Needle localization and segmentation for radiofrequency ablation of liver tumors under CT image guidance
Published in 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2022
This paper presents an automatic method for needle segmentation in CT images for radiofrequency ablation (RFA) guidance. We detect the needle in orthogonal 2D projections using YOLOv4 to construct a volume of interest, then apply a patch-based 3D CNN to precisely segment the needle within the VOI. The proposed method achieves high accuracy and fast inference time compared to other deep learning approaches.
Recommended citation: Le Quoc Anh, Luu Manh Ha, Theo Van Walsum, Adriaan Moelker, Dao Viet Hang, Pham Cam Phuong, Vu Duy Thanh, et al. "Needle localization and segmentation for radiofrequency ablation of liver tumors under CT image guidance." In 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pages 2015–2021. IEEE, 2022.
Download Paper