An improved deep learning approach and its applications on colonic polyp images detection

Abstract

Background: Colonic polyps are more likely to be cancerous, especially those with large diameter, large number and atypical hyperplasia. If colonic polyps cannot be treated in early stage, they are likely to develop into colon cancer. Colonoscopy is easily limited by the operator's experience, and factors such as inexperience and visual fatigue will directly affect the accuracy of diagnosis. Cooperating with Hunan children's hospital, we proposed and improved a deep learning approach with global average pooling (GAP) in colonoscopy for assisted diagnosis. Our approach for assisted diagnosis in colonoscopy can prompt endoscopists to pay attention to polyps that may be ignored in real time, improve the detection rate, reduce missed diagnosis, and improve the efficiency of medical diagnosis. Methods: We selected colonoscopy images from the gastrointestinal endoscopy room of Hunan children's hospital to form the colonic polyp datasets. And we applied the image classification method based on Deep Learning to the classification of Colonic Polyps. The classic networks we used are VGGNets and ResNets. By using global average pooling, we proposed the improved approaches: VGGNets-GAP and ResNets-GAP. Results: The accuracies of all models in datasets exceed 98%. The TPR and TNR are above 96 and 98% respectively. In addition, VGGNets-GAP networks not only have high classification accuracies, but also have much fewer parameters than those of VGGNets. Conclusions: The experimental results show that the proposed approach has good effect on the automatic detection of colonic polyps. The innovations of our method are in two aspects: (1) the detection accuracy of colonic polyps has been improved. (2) our approach reduces the memory consumption and makes the model lightweight. Compared with the original VGG networks, the parameters of our VGG19-GAP networks are greatly reduced.

Polyp Detection from Colorectum Images by Using Attentive YOLOv5

“…In view of the large proportion of small polyps in heterogeneous data sets, in order to enhance the generalization ability of the model, Li et al proposed a low-rank model by using the human resources network as the backbone to realize the accurate segmentation of polyps [ 31 ]. Wang et al combined the classical vggnets and resnets models with the global average pooling and proposed two new lightweight network structures, vggnets gap and resnets gap, which not only had high classification accuracy, but also had fewer parameters [ 32 ]. Manouchehri et al first proposed a new convolutional neural network for polyp frame detection based on the VGG network and then proposed a complete convolutional network and an effective post-processing algorithm for polyp segmentation [ 33 ].…”

Detecting COVID‐19 in Chest X‐Ray Images via MCFF‐Net

“…A wealth of research results has emerged in this field. For example, Wang et al [ 7 ] proposed and improved a deep learning method for detecting colon polyp images and achieved good results. Wang et al [ 8 ] introduced the dense connection idea of the DenseNet model in the MobileNet model and proposed a new type of image classification model Dense-MobileNet.…”

Medical Image Classification Based on Information Interaction Perception Mechanism

“…Based on the image classification algorithms using CNNs, the diagnostic efficiency of colonic polyps can be further improved. Wang et al [ 8 ] proposed an improved deep neural network to detect colonic polyp images. The DNN-CAD model constructed by Byrne et al [ 9 ] can output the histological prediction results almost in real time.…”