Abstract
There was an investigation of the diagnostic and prognostic effect of magnetic resonance imaging (MRI) based on multimodal feature fusion algorithm for impotence of perianal abscess. In this study, the second to fifth convolution blocks of the visual geometric group network were applied to extract the depth features in the way of transfer learning, and a multimode feature fusion algorithm was constructed. The whole network was trained by maximizing the energy proportion of the feature layers, which was compared with the fully convolutional neural network (FCN) algorithm. Then, this algorithm was adopted to the imaging diagnosis of 50 patients with anorectal diseases admitted to our hospital, and it was found that the similarity coefficient (85.37%), accuracy (80.02%), and recall rate (79.38%) of the improved deep learning algorithm were higher markedly than those of the FCN algorithm (70.18%, 67.82%, and 66.92%) (P < 0.05). As the number of convolutional layers increased, the segmentation accuracy of the convolutional neural network (CNN) algorithm was also improved. The detection rate of the observation group (84%) rose hugely compared with the control group (64%), and the difference was statistically obvious (P < 0.05). Besides, the detection accuracy of abscess location (84%), impotent tract location (80%), and internal orifice location (92%) in patients from the observation group was higher substantially than the accuracy of abscess location (60%), impotent tract location (68%), and internal orifice location (72%) from the control group (P < 0.05). In conclusion, the performance of the multimodal feature fusion algorithm was better, and the MRI image feature analysis based on this algorithm had a higher diagnostic accuracy, which had a positive effect on improving the detection rate, detection accuracy, and disease classification.
Highlights
Perianal abscess is a very common perianal disease, which is called anal pain and dirty poison in traditional Chinese medicine. e incidence rate is increasing every year, and it is more common in young men [1]
Lv et al [10] developed an anorectal MR injury detection system based on deep learning. e system consists of two convolutional neural networks (CNNs): the first CNN network is used for fast image segmentation; the second CNN network is adopted to evaluate structural abnormalities of the anorectal tract
50 patients with anorectal diseases were selected as the research objects, who were admitted to the hospital from January 20, 2018, to February 15, 2020. en, all of them were grouped randomly into the observation group and the control group. e observation group was diagnosed by magnetic resonance imaging (MRI) based on the deep learning algorithm, while the control group was diagnosed by routine MRI
Summary
Perianal abscess is a very common perianal disease, which is called anal pain and dirty poison in traditional Chinese medicine. e incidence rate is increasing every year, and it is more common in young men [1]. Perianal abscess is caused by infection of the anal gland located between the sphincter muscles. E diagnosis of perianal abscess and anal canal stenosis is clear before surgery, and the location of the perianal opening, abscess range, anal fistula trend, and its relationship with surrounding muscle tissue are clearly defined, which is of great significance for the selection of surgical methods and the protection of anal physiological functions [5,6]. Due to the low movement of pelvic organs, high-quality images can be collected, which can accurately describe the anatomical structures of the internal and external anal sphincter, levator ani, and puborectalis muscles and can show the relationship among perianal abscess, anal fistula, and muscles around the anus [8]. Deep learning methods have surpassed traditional medical image analysis methods and made great progress in the field of anorectal MRI of patients. Lv et al [10] developed an anorectal MR injury detection system based on deep learning. e system consists of two convolutional neural networks (CNNs): the first CNN network is used for fast image segmentation; the second CNN network is adopted to evaluate structural abnormalities of the anorectal tract
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
