Segmentation of kidney mass using AgDenseU-Net 2.5D model. (November 2022)

• Record Type: Journal Article
• Authors: Sun, Peng; Mo, Zengnan; Hu, Fangrong; Song, Xin; Mo, Taiping; Yu, Bonan; Zhang, Yewei; Chen, Zhencheng
• Is Part Of: Computers in biology and medicine. Volume 150(2022)
• Publication Date: 2022-11
• Subjects: Medical image segmentation -- Kidney tumor segmentation -- Automatic down-sampling of 3D images -- AgDenseU-Net -- 2.5D model -- KiTS21; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106223
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: The Kidney and Kidney Tumor Segmentation Challenge 2021 (KiTS21) released a kidney CT dataset with 300 patients. Unlike KiTS19, KiTS21 provided a cyst category. Therefore, the segmentation of kidneys, tumors, and cysts will be able to assess the complexity and aggressiveness of kidney mass. Deep learning models can save medical resources, but 3D models still have some disadvantages, such as the high cost of computing resources. This paper proposes a scheme that saves computing resources and achieves the segmentation of kidney mass in two steps. First, we preprocess the kidney volume data using the automatic down-sampling method of 3D images, reducing the volume while preserving the feature information. Second, we finely segment kidneys, tumors, and cysts using the AgDenseU-Net (Attention gate DenseU-Net) 2.5D model. KiTS21 proposed using Hierarchical Evaluation Classes (HECs) to compute a metric for the superset: the HEC of kidney considers kidneys, tumors, and cysts as the foreground to compute segmentation performance; the HEC of kidney mass considers both tumor and cyst as the foreground classes; the HEC of tumor considers tumor as the foreground only. For KiTS21, our model achieved a dice score of 0.971 for the kidney, 0.883 for the mass, and 0.815 for the tumor. In addition, we also tested segmentation results without HECs, and our model achieved a dice score of 0.950 for the kidney, 0.878 for the tumor, and 0.746 for the cyst. The results demonstrate that the method proposed in this paper can be used as a reference for kidney tumor segmentation. Highlights: We propose an automatic down-sampling method of the 3D image to preprocess the kidney data. We propose the AgDenseU-Net model to segment kidneys and tumors. The proposed method achieves good segmentation results in the KiTS21.