Deep Learning for Cardiac Image Segmentation: A Review.
Chen C, Qin C, Qiu H, Tarroni G, Duan J, Bai W, Rueckert D. · 2020
Read Deep Learning for Cardiac Image Segmentation: A Review. by Chen C, Qin C, Qiu H, Tarroni G, Duan J, Bai W, Rueckert D. (2020) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc7066212.txt.
Description
Chen and co-authors review deep learning for heart image segmentation in Frontiers in Cardiovascular Medicine. Segmentation, outlining the heart's chambers and vessels in a scan, is a basic step in cardiac diagnosis. Deep learning has become the dominant way to automate it. The authors survey more than 100 published studies to take stock of the field.
The review covers the three main imaging types, magnetic resonance, computed tomography, and ultrasound, and the structures clinicians most often need outlined: ventricles, atria, and vessels. It also lists public cardiac image datasets and code repositories to encourage reproducible work. Open problems get frank treatment: labels are scarce, models trained at one hospital often stumble at another, and the networks act as black boxes whose reasoning clinicians cannot inspect. The authors point to those challenges, plus adversarial attacks on medical images, as the directions future research must address.
Catalog record
| CREATOR | Chen C, Qin C, Qiu H, Tarroni G, Duan J, Bai W, Rueckert D. |
|---|---|
| YEAR | 2020 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 170 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |