Automatic deep learning-based assessment of spinopelvic coronal and sagittal alignment - 23/06/23
Benvenuto su EM|consulte, il riferimento dei professionisti della salute.
Articolo gratuito.
Si connetta per beneficiarne
Highlights |
• | Artificial intelligence yields excellent consistency without bias in the estimation of coronal spinopelvic alignment (ICC range: 0.95–0.97). |
• | Artificial intelligence yields excellent consistency in sagittal spinopelvic evaluation for all outputs except for kyphosis (ICC range: 0.85–0.98). |
• | Artificial intelligence allows classifying low Cobb angle and severe scoliosis with an accuracy ≥ 91%. |
• | Seventy-two p. cents of the artificial intelligence outputs are classified as reliable by the radiologist, without any measurement to modify. |
Abstract |
Purpose |
The purpose of this study was to evaluate an artificial intelligence (AI) solution for estimating coronal and sagittal spinopelvic alignment on conventional uniplanar two-dimensional whole-spine radiograph.
Material and methods |
This retrospective observational study included 100 patients (35 men, 65 women) with a median age of 14 years (IQR: 13, 15.25; age range: 3–64 years) who underwent conventional uniplanar two-dimensional whole-spine radiograph in standing position between January and July 2022. Ten most commonly used spinopelvic coronal and sagittal parameters were retrospectively measured without AI by a junior radiologist and approved or adjusted by a senior musculoskeletal radiologist to reach final measurements. Final measurements were used as the ground truth to assess AI performance for each parameter. AI performances were estimated using mean absolute errors (MAE), intraclass correlation coefficient (ICCs), and accuracy for selected clinically relevant thresholds. Readers visually classified AI outputs to assess reliability at a patient-level.
Results |
AI solution showed excellent consistency without bias in coronal (ICCs ≥ 0.95; MAE ≤ 2.9° or 1.97 mm) and sagittal (ICCs ≥ 0.85; MAE ≤ 4.4° or 2.7 mm) spinopelvic evaluation, except for kyphosis (ICC = 0.58; MAE = 8.7°). AI accuracy to classify low Cobb angle, severe scoliosis or frontal pelvic asymmetry was 91% (95% CI: 85–96), 99% (95% CI: 97–100) and 94% (95% CI: 89–98), respectively. Overall, AI provided reliable measurements in 72/100 patients (72%).
Conclusion |
The AI solution used in this study for combined coronal and sagittal spinopelvic balance assessment provides results consistent with those of a senior musculoskeletal radiologist, and shows potential benefit for reducing workload in future routine implementation.
Il testo completo di questo articolo è disponibile in PDF.Keywords : Artificial intelligence, Automated analysis, Uniplanar whole-spine radiographs, Deep learning, Spine deformities
Abbreviations : AI, CA, CI, CVA, FN, FP, FPA, GT, ICC, IQR, MAE, NPV, PI, PPV, PT, SS, SD, SVA, TN, TP
Mappa
Vol 104 - N° 7-8
P. 343-350 - luglio 2023 Ritorno al numero
Articolo precedente
- Vascular hyperintensities on baseline FLAIR images are associated with functional outcome in stroke patients with successful recanalization after mechanical thrombectomy
- Alexandre Bani-Sadr, Raphaël Escande, Laura Mechtouff, Dylan Pavie, Marc Hermier, Laurent Derex, Tae-Hee Choc, Omer F. Eker, Norbert Nighoghossian, Yves Berthezène
- Comparison between 2D FSE T2-weighted Dixon MRI and contrast-enhanced 2D FSE and 3D FSPGR T1-weighted Dixon MRI to quantify inflammation in hands of patients with early rheumatoid arthritis
- Brice Dion, Romain Lacrosse, Nicolas Michoux, Maria Stoenoiu, Patrick Durez, Frédéric Lecouvet, Thomas Kirchgesner
Benvenuto su EM|consulte, il riferimento dei professionisti della salute.