Artificial Intelligence in Colorectal Polyp Detection and Characterization

GCCSwin-UNet: Global Context and Cross-Shaped Windows Vision Transformer Network for Polyp Segmentation

Accurate polyp segmentation is of great importance for the diagnosis and treatment of colon cancer. Convolutional neural networks (CNNs) have made significant strides in the processing of medical images in recent years. The limited structure of convolutional operations prevents CNNs from learning adequately about global and long-range semantic information interactions, despite the remarkable performance they have attained. Therefore, the GCCSwin-UNet framework is suggested in this study. Specifically, the model utilizes an encoder–decoder structure, using the patch-embedding layer for feature downsampling and the CSwin Transformer block as the encoder for contextual feature extraction. To restore the feature map’s spatial resolution during upsampling operations, a symmetric decoder and patch expansion layer are also created. In order to help the backbone module to do better feature learning, we also create a global context module (GCM) and a local position-enhanced module (LPEM). We conducted extensive experiments on the Kvasir-SEG and CVC-ClinicDB datasets, and compared them with existing methods. GCCSwin-UNet reached remarkable results with Dice and MIoU of 86.37% and 83.19% for Kvasir-SEG, respectively, and 91.26% and 84.65% for CVC-ClinicDB, respectively. Finally, quantitative analysis and statistical tests are applied to further demonstrate the validity and plausibility of our method.

A Reliable and Sensitive Framework for Simultaneous Type and Stage Detection of Colorectal Cancer Polyps

With the goal of enhancing the early diagnosis of colorectal cancer (CRC) polyps and reducing the risk of mortality in cancer patients, in this article, we present a unique diagnosis framework including a Vision-based Surface Tactile Sensor (VS-TS) and complementary Artificial Intelligence algorithms. Leveraging the morphological characteristics (i.e., shape and texture) and stiffness features of the CRC polyps, the proposed framework is able to reliably and sensitively identify their type and stage. To thoroughly characterize and identify the required VS-TS sensitivity for reliable identification of polyps, we first fabricated three different VS-TSs and qualitatively evaluated their performances on 48 different types of polyp phantoms fabricated based on four different types of realistic CRC polyps and three different materials. Next, to quantitatively compare the performance and sensitivity of the fabricated VS-TSs, we used Support Vector Machine (SVM) algorithm and employed various statistical metrics (i.e., accuracy, reliability, and sensitivity). Next, using the most sensitive VS-TS, we classified the type of tumors using the SVM algorithm and applied the t-Distributed Stochastic Neighbor Embedding algorithm to successfully identify the stiffness of classified polyp phantoms solely based on the output images of the VS-TS sensor. Results demonstrated that an SVM algorithm applied on the image outputs of a VS-TS with a Shore hardness of 00-40 scale is able to classify all types of polyps with > 90% accuracy, sensitivity, and reliability. We also repeated experiments on samples of ex-vivo lamb tripe tissues and successfully verified the high sensitivity and reliability of the proposed framework (i.e., > 94%).

Polyp Detection from Colorectum Images by Using Attentive YOLOv5

Background: High-quality colonoscopy is essential to prevent the occurrence of colorectal cancers. The data of colonoscopy are mainly stored in the form of images. Therefore, artificial intelligence-assisted colonoscopy based on medical images is not only a research hotspot, but also one of the effective auxiliary means to improve the detection rate of adenomas. This research has become the focus of medical institutions and scientific research departments and has important clinical and scientific research value. Methods: In this paper, we propose a YOLOv5 model based on a self-attention mechanism for polyp target detection. This method uses the idea of regression, using the entire image as the input of the network and directly returning the target frame of this position in multiple positions of the image. In the feature extraction process, an attention mechanism is added to enhance the contribution of information-rich feature channels and weaken the interference of useless channels; Results: The experimental results show that the method can accurately identify polyp images, especially for the small polyps and the polyps with inconspicuous contrasts, and the detection speed is greatly improved compared with the comparison algorithm. Conclusions: This study will be of great help in reducing the missed diagnosis of clinicians during endoscopy and treatment, and it is also of great significance to the development of clinicians’ clinical work.