ABSTRACT
Objective:To explore the value of fast susceptibility weighted imaging (SWI) generated by a deep learning model in assessment of acute ischemic stroke (AIS).Methods:From January 2019 to January 2021, 118 AIS patients [75 males and 43 females, aged 23-100 (66±14) years] who underwent MR examination and SWI sequence scanning within 24 h of symptom onset in the First Medical Center of PLA General Hospital were retrospectively analyzed. MATLAB ′s randperm function was used to divide 118 patients into a training set of 96 cases and a test set of 22 cases at a ratio of 8∶2. Fourty-seven AIS patients [38 males and 9 females, aged 16-75 (58±12) years] from one center of a multicenter study were selected to build the external validation set. SWI image and filtered phase image were combined into complex value image as full sampling reference image. Undersampled SWI images were obtained by retrospective undersampling of reference fully sampled images, and the undersampling multiple was five times which could save 80% of the scanning time, then the complex-valued convolutional neural network (ComplexNet) was used to develop reconstruct fast SWI. Interclass correlation coefficient (ICC) or Kappa tests were used to compare the consistency of image quality and the diagnostic consistency for the presence of susceptibility vessel sign (SVS), cerebral microbleeds and asymmetry of cerebral deep medullary veins (DMVs) in AIS patient on fully sampled SWI and fast SWI based on ComplexNet.Results:In test set, score of image quality was 4.5±0.6 for fully sampled SWI image and 4.6±0.7 for fast SWI based on ComplexNet, and coefficient was excellent (ICC=0.86, P<0.05). Full sampling SWI had good agreement with fast SWI based on ComplexNet in detecting SVS (Kappa=0.79, P<0.05), microbleeds (Kappa=0.86, P<0.05), and DMVs asymmetry (Kappa=0.82, P<0.05) in AIS patients. In the external validation set, score of image quality was 4.1±1.0 for fully sampled SWI image and 4.0±0.9 for fast SWI based on ComplexNet, and coefficient was excellent (ICC=0.97, P<0.05). Full sampling SWI had good agreement with fast SWI based on ComplexNet in detecting SVS (Kappa=0.74, P<0.05), microbleeds (Kappa=0.83, P<0.05), and DMVs asymmetry (Kappa=0.74, P<0.05) in AIS patients. Conclusions:Deep learning techniques can significantly accelerate the speed of SWI, and the consistency of image quality and detected AIS signs between fast SWI based on ComplexNet and fully sampled SWI is good. The fast SWI based on ComplexNet can be applied to the radiographic assessment of clinical AIS patients
ABSTRACT
Objective To compare the diagnostic value of 3.0T and 1.5T magnetic resonance diffusion weighted imaging (DWI) in lymph node metastasis of gastric cancer. Methods Preoperative magnetic resonance examination was performed on 50 patients with gastric cancer by using Siemens 1.5T and 3.0T superconducting magnetic resonance imaging system, and the outcomes were compared with postoperative pathological results. The sensitivity, specificity and accuracy of the diagnosis in lymph node metastasis of gastric cancer were analyzed statistically. The apparent diffusion coefficient (ADC) values of lymph nodes were also evaluated for 1.5T and 3.0T magnetic resonance DWI. Results The sensitivity, specificity and accuracy of the diagnosis on lymph node metastasis of gastric cancer by 1.5T magnetic resonance DWI were 79.4 %, 81.4%and 80.0%, respectively, and the corresponding percentages of 3.0T magnetic resonance DWI were 84.6%, 79.7%and 83.1%. The accuracy rate of 3.0T magnetic resonance DWI was slightly higher than that of 1.5T in the diagnosis of lymph node metastasis of gastric cancer (χ2=5.451, P=0.020), but there were no significant differences in the sensitivity and specificity between the two groups (both P> 0.05). The accuracy rate of 1.5T magnetic resonance DWI in the diagnosis of lymph node metastasis of gastric cancer was less effective than that of the pathological diagnosis (χ2=7.410, P=0.007), but there was no significant difference between 3.0T magnetic resonance DWI and pathological diagnosis (χ2=2.450, P=0.120). The mean ADC values of metastatic and non-metastatic lymph nodes detected by 1.5T magnetic resonance DWI were (1.036 ±0.203) × 10-3 mm2/s and (1.476 ± 0.215) × 10-3 mm2/s (t= 6.813, P< 0.001), meanwhile, the corresponding values detected by 3.0T magnetic resonance DWI were (1.154 ± 0.183) × 10-3 mm2/s and (1.502 ± 0.264) × 10-3 mm2/s (t= 5.991, P< 0.001). The coincidence of the two methods for ADC value was favorable. Conclusions The diagnostic effect of 3.0T magnetic resonance DWI on lymph node metastasis of gastric cancer is better than that of 1.5T. ADC value provides a reliable imaging quantitative indicator for the determination of metastatic lymph nodes in gastric cancer, which plays a significant role in the clinical treatment options and prognosis of patients.