A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm
Abdominal aortic aneurysm (AAA) is one of the most common diseases worldwide. 3D segmentation of AAA provides useful information for surgical decisions and follow-up treatment. However, existing segmentation methods are time consuming and not practical in routine use. In this article, the segmentati...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2022-07-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1033.pdf |
| _version_ | 1818521977276596224 |
|---|---|
| author | Thanongchai Siriapisith Worapan Kusakunniran Peter Haddawy |
| author_facet | Thanongchai Siriapisith Worapan Kusakunniran Peter Haddawy |
| author_sort | Thanongchai Siriapisith |
| collection | DOAJ |
| description | Abdominal aortic aneurysm (AAA) is one of the most common diseases worldwide. 3D segmentation of AAA provides useful information for surgical decisions and follow-up treatment. However, existing segmentation methods are time consuming and not practical in routine use. In this article, the segmentation task will be addressed automatically using a deep learning based approach which has been proved to successfully solve several medical imaging problems with excellent performances. This article therefore proposes a new solution of AAA segmentation using deep learning in a type of 3D convolutional neural network (CNN) architecture that also incorporates coordinate information. The tested CNNs are UNet, AG-DSV-UNet, VNet, ResNetMed and DenseVoxNet. The 3D-CNNs are trained with a dataset of high resolution (256 × 256) non-contrast and post-contrast CT images containing 64 slices from each of 200 patients. The dataset consists of contiguous CT slices without augmentation and no post-processing step. The experiments show that incorporation of coordinate information improves the segmentation results. The best accuracies on non-contrast and contrast-enhanced images have average dice scores of 97.13% and 96.74%, respectively. Transfer learning from a pre-trained network of a pre-operative dataset to post-operative endovascular aneurysm repair (EVAR) was also performed. The segmentation accuracy of post-operative EVAR using transfer learning on non-contrast and contrast-enhanced CT datasets achieved the best dice scores of 94.90% and 95.66%, respectively. |
| first_indexed | 2024-12-11T01:58:35Z |
| format | Article |
| id | doaj.art-9164cbf304fa48fc95a01790cf32888c |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-11T01:58:35Z |
| publishDate | 2022-07-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-9164cbf304fa48fc95a01790cf32888c2022-12-22T01:24:33ZengPeerJ Inc.PeerJ Computer Science2376-59922022-07-018e103310.7717/peerj-cs.1033A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysmThanongchai Siriapisith0Worapan Kusakunniran1Peter Haddawy2Department of Radiology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, ThailandFaculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, ThailandFaculty of Information and Communication Technology, Mahidol University, Nakhon Pathom, ThailandAbdominal aortic aneurysm (AAA) is one of the most common diseases worldwide. 3D segmentation of AAA provides useful information for surgical decisions and follow-up treatment. However, existing segmentation methods are time consuming and not practical in routine use. In this article, the segmentation task will be addressed automatically using a deep learning based approach which has been proved to successfully solve several medical imaging problems with excellent performances. This article therefore proposes a new solution of AAA segmentation using deep learning in a type of 3D convolutional neural network (CNN) architecture that also incorporates coordinate information. The tested CNNs are UNet, AG-DSV-UNet, VNet, ResNetMed and DenseVoxNet. The 3D-CNNs are trained with a dataset of high resolution (256 × 256) non-contrast and post-contrast CT images containing 64 slices from each of 200 patients. The dataset consists of contiguous CT slices without augmentation and no post-processing step. The experiments show that incorporation of coordinate information improves the segmentation results. The best accuracies on non-contrast and contrast-enhanced images have average dice scores of 97.13% and 96.74%, respectively. Transfer learning from a pre-trained network of a pre-operative dataset to post-operative endovascular aneurysm repair (EVAR) was also performed. The segmentation accuracy of post-operative EVAR using transfer learning on non-contrast and contrast-enhanced CT datasets achieved the best dice scores of 94.90% and 95.66%, respectively.https://peerj.com/articles/cs-1033.pdfAbdominal aortic aneurysmComputed tomography3D segmentationDeep learningCoordinate informationTransfer learning |
| spellingShingle | Thanongchai Siriapisith Worapan Kusakunniran Peter Haddawy A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm PeerJ Computer Science Abdominal aortic aneurysm Computed tomography 3D segmentation Deep learning Coordinate information Transfer learning |
| title | A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm |
| title_full | A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm |
| title_fullStr | A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm |
| title_full_unstemmed | A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm |
| title_short | A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm |
| title_sort | retrospective study of 3d deep learning approach incorporating coordinate information to improve the segmentation of pre and post operative abdominal aortic aneurysm |
| topic | Abdominal aortic aneurysm Computed tomography 3D segmentation Deep learning Coordinate information Transfer learning |
| url | https://peerj.com/articles/cs-1033.pdf |
| work_keys_str_mv | AT thanongchaisiriapisith aretrospectivestudyof3ddeeplearningapproachincorporatingcoordinateinformationtoimprovethesegmentationofpreandpostoperativeabdominalaorticaneurysm AT worapankusakunniran aretrospectivestudyof3ddeeplearningapproachincorporatingcoordinateinformationtoimprovethesegmentationofpreandpostoperativeabdominalaorticaneurysm AT peterhaddawy aretrospectivestudyof3ddeeplearningapproachincorporatingcoordinateinformationtoimprovethesegmentationofpreandpostoperativeabdominalaorticaneurysm AT thanongchaisiriapisith retrospectivestudyof3ddeeplearningapproachincorporatingcoordinateinformationtoimprovethesegmentationofpreandpostoperativeabdominalaorticaneurysm AT worapankusakunniran retrospectivestudyof3ddeeplearningapproachincorporatingcoordinateinformationtoimprovethesegmentationofpreandpostoperativeabdominalaorticaneurysm AT peterhaddawy retrospectivestudyof3ddeeplearningapproachincorporatingcoordinateinformationtoimprovethesegmentationofpreandpostoperativeabdominalaorticaneurysm |