Automatic MRI Lymph Node Annotation From CT Labels
After annotating a medical imaging modality that is relatively straightforward to label, doctors often expect automatic annotations for images from other modalities of the same region, even though these modalities differ in contrast and structure. This study focuses on creating automatic lymph node...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10855406/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832088035656728576 |
|---|---|
| author | Souraja Kundu Yuji Iwahori M. K. Bhuyan Manish Bhatt Boonserm Kijsirikul Aili Wang Akira Ouchi Yasuhiro Shimizu |
| author_facet | Souraja Kundu Yuji Iwahori M. K. Bhuyan Manish Bhatt Boonserm Kijsirikul Aili Wang Akira Ouchi Yasuhiro Shimizu |
| author_sort | Souraja Kundu |
| collection | DOAJ |
| description | After annotating a medical imaging modality that is relatively straightforward to label, doctors often expect automatic annotations for images from other modalities of the same region, even though these modalities differ in contrast and structure. This study focuses on creating automatic lymph node annotation in MRI images using available CT annotations via deep-learning models. Training such models typically requires partial MRI labels for semi-supervision. However, annotating lymph nodes in MRI images is particularly challenging due to their small size and the high cost of MRI scans. These factors make it difficult to create labeled MRI datasets for deep learning model training. Moreover, existing cross-modal annotation methods primarily focus on large tumors and require large datasets, making them unsuitable for small lymph nodes with less training data. We address these challenges using cross-modal supervision through image registration. Our algorithm reduces the burden of manual annotation and the reliance on large labeled datasets and eliminates the need for any MRI ground truth. The algorithm has three steps: 1) unsupervised deformable image translation-based registration of MRI to CT image, producing registered MRI; 2) annotating lymph nodes in registered MRI with the available CT labels; and 3) deregistration of registered annotated MRI back to the original shape of MRI. The translation-based registration model for the algorithm’s first and third steps uses a discriminator-free StyleGAN2 translation network and a deformable image registration network with a U-Net-inspired architecture. This registration network includes local and global feature extraction modules, a local-global spatial correlation module, and a superresolution loss function. Our approach eliminates the need for MRI labels by registering MRI with CT images. Experiments show 2.19% and 4.08% MSE reductions, 5.40% and 3.28% SSIM improvements, 29.85% and 3.82% NCC increases for cross-modality and mono-modality registration, respectively, along with a 36.7% training speedup over state-of-the-art translation-based registration models. The lymph node annotation method achieves an average of 74.3% DSC in the region of interest. It also has broader applications in multimodality image segmentation. We open-source the code through a GitHub repository.INDEX TERMS Image registration, image annotation, magnetic resonance imaging, computed tomography, unsupervised learning, superresolution. |
| format | Article |
| id | doaj-art-9183a5aa085d43069cb94432050d609d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-9183a5aa085d43069cb94432050d609d2025-02-06T00:00:40ZengIEEEIEEE Access2169-35362025-01-0113219062192610.1109/ACCESS.2025.353521910855406Automatic MRI Lymph Node Annotation From CT LabelsSouraja Kundu0https://orcid.org/0009-0008-7115-0926Yuji Iwahori1https://orcid.org/0000-0002-6421-8186M. K. Bhuyan2https://orcid.org/0000-0003-2152-5466Manish Bhatt3https://orcid.org/0000-0002-3867-5180Boonserm Kijsirikul4https://orcid.org/0000-0002-9046-7151Aili Wang5https://orcid.org/0000-0002-9118-230XAkira Ouchi6Yasuhiro Shimizu7Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, IndiaDepartment of Computer Science, Chubu University, Kasugai, JapanDepartment of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, IndiaDepartment of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, IndiaDepartment of Computer Engineering, Chulalongkorn University, Bangkok, ThailandHeilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application, Harbin