Complete fully automatic detection, segmentation and 3D reconstruction of tumor volume for non-small cell lung cancer using YOLOv4 and region-based active contour model

作者：

Highlights：

• Development of an automatic system for NSCLC detection and segmentation.

• YOLOv4 and region-based active contour model were used to develop.

• YOLOv4 was trained on pre-trained weights to ensure good performance.

• Extracted contours were rendered into to a 3D volumetric tumor.

• System accuracy was verified using 3D printed images.

摘要

•Development of an automatic system for NSCLC detection and segmentation.•YOLOv4 and region-based active contour model were used to develop.•YOLOv4 was trained on pre-trained weights to ensure good performance.•Extracted contours were rendered into to a 3D volumetric tumor.•System accuracy was verified using 3D printed images.

论文关键词：Lung tumor,Detection,Segmentation,Active contour,YOLOv4

论文评审过程：Received 5 January 2022, Revised 4 August 2022, Accepted 21 August 2022, Available online 27 August 2022, Version of Record 9 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118661