Coarse-to-fine Kidney Segmentation Framework Incorporating with Abnormal Detection and Correction

TL;DR

This paper proposes a coarse-to-fine kidney segmentation framework that incorporates abnormal detection and correction, utilizing different preprocessing strategies for each stage and achieving high accuracy on CT images.

Contribution

It introduces a novel coarse-to-fine segmentation approach with an abnormal detection and correction method tailored for kidney segmentation in CT images.

Findings

Achieved 94.53% average DSC on testing data.

Demonstrated effective abnormal region correction between stages.

Validated the framework on 168 training and 42 testing images.

Abstract

In this paper, we formulated the kidney segmentation task in a coarse-to-fine fashion, predicting a coarse label based on the entire CT image and a fine label based on the coarse segmentation and separated image patches. A key difference between the two stages lies in how input images were preprocessed; for the coarse segmentation, each 2D CT slice was normalized to be of the same image size (but possible different pixel size), and for the fine segmentation, each 2D CT slice was first resampled to be of the same pixel size and then cropped to be of the same image size. In other words, the image inputs to the coarse segmentation were 2D CT slices of the same image size whereas those to the fine segmentation were 2D MR patches of the same image size as well as the same pixel size. In addition, we design an abnormal detection method based on component analysis and use another 2D convolutional neural network to correct these abnormal regions between two stages. A total of 168 CT images were used to train the proposed framework and the evaluations were conducted qualitatively on other 42 testing images. The proposed method showed promising results and achieved 94.53 \% averaged DSC in testing data.