University of Science and Technology, Harbin, Heilongjiang, ChinaDepartment of Gastroenterological Surgery, Aichi Cancer Center Hospital, Nagoya, JapanDepartment of Gastroenterological Surgery, Aichi Cancer Center Hospital, Nagoya, JapanAfter annotating a medical imaging modality that is relatively straightforward to label, doctors often expect automatic annotations for images from other modalities of the same region, even though these modalities differ in contrast and structure. This study focuses on creating automatic lymph node annotation in MRI images using available CT annotations via deep-learning models. Training such models typically requires partial MRI labels for semi-supervision. However, annotating lymph nodes in MRI images is particularly challenging due to their small size and the high cost of MRI scans. These factors make it difficult to create labeled MRI datasets for deep learning model training. Moreover, existing cross-modal annotation methods primarily focus on large tumors and require large datasets, making them unsuitable for small lymph nodes with less training data. We address these challenges using cross-modal supervision through image registration. Our algorithm reduces the burden of manual annotation and the reliance on large labeled datasets and eliminates the need for any MRI ground truth. The algorithm has three steps: 1) unsupervised deformable image translation-based registration of MRI to CT image, producing registered MRI; 2) annotating lymph nodes in registered MRI with the available CT labels; and 3) deregistration of registered annotated MRI back to the original shape of MRI. The translation-based registration model for the algorithm’s first and third steps uses a discriminator-free StyleGAN2 translation network and a deformable image registration network with a U-Net-inspired architecture. This registration network includes local and global feature extraction modules, a local-global spatial correlation module, and a superresolution loss function. Our approach eliminates the need for MRI labels by registering MRI with CT images. Experiments show 2.19% and 4.08% MSE reductions, 5.40% and 3.28% SSIM improvements, 29.85% and 3.82% NCC increases for cross-modality and mono-modality registration, respectively, along with a 36.7% training speedup over state-of-the-art translation-based registration models. The lymph node annotation method achieves an average of 74.3% DSC in the region of interest. It also has broader applications in multimodality image segmentation. We open-source the code through a GitHub repository.INDEX TERMS Image registration, image annotation, magnetic resonance imaging, computed tomography, unsupervised learning, superresolution.https://ieeexplore.ieee.org/document/10855406/Image registrationImage annotationMagnetic resonance imagingComputed tomographyUnsupervised learningSuperresolution |
| spellingShingle | Souraja Kundu Yuji Iwahori M. K. Bhuyan Manish Bhatt Boonserm Kijsirikul Aili Wang Akira Ouchi Yasuhiro Shimizu Automatic MRI Lymph Node Annotation From CT Labels IEEE Access Image registration Image annotation Magnetic resonance imaging Computed tomography Unsupervised learning Superresolution |
| title | Automatic MRI Lymph Node Annotation From CT Labels |
| title_full | Automatic MRI Lymph Node Annotation From CT Labels |
| title_fullStr | Automatic MRI Lymph Node Annotation From CT Labels |
| title_full_unstemmed | Automatic MRI Lymph Node Annotation From CT Labels |
| title_short | Automatic MRI Lymph Node Annotation From CT Labels |
| title_sort | automatic mri lymph node annotation from ct labels |
| topic | Image registration Image annotation Magnetic resonance imaging Computed tomography Unsupervised learning Superresolution |
| url | https://ieeexplore.ieee.org/document/10855406/ |
| work_keys_str_mv | AT sourajakundu automaticmrilymphnodeannotationfromctlabels AT yujiiwahori automaticmrilymphnodeannotationfromctlabels AT mkbhuyan automaticmrilymphnodeannotationfromctlabels AT manishbhatt automaticmrilymphnodeannotationfromctlabels AT boonsermkijsirikul automaticmrilymphnodeannotationfromctlabels AT ailiwang automaticmrilymphnodeannotationfromctlabels AT akiraouchi automaticmrilymphnodeannotationfromctlabels AT yasuhiroshimizu automaticmrilymphnodeannotationfromctlabels |