Development of Debiasing Technique for Lung Nodule Chest X-ray Datasets to Generalize Deep Learning Models
Screening programs for early lung cancer diagnosis are uncommon, primarily due to the challenge of reaching at-risk patients located in rural areas far from medical facilities. To overcome this obstacle, a comprehensive approach is needed that combines mobility, low cost, speed, accuracy, and privacy. One potential solution lies in combining the chest X-ray imaging mode with federated deep learning, ensuring that no single data source can bias the model adversely. This study presents a pre-processing pipeline designed to debias chest X-ray images, thereby enhancing internal classification and external generalization. The pipeline employs a pruning mechanism to train a deep learning model for nodule detection, utilizing the most informative images from a publicly available lung nodule X-ray dataset. Histogram equalization is used to remove systematic differences in image brightness and contrast. Model training is then performed using combinations of lung field segmentation, close cropping, and rib/bone suppression. The resulting deep learning models, generated through this pre-processing pipeline, demonstrate successful generalization on an independent lung nodule dataset. By eliminating confounding variables in chest X-ray images and suppressing signal noise from the bone structures, the proposed deep learning lung nodule detection algorithm achieves an external generalization accuracy of 89%. This approach paves the way for the development of a low-cost and accessible deep learning-based clinical system for lung cancer screening.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:23 |
|---|---|
| Enthalten in: |
Sensors (Basel, Switzerland) - 23(2023), 14 vom: 21. Juli |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Horry, Michael J [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Chest X-ray |
|---|
| Anmerkungen: |
Date Completed 31.07.2023 Date Revised 01.08.2023 published: Electronic Citation Status MEDLINE |
|---|
| doi: |
10.3390/s23146585 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM36014747X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM36014747X | ||
| 003 | DE-627 | ||
| 005 | 20231226082406.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.3390/s23146585 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1200.xml |
| 035 | |a (DE-627)NLM36014747X | ||
| 035 | |a (NLM)37514877 | ||
| 035 | |a (PII)6585 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Horry, Michael J |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Development of Debiasing Technique for Lung Nodule Chest X-ray Datasets to Generalize Deep Learning Models |
| 264 | 1 | |c 2023 | |
| 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 31.07.2023 | ||
| 500 | |a Date Revised 01.08.2023 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Screening programs for early lung cancer diagnosis are uncommon, primarily due to the challenge of reaching at-risk patients located in rural areas far from medical facilities. To overcome this obstacle, a comprehensive approach is needed that combines mobility, low cost, speed, accuracy, and privacy. One potential solution lies in combining the chest X-ray imaging mode with federated deep learning, ensuring that no single data source can bias the model adversely. This study presents a pre-processing pipeline designed to debias chest X-ray images, thereby enhancing internal classification and external generalization. The pipeline employs a pruning mechanism to train a deep learning model for nodule detection, utilizing the most informative images from a publicly available lung nodule X-ray dataset. Histogram equalization is used to remove systematic differences in image brightness and contrast. Model training is then performed using combinations of lung field segmentation, close cropping, and rib/bone suppression. The resulting deep learning models, generated through this pre-processing pipeline, demonstrate successful generalization on an independent lung nodule dataset. By eliminating confounding variables in chest X-ray images and suppressing signal noise from the bone structures, the proposed deep learning lung nodule detection algorithm achieves an external generalization accuracy of 89%. This approach paves the way for the development of a low-cost and accessible deep learning-based clinical system for lung cancer screening | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a chest X-ray | |
| 650 | 4 | |a confounding bias | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a federated learning | |
| 650 | 4 | |a lung cancer | |
| 650 | 4 | |a model generalization | |
| 700 | 1 | |a Chakraborty, Subrata |e verfasserin |4 aut | |
| 700 | 1 | |a Pradhan, Biswajeet |e verfasserin |4 aut | |
| 700 | 1 | |a Paul, Manoranjan |e verfasserin |4 aut | |
| 700 | 1 | |a Zhu, Jing |e verfasserin |4 aut | |
| 700 | 1 | |a Loh, Hui Wen |e verfasserin |4 aut | |
| 700 | 1 | |a Barua, Prabal Datta |e verfasserin |4 aut | |
| 700 | 1 | |a Acharya, U Rajendra |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Sensors (Basel, Switzerland) |d 2007 |g 23(2023), 14 vom: 21. Juli |w (DE-627)NLM187985170 |x 1424-8220 |7 nnns |
| 773 | 1 | 8 | |g volume:23 |g year:2023 |g number:14 |g day:21 |g month:07 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.3390/s23146585 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 23 |j 2023 |e 14 |b 21 |c 07 | ||