2021/05/17 by Jun Lv, Guangyuan Li, Lv, Jun +11 · 1 citation
Computer Science · Engineering · Medicine · #68T01 #Advanced MRI Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Medical Imaging Techniques and Applications #Radiomics and Machine Learning in Medical Imaging #cs.CV #cs.LG #eess.IV #electronic engineering #information engineering #msc:68T01
paper · pdf · doi:10.48550/arxiv.2105.08175
29 pages, 11 figures, accepted by CBM journal
arxiv created 2021/05/17 · openalex publication_date 2021/05/17 · arxiv updated 2021/05/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep learning based generative adversarial networks (GAN) can effectively perform image reconstruction with under-sampled MR data. In general, a large number of training samples are required to improve the reconstruction performance of a certain model. However, in real clinical applications, it is difficult to obtain tens of thousands of raw patient data to train the model since saving k-space data is not in the routine clinical flow. Therefore, enhancing the generalizability of a network based on small samples is urgently needed. In this study, three novel applications were explored based on parallel imaging combined with the GAN model (PI-GAN) and transfer learning. The model was pre-trained with public Calgary brain images and then fine-tuned for use in (1) patients with tumors in our center; (2) different anatomies, including knee and liver; (3) different k-space sampling masks with acceleration factors (AFs) of 2 and 6. As for the brain tumor dataset, the transfer learning results could remove the artifacts found in PI-GAN and yield smoother brain edges. The transfer learning results for the knee and liver were superior to those of the PI-GAN model trained with its own dataset using a smaller number of training cases. However, the learning procedure converged more slowly in the knee datasets compared to the learning in the brain tumor datasets. The reconstruction performance was improved by transfer learning both in the models with AFs of 2 and 6. Of these two models, the one with AF=2 showed better results. The results also showed that transfer learning with the pre-trained model could solve the problem of inconsistency between the training and test datasets and facilitate generalization to unseen data.