Combining multi-scale feature fusion with multi-attribute grading, a CNN model for benign and malignant classification of pulmonary nodules
Lung cancer has the highest mortality rate of all cancers, and early detection can improve survival rates. In the recent years, low-dose CT has been widely used to detect lung cancer. However, the diagnosis is limited by the subjective experience of doctors. Therefore, the main purpose of this study is to use convolutional neural network to realize the benign and malignant classification of pulmonary nodules in CT images. We collected 1004 cases of pulmonary nodules from LIDC-IDRI dataset, among which 554 cases were benign and 450 cases were malignant. According to the doctors' annotates on the center coordinates of the nodules, two 3D CT image patches of pulmonary nodules with different scales were extracted. In this study, our work focuses on two aspects. Firstly, we constructed a multi-stream multi-task network (MSMT), which combined multi-scale feature with multi-attribute classification for the first time, and applied it to the classification of benign and malignant pulmonary nodules. Secondly, we proposed a new loss function to balance the relationship between different attributes. The final experimental results showed that our model was effective compared with the same type of study. The area under ROC curve, accuracy, sensitivity, and specificity were 0.979, 93.92%, 92.60%, and 96.25%, respectively.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2020 |
---|---|
Erschienen: |
2020 |
Enthalten in: |
Zur Gesamtaufnahme - volume:33 |
---|---|
Enthalten in: |
Journal of digital imaging - 33(2020), 4 vom: 13. Aug., Seite 869-878 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zhao, Jumin [VerfasserIn] |
---|
Links: |
---|
Themen: |
Convolutional neural network |
---|
Anmerkungen: |
Date Completed 16.08.2021 Date Revised 03.11.2021 published: Print Citation Status MEDLINE |
---|
doi: |
10.1007/s10278-020-00333-1 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM308702336 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM308702336 | ||
003 | DE-627 | ||
005 | 20231225132309.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2020 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s10278-020-00333-1 |2 doi | |
028 | 5 | 2 | |a pubmed24n1028.xml |
035 | |a (DE-627)NLM308702336 | ||
035 | |a (NLM)32285220 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zhao, Jumin |e verfasserin |4 aut | |
245 | 1 | 0 | |a Combining multi-scale feature fusion with multi-attribute grading, a CNN model for benign and malignant classification of pulmonary nodules |
264 | 1 | |c 2020 | |
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 16.08.2021 | ||
500 | |a Date Revised 03.11.2021 | ||
500 | |a published: Print | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Lung cancer has the highest mortality rate of all cancers, and early detection can improve survival rates. In the recent years, low-dose CT has been widely used to detect lung cancer. However, the diagnosis is limited by the subjective experience of doctors. Therefore, the main purpose of this study is to use convolutional neural network to realize the benign and malignant classification of pulmonary nodules in CT images. We collected 1004 cases of pulmonary nodules from LIDC-IDRI dataset, among which 554 cases were benign and 450 cases were malignant. According to the doctors' annotates on the center coordinates of the nodules, two 3D CT image patches of pulmonary nodules with different scales were extracted. In this study, our work focuses on two aspects. Firstly, we constructed a multi-stream multi-task network (MSMT), which combined multi-scale feature with multi-attribute classification for the first time, and applied it to the classification of benign and malignant pulmonary nodules. Secondly, we proposed a new loss function to balance the relationship between different attributes. The final experimental results showed that our model was effective compared with the same type of study. The area under ROC curve, accuracy, sensitivity, and specificity were 0.979, 93.92%, 92.60%, and 96.25%, respectively | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
650 | 4 | |a Convolutional neural network | |
650 | 4 | |a Multi-scale feature fusion | |
650 | 4 | |a Multi-task learning | |
650 | 4 | |a Pulmonary nodule classification | |
700 | 1 | |a Zhang, Chen |e verfasserin |4 aut | |
700 | 1 | |a Li, Dengao |e verfasserin |4 aut | |
700 | 1 | |a Niu, Jing |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of digital imaging |d 1988 |g 33(2020), 4 vom: 13. Aug., Seite 869-878 |w (DE-627)NLM014390140 |x 1618-727X |7 nnns |
773 | 1 | 8 | |g volume:33 |g year:2020 |g number:4 |g day:13 |g month:08 |g pages:869-878 |
856 | 4 | 0 | |u http://dx.doi.org/10.1007/s10278-020-00333-1 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 33 |j 2020 |e 4 |b 13 |c 08 |h 869-878 |