Saved in:
Bibliographic Details
Main Authors: Zhu, Zhenchen, Hu, Ge, Tan, Weixiong, Gao, Kai, Sun, Chao, Zhou, Zhen, Xu, Kepei, Han, Wei, Shang, Meixia, Qiu, Xiaoming, Tan, Yiqing, Wang, Jinhua, Ying, Zhoumeng, Peng, Li, Song, Wei, Song, Lan, Jin, Zhengyu, Hong, Nan, Yu, Yizhou
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.25607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914425408061440
author Zhu, Zhenchen
Hu, Ge
Tan, Weixiong
Gao, Kai
Sun, Chao
Zhou, Zhen
Xu, Kepei
Han, Wei
Shang, Meixia
Qiu, Xiaoming
Tan, Yiqing
Wang, Jinhua
Ying, Zhoumeng
Peng, Li
Song, Wei
Song, Lan
Jin, Zhengyu
Hong, Nan
Yu, Yizhou
author_facet Zhu, Zhenchen
Hu, Ge
Tan, Weixiong
Gao, Kai
Sun, Chao
Zhou, Zhen
Xu, Kepei
Han, Wei
Shang, Meixia
Qiu, Xiaoming
Tan, Yiqing
Wang, Jinhua
Ying, Zhoumeng
Peng, Li
Song, Wei
Song, Lan
Jin, Zhengyu
Hong, Nan
Yu, Yizhou
contents The widespread adoption of CT has notably increased the number of detected lung nodules. However, current deep learning methods for classifying benign and malignant nodules often fail to comprehensively integrate global and local features, and most of them have not been validated through clinical trials. To address this, we developed DeepFAN, a transformer-based model trained on over 10K pathology-confirmed nodules and further conducted a multi-reader, multi-case clinical trial to evaluate its efficacy in assisting junior radiologists. DeepFAN achieved diagnostic area under the curve (AUC) of 0.939 (95% CI 0.930-0.948) on an internal test set and 0.954 (95% CI 0.934-0.973) on the clinical trial dataset involving 400 cases across three independent medical institutions. Explainability analysis indicated higher contributions from global than local features. Twelve readers' average performance significantly improved by 10.9% (95% CI 8.3%-13.5%) in AUC, 10.0% (95% CI 8.9%-11.1%) in accuracy, 7.6% (95% CI 6.1%-9.2%) in sensitivity, and 12.6% (95% CI 10.9%-14.3%) in specificity (P<0.001 for all). Nodule-level inter-reader diagnostic consistency improved from fair to moderate (overall k: 0.313 vs. 0.421; P=0.019). In conclusion, DeepFAN effectively assisted junior radiologists and may help homogenize diagnostic quality and reduce unnecessary follow-up of indeterminate pulmonary nodules. Chinese Clinical Trial Registry: ChiCTR2400084624.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25607
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DeepFAN, a transformer-based deep learning model for human-artificial intelligence collaborative assessment of incidental pulmonary nodules in CT scans: a multi-reader, multi-case trial
Zhu, Zhenchen
Hu, Ge
Tan, Weixiong
Gao, Kai
Sun, Chao
Zhou, Zhen
Xu, Kepei
Han, Wei
Shang, Meixia
Qiu, Xiaoming
Tan, Yiqing
Wang, Jinhua
Ying, Zhoumeng
Peng, Li
Song, Wei
Song, Lan
Jin, Zhengyu
Hong, Nan
Yu, Yizhou
Computer Vision and Pattern Recognition
Artificial Intelligence
The widespread adoption of CT has notably increased the number of detected lung nodules. However, current deep learning methods for classifying benign and malignant nodules often fail to comprehensively integrate global and local features, and most of them have not been validated through clinical trials. To address this, we developed DeepFAN, a transformer-based model trained on over 10K pathology-confirmed nodules and further conducted a multi-reader, multi-case clinical trial to evaluate its efficacy in assisting junior radiologists. DeepFAN achieved diagnostic area under the curve (AUC) of 0.939 (95% CI 0.930-0.948) on an internal test set and 0.954 (95% CI 0.934-0.973) on the clinical trial dataset involving 400 cases across three independent medical institutions. Explainability analysis indicated higher contributions from global than local features. Twelve readers' average performance significantly improved by 10.9% (95% CI 8.3%-13.5%) in AUC, 10.0% (95% CI 8.9%-11.1%) in accuracy, 7.6% (95% CI 6.1%-9.2%) in sensitivity, and 12.6% (95% CI 10.9%-14.3%) in specificity (P<0.001 for all). Nodule-level inter-reader diagnostic consistency improved from fair to moderate (overall k: 0.313 vs. 0.421; P=0.019). In conclusion, DeepFAN effectively assisted junior radiologists and may help homogenize diagnostic quality and reduce unnecessary follow-up of indeterminate pulmonary nodules. Chinese Clinical Trial Registry: ChiCTR2400084624.
title DeepFAN, a transformer-based deep learning model for human-artificial intelligence collaborative assessment of incidental pulmonary nodules in CT scans: a multi-reader, multi-case trial
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.25607