Fatih Sultan Mehmet Vakif University, Computer Engineering, İstanbul, 34445, Türkiye.
Sci Data. 2024 Nov 25;11(1):1283. doi: 10.1038/s41597-024-04159-2.
MedSegBench is a comprehensive benchmark designed to evaluate deep learning models for medical image segmentation across a wide range of modalities. It covers a wide range of modalities, including 35 datasets with over 60,000 images from ultrasound, MRI, and X-ray. The benchmark addresses challenges in medical imaging by providing standardized datasets with train/validation/test splits, considering variability in image quality and dataset imbalances. The benchmark supports binary and multi-class segmentation tasks with up to 19 classes and uses the U-Net architecture with various encoder/decoder networks such as ResNets, EfficientNet, and DenseNet for evaluations. MedSegBench is a valuable resource for developing robust and flexible segmentation algorithms and allows for fair comparisons across different models, promoting the development of universal models for medical tasks. It is the most comprehensive study among medical segmentation datasets. The datasets and source code are publicly available, encouraging further research and development in medical image analysis.
MedSegBench 是一个综合性的基准，旨在评估医学图像分割的深度学习模型，涵盖了多种模态。它涵盖了多种模态，包括 35 个数据集，涵盖了来自超声、MRI 和 X 射线的超过 60000 张图像。该基准通过提供具有训练/验证/测试分割的标准化数据集，考虑到图像质量和数据集不平衡的可变性，解决了医学成像中的挑战。该基准支持二进制和多类分割任务，最多可达 19 个类别，并使用 U-Net 架构和各种编码器/解码器网络（如 ResNets、EfficientNet 和 DenseNet）进行评估。MedSegBench 是开发强大和灵活的分割算法的有价值资源，并允许在不同模型之间进行公平比较，促进用于医疗任务的通用模型的发展。它是医学分割数据集的最全面研究。数据集和源代码都是公开的，鼓励在医学图像分析方面进行进一步的研究和开发。
