Improving small lesion segmentation in CT scans using intensity distribution supervision: application to small bowel carcinoid tumor

Abstract

Finding small lesions is very challenging due to lack of noticeable features, severe class imbalance, as well as the size itself. One approach to improve small lesion segmentation is to reduce the region of interest and inspect it at a higher sensitivity rather than performing it for the entire region. It is usually implemented as sequential or joint segmentation of organ and lesion, which requires additional supervision on organ segmentation. Instead, we propose to utilize an intensity distribution of a target lesion at no additional labeling cost to effectively separate regions where the lesions are possibly located from the background. It is incorporated into network training as an auxiliary task. We applied the proposed method to segmentation of small bowel carcinoid tumors in CT scans. We observed improvements for all metrics (33.5% → 38.2%, 41.3% → 47.8%, 30.0% → 35.9% for the global, per case, and per tumor Dice scores, respectively.) compared to the baseline method, which proves the validity of our idea. Our method can be one option for explicitly incorporating intensity distribution information of a target in network training.

Fully‐automated detection of small bowel carcinoid tumors in CT scans using deep learning

“…The detection can be achieved also by performing tumor segmentation. We use a small lesion segmentation method proposed by Shin et al 11 Their proposed network predicts tumor intensity likelihood as well as tumor segmentation, by which intensity distribution information of the target tumor can be explicitly incorporated in network training, thus improves the tumor segmentation.…”

“…8 There have been a few relevant works for automatic segmentation/detection of small bowel carcinoid tumors in recent years. [9][10][11] Carlsen et al developed a semiautomatic segmentation method for NETs in PET scans. A region encompassing each lesion is drawn manually, then voxels with an intensity above the patient-specific threshold are delineated automatically.…”

“…In this work, NETs located throughout the body were taken into account regardless of tumor site. In contrast, only CT scans are used to segment carcinoid tumors within the small bowel in the work of Shin et al 11 An intensity distribution of tumors has been utilized to improve the segmentation. This approach that uses only CT scans holds a higher usability since CT has a higher availability than PET.…”

Improving segmentation and detection of lesions in CT scans using intensity distribution supervision

“…The main contributions of our work are as follows. (1) We extend the idea of our previous paper (Shin et al, 2023) to the segmentation of different lesions at different body locations to verify its generability. (2) We further investigate the effectiveness of the proposed method in several aspects, namely with varied amount of training data, in comparison to the joint organ segmentation, and even on a detection task.…”