LXNet: A lightweight CNN for lung disease classification from Chest X-ray with XAI-based interpretability
Juiria Humayan, Md Najmus Sakib Nahid, Amir Sohel, Md Alamgir Kabir, Md Shakhawat Hossain, Zahid Ullah, Mona Jamjoom · 2026
Read LXNet: A lightweight CNN for lung disease classification from Chest X-ray with XAI-based interpretability by Juiria Humayan, Md Najmus Sakib Nahid, Amir Sohel, Md Alamgir Kabir, Md Shakhawat Hossain, Zahid Ullah, Mona Jamjoom (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/plos-pone-0351762.txt.
Description
Reading chest X-rays takes training that many clinics lack. Juiria Humayan and colleagues built a small computer program to help. It sorts scans into nine lung conditions. Healthy scans are one class. Pneumonia and tuberculosis are among the others. The study appeared in PLOS One in 2026. It targets places where heavy software cannot run.
The program is far smaller than standard rival models. It trained in about five minutes on ordinary hardware. Across repeated tests, it scored about ninety-six percent accuracy. It learned from nearly seven thousand images from one Brazilian center. Display tools highlight the image regions behind each call. Scores fell on outside data, though. Wider testing must come before clinic use.
Catalog record
| CREATOR | Juiria Humayan, Md Najmus Sakib Nahid, Amir Sohel, Md Alamgir Kabir, Md Shakhawat Hossain, Zahid Ullah, Mona Jamjoom |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 82400 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |