Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications

Abstract

Medical Image Segmentation (MIS) stands as a cornerstone in medical image analysis, playing a pivotal role in precise diagnostics, treatment planning, and monitoring of various medical conditions. This paper presents a comprehensive and systematic survey of MIS methodologies, bridging the gap between traditional image processing techniques and modern deep learning approaches. The survey encompasses thresholding, edge detection, region-based segmentation, clustering algorithms, and model-based techniques while also delving into state-of-the-art deep learning architectures such as Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), and the widely adopted U-Net and its variants. Moreover, integrating attention mechanisms, semi-supervised learning, generative adversarial networks (GANs), and Transformer-based models is thoroughly explored. In addition to covering established methods, this survey highlights emerging trends, including hybrid architectures, cross-modality learning, federated and distributed learning frameworks, and active learning strategies, which aim to address challenges such as limited labeled datasets, computational complexity, and model generalizability across diverse imaging modalities. Furthermore, a specialized case study on lumbar spine segmentation is presented, offering insights into the challenges and advancements in this relatively underexplored anatomical region. Despite significant progress in the field, critical challenges persist, including dataset bias, domain adaptation, interpretability of deep learning models, and integration into real-world clinical workflows.

Computers in Biology and Medicine (to appear)

References in corpus (34)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Distilling the Knowledge in a Neural Network
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Conditional Generative Adversarial Nets
• Attention U-Net: Learning Where to Look for the Pancreas
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• An Overview of Multi-Task Learning in Deep Neural Networks
• U-Net and its variants for medical image segmentation: theory and applications
• Temporal Ensembling for Semi-Supervised Learning
• Medical Image Segmentation Using Deep Learning: A Survey
• Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation
• SegAN: Adversarial Network with Multi-scale $L_1$ Loss for Medical Image Segmentation
• A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis
• Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
• Semantic Segmentation using Adversarial Networks
• Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization
• Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers
• Causality matters in medical imaging
• Iterative fully convolutional neural networks for automatic vertebra segmentation and identification
• Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
• Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation
• Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective
• A Localisation-Segmentation Approach for Multi-label Annotation of Lumbar Vertebrae using Deep Nets
• Bayesian Optimization with Unknown Search Space
• Efficient Bayesian Uncertainty Estimation for nnU-Net
• Multi-structure bone segmentation in pediatric MR images with combined regularization from shape priors and adversarial network
• Machine-agnostic Automated Lumbar MRI Segmentation using a Cascaded Model Based on Generative Neurons
• Edge detection with trigonometric polynomial shearlets
• Universal Segmentation of 33 Anatomies
• Characterizing Renal Structures with 3D Block Aggregate Transformers