Research on improved intestinal image classification for LARS based on ResNet

Abstract

Low anterior rectal resection is an effective way to treat rectal cancer at present, but it is easy to cause low anterior resection syndrome after surgery; so, a comprehensive diagnosis of defecation and pelvic floor function must be carried out. There are few studies on the classification of diagnoses in the field of intestinal diseases. In response to these outstanding problems, this research will focus on the design of the intestinal function diagnosis system and the image processing and classification algorithm of the intestinal wall to verify an efficient fusion method, which can be used to diagnose the intestinal diseases in clinical medicine. The diagnostic system designed in this paper makes up for the singleness of clinical monitoring methods. At the same time, the Res-SVDNet neural network model is used to solve the problems of small intestinal image samples and network overfitting, and achieve efficient fusion diagnosis of intestinal diseases in patients. Different models were used to compare experiments on the constructed datasets to verify the applicability of the Res-SVDNet model in intestinal image classification. The accuracy of the model was 99.54%, which is several percentage points higher than other algorithm models.

Intelligent Crack Detection and Analysis of Building Walls Based on DeepCrack Network

“…The ResNet core structure model is shown in Fig. 6, and the learning process will change from directly learning features to adding some features to the previously learned features to obtain better features [31]. In the past, features were independently learned layer by layer, but now it has become a model where H(x)=F(x) + x.…”

“…The prediction includes "side output m" (m = 1, ..., 5). The losses generated by each side's output are called ɑ m Δ(P (m) , G, W, w (m) ) [31]. The final fuse prediction, also known as L fuse The loss of fuse.…”

IoT Agricultural Pest Identification Based on Multiple Convolutional Models

“…As the network gets deeper and deeper, it becomes more and more difficult to learn features. If a shortcut link is added, the learning process changes from learning features directly to adding some features to the previously learned features to obtain better features [24]. In the previous case, the features were learned independently layer by layer, but now it becomes such a model H(x) = F(x) + x, where x is the feature at the beginning of the shortcut link, and F(x) is the fill and increase of x, which becomes the residual.…”