Development of a modified 3D region proposal network for lung nodule detection in computed tomography scans: a secondary analysis of lung nodule datasets
Background Low-dose computed tomography (LDCT) has been shown useful in early lung cancer detection. This study aimed to develop a novel deep learning model for detecting pulmonary nodules on chest LDCT images. Methods In this secondary analysis, three lung nodule datasets, including Lung Nodule Analysis 2016 (LUNA16), Lung Nodule Received Operation (LNOP), and Lung Nodule in Health Examination (LNHE), were used to train and test deep learning models. The 3D region proposal network (RPN) was modified via a series of pruning experiments for better predictive performance. The performance of each modified deep leaning model was evaluated based on sensitivity and competition performance metric (CPM). Furthermore, the performance of the modified 3D RPN trained on three datasets was evaluated by 10-fold cross validation. Temporal validation was conducted to assess the reliability of the modified 3D RPN for detecting lung nodules. Results The results of pruning experiments indicated that the modified 3D RPN composed of the Cross Stage Partial Network (CSPNet) approach to Residual Network (ResNet) Xt (CSP-ResNeXt) module, feature pyramid network (FPN), nearest anchor method, and post-processing masking, had the optimal predictive performance with a CPM of 92.2%. The modified 3D RPN trained on the LUNA16 dataset had the highest CPM (90.1%), followed by the LNOP dataset (CPM: 74.1%) and the LNHE dataset (CPM: 70.2%). When the modified 3D RPN trained and tested on the same datasets, the sensitivities were 94.6%, 84.8%, and 79.7% for LUNA16, LNOP, and LNHE, respectively. The temporal validation analysis revealed that the modified 3D RPN tested on LNOP test set achieved a CPM of 71.6% and a sensitivity of 85.7%, and the modified 3D RPN tested on LNHE test set had a CPM of 71.7% and a sensitivity of 83.5%. Conclusion A modified 3D RPN for detecting lung nodules on LDCT scans was designed and validated, which may serve as a computer-aided diagnosis system to facilitate lung nodule detection and lung cancer diagnosis..
Key message The optimal 3D RPN for detecting lung nodules in chest CT was established. The modified 3D RPN trained on the LUNA16 dataset had a higher CPM. But CMP dropped if the modified 3D RPN trained on Taiwanese datasets..
Summary statement A modified 3D RPN for detecting lung nodules on CT images that exhibited greater sensitivity and CPM than did several previously reported CAD detection models was established..
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:24 |
|---|---|
| Enthalten in: |
Cancer imaging - 24(2024), 1 vom: 20. März |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Lin, Chia-Ying [VerfasserIn] |
|---|
| Links: |
Volltext [kostenfrei] |
|---|
| Themen: |
3D region proposal network |
|---|
| Anmerkungen: |
© The Author(s) 2024 |
|---|
| doi: |
10.1186/s40644-024-00683-x |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
SPR05523240X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR05523240X | ||
| 003 | DE-627 | ||
| 005 | 20240321064724.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240321s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s40644-024-00683-x |2 doi | |
| 035 | |a (DE-627)SPR05523240X | ||
| 035 | |a (SPR)s40644-024-00683-x-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 610 |q VZ |
| 100 | 1 | |a Lin, Chia-Ying |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Development of a modified 3D region proposal network for lung nodule detection in computed tomography scans: a secondary analysis of lung nodule datasets |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a © The Author(s) 2024 | ||
| 520 | |a Background Low-dose computed tomography (LDCT) has been shown useful in early lung cancer detection. This study aimed to develop a novel deep learning model for detecting pulmonary nodules on chest LDCT images. Methods In this secondary analysis, three lung nodule datasets, including Lung Nodule Analysis 2016 (LUNA16), Lung Nodule Received Operation (LNOP), and Lung Nodule in Health Examination (LNHE), were used to train and test deep learning models. The 3D region proposal network (RPN) was modified via a series of pruning experiments for better predictive performance. The performance of each modified deep leaning model was evaluated based on sensitivity and competition performance metric (CPM). Furthermore, the performance of the modified 3D RPN trained on three datasets was evaluated by 10-fold cross validation. Temporal validation was conducted to assess the reliability of the modified 3D RPN for detecting lung nodules. Results The results of pruning experiments indicated that the modified 3D RPN composed of the Cross Stage Partial Network (CSPNet) approach to Residual Network (ResNet) Xt (CSP-ResNeXt) module, feature pyramid network (FPN), nearest anchor method, and post-processing masking, had the optimal predictive performance with a CPM of 92.2%. The modified 3D RPN trained on the LUNA16 dataset had the highest CPM (90.1%), followed by the LNOP dataset (CPM: 74.1%) and the LNHE dataset (CPM: 70.2%). When the modified 3D RPN trained and tested on the same datasets, the sensitivities were 94.6%, 84.8%, and 79.7% for LUNA16, LNOP, and LNHE, respectively. The temporal validation analysis revealed that the modified 3D RPN tested on LNOP test set achieved a CPM of 71.6% and a sensitivity of 85.7%, and the modified 3D RPN tested on LNHE test set had a CPM of 71.7% and a sensitivity of 83.5%. Conclusion A modified 3D RPN for detecting lung nodules on LDCT scans was designed and validated, which may serve as a computer-aided diagnosis system to facilitate lung nodule detection and lung cancer diagnosis. | ||
| 520 | |a Key message The optimal 3D RPN for detecting lung nodules in chest CT was established. The modified 3D RPN trained on the LUNA16 dataset had a higher CPM. But CMP dropped if the modified 3D RPN trained on Taiwanese datasets. | ||
| 520 | |a Summary statement A modified 3D RPN for detecting lung nodules on CT images that exhibited greater sensitivity and CPM than did several previously reported CAD detection models was established. | ||
| 650 | 4 | |a Anchor Assignment |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Computer-aided detection system |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a Ground glass nodules |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a LUNA16 dataset |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a 3D region proposal network |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Guo, Shu-Mei |4 aut | |
| 700 | 1 | |a Lien, Jenn-Jier James |4 aut | |
| 700 | 1 | |a Tsai, Tzung-Yi |4 aut | |
| 700 | 1 | |a Liu, Yi-Sheng |4 aut | |
| 700 | 1 | |a Lai, Chao-Han |4 aut | |
| 700 | 1 | |a Hsu, I-Lin |4 aut | |
| 700 | 1 | |a Chang, Chao-Chun |4 aut | |
| 700 | 1 | |a Tseng, Yau-Lin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Cancer imaging |d BioMed Central, 2000 |g 24(2024), 1 vom: 20. März |w (DE-627)SPR037099965 |w (DE-600)2104862-9 |x 1470-7330 |7 nnns |
| 773 | 1 | 8 | |g volume:24 |g year:2024 |g number:1 |g day:20 |g month:03 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1186/s40644-024-00683-x |z kostenfrei |3 Volltext |
| 912 | |a GBV_SPRINGER | ||
| 912 | |a SSG-OLC-PHA | ||
| 951 | |a AR | ||
| 952 | |d 24 |j 2024 |e 1 |b 20 |c 03 | ||