Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs
Background Chest radiography remains the most common radiologic examination, and interpretation of its results can be difficult. Purpose To explore the potential benefit of artificial intelligence (AI) assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, with and without AI assistance. Materials and Methods Patients who underwent both chest radiography and thoracic CT within 72 hours between January 2010 and December 2020 in a French public hospital were screened retrospectively. Radiographs were randomly included until reaching 500 radiographs, with about 50% of radiographs having abnormal findings. A senior thoracic radiologist annotated the radiographs for five abnormalities (pneumothorax, pleural effusion, consolidation, mediastinal and hilar mass, lung nodule) based on the corresponding CT results (ground truth). A total of 12 readers (four thoracic radiologists, four general radiologists, four radiology residents) read half the radiographs without AI and half the radiographs with AI (ChestView; Gleamer). Changes in sensitivity and specificity were measured using paired t tests. Results The study included 500 patients (mean age, 54 years ± 19 [SD]; 261 female, 239 male), with 522 abnormalities visible on 241 radiographs. On average, for all readers, AI use resulted in an absolute increase in sensitivity of 26% (95% CI: 20, 32), 14% (95% CI: 11, 17), 12% (95% CI: 10, 14), 8.5% (95% CI: 6, 11), and 5.9% (95% CI: 4, 8) for pneumothorax, consolidation, nodule, pleural effusion, and mediastinal and hilar mass, respectively (P < .001). Specificity increased with AI assistance (3.9% [95% CI: 3.2, 4.6], 3.7% [95% CI: 3, 4.4], 2.9% [95% CI: 2.3, 3.5], and 2.1% [95% CI: 1.6, 2.6] for pleural effusion, mediastinal and hilar mass, consolidation, and nodule, respectively), except in the diagnosis of pneumothorax (-0.2%; 95% CI: -0.36, -0.04; P = .01). The mean reading time was 81 seconds without AI versus 56 seconds with AI (31% decrease, P < .001). Conclusion AI-assisted chest radiography interpretation resulted in absolute increases in sensitivity for all radiologists of various levels of expertise and reduced the reading times; specificity increased with AI, except in the diagnosis of pneumothorax. © RSNA, 2023 Supplemental material is available for this article.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:309 |
---|---|
Enthalten in: |
Radiology - 309(2023), 3 vom: 12. Dez., Seite e230860 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Bennani, Souhail [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Revised 12.12.2023 published: Print Citation Status In-Process |
---|
doi: |
10.1148/radiol.230860 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM365758388 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM365758388 | ||
003 | DE-627 | ||
005 | 20231229123602.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1148/radiol.230860 |2 doi | |
028 | 5 | 2 | |a pubmed24n1227.xml |
035 | |a (DE-627)NLM365758388 | ||
035 | |a (NLM)38085079 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Bennani, Souhail |e verfasserin |4 aut | |
245 | 1 | 0 | |a Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs |
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 Revised 12.12.2023 | ||
500 | |a published: Print | ||
500 | |a Citation Status In-Process | ||
520 | |a Background Chest radiography remains the most common radiologic examination, and interpretation of its results can be difficult. Purpose To explore the potential benefit of artificial intelligence (AI) assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, with and without AI assistance. Materials and Methods Patients who underwent both chest radiography and thoracic CT within 72 hours between January 2010 and December 2020 in a French public hospital were screened retrospectively. Radiographs were randomly included until reaching 500 radiographs, with about 50% of radiographs having abnormal findings. A senior thoracic radiologist annotated the radiographs for five abnormalities (pneumothorax, pleural effusion, consolidation, mediastinal and hilar mass, lung nodule) based on the corresponding CT results (ground truth). A total of 12 readers (four thoracic radiologists, four general radiologists, four radiology residents) read half the radiographs without AI and half the radiographs with AI (ChestView; Gleamer). Changes in sensitivity and specificity were measured using paired t tests. Results The study included 500 patients (mean age, 54 years ± 19 [SD]; 261 female, 239 male), with 522 abnormalities visible on 241 radiographs. On average, for all readers, AI use resulted in an absolute increase in sensitivity of 26% (95% CI: 20, 32), 14% (95% CI: 11, 17), 12% (95% CI: 10, 14), 8.5% (95% CI: 6, 11), and 5.9% (95% CI: 4, 8) for pneumothorax, consolidation, nodule, pleural effusion, and mediastinal and hilar mass, respectively (P < .001). Specificity increased with AI assistance (3.9% [95% CI: 3.2, 4.6], 3.7% [95% CI: 3, 4.4], 2.9% [95% CI: 2.3, 3.5], and 2.1% [95% CI: 1.6, 2.6] for pleural effusion, mediastinal and hilar mass, consolidation, and nodule, respectively), except in the diagnosis of pneumothorax (-0.2%; 95% CI: -0.36, -0.04; P = .01). The mean reading time was 81 seconds without AI versus 56 seconds with AI (31% decrease, P < .001). Conclusion AI-assisted chest radiography interpretation resulted in absolute increases in sensitivity for all radiologists of various levels of expertise and reduced the reading times; specificity increased with AI, except in the diagnosis of pneumothorax. © RSNA, 2023 Supplemental material is available for this article | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Regnard, Nor-Eddine |e verfasserin |4 aut | |
700 | 1 | |a Ventre, Jeanne |e verfasserin |4 aut | |
700 | 1 | |a Lassalle, Louis |e verfasserin |4 aut | |
700 | 1 | |a Nguyen, Toan |e verfasserin |4 aut | |
700 | 1 | |a Ducarouge, Alexis |e verfasserin |4 aut | |
700 | 1 | |a Dargent, Lucas |e verfasserin |4 aut | |
700 | 1 | |a Guillo, Enora |e verfasserin |4 aut | |
700 | 1 | |a Gouhier, Elodie |e verfasserin |4 aut | |
700 | 1 | |a Zaimi, Sophie-Hélène |e verfasserin |4 aut | |
700 | 1 | |a Canniff, Emma |e verfasserin |4 aut | |
700 | 1 | |a Malandrin, Cécile |e verfasserin |4 aut | |
700 | 1 | |a Khafagy, Philippe |e verfasserin |4 aut | |
700 | 1 | |a Koulakian, Hasmik |e verfasserin |4 aut | |
700 | 1 | |a Revel, Marie-Pierre |e verfasserin |4 aut | |
700 | 1 | |a Chassagnon, Guillaume |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Radiology |d 1945 |g 309(2023), 3 vom: 12. Dez., Seite e230860 |w (DE-627)NLM000054860 |x 1527-1315 |7 nnns |
773 | 1 | 8 | |g volume:309 |g year:2023 |g number:3 |g day:12 |g month:12 |g pages:e230860 |
856 | 4 | 0 | |u http://dx.doi.org/10.1148/radiol.230860 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 309 |j 2023 |e 3 |b 12 |c 12 |h e230860 |