Multi-label segmentation of carpal bones in MRI using expansion transfer learning

Abstract

<i>Objective.</i>The purpose of this study was to develop a robust deep learning approach trained with a small<i>in-vivo</i>MRI dataset for multi-label segmentation of all eight carpal bones for therapy planning and wrist dynamic analysis.<i>Approach.</i>A small dataset of 15 3.0-T MRI scans from five health subjects was employed within this study. The MRI data was variable with respect to the field of view (FOV), wide range of image intensity, and joint pose. A<i>two-stage</i>segmentation pipeline using modified 3D U-Net was proposed. In the<i>first stage</i>, a novel architecture, introduced as expansion transfer learning (ETL), cascades the use of a focused region of interest (ROI) cropped around ground truth for pretraining and a subsequent transfer by an expansion to the original FOV for a primary prediction. The bounding box around the ROI generated was utilized in the<i>second stage</i>for high-accuracy, labeled segmentations of eight carpal bones. Different metrics including dice similarity coefficient (DSC), average surface distance (ASD) and hausdorff distance (HD) were used to evaluate performance between proposed and four state-of-the-art approaches.<i>Main results.</i>With an average DSC of 87.8 %, an ASD of 0.46 mm, an average HD of 2.42 mm in all datasets (96.1 %, 0.16 mm, 1.38 mm in 12 datasets after exclusion criteria, respectively), the proposed approach showed an overall strongest performance than comparisons.<i>Significance.</i>To our best knowledge, this is the first CNN-based multi-label segmentation approach for MRI human carpal bones. The ETL introduced in this work improved the ability to localize a small ROI in a large FOV. Overall, the interplay of a<i>two-stage</i>approach and ETL culminated in convincingly accurate segmentation scores despite a very small amount of image data.

Ähnliche Arbeiten