Back to all papers

U-ConvNext: A Robust Approach to Glioma Segmentation in Intraoperative Ultrasound.

Authors

Vahdani AM,Rahmani M,Pour-Rashidi A,Ahmadian A,Farnia P

Affiliations (5)

  • Research Center for Biomedical Technologies and Robotics (RCBTR), Advanced Medical Technologies and Equipment Institute (AMTEI), Imam Khomeini Hospital Complex , Tehran University of Medical Sciences (TUMS), Tehran, Iran.
  • Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences (TUMS), Tehran, Iran.
  • Department of Radiology, Northwestern University, Chicago, IL, USA.
  • Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences (TUMS), Tehran, Iran. [email protected].
  • Research Center for Intelligent Technologies in Medicine (RCITM), Advanced Medical Technologies and Equipment Institute (AMTEI), Tehran University of Medical Sciences (TUMS), Tehran, Iran. [email protected].

Abstract

Intraoperative tumor imaging is critical to achieving maximal safe resection during neurosurgery, especially for low-grade glioma resection. Given the convenience of ultrasound as an intraoperative imaging modality, but also the limitations of the ultrasound modality and the time-consuming process of manual tumor segmentation, we propose a learning-based model for the accurate segmentation of low-grade gliomas in ultrasound images. We developed a novel U-net-based architecture adopting the block architecture of the ConvNext V2 model, titled U-ConvNext, which also incorporates various architectural improvements including global response normalization, fine-tuned kernel sizes, and inception layers. We also adopted the CutMix data augmentation technique for semantic segmentation, aiming for enhanced texture detection. Conformal segmentation, a novel approach to conformal prediction for binary semantic segmentation, was also developed for uncertainty quantification, providing calibrated measures of model uncertainty in a visual format. The proposed models were trained and evaluated on three subsets of images in the RESECT dataset and achieved hold-out test Dice scores of 84.63%, 74.52%, and 90.82% on the "before," "during," and "after" subsets, respectively, which indicates increases of ~ 13-31% compared to the state of the art. Furthermore, external evaluation on the ReMIND dataset indicated a robust performance (dice score of 79.17% [95% CI: 77.82-81.62] and only a moderate decline of < 3% in expected calibration error. Our approach integrates various innovations in model design, model training, and uncertainty quantification, achieving improved results on the segmentation of low-grade glioma in ultrasound images during neurosurgery.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.