ChestView
Efficacy of a deep learning-based software for chest X-ray analysis in an emergency department.
Sathiyamurthy Selvam, Olivier Peyrony, Arben Elezi, Adelia Braganca, Anne-Marie Zagdanski, Lucie Biard, Jessica Assouline, Guillaume Chassagnon, Guillaume Mulier, Constance de Margerie-Mellon
Data
404 patients included in the study (74.5% of exams didn’t have any of the ChestView abnormalities)
- 295 had only CXRs
- 109 had CXRs + subsequent CT exam
Design
Retrospective single-center study
3 emergency physicians, 1 junior radiologist and 1 general radiologist independently reviewed the CXRs (with available clinical information)
Without AI → Washout ≥ 2 weeks → With AI
Ground truth = consensus between 2 experienced radiologists (with all available clinical and imaging information)
Results
Standalone performance [see study]
Readers
- DL-assisted reading had a significantly higher combined sensitivity compared to unassisted reading
- No significant change in the combined specificity between unassisted and assisted readings
- Most important increase in sensitivity with DL assistance was obtained for nodules (38.1% → 67.6%)
- Combined sensitivity was higher for bedside CXRs while the specificity and accuracy were significantly lower
Read more study
ChestView
Using AI to improve radiologist performance in detecting abnormalities on chest radiographs
Bennani, Souhail; Regnard, Nor-Eddine; Ventre, Jeanne; Lassalle, Louis; Nguyen, Toan; Ducarouge, Alexis; Dargent, Lucas; Guillo, Enora; Gouhier, Elodie; Zaimi, Sophie-Hélène; Canniff, Emma; Malandrin, Cécile; Khafagy, Philippe; Koulakian, Hasmik; Revel, Marie-Pierre; Chassagnon, Guillaume
ChestView
Learning from the machine: AI assistance is not an effective learning tool for resident education in chest x-ray interpretation
Chassagnon G, Billet N, Rutten C, Toussaint T, Cassius de Linval Q, Collin M et al.
ChestView
AI solution for critical chest pathology