Kundeti, SR and Ansari, MA and Mv, AS and Sharma, S and Cr, J (2020) Sub-Object Data Augmentation and Custom Loss Functions for Automated Anatomical Landmarks Localisation in 3D Brain MR Images. In: 9th IEEE International Conference on Cloud Computing in Emerging Markets, CCEM 2020, 4-7 Nov 2020, pp. 24-31.
![]() |
PDF
CCEM_24-31_2020.pdf - Published Version Restricted to Registered users only Download (6MB) | Request a copy |
Abstract
In medical image analysis, the landmarks detection helps to localize each anatomy for tasks like image registration. Deep learning models help to automate the landmark detection pipeline reducing medical technician efforts. The major challenge faced to apply deep learning in medical image analysis is the limited data available for training these models. In this work, we implemented several approaches for data augmentation to address this problem. We modified 2D Flat-net to 3D Flat-net landmark detection network, later used sub-object data augmentation and custom loss function-Masked loss and Soft-argmax loss. We trained and evaluated the combination of data augmentation and custom loss function. On the test set (n=63), using 3D Flat-net with sub-object augmentation, and masked loss function performed the best with Mean Absolute Error improved by 43 (from 9.84 mm to 5.76 mm), Mean Euclidean Error improved by 34 (19.94 mm to 13.16 mm). Root Mean Square Error (RMSE) improved by 39 (from 11.52 mm to 7 mm) compared to Soft-argmax loss function and no augmentation. Data Augmentation of sub-objects and masked loss function improved 3D Flat-net performance for localizing landmarks on medical images. © 2020 IEEE.
Item Type: | Conference Paper |
---|---|
Publication: | Proceedings - 2020 IEEE International Conference on Cloud Computing in Emerging Markets, CCEM 2020 |
Publisher: | Institute of Electrical and Electronics Engineers Inc. |
Additional Information: | The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc. |
Keywords: | Cloud computing; Commerce; Deep learning; Errors; Image analysis; Learning systems; Magnetic resonance imaging; Mean square error; Medical imaging, Anatomical landmarks; Brain MR images; Data augmentation; Landmark detection; Landmarks detection; Learning models; Mean absolute error; Root mean square errors, Image enhancement |
Department/Centre: | Division of Electrical Sciences > Electrical Communication Engineering |
Date Deposited: | 03 Dec 2021 08:31 |
Last Modified: | 03 Dec 2021 08:31 |
URI: | http://eprints.iisc.ac.in/id/eprint/70216 |
Actions (login required)
![]() |
View Item |