Quantitative evaluation model of variable diagnosis for chest X-ray images using deep learning
Copyright: © 2024 Nakagawa et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited..
The purpose of this study is to demonstrate the use of a deep learning model in quantitatively evaluating clinical findings typically subject to uncertain evaluations by physicians, using binary test results based on routine protocols. A chest X-ray is the most commonly used diagnostic tool for the detection of a wide range of diseases and is generally performed as a part of regular medical checkups. However, when it comes to findings that can be classified as within the normal range but are not considered disease-related, the thresholds of physicians' findings can vary to some extent, therefore it is necessary to define a new evaluation method and quantify it. The implementation of such methods is difficult and expensive in terms of time and labor. In this study, a total of 83,005 chest X-ray images were used to diagnose the common findings of pleural thickening and scoliosis. A novel method for quantitatively evaluating the probability that a physician would judge the images to have these findings was established. The proposed method successfully quantified the variation in physicians' findings using a deep learning model trained only on binary annotation data. It was also demonstrated that the developed method could be applied to both transfer learning using convolutional neural networks for general image analysis and a newly learned deep learning model based on vector quantization variational autoencoders with high correlations ranging from 0.89 to 0.97.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:3 |
|---|---|
| Enthalten in: |
PLOS digital health - 3(2024), 3 vom: 15. März, Seite e0000460 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Nakagawa, Shota [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 17.03.2024 published: Electronic-eCollection Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1371/journal.pdig.0000460 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM36979060X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM36979060X | ||
| 003 | DE-627 | ||
| 005 | 20240317233300.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240316s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1371/journal.pdig.0000460 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1333.xml |
| 035 | |a (DE-627)NLM36979060X | ||
| 035 | |a (NLM)38489375 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Nakagawa, Shota |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Quantitative evaluation model of variable diagnosis for chest X-ray images using deep learning |
| 264 | 1 | |c 2024 | |
| 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 Revised 17.03.2024 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Copyright: © 2024 Nakagawa et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. | ||
| 520 | |a The purpose of this study is to demonstrate the use of a deep learning model in quantitatively evaluating clinical findings typically subject to uncertain evaluations by physicians, using binary test results based on routine protocols. A chest X-ray is the most commonly used diagnostic tool for the detection of a wide range of diseases and is generally performed as a part of regular medical checkups. However, when it comes to findings that can be classified as within the normal range but are not considered disease-related, the thresholds of physicians' findings can vary to some extent, therefore it is necessary to define a new evaluation method and quantify it. The implementation of such methods is difficult and expensive in terms of time and labor. In this study, a total of 83,005 chest X-ray images were used to diagnose the common findings of pleural thickening and scoliosis. A novel method for quantitatively evaluating the probability that a physician would judge the images to have these findings was established. The proposed method successfully quantified the variation in physicians' findings using a deep learning model trained only on binary annotation data. It was also demonstrated that the developed method could be applied to both transfer learning using convolutional neural networks for general image analysis and a newly learned deep learning model based on vector quantization variational autoencoders with high correlations ranging from 0.89 to 0.97 | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Ono, Naoaki |e verfasserin |4 aut | |
| 700 | 1 | |a Hakamata, Yukichika |e verfasserin |4 aut | |
| 700 | 1 | |a Ishii, Takashi |e verfasserin |4 aut | |
| 700 | 1 | |a Saito, Akira |e verfasserin |4 aut | |
| 700 | 1 | |a Yanagimoto, Shintaro |e verfasserin |4 aut | |
| 700 | 1 | |a Kanaya, Shigehiko |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t PLOS digital health |d 2022 |g 3(2024), 3 vom: 15. März, Seite e0000460 |w (DE-627)NLM33756020X |x 2767-3170 |7 nnns |
| 773 | 1 | 8 | |g volume:3 |g year:2024 |g number:3 |g day:15 |g month:03 |g pages:e0000460 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1371/journal.pdig.0000460 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 3 |j 2024 |e 3 |b 15 |c 03 |h e0000460 | ||