Segmentation Baseline

Segmentation baselines in medical imaging aim to establish reliable and robust methods for automatically delineating anatomical structures in images, crucial for accurate diagnosis and treatment planning. Current research focuses on improving baseline performance through techniques like transformer networks for direct segmentation from raw data, test-time training with knowledge distillation from foundation models to adapt to varying image distributions, and incorporating uncertainty quantification for more reliable predictions. These advancements address limitations of traditional methods, improving accuracy, robustness to artifacts (e.g., motion, noise), and providing confidence measures for clinicians, ultimately enhancing the reliability and clinical utility of automated segmentation in healthcare.

Papers

May 31, 2024

Direct Cardiac Segmentation from Undersampled K-space Using Transformers
Yundi Zhang, Nil Stolt-Ansó, Jiazhen Pan, Wenqi Huang, Kerstin Hammernik, Daniel Rueckert
Transformer Megatron Decepticons K Space Segmentation Label Cardiac Segmentation Fast Magnetic Resonance Imaging Reconstruction Segmentation Baseline

March 18, 2024

TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models
Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla
Semantic Segmentation Knowledge Distillation Foundation Model 3D Segmentation 3D Semantic Segmentation Test Time Training Point Cloud Instance Segmentation Segmentation Baseline

October 5, 2023

Certification of Deep Learning Models for Medical Image Segmentation
Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Nikos Paragios, Marie-Pierre Revel, Maria Vakalopoulou
Deep Learning Model Medical Image Segmentation Segmentation Model Randomized Smoothing Smoothing Factor Segmentation Baseline

January 1, 2023

Towards Reliable Medical Image Segmentation by utilizing Evidential Calibrated Uncertainty
Ke Zou, Yidi Chen, Ling Huang, Xuedong Yuan, Xiaojing Shen, Meng Wang, Rick Siow Mong Goh, Yong Liu, Huazhu Fu
Medical Image Segmentation Segmentation Result Region Segmentation Evidential Uncertainty Segmentation Capability Segmentation Baseline

December 11, 2022

YoloCurvSeg: You Only Label One Noisy Skeleton for Vessel-style Curvilinear Structure Segmentation
Li Lin, Linkai Peng, Huaqing He, Pujin Cheng, Jiewei Wu, Kenneth K. Y. Wong, Xiaoying Tang
Weakly Supervised Full Label Segmentation Label Weakly Supervised Segmentation Skeleton Annotation Segmentation Baseline Curvilinear Structure Segmentation

September 20, 2022

Cardiac Segmentation using Transfer Learning under Respiratory Motion Artifacts
Carles Garcia-Cabrera, Eric Arazo, Kathleen M. Curran, Noel E. O'Connor, Kevin McGuinness
Data Augmentation Fine Tuning Transfer Learning Cardiac Magnetic Resonance Cardiac Segmentation Respiratory Motion Ventricle Segmentation Segmentation Baseline