Integration of histopathological images and immunological analysis to predict M2 macrophage infiltration and prognosis in patients with serous ovarian cancer

Frontiers in Immunology, Год журнала: 2025, Номер 16

Опубликована: Март 17, 2025

Investigating the effect of M2 macrophage infiltration on overall survival and to use histopathological imaging features (HIF) predict in patients with serous ovarian cancer (SOC) is important for improving prognostic accuracy, identifying new therapeutic targets, advancing personalized treatment approaches. We downloaded data from 86 SOC The Cancer Genome Atlas (TCGA) divided these into a training set validation ratio 8:2. In addition, tissue microarrays 106 were included as an external set. HIF recognized by deep multiple instance learning (MIL) via theResNet18 network final model was evaluated using internal Using acquired TCGA database, we applied univariate Cox analysis determined that higher levels associated poor prognosis (hazard [HR]=6.8; 95% CI [confidence interval]: 1.6-28, P=0.0083). External revealed independent risk factor (HR=3.986; CI: 2.436-6.522; P<0.001). Next, constructed four MIL strategies (Mean probability, Top-10 Mean, Top-100 Maximum probability) identify images could infiltration. Mean Probability Method most suitable used generate AUC, recall rate, precision F1 score 0.7500, 0.6932, 0.600, respectively. Collectively, our findings indicated may increase prediction patients. Machine pathological immunohistochemical exhibited good potential direct

Язык: Английский

---

Enhanced Superpixel-Guided ResNet Framework with Optimized Deep-Weighted Averaging-Based Feature Fusion for Lung Cancer Detection in Histopathological Images

Diagnostics, Год журнала: 2025, Номер 15(7), С. 805 - 805

Опубликована: Март 21, 2025

Background/Objectives: Lung cancer is a leading cause of cancer-related mortalities, with early diagnosis crucial for survival. While biopsy the gold standard, manual histopathological analysis time-consuming. This research enhances lung through deep learning-based feature extraction, fusion, optimization, and classification improved accuracy efficiency. Methods: The study begins image preprocessing using an adaptive fuzzy filter, followed by segmentation modified simple linear iterative clustering (SLIC) algorithm. segmented images are input into learning architectures, specifically ResNet-50 (RN-50), ResNet-101 (RN-101), ResNet-152 (RN-152), extraction. extracted features fused deep-weighted averaging-based fusion (DWAFF) technique, producing ResNet-X (RN-X)-fused features. To further refine these features, particle swarm optimization (PSO) red deer (RDO) techniques employed within selective pooling layer. optimized classified various machine classifiers, including support vector (SVM), decision tree (DT), random forest (RF), K-nearest neighbor (KNN), SoftMax discriminant classifier (SDC), Bayesian (BLDC), multilayer perceptron (MLP). A performance evaluation performed K-fold cross-validation K values 2, 4, 5, 8, 10. Results: proposed DWAFF combined selection RDO MLP, achieved highest 98.68% when = 10 cross-validation. RN-X demonstrated superior compared to individual ResNet variants, integration significantly enhanced accuracy. Conclusions: methodology automates learning, advanced techniques. Segmentation enhance performance, improving diagnostic Future work may explore optimizations hybrid models.

Язык: Английский

---

Explainable deep learning model with the internet of medical devices for early lung abnormality detection

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 153, С. 110961 - 110961

Опубликована: Апрель 29, 2025

Язык: Английский

---

Intelligent decision support system for lung cancer classification with ensemble inference system using fuzzy

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 108, С. 107958 - 107958

Опубликована: Апрель 30, 2025

Язык: Английский

---

LungSE-Net: Enhanced Lung Cancer Diagnosis via Lightweight CNN Model using Histopathological Images

Procedia Computer Science, Год журнала: 2025, Номер 260, С. 118 - 125

Опубликована: Янв. 1, 2025

Язык: Английский

---