Deep learning and Diagnostic value of cardiac cine MRI for assessing patent foramen ovale in patients with cerebral disorders compared with cTCD

Abstract Purpose To investigate the clinical feasibility of cardiac MRI (CMRI) cine technology using deeplearning without contrast for diagnosis and classification of patent foramen ovales (PFOs) in patients with cerebral disorders. Materials and Methods Fourty-four patients (24 males and 20 females; mean age, 41.3 years; range, 21-64 years) with cerebral disorders underwent both contrast transcranial doppler sonography (cTCD) and non-enhanced CMRI examinations between October 2019 and March 2020. and datas from 335 patients were collected by 2023.CMRI was performed with a 3.0T MR scanner by using OBL FIESTA CINE 4CH sequence. The scanning direction was perpendicular to the interatrial septum (IAS) slice. The obtained MR images were analyzed by AW station 4.7 and the pseudo-color coding was also performed according to the different phases. The condition of the blood shunt was observed and recorded by using deep learning, including measuring the length and width of the PFO and observing whether it was complicated with IAS aneurysm or secondary septum thickening. Results Thirty-nine of 44 patients with cerebral disorders were confirmed with positive RLS by cTCD test, and 37 of the 39 patients were diagnosed with a PFO at CMRI. Two of 5 patients with negative cTCD test were also diagnosed with a PFO at CMRI. Compared with cTCD as a standard, CMRI had a sensitivity of 94.9%, specificity of 60.0%, accuracy of 90.9%, positive predictive value of 94.9%, negative predictive value of 60.0%, and AUC of 0.774. Based on the pseudo-color coding, the right-to-left color jet was observed in 34 patients, and the two-way shunting was found in 5 patients. The IAS aneurysm and secondary septum thickening were found in 5 and 3 patients (11.4% and 6.8%). The maximum diameters of PFOs ranged from 1.7 mm to 16.8 mm and the mean diameter was 5.4±3.4 mm. Conclusion By using deep learning,CMRI cine technology without contrast provided a noninvasive and excellent method for PFO identification, evaluation and classification, with both high sensibility (92.85%) and concordance (90.9%) when compared to cTCD.PFO types