Hybrid transformer-CNN and LSTM model for lung disease segmentation and classification
Syed Mohammed Shafi, Sathiya Kumar Chinnappan · 2024
Read Hybrid transformer-CNN and LSTM model for lung disease segmentation and classification by Syed Mohammed Shafi, Sathiya Kumar Chinnappan (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-11784776.txt.
Description
Syed Mohammed Shafi and Sathiya Kumar Chinnappan propose a hybrid deep learning pipeline that first outlines diseased lung regions in scans and then names the disease. Lung disorders kill millions each year, and their scan appearances vary unpredictably, which makes automated reading hard. Writing in twenty twenty-four, their system cleans images with a noise filter, segments the affected area with an improved transformer and convolution design, and pulls out texture, shape, color, and learned features. A linked memory network then classifies the case, with the segmenter and classifier sharing a modified design.
Tested on two CT data sets, one covering COVID cases, the hybrid beat a long list of earlier models in the authors comparisons, with accuracy rising as more training data was used. The paper is aimed at builders of diagnostic support tools.
Catalog record
| CREATOR | Syed Mohammed Shafi, Sathiya Kumar Chinnappan |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 153 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |