Abstract
Medical image segmentation is the process of anatomically isolating organs for analysis and treatment. Leading works within this domain emerged with the well-known U-Net. Despite its success, recent works have shown the limitations of U-Net to conduct segmentation given image particularities such as noise, corruption or lack of contrast. Prior knowledge integration allows to overcome segmentation ambiguities. This paper introduces BB-UNet (Bounding Box U-Net), a deep learning model that integrates location as well as shape prior onto model training. The proposed model is inspired by U-Net and incorporates priors through a novel convolutional layer introduced at the level of skip connections. The proposed architecture helps in presenting attention kernels onto the neural training in order to guide the model on where to look for the organs. Moreover, it fine-Tunes the encoder layers based on positional constraints. The proposed model is exploited within two main paradigms: As a solo model given a fully supervised framework and as an ancillary model, in a weakly supervised setting. In the current experiments, manual bounding boxes are fed at inference and as such BB-Unet is exploited in a semi-Automatic setting; however, BB-Unet has the potential of being part of a fully automated process, if it relies on a preliminary step of object detection. To validate the performance of the proposed model, experiments are conducted on two public datasets: The SegTHOR dataset which focuses on the segmentation of thoracic organs at risk in computed tomography (CT) images, and the Cardiac dataset which is a mono-modal MRI dataset released as part of the Decathlon challenge and dedicated to segmentation of the left atrium. Results show that the proposed method outperforms state-of-The-Art methods in fully supervised learning frameworks and registers relevant results given the weakly supervised domain.
Original language | English |
---|---|
Article number | 9113460 |
Pages (from-to) | 1189-1198 |
Number of pages | 10 |
Journal | IEEE Journal on Selected Topics in Signal Processing |
Volume | 14 |
Issue number | 6 |
DOIs | |
Publication status | Published - Oct 2020 |
Externally published | Yes |
Bibliographical note
Funding Information:The authors would like to acknowledge the CNRS-Lebanon and AUF for granting a doctoral fellowship to R. El Jurdi, as well as the ANR (Project APi, grant ANR-18-CE23-0014) and the CRIANN for providing computational resources.
Funding Information:
Manuscript received December 10, 2019; revised April 16, 2020 and June 4, 2020; accepted June 4, 2020. Date of publication June 10, 2020; date of current version September 24, 2020. This work was supported in part by the DAISI project, in part by the European Union with the European Regional Development Fund (ERDF), and in part by the Normandy Region. The guest editor coordinating the review of this manuscript and approving it for publication was Dr. Vishal Monga. (Corresponding author: Rosana El Jurdi.) Rosana El Jurdi is with the Normandie Université, UNIROUEN, UNIHAVRE, INSA Rouen, LITIS, 76000 Rouen, France, and also with the Lebanese University, Beirut, Lebanon (e-mail: rosana.el-jurdi@univ-rouen.fr).
Keywords
- attention maps
- deep learning
- location prior
- shape prior
- U-Net
- weakly supervised segmentation