2.5D MFFAU-Net: a convolutional neural network for kidney segmentation

Abstract

Background Kidney tumors have become increasingly prevalent among adults and are now considered one of the most common types of tumors. Accurate segmentation of kidney tumors can help physicians assess tumor complexity and aggressiveness before surgery. However, segmenting kidney tumors manually can be difficult because of their heterogeneity. Methods This paper proposes a 2.5D MFFAU-Net (multi-level Feature Fusion Attention U-Net) to segment kidneys, tumors and cysts. First, we propose a 2.5D model for learning to combine and represent a given slice in 2D slices, thereby introducing 3D information to balance memory consumption and model complexity. Then, we propose a ResConv architecture in MFFAU-Net and use the high-level and low-level feature in the model. Finally, we use multi-level information to analyze the spatial features between slices to segment kidneys and tumors. Results The 2.5D MFFAU-Net was evaluated on KiTS19 and KiTS21 kidney datasets and demonstrated an average dice score of 0.924 and 0.875, respectively, and an average Surface dice (SD) score of 0.794 in KiTS21. Conclusion The 2.5D MFFAU-Net model can effectively segment kidney tumors, and the results are comparable to those obtained with high-performance 3D CNN models, and have the potential to serve as a point of reference in clinical practice.

Improving Generation and Evaluation of Long Image Sequences for Embryo Development Prediction

“…Many works are now moving toward the use of image sequences, inspired by the success of using DL models in medicine for the treatment and analysis of static images. These sequences can either be located in space [22,23] or within a temporal context as videos [24][25][26]. Among the most common tasks when working with image sequences is the prediction of frames and filling in gaps between two existing images [27].…”