Cross attention guided multi-scale feature fusion for false-positive reduction in pulmonary nodule detection
Copyright © 2022 Elsevier Ltd. All rights reserved..
False-positive reduction is a crucial step of computer-aided diagnosis (CAD) system for pulmonary nodules detection and it plays an important role in lung cancer diagnosis. In this paper, we propose a novel cross attention guided multi-scale feature fusion method for false-positive reduction in pulmonary nodule detection. Specifically, a 3D SENet50 fed with a candidate nodule cube is applied as the backbone to acquire multi-scale coarse features. Then, the coarse features are refined and fused by the multi-scale fusion part to achieve a better feature extraction result. Finally, a 3D spatial pyramid pooling module is used to enhance receptive field and a distributed aligned linear classifier is applied to get the confidence score. In addition, each of the five nodule cubes with different sizes centering on every testing nodule position is fed into the proposed framework to obtain a confidence score separately and a weighted fusion method is used to improve the generalization performance of the model. Extensive experiments are conducted to demonstrate the effectiveness of the classification performance of the proposed model. The data used in our work is from the LUNA16 pulmonary nodule detection challenge. In this data set, the number of true-positive pulmonary nodules is 1,557, while the number of false-positive ones is 753,418. The new method is evaluated on the LUNA16 dataset and achieves the score of the competitive performance metric (CPM) 84.8%.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:151 |
|---|---|
| Enthalten in: |
Computers in biology and medicine - 151(2022), Pt A vom: 15. Dez., Seite 106302 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Gu, Zhongxuan [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Cross attention |
|---|
| Anmerkungen: |
Date Completed 19.09.2023 Date Revised 19.09.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.compbiomed.2022.106302 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM34915189X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM34915189X | ||
| 003 | DE-627 | ||
| 005 | 20231226041933.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.compbiomed.2022.106302 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1163.xml |
| 035 | |a (DE-627)NLM34915189X | ||
| 035 | |a (NLM)36401972 | ||
| 035 | |a (PII)S0010-4825(22)01010-1 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Gu, Zhongxuan |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Cross attention guided multi-scale feature fusion for false-positive reduction in pulmonary nodule detection |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 19.09.2023 | ||
| 500 | |a Date Revised 19.09.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2022 Elsevier Ltd. All rights reserved. | ||
| 520 | |a False-positive reduction is a crucial step of computer-aided diagnosis (CAD) system for pulmonary nodules detection and it plays an important role in lung cancer diagnosis. In this paper, we propose a novel cross attention guided multi-scale feature fusion method for false-positive reduction in pulmonary nodule detection. Specifically, a 3D SENet50 fed with a candidate nodule cube is applied as the backbone to acquire multi-scale coarse features. Then, the coarse features are refined and fused by the multi-scale fusion part to achieve a better feature extraction result. Finally, a 3D spatial pyramid pooling module is used to enhance receptive field and a distributed aligned linear classifier is applied to get the confidence score. In addition, each of the five nodule cubes with different sizes centering on every testing nodule position is fed into the proposed framework to obtain a confidence score separately and a weighted fusion method is used to improve the generalization performance of the model. Extensive experiments are conducted to demonstrate the effectiveness of the classification performance of the proposed model. The data used in our work is from the LUNA16 pulmonary nodule detection challenge. In this data set, the number of true-positive pulmonary nodules is 1,557, while the number of false-positive ones is 753,418. The new method is evaluated on the LUNA16 dataset and achieves the score of the competitive performance metric (CPM) 84.8% | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Cross attention | |
| 650 | 4 | |a Distributed aligned linear classifier | |
| 650 | 4 | |a False-positive reduction | |
| 650 | 4 | |a Multi-scale feature fusion | |
| 650 | 4 | |a Pulmonary nodule detection | |
| 700 | 1 | |a Li, Yueyang |e verfasserin |4 aut | |
| 700 | 1 | |a Luo, Haichi |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Caidi |e verfasserin |4 aut | |
| 700 | 1 | |a Du, Hongqun |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Computers in biology and medicine |d 1970 |g 151(2022), Pt A vom: 15. Dez., Seite 106302 |w (DE-627)NLM000382272 |x 1879-0534 |7 nnns |
| 773 | 1 | 8 | |g volume:151 |g year:2022 |g number:Pt A |g day:15 |g month:12 |g pages:106302 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.compbiomed.2022.106302 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 151 |j 2022 |e Pt A |b 15 |c 12 |h 106302 | ||