Journal Full-text Available

Fine-Tuning U-Net for Ultrasound Image Segmentation: Different Layers, Different Outcomes

Authors: Mina Amiri , Rupert Brooks , Hassan Rivaz

DOI: 10.1109/TUFFC.2020.3015081

Keywords:

Description: One way of resolving the problem scarce and expensive data in deep learning for medical applications is using transfer fine-tuning a network which has been trained on large set. The common practice to keep shallow layers unchanged modify deeper according new This approach may not work when U-Net moving from different domain ultrasound (US) images due their drastically appearance. In this study, we investigated effect sets pretrained US image segmentation. Two schemes were analyzed, based two definitions layers. We studied simulated images, as well human sets. also included chest X-ray results showed that choosing fine-tune critical task. particular, they demonstrated last network, classification networks, often worst strategy. It therefore be more appropriate rather than segmentation U-Net. Shallow learn lower level features are automatic images. Even set available, observed faster compared whole network.

.The resource attribute category is marked as computer automatic recognition, which may not be accurate. You can try clicking the link to view the resource details.

References(38)
Philipp Fischer, Thomas Brox, None, U-Net: Convolutional Networks for Biomedical Image Segmentation medical image computing and computer assisted intervention. pp. 234- 241 ,(2015) , 10.1007/978-3-319-24574-4_28
Peng Gu, Won-Mean Lee, Marilyn A. Roubidoux, Jie Yuan, Xueding Wang, Paul L. Carson, Automated 3D ultrasound image segmentation to aid breast cancer image interpretation Ultrasonics. ,vol. 65, pp. 51- 58 ,(2016) , 10.1016/J.ULTRAS.2015.10.023
Sylvia Rueda, Sana Fathima, Caroline L. Knight, Mohammad Yaqub, Aris T. Papageorghiou, Bahbibi Rahmatullah, Alessandro Foi, Matteo Maggioni, Antonietta Pepe, Jussi Tohka, Richard V. Stebbing, John E. McManigle, Anca Ciurte, Xavier Bresson, Meritxell Bach Cuadra, Changming Sun, Gennady V. Ponomarev, Mikhail S. Gelfand, Marat D. Kazanov, Ching-Wei Wang, Hsiang-Chou Chen, Chun-Wei Peng, Chu-Mei Hung, J. Alison Noble, Evaluation and Comparison of Current Fetal Ultrasound Image Segmentation Methods for Biometric Measurements: A Grand Challenge IEEE Transactions on Medical Imaging. ,vol. 33, pp. 797- 813 ,(2014) , 10.1109/TMI.2013.2276943
Ivica Zalud, Sara Good, Gustavo Carneiro, Bogdan Georgescu, Kathleen Aoki, Lorry Green, Farzaneh Shahrestani, Russell Okumura, Fetal biometry: a comparison between experienced sonographers and automated measurements. Journal of Maternal-fetal & Neonatal Medicine. ,vol. 22, pp. 43- 50 ,(2009) , 10.1080/14767050802415736
Bram van Ginneken, Mikkel B. Stegmann, Marco Loog, Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database. Medical Image Analysis. ,vol. 10, pp. 19- 40 ,(2006) , 10.1016/J.MEDIA.2005.02.002
K. G. Boone, D. S. Holder, Effect of skin impedance on image quality and variability in electrical impedance tomography: a model study Medical & Biological Engineering & Computing. ,vol. 34, pp. 351- 353 ,(1996) , 10.1007/BF02520003
G. Carneiro, B. Georgescu, S. Good, D. Comaniciu, Detection and Measurement of Fetal Anatomies from Ultrasound Images using a Constrained Probabilistic Boosting Tree IEEE Transactions on Medical Imaging. ,vol. 27, pp. 1342- 1355 ,(2008) , 10.1109/TMI.2008.928917
Yoshua Bengio, Hod Lipson, Jeff Clune, Jason Yosinski, How transferable are features in deep neural networks neural information processing systems. ,vol. 27, pp. 3320- 3328 ,(2014)