ABSTRACT
Background: Multi-parametric magnetic resonance imaging (MP-MRI) may provide comprehensive information for graded diagnosis of bladder cancer (BCa). Nevertheless, existing methods ignore the complex correlation between these MRI sequences, failing to provide adequate information. Therefore, the main objective of this study is to enhance feature fusion and extract comprehensive features from MP-MRI using deep learning methods to achieve an accurate diagnosis of BCa grading. Methods: In this study, a self-attention-based MP-MRI feature fusion framework (SMMF) is proposed to enhance the performance of the model by extracting and fusing features of both T2-weighted imaging (T2WI) and dynamic contrast-enhanced imaging (DCE) sequences. A new multiscale attention (MA) model is designed to embed into the neural network (CNN) end to further extract rich features from T2WI and DCE. Finally, a self-attention feature fusion strategy (SAFF) was used to effectively capture and fuse the common and complementary features of patients' MP-MRIs. Results: In a clinically collected sample of 138 BCa patients, the SMMF network demonstrated superior performance compared to the existing deep learning-based bladder cancer grading model, with accuracy, F1 value, and AUC values of 0.9488, 0.9426, and 0.9459, respectively. Conclusion: Our proposed SMMF framework combined with MP-MRI information can accurately predict the pathological grading of BCa and can better assist physicians in diagnosing BCa.
ABSTRACT
OBJECTIVE: In this study, umbilical cord mesenchymal stem cell (UC-MSC) transplantation was used to treat patients with spinal cord injury (SCI). The microstructural changes of the spinal cord before and after transplantation were observed by diffusion tensor imaging (DTI). METHODS: From January 2014 to May 2015, seven patients who met the inclusion criteria were enrolled in this study. In the experimental group, both UC-MSC transplantation and comprehensive rehabilitation treatment were applied, while the control group received only comprehensive rehabilitation treatment. American Spinal Injury Association (ASIA) sensory and motor scores and the degree of SCI, spasticity, and urine/defecation functions were measured and evaluated together with DTI before the treatment and again at two and six months after the first treatment. RESULTS: From the DTI, the changes in the fractional anisotropy (FA) value and the apparent diffusion coefficient (ADC) value were as follows: in the experimental group, there were significant differences in the FA and ADC values before and after treatment (P < 0.05) with a decreased ADC value and an increased FA value. The differences in the ADC and FA values of the normal layer and the lesion layer before and after treatment were compared. The differences in ADC and FA at the lesion layer before and after transplantation were greater than those of the normal layer, and the differences were statistically significant (P < 0.05). In the experimental group, one patient with incomplete SCI and one patient with a short course of complete SCI improved in terms of light touch, acupuncture sensation, and motor score. One patient with incomplete SCI achieved improvement in spasticity and urine/defecation functions. CONCLUSION: The combination of UC-MSC transplantation and comprehensive rehabilitation therapy could help to promote the structural repair of the spinal nerve in patients with SCI.
ABSTRACT
BACKGROUND: The Vesical Imaging-Reporting and Data System (VI-RADS) was created in 2018, and a 5-point VI-RADS scoring system was proposed to determine whether the muscularis of the bladder has been infiltrated by tumor tissues. PURPOSE: To verify the accuracy of the VI-RADS scoring system in predicting muscle-invasive bladder cancer and to explore its value in clinical application. MATERIALS AND METHODS: A total of 220 patients with bladder cancer who underwent multiparameter magnetic resonance imaging from January 2017 to June 2019 were selected. Then, two radiologists with equivalent qualifications gave their diagnoses of bladder tumors on T2-weighted imaging, diffusion-weighted imaging and dynamic contrast enhanced imaging. Meanwhile, the bladder tumor was also scored on the basis of the VI-RADS system; for multifocal tumors, the highest tumor load was selected for scoring. Furthermore, the final pathological results of the patients were unknown during the imaging diagnosis and scoring. Next, the VI-RADS score was compared with the pathological results after surgery, and the ability of the VI-RADS score to assess the degree of muscularis infiltration was finally analyzed. RESULTS: A total of 220 patients were included in our study, including 194 males and 26 females. Among them, the pathological results were 113 cases of muscle-invasive bladder cancer and 107 cases of non-muscle-invasive bladder cancer. The results showed that there was a positive correlation between the pathological results and VI-RADS score (r = 0.821, P < 0.05). The area under the receiver operating characteristic curve of the VI-RADS score was 0.960 (95% CI: 0.937, 0.983). When the VI-RADS score was above 3, the sensitivity, specificity and accuracy of predicting muscle-invasive bladder cancer were 82.3, 95.3 and 88.64%, respectively. CONCLUSION: The VI-RADS scoring system has good diagnostic value in predicting the degree of tumor invasion and can be used to guide clinical decision-making and management.
