Intelligent diagnosis of major depressive disorder with edge convolution and contrastive learning
Dan Long, Chen Zhu, Lei Xiong, Zhou Long, Fangfang Dong · 2026
Read Intelligent diagnosis of major depressive disorder with edge convolution and contrastive learning by Dan Long, Chen Zhu, Lei Xiong, Zhou Long, Fangfang Dong (2026) 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/pmc-13143075.txt.
Description
Dan Long, Chen Zhu, Lei Xiong, Zhou Long, and Fangfang Dong build a brain-network classifier for major depression that respects each region's identity, in a two thousand twenty-six neuroimaging paper. Standard graph networks treat brain regions as interchangeable, erasing spatial specificity.
Their framework pairs an edge convolution encoder with adversarial graph contrastive learning over resting-state connectivity from eleven hundred sixty participants, about half with depression. It beat conventional machine learning and graph models, reaching an area under the curve of about seventy-one percent. The model highlighted the dorsolateral superior frontal gyrus, thalamus, and insula, regions prior studies implicate in depression. The authors present it as explainable diagnostic support.
Catalog record
| CREATOR | Dan Long, Chen Zhu, Lei Xiong, Zhou Long, Fangfang Dong |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |