Deep Learning-Based Computed Tomography Image Features in the Detection and Diagnosis of Perianal Abscess Tissue

The performance characteristics of deep learning fully convolutional neural network (DLFCNN) algorithm-based computed tomography (CT) images were investigated in the detection and diagnosis of perianal abscess tissue. 60 patients who were medically diagnosed as perianal abscesses in the hospital were selected as the experimental group, and 60 healthy volunteers were selected as the control group. In this study, the DLFCNN algorithm based on deep learning was compared with the CNN algorithm and applied to the segmentation training of CT images of patients with perianal abscesses. Then, the segmentation metrics Jaccard, Dice coefficient, precision rate, and recall rate were compared by extracting the region of interest. The results showed that Jaccard (0.7326) calculated by the CNN algorithm was sharply lower than that of the DLFCNN algorithm (0.8525), and the Dice coefficient (0.7264) was also steeply lower than that of the DLFCNN algorithm (0.8434) (P < 0.05). The thickness range of the epidermis and dermis in patients from the experimental group was 4.1–4.9 mm, which was markedly greater than the range of the control group (1.8–3.6 mm) (P < 0.05). Besides, the CT value of the subcutaneous fascia in the experimental group (−95.45 ± 8.26) hugely reduced compared with the control group (−76.34 ± 7.69) (P < 0.05). The accuracy rate of the patients with perianal abscesses was 96.67% by multislice spiral CT (MSCT). Therefore, the DLFCNN algorithm in this study had good stability and good segmentation effect. The skin at the focal site of anal abscess was obviously thickened, and it was simple and accurate to use CT images in the diagnosis of patients with perianal abscesses, which could effectively locate the lesion and clarify the relationship between the lesion and the surrounding structure.