Dai, Siyuan
(2024)
SIN-Seg: A Joint Spatial-Spectral Information Fusion Model for Medical Image Segmentation.
Master's Thesis, University of Pittsburgh.
(Unpublished)
Abstract
In recent years, the application of deep convolutional neural networks (DCNNs) to medical image segmentation has shown significant promise in computer-aided detection and diagnosis (CAD). Leveraging features from different spaces(i.e. multi-modalities, Euclidean, non-Euclidean, and spectrum spaces) has the potential to enrich the information available to CAD systems, enhancing both effectiveness and efficiency. However, directly acquiring the data across different spaces is often prohibitively expensive and time-consuming. Consequently, most current brain imaging segmentation techniques are confined to the spatial domain, which means just utilizing MRI or CT images. Our research introduces an innovative Joint Spatial-Spectral Information Fusion method that requires no additional data collection. We translate existing MRI data into a new domain to extract features from an alternative space. More precisely, we apply Discrete Cosine Transformation (DCT) to enter the spectrum domain, thereby accessing supplementary feature information from an alternate space. Recognizing that information from different spaces typically necessitates complex alignment modules, we also introduce a contrastive loss function for achieving feature alignment before synchronizing information across different feature spaces. Our empirical results illustrate the effectiveness of our model in harnessing additional information from the spectrum-based space and affirm its superior performance against influential state-of-the-art segmentation baselines.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
3 June 2024 |
| Date Type: |
Publication |
| Defense Date: |
6 December 2023 |
| Approval Date: |
3 June 2024 |
| Submission Date: |
11 March 2024 |
| Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
| Number of Pages: |
45 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
Swanson School of Engineering > Electrical and Computer Engineering |
| Degree: |
MS - Master of Science |
| Thesis Type: |
Master's Thesis |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
Spectral Information, Feature Alignment, Medical Image Segmentation, Contrastive Learning |
| Date Deposited: |
03 Jun 2024 14:37 |
| Last Modified: |
03 Jun 2024 14:37 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/45852 |
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}