基于神经网络的结直肠息肉检测
Colorectal Polyp Detection Based on Neural Network
DOI: 10.12677/SEA.2022.113051, PDF,   
作者: 郑凯强:浙江理工大学,浙江 杭州
关键词: 息肉深度学习目标检测神经网络Polyp Deep Learning Target Detection Neural Network
摘要: 随着人们生活水平的不断提升,医疗水平不断完善,人们越来越关注自身的生理健康,而结直肠癌作为常见的恶性肿瘤之一,医学上对其关注度也越来越堵多。其中结直肠息肉是结直肠癌的早期病变,其早期诊断和检测是预防结直肠癌、减少患者发病率、死亡率提高的有效途径。针对结直肠检测问题,同时随着深度神经网络的兴起,计算机辅助医师检查结直肠息肉已越来越获得关注,因此本次研究以结直肠息肉当做主要研究对象,通过分析对比主流目标检测算法,分析对比并提出更高精度的检测模型,有效提高结直肠息肉准确度,提高医师检测效率以及降低检测难度。
Abstract: With the continuous improvement of people’s living standards and the continuous improvement of medical care, people are paying more and more attention to their own physical health. As one of the common malignant tumors, colorectal cancer has attracted more and more medical attention. Among them, colorectal polyps are the early lesions of colorectal cancer, and its early diagnosis and detection is an effective way to prevent colorectal cancer, reduce the morbidity of patients, and increase the mortality rate. Aiming at the problem of colorectal detection, and with the rise of deep neural networks, computer-aided physicians in the detection of colorectal polyps have received more and more attention. Therefore, this study takes colorectal polyps as the main research object, and analyzes and compares mainstream target detection algorithms. Analyzed and compared and proposed a higher-precision detection model, which can effectively improve the accuracy of colorectal polyps, improve the detection efficiency of physicians, and reduce the difficulty of detection.
文章引用:郑凯强. 基于神经网络的结直肠息肉检测[J]. 软件工程与应用, 2022, 11(3): 487-493. https://doi.org/10.12677/SEA.2022.113051

参考文献

[1] 东帅. 结直肠息肉临床特征及治疗方式的研究[D]: [硕士学位论文]. 天津: 天津医科大学, 2013.
[2] 王锡山. 从流行病学看结直肠癌防治[N]. 健康报, 2021-02-10(006).
[3] 罗来盛. 结肠息肉临床病理特征和癌变相关危险因素研究[D]: [硕士学位论文]. 杭州: 浙江大学, 2016.
[4] Misawa, M., Kudo, S.E., Mori, Y., et al. (2018) Artificial Intelligence-Assisted Polyp Detection for Colonoscopy: Initial Experience. Gastroenterology, 154, 2027-2029. [Google Scholar] [CrossRef] [PubMed]
[5] 陈祎琼, 刘澳, 范国华, 毕家泽, 陈滔. 基于深度森林的CT图像结直肠息肉检测研究[J]. 洛阳理工学院学报(自然科学版), 2022, 32(1): 68-74.
[6] 李素琴, 吴练练, 宫德馨, 胡珊, 陈奕云, 朱晓芸, 李夏, 于红刚. 基于YOLO算法和ResNet深度卷积神经网络的结直肠息肉检测[J]. 中华消化内镜杂志, 2020, 37(8): 584-590.
[7] 孙雪华, 潘晓英. Faster R-CNN内窥镜息肉检测[J]. 西安邮电大学学报, 2020, 25(2): 29-34.
[8] 包俊, 董亚超, 刘宏哲. 卷积神经网络的发展综述[C]//中国计算机用户协会网络应用分会. 中国计算机用户协会网络应用分会2020年第二十四届网络新技术与应用年会论文集. 中国计算机用户协会网络应用分会: 北京联合大学北京市信息服务工程重点实验室, 2020: 6.
[9] Redmon, J. and Farhadi, A. (2018) YOLOv3: An Incremental Improvement. ar Xiv:1804.02767.
[10] Tian, Z., Shen, C., Chen, H., et al. (2020) FCOS: Fully Convolutional One-Stage Object Detection. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October 2019 - 02 November 2019, 9626-9635. [Google Scholar] [CrossRef
[11] 刘琦, 蔡旭, 黄飞, 吴一楠. 基于Faster RCNN的复杂场景目标检测[J]. 集成电路应用, 2022, 39(2): 112-113. [Google Scholar] [CrossRef
[12] Lin, T.Y., Maire, M., Belongie, S., et al. (2014) Microsoft COCO: Common Objects in Context. European Conference on Computer Vision. Springer International Publishing, New York. [Google Scholar] [CrossRef
[13] He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef