Book chapter
Joint Calibrationless Reconstruction and Segmentation of Parallel MRI
Computer Vision – ECCV 2022 Workshops, pp.437-453
Lecture Notes in Computer Science, 13803, Springer Nature Switzerland
02/18/2023
DOI: 10.1007/978-3-031-25066-8_24
Abstract
The volume estimation of brain regions from MRI data is a key problem in many clinical applications, where the acquisition of data at high spatial resolution is desirable. While parallel MRI and constrained image reconstruction algorithms can accelerate the scans, image reconstruction artifacts are inevitable, especially at high acceleration factors. We introduce a novel image domain deep-learning framework for calibrationless parallel MRI reconstruction, coupled with a segmentation network to improve image quality and to reduce the vulnerability of current segmentation algorithms to image artifacts resulting from acceleration. Combination of the proposed calibrationless approach with a segmentation algorithm offers improved image quality, while improving segmentation accuracy. The novel architecture with an encoder shared between the reconstruction and segmentation tasks is seen to reduce the need for segmented training datasets. In particular, the proposed few-shot training strategy requires only 10% of segmented datasets to offer good performance.
Details
- Title: Subtitle
- Joint Calibrationless Reconstruction and Segmentation of Parallel MRI
- Creators
- Aniket Pramanik - University of IowaMathews Jacob - University of Iowa
- Resource Type
- Book chapter
- Publication Details
- Computer Vision – ECCV 2022 Workshops, pp.437-453
- Publisher
- Springer Nature Switzerland; Cham
- Series
- Lecture Notes in Computer Science; 13803
- DOI
- 10.1007/978-3-031-25066-8_24
- eISSN
- 1611-3349
- ISSN
- 0302-9743
- Language
- English
- Date published
- 02/18/2023
- Academic Unit
- Radiology; Radiation Oncology; Iowa Neuroscience Institute; Electrical and Computer Engineering
- Record Identifier
- 9984367457402771
Metrics
10 Record Views