AI Article Synopsis

  • Whole-body Metabolic Tumor Volume (MTVwb) is crucial for predicting survival in lung cancer patients, but existing automatic segmentation methods often fail to cover tumors outside the thoracic area.
  • This paper introduces TS-Code-Net, a two-stage neural network that utilizes camouflaged object detection mechanisms to automatically segment tumors in whole-body PET/CT scans.
  • Testing on a dataset of 480 Non-Small Cell Lung Cancer patients shows TS-Code-Net's effectiveness, achieving a Dice score of 0.70, Sensitivity of 0.76, and Precision of 0.70, outperforming other current segmentation methods.

Article Abstract

Background: Whole-body Metabolic Tumor Volume (MTVwb) is an independent prognostic factor for overall survival in lung cancer patients. Automatic segmentation methods have been proposed for MTV calculation. Nevertheless, most of existing methods for patients with lung cancer only segment tumors in the thoracic region.

Purpose: In this paper, we present a Two-Stage cascaded neural network integrated with Camouflaged Object Detection mEchanisms (TS-Code-Net) for automatic segmenting tumors from whole-body PET/CT images.

Methods: Firstly, tumors are detected from the Maximum Intensity Projection (MIP) images of PET/CT scans, and tumors' approximate localizations along z-axis are identified. Secondly, the segmentations are performed on PET/CT slices that contain tumors identified by the first step. Camouflaged object detection mechanisms are utilized to distinguish the tumors from their surrounding regions that have similar Standard Uptake Values (SUV) and texture appearance. Finally, the TS-Code-Net is trained by minimizing the total loss that incorporates the segmentation accuracy loss and the class imbalance loss.

Results: The performance of the TS-Code-Net is tested on a whole-body PET/CT image data-set including 480 Non-Small Cell Lung Cancer (NSCLC) patients with five-fold cross-validation using image segmentation metrics. Our method achieves 0.70, 0.76, and 0.70, for Dice, Sensitivity and Precision, respectively, which demonstrates the superiority of the TS-Code-Net over several existing methods related to metastatic lung cancer segmentation from whole-body PET/CT images.

Conclusions: The proposed TS-Code-Net is effective for whole-body tumor segmentation of PET/CT images. Codes for TS-Code-Net are available at: https://github.com/zyj19/TS-Code-Net.

Download full-text PDF

Source
http://dx.doi.org/10.1002/mp.16438DOI Listing

Publication Analysis

Top Keywords

lung cancer
16
camouflaged object
12
object detection
12
detection mechanisms
12
whole-body tumor
8
tumor segmentation
8
segmentation pet/ct
8
pet/ct images
8
two-stage cascaded
8
cascaded neural
8

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!