3D multi-scale residual fully convolutional neural network for segmentation of extremely large-sized kidney tumor

We propose a novel deep neural network, the 3D Multi-Scale Residual Fully Convolutional Neural Network (3D-MS-RFCNN) to improve segmentation in extremely large-sized kidney tumors.

The multi-scale approach with a deep neural network is applied to capture global contextual features. Our method, 3D-MS-RFCNN, consists of two encoders and one decoder as a single complete network. One of the encoders is designed for capturing global contextual information by using the low-resolution, down-sampled data from input images. In the decoder, features from the encoder for global contextual features are concatenated with up-sampled features from the previous layer and features from the other encoder. Ensemble learning strategy is also applied.

We evaluated the performance of our proposed method using the KiTS public dataset and the in-house hospital dataset. When compared with the state-of-the-art method, Res3D U-Net, our model, 3D-MS-RFCNN, demonstrated greater accuracy (0.9390 dice score for KiTS dataset and 0.8575 dice score for external dataset) for segmenting extremely large-sized kidney tumors.

Our proposed network shows significantly improved segmentation performance of extremely large-sized targets. This study can be usefully employed in the field of medical image analysis.