Search: onr:"swepub:oai:DiVA.org:kth-296810" >
Normal appearance a...
Normal appearance autoencoder for lung cancer detection and segmentation
-
- Astaraki, Mehdi, PhD Student, 1984- (author)
- KTH,Medicinsk avbildning,Department of Oncology-Pathology, Karolinska Institutet Karolinska Universitetssjukhuset Stockholm Sweden
-
Toma-Dasu, Iuliana (author)
-
- Smedby, Örjan, Professor, 1956- (author)
- KTH,Medicinsk avbildning
-
show more...
-
- Wang, Chunliang, 1980- (author)
- KTH,Medicinsk avbildning
-
show less...
-
(creator_code:org_t)
- 2019-10-10
- 2019
- English.
-
In: International Conference on Medical Image Computing and Computer-Assisted Intervention. - Cham : Springer Nature. ; , s. 249-256
- Related links:
-
https://link.springe...
-
show more...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- One of the major differences between medical doctor training and machine learning is that doctors are trained to recognize normal/healthy anatomy first. Knowing the healthy appearance of anatomy structures helps doctors to make better judgement when some abnormality shows up in an image. In this study, we propose a normal appearance autoencoder (NAA), that removes abnormalities from a diseased image. This autoencoder is semi-automatically trained using another partial convolutional in-paint network that is trained using healthy subjects only. The output of the autoencoder is then fed to a segmentation net in addition to the original input image, i.e. the latter gets both the diseased image and a simulated healthy image where the lesion is artificially removed. By getting access to knowledge of how the abnormal region is supposed to look, we hypothesized that the segmentation network could perform better than just being shown the original slice. We tested the proposed network on the LIDC-IDRI dataset for lung cancer detection and segmentation. The preliminary results show the NAA approach improved segmentation accuracy substantially in comparison with the conventional U-Net architecture.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Medicinteknik -- Medicinsk bildbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Medical Engineering -- Medical Image Processing (hsv//eng)
Keyword
- Lung nodule segmentation
- Anomaly detection
- Convolutional variational autoencoder
- Medical Technology
- Medicinsk teknologi
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database