Aug 2026· European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery· 0 citations· 30 references
Medicine
TL;DR
The proposed IMIL-Net provides a high-accuracy, interpretable, and clinically-aligned diagnostic solution by analyzing complete patient examinations and providing a statistically validated decision-making process, and represents a trustworthy tool for integration into the clinical otolaryngology workflow.
Lung cancer is a leading cause of death worldwide, with delayed or misdiagnosis further hindering professionals' ability to lower lung cancer-related mortality rates. Misdiagnosis could look like false positive results, where benign lung diseases are mistaken for malignant lung carcinomas, or more life-threatening false negative results, where harmful eosinophilic pneumonia is misinterpreted as a benign lung hamartoma. The objective of this study consists of the following goals: (1) to develop CNN-based classification models for lung nodule analysis, (2) to compare the performance of multiple deep learning models under consistent controlled environments, (3) to evaluate and present the interpretability of the models through a clinically grounded probability equation, and (4) to propose an integrated risk-scoring framework that combines the imaging and clinical pipelines into a single interpretable measure of lung cancer risk. However this framework is only theoretical as imaging and clinical models were developed using separate datasets; future studies should note that a practical development will require validation on a unified multimodel patient cohort. In regard to the creation of the models, the deep learning convolutional neural network, which utilized a YOLOv8n backbone trained on the IQ-OTH/NCCD dataset of 649 annotated CT images, achieved a mean average precision (mAP50) of 0.687 when evaluated against expert-verified annotations. The machine learning branch utilizes a structured clinical dataset of 309 patient records with symptom- and risk-based features, including age, smoking status, chronic disease, fatigue, wheezing, and shortness of breath, all evaluated under standardized conditions. These machine learning models, showed similarly promising results, with the Logistic Regression (Log) achieving the highest mean accuracy of 0.929, while CatBoost (CB) demonstrated the strongest overall balance with a Mean F1 score of 0.953 at optimal hyperparameter settings of 1,000 iterations and a tree depth of 8. Interpretability is further enhanced through a clinically grounded cancer probability equation. This framework that showcases both deep and machine learning models will offer insight into the effectiveness of incorporating artificial intelligence in the screen accuracy of lung cancer classification.
Patthanan Uthaititpitak· Journal of Applied Research...· 0 citations
MagViT, an interpretable multi-magnification transformer framework with scale-gated fusion and patient-level model selection, is presented, an interpretable multi-magnification transformer framework with scale-gated fusion and patient-level model selection relative to prior ViT-centered BreakHis work.
Nabil Ashab, Soumitra Kundu, Saif Mahmud Parvez et al.· 0 citations
Due to its late identification and challenging diagnosis, lung cancer continues to be one of the top causes of death for cancer patients globally, positioning it as one of the most critical concerns. Timely identification of cancerous nodules is essential for enhancing the patient’s survival likelihood CT image analysis by hand is not very productive and significantly relies on a specialist’s expertise. In this study, we offer an autonomous lung cancer classification method based on explainable deep learning. The popular DenseNet121 network serves as the foundation for our deep learning model, which is enhanced by the Convolutional Block Attention Module (CBAM). To improve feature extraction of significant spatial and channel properties of input data, attention techniques are added. Furthermore, our method is interpretable because the Grad-CAM technique makes it possible to explain the choices made by a machine learning system. A database of CT scans, comprising 4,598 pictures categorized by large cell carcinoma, adenocarcinoma, and healthy lungs, was utilized. Our evaluations show the model’s effectiveness with an accuracy rate of 94.6\%.
