Convolutional Neural Network–Vision Transformer Architecture with Gated Control Mechanism and Multi-Scale Fusion for Enhanced Pulmonary Disease Classification
Okpala Chibuike, Xiaopeng Yang, Ayman El-Baz · 2024
Read Convolutional Neural Network–Vision Transformer Architecture with Gated Control Mechanism and Multi-Scale Fusion for Enhanced Pulmonary Disease Classification by Okpala Chibuike, Xiaopeng Yang, Ayman El-Baz (2024) 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-11727035.txt.
Description
Okpala Chibuike, Xiaopeng Yang, and Ayman El-Baz build a hybrid vision model for lung disease classification, in work published in 2024. Vision transformers capture broad context in an image but can miss fine detail. Convolutional networks capture local detail well but struggle with long range links across lung regions.
Their design stacks convolutional blocks and transformer blocks in one modular unit. A gated attention step mixes channel, spatial, and element wise cues to stress key features. A multi-scale fusion module then joins features at different scales. Tests reached very high accuracy across four pulmonary conditions. Long tests and ablation studies supported the design, which also showed good calibration for medical image use.
Catalog record
| CREATOR | Okpala Chibuike, Xiaopeng Yang, Ayman El-Baz |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |