Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark

About

Transformers have demonstrated remarkable performance in natural language processing and computer vision. However, existing vision Transformers struggle to learn from limited medical data and are unable to generalize on diverse medical image tasks. To tackle these challenges, we present MedFormer, a data-scalable Transformer designed for generalizable 3D medical image segmentation. Our approach incorporates three key elements: a desirable inductive bias, hierarchical modeling with linear-complexity attention, and multi-scale feature fusion that integrates spatial and semantic information globally. MedFormer can learn across tiny- to large-scale data without pre-training. Comprehensive experiments demonstrate MedFormer's potential as a versatile segmentation backbone, outperforming CNNs and vision Transformers on seven public datasets covering multiple modalities (e.g., CT and MRI) and various medical targets (e.g., healthy organs, diseased tissues, and tumors). We provide public access to our models and evaluation pipeline, offering solid baselines and unbiased comparisons to advance a wide range of downstream clinical applications.

Yunhe Gao, Mu Zhou, Di Liu, Zhennan Yan, Shaoting Zhang, Dimitris N. Metaxas• 2022

Related benchmarks

TaskDatasetResultRank
Medical Image SegmentationBUSI (test)--
121
Skin Lesion SegmentationISIC 2017 (test)
Dice Score87.23
100
Skin Lesion SegmentationISIC 2018 (test)
Dice Score88.25
74
Medical Image SegmentationISIC (test)
IoU0.8114
55
Tumor Segmentation and DetectionUCSF Pancreas Tumor internal (test)
F1 Score67
11
Tumor Segmentation and DetectionUCSF Kidney Tumor internal (test)
F1 Score71
11
Tumor Segmentation and DetectionJHH Pancreas Tumor external (test)
DSC51
11
Binary SegmentationISIC 17
mIoU77.35
9
Fluence map predictionProstate IMRT dataset
MAE0.14
8
Medical Image SegmentationAMOS-CT (val)
mDice90.1
5
Showing 10 of 10 rows

Other info

Follow for update