S. Jegadeesan, S. Matheswaran, R. Palanivelrajan· International Conference on...· 0 citations
Breast cancer is a significant cause of cancer-related deaths among women worldwide. Its early identification and screening are essential for improved patient outcomes and reduced mortality rates. Histopathological image analysis is considered as the gold standard for the diagnosis and prognosis of breast cancer. Nevertheless, the complexity of Whole-Slide Images (WSI) and their manual examination make this task time consuming, and prone to pathologist subjectivity. Recently, Deep Learning (DL) technology has achieved remarkable success in computer vision. However, their application still faces critical challenges in pathology analysis, including Region-of-Interest (RoI) scale variations, inter- and intra-class heterogeneity, diverse staining protocols, and the scarcity of annotated datasets. Furthermore, DL model’s findings are opaque and lack decision-level transparency. This study proposes a novel explainable multi-model DL framework for breast cancer classification leveraging histopathological images. The framework integrates Contrast Limited Adaptive Histogram Equalization (CLAHE) for image contrast enhancement, and diverse data augmentation to mitigate class imbalance and overfitting. Proposed architecture ensembles two branches, one employes DenseNet201 benefiting from Transfer Learning (TL) via ImageNet weights, while other utilizes a custom light weight attention based Hierarchal Feature Fusion (HFF) Network. DenseNet201 utilizes multilevel features to effectively tackle gradient vanishing issues and capture intricate feature representations, while HFF-Net, designed specifically for biomedical imaging, leverages HFF stem and multiscale feature extraction with Swish activation to enhance learning stability. Attention mechanism introduced within HFF-Net further refines the output features. Final feature vectors from the two branches are fused at the Global Average Pooling (GAP) layer, consolidating discriminative information. Experimental results on BRACS dataset demonstrate the proposed framework achieves 97.15% accuracy, 92.59% precision, 93.81% recall, and a 93.19% F1-score in screening tasks, while for grading tasks, it attains 84.08% accuracy, 83.39% precision, 83.64% recall, and 83.44% F1-score on 4391 test samples. Additionally, Gradient-Class Activation Mapping (Grad-CAM) saliency heatmap are generated for visual representation of proposed model’s choices, thereby increased transparency. The integration of these advanced techniques significantly enhances diagnostic reliability, addressing the challenges in histopathological image analysis.
Muhammad Nabeel Mehmood, Muhammad Hassaan Ashraf· Informatica· 0 citations
Lung and colon cancer (LCC), the second leading cause of death and illness worldwide, is often diagnosed at advanced stages because early symptoms are subtle or absent. Late-stage detection reduces treatment effectiveness and increases the chance of mortality. However, deep learning models, such as the Compact Convolutional Transformer (CCT), have emerged as effective methods for detecting and classifying LCC histopathological images. Histopathological image analysis is challenging due to tissue heterogeneity, staining variability, and class imbalance. CCT has challenges such as high data requirements, computational complexity, and limited interpretability of how global attention patterns influence final classification decisions. Additionally, past research has been criticized for relying on a small number of experiments in CLC. To address these challenges, we develop an optimized CCT (oCCT) that addresses Computational and Architectural Complexity, as well as Local and Global Feature Learning. oCCT was applied to a publicly available CLC dataset with 5 classes and 25,000 histopathological images. The oCCT performance was compared with state-of-the-art CNN architectures, transformer-based networks such as Vision Transformer (ViT) and Swin Transformer, and the original CCT. Among the evaluated models, the oCCT model reliably classifies five histopathological tissue types, achieving 98–99% overall accuracy and over 95% for precision, recall, and F1-score across all classes. This remarkable accuracy underscores the model’s capacity to minimize information loss during processing, a common issue in conventional CNNs. Seven extensive ablation studies were conducted to realize the compactness of oCCT. Since CCT is criticized for functioning largely as “black boxes,” we integrated explainable artificial intelligence to make oCCT easier for clinicians to trust and deploy, with clear explanations of its predictions.
An attention-enhanced deep learning framework for clinically accurate pneumonia identification from chest imaging radiology that combines a self-attention mechanism with a pretrained VGG16 backbone is proposed and tested against many cutting-edge convolutional neural network architectures.
Mohini Gahlot, Pinaki Ghosh· International journal of com...· 0 citations