Automatic detection of decreased ejection fraction and left ventricular hypertrophy on 4D cardiac CTA: Use of artificial intelligence with transfer learning to facilitate multi-site operations

Introduction Artificial intelligence models trained in one site may not have acceptable performance when used in another site. Transfer learning (TL) can be used to adapt the original model to a new institution, making it more robust and generalizable. Methods Performance of a 4D cardiac computed tomography angiography (CCTA) segmentation model trained at Site 1 was assessed at Site 2, before and after TL. Two separate image-annotated 4D CCTA datasets were collected at each site. Segmentation output from the model was used to measure left ventricular (LV) ejection fraction (EF), LV end-diastolic volume (EDV), and LV mass and compared with the ground-truth (measurements derived from the segmentation performed by trained radiologists). Wilcoxon signed-rank test (with 95% CI) was used to compare the absolute errors between predicted and ground-truth values obtained at Site 2 before and after TL. Results Test set at Site 2 included 45 patients (27 women, mean age 47.9 ± 10.8 years). There was a significant difference in absolute errors of LVEF (mean ± std 10.0 ± 6.0% vs 3.7 ± 2.5%, p < 0.05), LVEDV (mean ± std 8.4 ± 6.7 mL vs 5.9 ± 5.9 mL, p < 0.05) and LV mass (mean ± std 12.0 ± 11.6g vs 7.7 ± 9.9g, p < 0.05) when comparing model performance before and after TL at Site 2. Conclusion The TL process significantly improved the prediction of LV volumetric parameters obtained at Site 2 by adapting the model to another source. A small number of annotated cases can be used to significantly improve a deep learning model developed elsewhere, increasing model generalizability and encouraging institutions to engage in artificial intelligence initiatives.