Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Cheng, Junlong, Fu, Bin, Ye, Jin, Wang, Guoan, Li, Tianbin, Wang, Haoyu, Li, Ruoyu, Yao, He, Chen, Junren, Li, Jingwen, Su, Yanzhou, Zhu, Min, He, Junjun
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917847200956416
author Cheng, Junlong
Fu, Bin
Ye, Jin
Wang, Guoan
Li, Tianbin
Wang, Haoyu
Li, Ruoyu
Yao, He
Chen, Junren
Li, Jingwen
Su, Yanzhou
Zhu, Min
He, Junjun
author_facet Cheng, Junlong
Fu, Bin
Ye, Jin
Wang, Guoan
Li, Tianbin
Wang, Haoyu
Li, Ruoyu
Yao, He
Chen, Junren
Li, Jingwen
Su, Yanzhou
Zhu, Min
He, Junjun
contents Interactive Medical Image Segmentation (IMIS) has long been constrained by the limited availability of large-scale, diverse, and densely annotated datasets, which hinders model generalization and consistent evaluation across different models. In this paper, we introduce the IMed-361M benchmark dataset, a significant advancement in general IMIS research. First, we collect and standardize over 6.4 million medical images and their corresponding ground truth masks from multiple data sources. Then, leveraging the strong object recognition capabilities of a vision foundational model, we automatically generated dense interactive masks for each image and ensured their quality through rigorous quality control and granularity management. Unlike previous datasets, which are limited by specific modalities or sparse annotations, IMed-361M spans 14 modalities and 204 segmentation targets, totaling 361 million masks-an average of 56 masks per image. Finally, we developed an IMIS baseline network on this dataset that supports high-quality mask generation through interactive inputs, including clicks, bounding boxes, text prompts, and their combinations. We evaluate its performance on medical image segmentation tasks from multiple perspectives, demonstrating superior accuracy and scalability compared to existing interactive segmentation models. To facilitate research on foundational models in medical computer vision, we release the IMed-361M and model at https://github.com/uni-medical/IMIS-Bench.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12814
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline
Cheng, Junlong
Fu, Bin
Ye, Jin
Wang, Guoan
Li, Tianbin
Wang, Haoyu
Li, Ruoyu
Yao, He
Chen, Junren
Li, Jingwen
Su, Yanzhou
Zhu, Min
He, Junjun
Computer Vision and Pattern Recognition
Interactive Medical Image Segmentation (IMIS) has long been constrained by the limited availability of large-scale, diverse, and densely annotated datasets, which hinders model generalization and consistent evaluation across different models. In this paper, we introduce the IMed-361M benchmark dataset, a significant advancement in general IMIS research. First, we collect and standardize over 6.4 million medical images and their corresponding ground truth masks from multiple data sources. Then, leveraging the strong object recognition capabilities of a vision foundational model, we automatically generated dense interactive masks for each image and ensured their quality through rigorous quality control and granularity management. Unlike previous datasets, which are limited by specific modalities or sparse annotations, IMed-361M spans 14 modalities and 204 segmentation targets, totaling 361 million masks-an average of 56 masks per image. Finally, we developed an IMIS baseline network on this dataset that supports high-quality mask generation through interactive inputs, including clicks, bounding boxes, text prompts, and their combinations. We evaluate its performance on medical image segmentation tasks from multiple perspectives, demonstrating superior accuracy and scalability compared to existing interactive segmentation models. To facilitate research on foundational models in medical computer vision, we release the IMed-361M and model at https://github.com/uni-medical/IMIS-Bench.
title Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.12814