Feature learning based on visual similarity triplets in medical image analysis
| Autor: | Nyboe Ørting, Silas, Petersen, Jens, Cheplygina, Veronika, Thomsen, Laura H., Wille, Mathilde M.W., de Bruijne, Marleen, Lee, Su-Lin, Trucco, Emanuele, Maier-Hein, Lena, Moriconi, Stefano, Albarqouni, Shadi, Jannin, Pierre, Balocco, Simone, Zahnd, Guillaume, Mateus, Diana, Taylor, Zeike, Demirci, Stefanie, Stoyanov, Danail, Sznitman, Raphael, Martel, Anne, Granger, Eric, Duong, Luc |
|---|---|
| Přispěvatelé: | Medical Informatics, Radiology & Nuclear Medicine |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: | |
| Zdroj: | Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis ISBN: 9783030013639 CVII-STENT/LABELS@MICCAI Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis-7th Joint International Workshop, CVII-STENT 2018 and Third International Workshop, LABELS 2018 Held in Conjunction with MICCAI 2018, 140-149 STARTPAGE=140;ENDPAGE=149;TITLE=Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis-7th Joint International Workshop, CVII-STENT 2018 and Third International Workshop, LABELS 2018 Held in Conjunction with MICCAI 2018 |
| ISSN: | 0302-9743 |
| Popis: | Supervised feature learning using convolutional neural networks (CNNs) can provide concise and disease relevant representations of medical images. However, training CNNs requires annotated image data. Annotating medical images can be a time-consuming task and even expert annotations are subject to substantial inter- and intra-rater variability. Assessing visual similarity of images instead of indicating specific pathologies or estimating disease severity could allow non-experts to participate, help uncover new patterns, and possibly reduce rater variability. We consider the task of assessing emphysema extent in chest CT scans. We derive visual similarity triplets from visually assessed emphysema extent and learn a low dimensional embedding using CNNs. We evaluate the networks on 973 images, and show that the CNNs can learn disease relevant feature representations from derived similarity triplets. To our knowledge this is the first medical image application where similarity triplets has been used to learn a feature representation that can be used for embedding unseen test images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|