MSFE-GallNet-X: a multi-scale feature extraction-based CNN Model for gallbladder disease analysis with enhanced explainability

保存先:

書誌詳細
出版年:	BMC Medical Imaging vol. 25 (2025), p. 1-22
第一著者:	Hadiur Rahman Nabil
その他の著者:	Istyak Ahmed, Das, Aritra, M. F. Mridha Mohsin Kabir, Aung, Zeyar
出版事項:	Springer Nature B.V.
主題:	Feature extraction Accuracy Gallbladder Artificial intelligence Datasets Deep learning Performance evaluation Classification Image resolution Disease Artificial neural networks Gallbladder cancer Medical imaging Gallbladder diseases Gallstones Abdomen Machine learning Explainable artificial intelligence Breast cancer Efficiency Calculi Ultrasound Clinical decision making Cholecystitis Parameters Ultrasonic imaging Decision making Neural networks
オンライン･アクセス:	Citation/Abstract Full Text Full Text - PDF
タグ:	タグ追加タグなし, このレコードへの初めてのタグを付けませんか!

その他の書誌記述
抄録:	Section ObjectiveThis study introduces MSFE-GallNet-X, a domain-adaptive deep learning model utilizing multi-scale feature extraction (MSFE) to improve the classification accuracy of gallbladder diseases from grayscale ultrasound images, while integrating explainable artificial intelligence (XAI) methods to enhance clinical interpretability.AbstractSection MethodsWe developed a convolutional neural network-based architecture that automatically learns multi-scale features from a dataset comprising 10,692 high-resolution ultrasound images from 1,782 patients, covering nine gallbladder disease classes, including gallstones, cholecystitis, and carcinoma. The model incorporated Gradient-Weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME) to provide visual interpretability of diagnostic predictions. Model performance was evaluated using standard metrics, including accuracy and F1 score.AbstractSection ResultsThe MSFE-GallNet-X achieved a classification accuracy of 99.63% and an F1 score of 99.50%, outperforming state-of-the-art models including VGG-19 (98.89%) and DenseNet121 (91.81%), while maintaining greater parameter efficiency, only 1·91 M parameters in gallbladder disease classification. Visualization through Grad-CAM and LIME highlighted critical image regions influencing model predictions, supporting explainability for clinical use.AbstractSection ConclusionMSFE-GallNet-X demonstrates strong performance on a controlled and balanced dataset, suggesting its potential as an AI-assisted tool for clinical decision-making in gallbladder disease management.AbstractSection Clinical trial numberNot applicable.
ISSN:	1471-2342
DOI:	10.1186/s12880-025-01902-y
ソース:	Health & Medical Collection