Few-Shot Learning for Cytological Classification of Primary Lung Cancer and Pulmonary Metastases During Endobronchial Ultrasound
Ching-Kai Lin, Di-Chun Wei, Hsin-Hung Chou, I-Shiow Jan, Yun-Chien Cheng · 2026
Read Few-Shot Learning for Cytological Classification of Primary Lung Cancer and Pulmonary Metastases During Endobronchial Ultrasound by Ching-Kai Lin, Di-Chun Wei, Hsin-Hung Chou, I-Shiow Jan, Yun-Chien Cheng (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-13564624.txt.
Description
Ching-Kai Lin and four co-authors built an AI helper for lung biopsies in a 2026 study. A scope passed through the airways can sample lung spots, and a quick stain check during the procedure helps doctors judge what they found. Telling a lung-born cancer from one that spread there is hard on the spot, yet it shapes treatment.
The team trained a model on just 346 cell images from forty-one patients. Their design learns from very few examples by borrowing a pretrained network and mixing two model types. The task was to sort three cancers: lung adenocarcinoma and spread from breast and colon tumors. In a test where the model saw five examples per class, it scored about forty-nine percent, beating other few-example methods. The scores are modest, but labeled samples in this setting are scarce, and the authors frame the tool as early decision support.
Catalog record
| CREATOR | Ching-Kai Lin, Di-Chun Wei, Hsin-Hung Chou, I-Shiow Jan, Yun-Chien Cheng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |