University of Leicester
Browse
Improving CT-image universal lesion detection with comprehensive data and feature enhancements.pdf (2.68 MB)

Improving CT-image universal lesion detection with comprehensive data and feature enhancements

Download (2.68 MB)
journal contribution
posted on 2022-06-28, 09:47 authored by Zhe Liu, Kai Han, Kaifeng Xue, Yuqing Song, Lu Liu, Yangyang Tang, Yan Zhu
As a crucial task in Computer Vision, object detection has substantially improved in recent years, with the aid of deep learning and increasingly abundant datasets. However, compared with natural image detection, medical CT images require more precision due to the obvious clinical implications. Detecting multiple lesions or clusters with relatively few training samples and indistinctive feature representation is extremely problematic. In this paper, we propose comprehensive improvements to the original YOLOv3, such as data augmentation, feature attention enhancement and feature complementarity enhancement to increase general lesion area detection performance. Ablation studies use the open DeepLesion dataset to validate these improvements and confirm the effectiveness of each amendment. Comparisons between state-of-the-art counterparts demonstrated that the proposed lesion object detector has enhanced salient accuracy (under two commonly used metrics) and an exceptional speed-accuracy trade-off. The proposed model achieved 57.5% mAP and 85.07% sensitivity at 4 false positives (FPs) per image, while running at reliable 35.6 frames per second (FPS). These findings indicate that the proposed detector is more practicable than other currently available computer aided diagnostics (CAD).

Funding

National Natural Science Foundation of China (61976106, 61772242, 61572239)

China Postdoctoral Science Foundation (2017M611737)

Six talent peaks project in Jiangsu Province (DZXX-122)

Zhenjiang City Social Development Key R&D Program (SH2021056)

History

Citation

Multimedia Systems (2022). https://doi.org/10.1007/s00530-022-00943-5

Author affiliation

School of Computing and Mathematical Sciences, University of Leicester

Version

  • AM (Accepted Manuscript)

Published in

Multimedia Systems

Publisher

SPRINGER

issn

0942-4962

eissn

1432-1882

Acceptance date

2022-04-11

Copyright date

2022

Available date

2023-05-07

Language

English