AUTHOR=Zhen Shihui , Zhang Peng , Huang Hanxiao , Jiang Zhiyu , Jiang Yankai , Sun Jihong , Zhang Liqing , Ruan Mei , Chen Qingqing , Wang Yujun , Tao Yubo , Luo Weizhi , Cheng Ming , Qi Zhetuo , Lu Wei , Lin Hai , Cai Xiujun TITLE=Deep learning-assisted diagnosis of liver tumors using non-contrast magnetic resonance imaging: a multicenter study JOURNAL=Frontiers in Oncology VOLUME=Volume 15 - 2025 YEAR=2025 URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2025.1582322 DOI=10.3389/fonc.2025.1582322 ISSN=2234-943X ABSTRACT=ObjectivesNon-contrast MRI(NC-MRI) is an attractive option for liver tumors screening and follow-up. This study aims to develop and validate a deep convolutional neural network for the classification of liver lesions using non-contrast MRI.MethodsA total of 50418 enhanced MRI images from 1959 liver tumor patients across three centers were included. Inception-ResNet V2 was used to generate four models through transfer-learning for three-way lesion classification, which processed T2-weighted, diffusion-weighted (DWI) and multiphasic T1-weighted images. The models were then validated using one independent internal and two external datasets with 5172, 2916, and 1338 images, respectively. The efficacy of non-contrast models (T2,T2+DWI) in differentiating between benign and malignant liver lesions at the patient level was also evaluated and compared with radiologists. The performance of models was evaluated using the area under the receiver operating characteristic curve (AUC),sensitivity and specificity.ResultsSimilar to multi-sequence and enhanced image-based models, the non-contrast models showed comparable accuracy in classifying liver lesions as benign, primary malignant or metastatic. In the independent internal cohort, the T2+DWI model achieved AUC of 0.91(95% CI,0.888–0.932), 0.873(0.848-0.899), and 0.876(0.840-0.911) for three tumour categories, respectively. The sensitivities for distinguishing malignant tumors in three validation sets were 98.1%, 89.7%, and 87.5%%, with specificities over 70% in all three sets.ConclusionsOur deep-learning-based model yielded good applicability in classifying liver lesions in non-contrast MRI. It provides a potential alternative for screening liver tumors with the advantage of reducing costs, scanning time and contrast-agents risks. It is more suitable for benign tumours follow-up, surveillance of HCC and liver metastasis that need periodic repetitive examinations.