Improving Segmentation and Detection of Lesions in CT Scans Using Intensity Distribution Supervision
This work addresses the challenge of accurate lesion identification in medical imaging for clinicians, but it is incremental as it builds on existing segmentation and detection networks with a new supervision technique.
The paper tackled the problem of improving lesion segmentation and detection in CT scans by incorporating intensity distribution supervision, resulting in Dice score improvements from 41.3% to 47.8% for small bowel carcinoid tumors, 74.2% to 76.0% for kidney tumors, and 26.4% to 32.7% for lung nodules, and an average precision increase from 64.6% to 75.5% for kidney tumor detection.
We propose a method to incorporate the intensity information of a target lesion on CT scans in training segmentation and detection networks. We first build an intensity-based lesion probability (ILP) function from an intensity histogram of the target lesion. It is used to compute the probability of being the lesion for each voxel based on its intensity. Finally, the computed ILP map of each input CT scan is provided as additional supervision for network training, which aims to inform the network about possible lesion locations in terms of intensity values at no additional labeling cost. The method was applied to improve the segmentation of three different lesion types, namely, small bowel carcinoid tumor, kidney tumor, and lung nodule. The effectiveness of the proposed method on a detection task was also investigated. We observed improvements of 41.3% -> 47.8%, 74.2% -> 76.0%, and 26.4% -> 32.7% in segmenting small bowel carcinoid tumor, kidney tumor, and lung nodule, respectively, in terms of per case Dice scores. An improvement of 64.6% -> 75.5% was achieved in detecting kidney tumors in terms of average precision. The results of different usages of the ILP map and the effect of varied amount of training data are also presented.