Computer-Aided Volumetry with Convolutional Neural Network: Application in the Evaluation of Invasiveness of Lung Adenocarcinoma on High-Definition CT Images

May 1, 2026European Journal of Radiology Artificial IntelligenceOpen Access

View Full Paper

Ask AI

Bookmark

Share

Key Points

To compare the effectiveness of computer-aided volumetry and convolutional neural networks in distinguishing invasive from non-invasive lung adenocarcinoma.
Included 181 patients with lung adenocarcinomas who underwent HDCT imaging with varying dose levels (SDCT, RDCT, ULDCT).
Utilized 3D volumetry and 2D maximum diameter measurements to assess tumor characteristics using CTRvolume and CTRLAD.
Performed receiver operating characteristic analysis and McNemar's test to evaluate diagnostic performance and survival outcomes.
CTRvolume showed a significantly larger area under the curve compared to CTRLAD (p<0.05).
Sensitivity and accuracy of CTRvolume were significantly higher than CTRLAD for all HDCTs (p<0.05).
No significant differences in disease-free survival or overall survival between invasive and non-invasive groups.

We only have this paper's title and publication details.

Compares CADv and CNN for assessing lung adenocarcinoma invasiveness, suggesting improved diagnostic performance.

No takes yet. Share an insight, caveat, or question.

Ozawa et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Share