Large Batch and Patch Size Training for Medical Image Segmentation
This work addresses the problem of limited datasets and computational resources for medical image segmentation, offering a reference for parameter selection, but it is incremental as it applies existing methods to a new dataset.
The authors tackled the challenge of accurate multi-organ segmentation in medical imaging by training a 3D-UNet model with large batch and patch sizes on the AMOS2022 benchmark, finding that these settings improved segmentation performance and were further enhanced by ensemble models.
Multi-organ segmentation enables organ evaluation, accounts the relationship between multiple organs, and facilitates accurate diagnosis and treatment decisions. However, only few models can perform segmentation accurately because of the lack of datasets and computational resources. On AMOS2022 challenge, which is a large-scale, clinical, and diverse abdominal multiorgan segmentation benchmark, we trained a 3D-UNet model with large batch and patch sizes using multi-GPU distributed training. Segmentation performance tended to increase for models with large batch and patch sizes compared with the baseline settings. The accuracy was further improved by using ensemble models that were trained with different settings. These results provide a reference for parameter selection in organ segmentation.