Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection

Qiuyu Dong; Huijuan Lu; Renfeng Wang; Zhendong Ming; Wenjie Zhu; Yudong Yao

doi:10.1109/ITME60234.2023.00152

Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection

Qiuyu Dong
, Huijuan Lu
, Renfeng Wang
, Zhendong Ming
, Wenjie Zhu
, Yudong Yao

Department of Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Lung cancer is one of the cancers with the highest incidence and mortality in the world, and early detection of lung nodules can effectively reduce the mortality rate of lung cancer. At present, most of the lung nodule detection methods based on deep learning face the problem of low sensitivity or high false positive rate. This paper proposes a loss function suitable for the clinical features of lung nodules and introduces a novel Squeeze-and-Excitation module in the depth direction, which alleviates the problem of high false positive rate in the detection process and achieves good results. In this paper, the competition performance metric (CPM) on the LUNA16 dataset reached 88.16%.

Original language	English
Title of host publication	Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023
Pages	740-744
Number of pages	5
ISBN (Electronic)	9798350319156
DOIs	https://doi.org/10.1109/ITME60234.2023.00152
State	Published - 2023
Event	13th International Conference on Information Technology in Medicine and Education, ITME 2023 - Wuyishan, China Duration: 24 Nov 2023 → 26 Nov 2023

Publication series

Name	Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023

Conference

Conference	13th International Conference on Information Technology in Medicine and Education, ITME 2023
Country/Territory	China
City	Wuyishan
Period	24/11/23 → 26/11/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Attention mechanisms
Feature pyramids
Pulmonary nodule detection
Spherical detection frame

Access to Document

10.1109/ITME60234.2023.00152

Cite this

Dong, Q., Lu, H., Wang, R., Ming, Z., Zhu, W., & Yao, Y. (2023). Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection. In Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023 (pp. 740-744). (Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023). https://doi.org/10.1109/ITME60234.2023.00152

Dong, Qiuyu ; Lu, Huijuan ; Wang, Renfeng et al. / Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection. Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023. 2023. pp. 740-744 (Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023).

@inproceedings{8fcd53c3cee044e98f5946764f899b8a,

title = "Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection",

abstract = "Lung cancer is one of the cancers with the highest incidence and mortality in the world, and early detection of lung nodules can effectively reduce the mortality rate of lung cancer. At present, most of the lung nodule detection methods based on deep learning face the problem of low sensitivity or high false positive rate. This paper proposes a loss function suitable for the clinical features of lung nodules and introduces a novel Squeeze-and-Excitation module in the depth direction, which alleviates the problem of high false positive rate in the detection process and achieves good results. In this paper, the competition performance metric (CPM) on the LUNA16 dataset reached 88.16\%.",

keywords = "Attention mechanisms, Feature pyramids, Pulmonary nodule detection, Spherical detection frame",

author = "Qiuyu Dong and Huijuan Lu and Renfeng Wang and Zhendong Ming and Wenjie Zhu and Yudong Yao",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 13th International Conference on Information Technology in Medicine and Education, ITME 2023 ; Conference date: 24-11-2023 Through 26-11-2023",

year = "2023",

doi = "10.1109/ITME60234.2023.00152",

language = "English",

series = "Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023",

pages = "740--744",

booktitle = "Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023",

}

Dong, Q, Lu, H, Wang, R, Ming, Z, Zhu, W & Yao, Y 2023, Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection. in Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023. Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023, pp. 740-744, 13th International Conference on Information Technology in Medicine and Education, ITME 2023, Wuyishan, China, 24/11/23. https://doi.org/10.1109/ITME60234.2023.00152

Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection. / Dong, Qiuyu; Lu, Huijuan; Wang, Renfeng et al.
Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023. 2023. p. 740-744 (Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection

AU - Dong, Qiuyu

AU - Lu, Huijuan

AU - Wang, Renfeng

AU - Ming, Zhendong

AU - Zhu, Wenjie

AU - Yao, Yudong

PY - 2023

Y1 - 2023

N2 - Lung cancer is one of the cancers with the highest incidence and mortality in the world, and early detection of lung nodules can effectively reduce the mortality rate of lung cancer. At present, most of the lung nodule detection methods based on deep learning face the problem of low sensitivity or high false positive rate. This paper proposes a loss function suitable for the clinical features of lung nodules and introduces a novel Squeeze-and-Excitation module in the depth direction, which alleviates the problem of high false positive rate in the detection process and achieves good results. In this paper, the competition performance metric (CPM) on the LUNA16 dataset reached 88.16%.

AB - Lung cancer is one of the cancers with the highest incidence and mortality in the world, and early detection of lung nodules can effectively reduce the mortality rate of lung cancer. At present, most of the lung nodule detection methods based on deep learning face the problem of low sensitivity or high false positive rate. This paper proposes a loss function suitable for the clinical features of lung nodules and introduces a novel Squeeze-and-Excitation module in the depth direction, which alleviates the problem of high false positive rate in the detection process and achieves good results. In this paper, the competition performance metric (CPM) on the LUNA16 dataset reached 88.16%.

KW - Attention mechanisms

KW - Feature pyramids

KW - Pulmonary nodule detection

KW - Spherical detection frame

UR - https://www.scopus.com/pages/publications/85192447440

UR - https://www.scopus.com/pages/publications/85192447440#tab=citedBy

U2 - 10.1109/ITME60234.2023.00152

DO - 10.1109/ITME60234.2023.00152

M3 - Conference contribution

AN - SCOPUS:85192447440

T3 - Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023

SP - 740

EP - 744

BT - Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023

T2 - 13th International Conference on Information Technology in Medicine and Education, ITME 2023

Y2 - 24 November 2023 through 26 November 2023

ER -

Dong Q, Lu H, Wang R, Ming Z, Zhu W, Yao Y. Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection. In Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023. 2023. p. 740-744. (Proceedings - 2023 13th International Conference on Information Technology in Medicine and Education, ITME 2023). doi: 10.1109/ITME60234.2023.00152

Spherical Detection Frame and Attention-Based Pulmonary Nodule Detection

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this