Rashid Suzain, Das Chandan J, Chauhan Anshika, Aggarwal Garima, Joshi Rakesh Chandra, Burget Radim, Dutta Malay Kishore
Amity School of Engineering and Technology, Amity University, Noida, 201313, India.
Department of Radiodiagnosis and Interventional Radiology, All India Institute of Medical Sciences (AIIMS), New Delhi, 110029, India.
Comput Methods Programs Biomed. 2025 Nov;271:109020. doi: 10.1016/j.cmpb.2025.109020. Epub 2025 Aug 12.
Gallbladder diseases present a critical challenge and can cause serious complications, if not diagnosed and treated promptly. Diseases including gallstone, inflammation, and other abnormalities may lead to a number of significant consequences, such as bile duct obstructions, chronic pain, infections, and in severe cases, life-threatening sepsis or gallbladder cancer.
This study presents a novel deep learning-based diagnostic model using an attention-guided residual convolutional neural network to classify nine distinct gallbladder diseases, including gallstones, abdomen and retroperitoneal pathology, cholecystitis, membranous and gangrenous cholecystitis, perforation, polyps and cholesterol crystals, adenomyomatosis, carcinoma, and various causes of gallbladder wall thickening. It combines multi-scale feature extraction using dilated convolutions and, attention mechanisms for refined feature selection, and residual connections to preserve spatial information and prevent vanishing gradient issues.
Experimental findings show an accuracy of 99.17%, and a recall of 98.94%. These findings demonstrate the reliability of the model in distinguishing between different gallbladder pathologies. The presented methodology offers a rapid, accurate, and scalable diagnostic tool, to help clinicians identify gallbladder diseases from complex radiological medical images efficiently and with high accuracy.
The proposed work has the potential to advance patient care and provides a foundation for robust, efficient, and scalable AI-assisted gallbladder disease diagnosis in clinical practice. The source code is publicly available in the GitHub repository.
胆囊疾病是一项严峻挑战，若不及时诊断和治疗，可能引发严重并发症。包括胆结石、炎症及其他异常情况在内的疾病，可能导致诸多严重后果，如胆管梗阻、慢性疼痛、感染，在严重情况下还会引发危及生命的败血症或胆囊癌。
本研究提出一种基于深度学习的新型诊断模型，该模型使用注意力引导的残差卷积神经网络对九种不同的胆囊疾病进行分类，这些疾病包括胆结石、腹部及腹膜后病变、胆囊炎、膜性和坏疽性胆囊炎、穿孔、息肉和胆固醇结晶、腺肌增生症、癌以及胆囊壁增厚的各种病因。它结合了使用空洞卷积的多尺度特征提取、用于精细特征选择的注意力机制以及用于保留空间信息和防止梯度消失问题的残差连接。
实验结果显示准确率为99.17%，召回率为98.94%。这些结果证明了该模型在区分不同胆囊病变方面的可靠性。所提出的方法提供了一种快速、准确且可扩展的诊断工具，有助于临床医生从复杂的放射医学图像中高效且高精度地识别胆囊疾病。
所提出的工作有潜力推动患者护理，并为临床实践中强大、高效且可扩展的人工智能辅助胆囊疾病诊断奠定基础。源代码可在GitHub仓库中公开获取。
