodules, tumor size group, and DLRad. The combined model demonstrated superior diagnostic performance with AUCs of 0.830 (training), 0.799 (validation), 0.819 (temporal test), and 0.756 (external test), outperforming the DLRad model (AUCs: 0.786, 0.730, 0.753, 0.642), clinical model (AUCs: 0.723, 0.745, 0.671, 0.660), and radiologist evaluations (AUCs: 0.529, 0.606, 0.620, 0.503). It also achieved the lowest Brier scores (0.167, 0.184, 0.175, 0.201) and the highest net benefit in decision-curve analysis at threshold probabilities > 20 %. Conclusions: The combined model integrating DLRad and clinical features exhibits good performance in predicting LNM in PTC patients.

Tímea Rozsvai, Boglárka Pósfai, László Torday et al.

Testicular germ cell tumors (TGCTs), though typically responsive to therapy, may rarely develop somatic-type malignancy (STM), a transformation associated with poor prognosis and chemoresistance. This study presents two cases of postpubertal-type teratoma with intestinal-type adenocarcinoma as STM, offering insights into their clinical, histopathological, immunophenotypic, and molecular profiles. The first patient, a 63-year-old male, presented with pulmonary and retroperitoneal metastases and underwent orchiectomy, revealing an intratesticular intestinal-type adenocarcinoma. Molecular testing confirmed 12p overrepresentation and pathogenic mutations in CTNNB1, STK11, and MDM2. The second patient, initially diagnosed at age 35 with a mixed TGCT, developed STM as a late recurrence 16 years post-orchiectomy, manifesting as a retroperitoneal mass with vertebral invasion. Histology again confirmed intestinal-type adenocarcinoma, and molecular testing revealed amplification of ERBB2, KRAS, along with mutations in TP53 and PIK3CA. Both cases were managed with capecitabine-oxaliplatin plus bevacizumab, followed by maintenance therapy, achieving disease stabilization for at least 9 months. These cases illustrate the diagnostic and therapeutic complexities of STM, particularly with adenocarcinoma morphology that may mimic primary gastrointestinal neoplasms. Accurate diagnosis required exclusion of alternate primary sites and demonstration of chromosome 12 aberrations using FISH and next-generation sequencing. Our findings emphasize the importance of long-term follow-up in TGCT patients, particularly those with teratomatous elements, and highlight the value of cytogenetic and molecular profiling in confirming STM and identifying potential therapeutic targets. Given the rarity of STM, especially in metastatic or recurrent settings, there is an urgent need for standardized diagnostic protocols and evidence-based treatment strategies. These cases support the use of tumor-specific chemotherapy regimens guided by the histological and molecular characteristics of STM.

Ammar Ahmed, Ali Shariq Imran, Zenun Kastrati et al.

Pediatric wrist pathologies recognition from radiographs is challenging because normal anatomy changes rapidly with development: evolving carpal ossification and open physes can resemble pathology, and maturation timing differs by sex. Image-only models trained on limited medical datasets therefore risk confusing normal developmental variation with true pathologies. We address this by framing pediatric wrist diagnosis as a fine-grained visual recognition (FGVR) problem and proposing a demographic-aware hybrid convolution--transformer model that fuses X-rays with patient age and sex. To leverage demographic context while avoiding shortcut reliance, we introduce progressive metadata masking during training. We evaluate on a curated dataset that mirrors the typical constraints in real-world medical studies. The hybrid FGVR backbone outperforms traditional and modern CNNs, and demographic fusion yields additional gains. Finally, we show that initializing from a fine-grained pretraining source improves transfer relative to standard ImageNet initialization, suggesting that label granularity, even from non-medical data, can be a key driver of generalization for subtle radiographic findings.

Jiawen Li, Jiali Hu, Qiehe Sun et al.

