TP-UNet: Temporal Prompt Guided UNet for Medical Image Segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Ranmin, Zhuang, Limin, Chen, Hongkun, Xu, Boyan, Cai, Ruichu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929598106697728
author Wang, Ranmin
Zhuang, Limin
Chen, Hongkun
Xu, Boyan
Cai, Ruichu
author_facet Wang, Ranmin
Zhuang, Limin
Chen, Hongkun
Xu, Boyan
Cai, Ruichu
contents The advancement of medical image segmentation techniques has been propelled by the adoption of deep learning techniques, particularly UNet-based approaches, which exploit semantic information to improve the accuracy of segmentations. However, the order of organs in scanned images has been disregarded by current medical image segmentation approaches based on UNet. Furthermore, the inherent network structure of UNet does not provide direct capabilities for integrating temporal information. To efficiently integrate temporal information, we propose TP-UNet that utilizes temporal prompts, encompassing organ-construction relationships, to guide the segmentation UNet model. Specifically, our framework is featured with cross-attention and semantic alignment based on unsupervised contrastive learning to combine temporal prompts and image features effectively. Extensive evaluations on two medical image segmentation datasets demonstrate the state-of-the-art performance of TP-UNet. Our implementation will be open-sourced after acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11305
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TP-UNet: Temporal Prompt Guided UNet for Medical Image Segmentation
Wang, Ranmin
Zhuang, Limin
Chen, Hongkun
Xu, Boyan
Cai, Ruichu
Computer Vision and Pattern Recognition
Artificial Intelligence
The advancement of medical image segmentation techniques has been propelled by the adoption of deep learning techniques, particularly UNet-based approaches, which exploit semantic information to improve the accuracy of segmentations. However, the order of organs in scanned images has been disregarded by current medical image segmentation approaches based on UNet. Furthermore, the inherent network structure of UNet does not provide direct capabilities for integrating temporal information. To efficiently integrate temporal information, we propose TP-UNet that utilizes temporal prompts, encompassing organ-construction relationships, to guide the segmentation UNet model. Specifically, our framework is featured with cross-attention and semantic alignment based on unsupervised contrastive learning to combine temporal prompts and image features effectively. Extensive evaluations on two medical image segmentation datasets demonstrate the state-of-the-art performance of TP-UNet. Our implementation will be open-sourced after acceptance.
title TP-UNet: Temporal Prompt Guided UNet for Medical Image Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.11305