AI Science Tracker
EN

National Tsing Hua University

1 discovery from 2024

Discoveries

A small CT study evaluates learned pneumothorax classification

Source check: Source checked. Not independent scientific confirmation.

Finding: A convolutional model classified selected, preprocessed coronal CT slices from 26 surgical patients with primary spontaneous pneumothorax and 26 surgical controls. EfficientNetB3 classified 43 of 46 unaugmented test images correctly. The image-level result does not establish screening performance or show that AI discovered the anatomical feature described by surgeons.

Technology: EfficientNetB3 transfer learning

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
EfficientNetB3 transfer learning fitted the represented classification or candidate-selection model; preprocessing and expert reference labels are distinguished from the learned contribution.
Test and result
Twenty-six cases and twenty-six surgical controls supplied multiple CT images. Authors report assigning patients separately to training, validation and testing; the unaugmented test table contains 21 true positives, 22 true negatives, two false positives and one false negative.
Limitation / still unknown
Only a small number of patients supplied test images; the exact patient denominator of the 46-image test is not explicit. Cases and controls differ in age, sex and body habitus. The 903 augmented test images are transformations, not independent patients. Two surgeons defined/reviewed the anatomical feature; the learned contribution is the classifier, not initial anatomical discovery.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC11078867/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 21 Nov 2026. Review scope: Primary article full-text bibliographic metadata and relevant computational evaluation Methods/Results: sec2.1, sec2.2, sec2.3, sec2.6, sec3, tbl2. Primary-source caveat and denominator review; candidate-panel identity corrected where relevant..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 1/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.