The emergence of foundation models in computational pathology has transformed histopathological image analysis, with whole slide imaging (WSI) diagnosis being a core application. Traditionally, weakly supervised fine-tuning via multiple instance learning (MIL) has been the primary method for adapting foundation models to WSIs. However, in this work we present a key experimental finding: a simple nonlinear mapping strategy combining mean pooling and a multilayer perceptron, called SiMLP, can effectively adapt patch-level foundation models to slide-level tasks without complex MIL-based learning. Through extensive experiments across diverse downstream tasks, we demonstrate the superior performance of SiMLP with state-of-the-art methods. For instance, on a large-scale pan-cancer classification task, SiMLP surpasses popular MIL-based methods by 3.52%. Furthermore, SiMLP shows strong learning ability in few-shot classification and remaining highly competitive with slide-level foundation models pretrained on tens of thousands of slides. Finally, SiMLP exhibits remarkable robustness and transferability in lung cancer subtyping. Overall, our findings challenge the conventional MIL-based fine-tuning paradigm, demonstrating that a task-agnostic representation strategy alone can effectively adapt foundation models to WSI analysis. These insights offer a unique and meaningful perspective for future research in digital pathology, paving the way for more efficient and broadly applicable methodologies.

Shakib Khan, Fariba Dambandkhameneh, Nazim Shaikh et al.

Advances in computational pathology increasingly rely on extracting meaningful representations from Whole Slide Images (WSIs) to support various clinical and biological tasks. In this study, we propose a generalizable deep learning framework that integrates the Mamba architecture with Graph Neural Networks (GNNs) for enhanced WSI analysis. Our method is designed to capture both local spatial relationships and long-range contextual dependencies, offering a flexible architecture for digital pathology analysis. Mamba modules excels in capturing long-range global dependencies, while GNNs emphasize fine-grained short-range spatial interactions. To effectively combine these complementary signals, we introduce an adaptive fusion strategy that uses an entropy-based confidence weighting mechanism. This approach dynamically balances contributions from both branches by assigning higher weight to the branch with more confident (lower-entropy) predictions, depending on the contextual importance of local versus global information for different downstream tasks. We demonstrate the utility of our approach on a representative task: predicting gene fusion and mutation status from WSIs. Our framework, SlideMamba, achieves an area under the precision recall curve (PRAUC) of 0.751 \pm 0.05, outperforming MIL (0.491 \pm 0.042), Trans-MIL (0.39 \pm 0.017), Mamba-only (0.664 \pm 0.063), GNN-only (0.748 \pm 0.091), and a prior similar work GAT-Mamba (0.703 \pm 0.075). SlideMamba also achieves competitive results across ROC AUC (0.738 \pm 0.055), sensitivity (0.662 \pm 0.083), and specificity (0.725 \pm 0.094). These results highlight the strength of the integrated architecture, enhanced by the proposed entropy-based adaptive fusion strategy, and suggest promising potential for application of spatially-resolved predictive modeling tasks in computational pathology.

Mingchi Hou, Ina Kodrasi

The generalizability of speech enhancement (SE) models across speaker conditions remains largely unexplored, despite its critical importance for broader applicability. This paper investigates the performance of the hybrid variational autoencoder (VAE)-non-negative matrix factorization (NMF) model for SE, focusing primarily on its generalizability to pathological speakers with Parkinson's disease. We show that VAE models trained on large neurotypical datasets perform poorly on pathological speech. While fine-tuning these pre-trained models with pathological speech improves performance, a performance gap remains between neurotypical and pathological speakers. To address this gap, we propose using personalized SE models derived from fine-tuning pre-trained models with only a few seconds of clean data from each speaker. Our results demonstrate that personalized models considerably enhance performance for all speakers, achieving comparable results for both neurotypical and pathological speakers.

Eugene Vorontsov, George Shaikovski, Adam Casson et al.

Recent rapid progress in the field of computational pathology has been enabled by foundation models. These models are beginning to move beyond encoding image patches towards whole-slide understanding but their clinical utility remains limited. In this work, we present PRISM2, a multimodal slide-level foundation model trained on data from 700,000 diagnostic specimen-report pairs, the largest vision (2.3 million whole slide images) and language (14M question-answer pairs) histopathology dataset to date. By learning through clinical-dialogue supervision, PRISM2 aligns histomorphologic features with the language of diagnostic reasoning, producing slide-level representations that support both direct diagnostic question-answering and transferable embeddings for downstream tasks. Without additional training, PRISM2 matches or exceeds the cancer-detection performance of clinical-grade products. This is observed without loss of generality on other tasks, where PRISM2 achieves top performance. Finally, using survival prediction as the example, we show that task-specific finetuning with a large dataset can outperform task-specific models, further improving performance. These results demonstrate how language-supervised pretraining provides a scalable, clinically grounded signal for learning generalizable pathology representations, bridging human diagnostic reasoning and foundation-model performance.

Peter Neidlinger, Tim Lenz, Sebastian Foersch et al.

Artificial intelligence (AI) has transformed digital pathology by enabling biomarker prediction from high-resolution whole-slide images (WSIs). However, current methods are computationally inefficient, processing thousands of redundant tiles per WSI and requiring complex aggregator models. We introduce EAGLE (Efficient Approach for Guided Local Examination), a deep learning framework that emulates pathologists by selectively analyzing informative regions. EAGLE incorporates two foundation models: CHIEF for efficient tile selection and Virchow2 for extracting high-quality features. Benchmarking was conducted against leading slide- and tile-level foundation models across 43 tasks from nine cancer types, spanning morphology, biomarker prediction, treatment response and prognosis. EAGLE outperformed state-of-the-art patch aggregation methods by up to 23% and achieved the highest AUROC overall. It processed a slide in 2.27 seconds, reducing computational time by more than 99% compared to existing models. This efficiency enables real-time workflows, allows rapid review of the exact tiles used for each prediction, and reduces dependence on high-performance computing, making AI-powered pathology more accessible. By reliably identifying meaningful regions and minimizing artifacts, EAGLE provides robust and auditable outputs, supported by systematic negative controls and attention concentration analyses. Its unified embedding enables rapid slide searches, integration into multi-omics pipelines and emerging clinical foundation models.

You Z, Zhang J, Xu Y et al.

Zhiyuan You,1 Jialin Zhang,1 Yifeng Xu,1 Junhong Lu,1 Renling Zhang,2 Zhujing Zhu,3 Yiqin Wang,1 Yiming Hao1 1Shanghai Key Laboratory of Health Identification and Assessment/Laboratory of TCM Four Diagnostic Information, Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, People’s Republic of China; 2Gastroenterology, Longhua Hospital Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, People’s Republic of China; 3Rheumatology, Longhua Hospital Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, People’s Republic of ChinaCorrespondence: Yiming Hao, Email hymjj888@163.com

Peter Neidlinger, Omar S. M. El Nahhas, Hannah Sophie Muti et al.

Advancements in artificial intelligence have driven the development of numerous pathology foundation models capable of extracting clinically relevant information. However, there is currently limited literature independently evaluating these foundation models on truly external cohorts and clinically-relevant tasks to uncover adjustments for future improvements. In this study, we benchmarked 19 histopathology foundation models on 13 patient cohorts with 6,818 patients and 9,528 slides from lung, colorectal, gastric, and breast cancers. The models were evaluated on weakly-supervised tasks related to biomarkers, morphological properties, and prognostic outcomes. We show that a vision-language foundation model, CONCH, yielded the highest performance when compared to vision-only foundation models, with Virchow2 as close second. The experiments reveal that foundation models trained on distinct cohorts learn complementary features to predict the same label, and can be fused to outperform the current state of the art. An ensemble combining CONCH and Virchow2 predictions outperformed individual models in 55% of tasks, leveraging their complementary strengths in classification scenarios. Moreover, our findings suggest that data diversity outweighs data volume for foundation models. Our work highlights actionable adjustments to improve pathology foundation models.

Victor Ibañez, Przemyslaw Szostak, Quincy Wong et al.

Graph convolutional networks (GCNs) have emerged as a powerful alternative to multiple instance learning with convolutional neural networks in digital pathology, offering superior handling of structural information across various spatial ranges - a crucial aspect of learning from gigapixel H&E-stained whole slide images (WSI). However, graph message-passing algorithms often suffer from oversmoothing when aggregating a large neighborhood. Hence, effective modeling of multi-range interactions relies on the careful construction of the graph. Our proposed multi-scale GCN (MS-GCN) tackles this issue by leveraging information across multiple magnification levels in WSIs. MS-GCN enables the simultaneous modeling of long-range structural dependencies at lower magnifications and high-resolution cellular details at higher magnifications, akin to analysis pipelines usually conducted by pathologists. The architecture's unique configuration allows for the concurrent modeling of structural patterns at lower magnifications and detailed cellular features at higher ones, while also quantifying the contribution of each magnification level to the prediction. Through testing on different datasets, MS-GCN demonstrates superior performance over existing single-magnification GCN methods. The enhancement in performance and interpretability afforded by our method holds promise for advancing computational pathology models, especially in tasks requiring extensive spatial context.

Huy Trinh, Khang Tran, Nam Nguyen et al.

Segmentation has long been essential in computer vision due to its numerous real-world applications. However, most traditional deep learning and machine learning models need help to capture geometric features such as size and convexity of the segmentation targets, resulting in suboptimal outcomes. To resolve this problem, we propose using a CovHuSeg algorithm to solve the problem of kidney glomeruli segmentation. This simple post-processing method is specified to adapt to the segmentation of ball-shaped anomalies, including the glomerulus. Unlike other post-processing methods, the CovHuSeg algorithm assures that the outcome mask does not have holes in it or comes in unusual shapes that are impossible to be the shape of a glomerulus. We illustrate the effectiveness of our method by experimenting with multiple deep-learning models in the context of segmentation on kidney pathology images. The results show that all models have increased accuracy when using the CovHuSeg algorithm.

Ying Chen, Guoan Wang, Yuanfeng Ji et al.

Despite the progress made by multimodal large language models (MLLMs) in computational pathology, they remain limited by a predominant focus on patch-level analysis, missing essential contextual information at the whole-slide level. The lack of large-scale instruction datasets and the gigapixel scale of whole slide images (WSIs) pose significant developmental challenges. In this paper, we present SlideChat, the first vision-language assistant capable of understanding gigapixel whole-slide images, exhibiting excellent multimodal conversational capability and response complex instruction across diverse pathology scenarios. To support its development, we created SlideInstruction, the largest instruction-following dataset for WSIs consisting of 4.2K WSI captions and 176K VQA pairs with multiple categories. Furthermore, we propose SlideBench, a multimodal benchmark that incorporates captioning and VQA tasks to assess SlideChat's capabilities in varied clinical settings such as microscopy, diagnosis. Compared to both general and specialized MLLMs, SlideChat exhibits exceptional capabilities achieving state-of-the-art performance on 18 of 22 tasks. For example, it achieved an overall accuracy of 81.17% on SlideBench-VQA (TCGA), and 54.15% on SlideBench-VQA (BCNB). Our code, data, and model is publicly accessible at https://uni-medical.github.io/SlideChat.github.io.

Maximilian Wiesmann, Paul Larsen

In this paper we demonstrate the possibility of a trend reversal in binary classification tasks between the dataset and a classification score obtained from a trained model. This trend reversal occurs for certain choices of the regularization parameter for model training, namely, if the parameter is contained in what we call the pathological regularization regime. For ridge regression, we give necessary and sufficient algebraic conditions on the dataset for the existence of a pathological regularization regime. Moreover, our results provide a data science practitioner with a hands-on tool to avoid hyperparameter choices suffering from trend reversal. We furthermore present numerical results on pathological regularization regimes for logistic regression. Finally, we draw connections to datasets exhibiting Simpson's paradox, providing a natural source of pathological datasets.