Abstract Ulcer lesions under enteroscopy are complex in shape and difficult to differentiate and diagnose. To realize the artificial intelligence-assisted recognition of small intestinal ulcer lesions and improve the diagnosis efficiency and accuracy, a small intestinal ulcer lesion recognition algorithm based on the MobileNetV2 network was constructed. The MobileNetV2 was used as the backbone feature extraction network, and the output feature map was extracted in space at multiple scales and then input to the channel attention module for feature recalibration, and the features on multiple scales were fused and output classification, in order to alleviate the impact of data imbalance, an improved loss function was proposed. The data set used were collected from a total of 2124 enteroscopy clinical images of 282 patients in Shanghai Changhai Hospital. The proposed method was used to test the data set, and the recognition accuracy was 87.86%, the average accuracy of 5-fold cross-validation was 87.24%. The gradient weighted class activation map was used for visual verification. At the same time, the proposed modules were applied to different backbone network architectures, which reached an improvement to a certain extent, and displayed good versatility. Experimental results showed that the network model extracted more information of lesion, strengthened the identification of lesion characteristics, and had a higher recognition accuracy for small intestinal ulcer images, and was able to initially realize the automatic identification of small intestinal ulcer types.
Liu Zhang,Guo Xudong,Li Shengnan. Image Recognition of Small Intestinal Ulcer Based on MobileNetV2[J]. Chinese Journal of Biomedical Engineering, 2024, 43(1): 70-79.
[1] 宋彩霞,马强.小肠疾病的临床特点及研究现状[J].中国临床研究,2018,31(3):424-426. [2] Clarke WT, Feuerstein JD.Colorectal cancer surveillance in inflammatory bowel disease: Practice guidelines and recent developments [ J] World Gastroenterol, 2019; 25(30): 4148-4157. [3] Lichtenstein GR, Loft EV, Isaacs KL, et al.ACG Clinical Guideline: management of Crohn's disease in adults[J]. American Journal of Gastroenterology, 2018, 113(4): 481-517. [4] Stern RA, Daneshvar DH, Baugh CM, et al.Clinical presentation of chronic traumatic encephalopathy[J]. Neurology, 2013, 81(13): 1122-1129. [5] Liu T, Zheng H, Gong W, et al.The accuracy of confocal laser endomicroscopy, narrow band imaging, and chromoendoscopy for the detection of atrophic gastritis[J]. Journal of Clinical Gastroenterology, 2015,49(5):379. [6] 王巍峰,杨云生.非特异性小肠溃疡发病机制及新分类[J].中国实用内科杂志,2013,33(3):239-242. [7] 于海生,张亚历. 临床表现、内镜及组织病理在克罗恩病、肠结核和原发性结直肠淋巴瘤鉴别诊断中的价值[C]//全国消化内镜学术大会暨第七届中日消化内镜学术研讨会资料汇编.北京:中华医学会消化内镜学分会, 2011:2-2. [8] 叶静,侯志丽,张映雪,等.肠结核与克罗恩病鉴别的研究进展[J].中国临床医生杂志,2020,48(12):1400-1403. [9] 马贤纵,陆晓娟,刘华,等.克罗恩病早期诊断的研究进展[J].解放军医学院学报,2020,41(12):1256-1261,1273. [10] Boschetto D, Di Claudio G, Mirzaei H, et al.Automatic classification of small bowel mucosa alterations in celiac disease for confocal laser endomicroscopy[C] // SPIE Medical Imaging. San Diego: SPIE, 2016: 978809. [11] Souaidi M, Abdelouahed AA, Ansari M.Multi-scale completed local binary patterns for ulcer detection in wireless capsule endoscopy images[J].Multimedia Tools and Applications,2019, 78(10), 13091-13108. [12] Hwang S, Celebi ME.Polyp detection in wireless capsule endoscopy videos based on image segmentation and geometric feature[C]// IEEE International Conference of Acoustics, Speech, Signal Processing (ICASSP’10).Dallas:IEEE, 2010: 678-681. [13] Sharif M, Attique Khan M, Rashid M, et al.Deep CNN and geometric features-based gastrointestinal tract diseases detection and classification from wireless capsule endoscopy images[J]. Journal of Experimental & Theoretical Artificial Intelligence,2021, 33(4):577-599. [14] Rawat W, Wang ZH.Deep convolutional neural networks for image classification: a comprehensive review[J]. Neural Computation, 2017, 29(9): 2352-2449. [15] Cheng G, Zhou PC, Han JW.Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(12): 7405-7415. [16] Long J, Shelhamer E, Darrell T, et al.Fully convolutional networks for semantic segmentation[C]// IEEE Conference on Computer Vision and Pattern Recognition. Boston:IEEE, 2015, 3431-3440. [17] Zhang K, Zuo WM, Zhang L.FFDNet: toward a fast and flexible solution for CNN-based image denoising[J]. IEEE Transactions on Image Processing, 2018, 27(9): 4608-4622. [18] Xu Lanmeng, Fan Shanhui, Fan Yihong, et al.Automatic polyp recognition of small bowel in wireless capsule endoscopy images[C]// Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Houston:SPIE,2018: 10579. [19] Wei JW, Jackson CR.Automated detection of celiac disease on duodenal biopsy slides: a deep learning approach[J]. Journal of Pathology Informatics, 2019, 10(1): 521-534. [20] Xia J, Xia T, Pan J, et al.Use of artificial intelligence for detection of gastric lesions by magnetically controlled capsule endoscopy[J]. Gastrointestinal Endoscopy,2021, 93(1):133-139. [21] Fan S, Xu L, Fan Y, et al.Computer-aided detection of small intestinal ulcer and erosion in wireless capsule endoscopy images[J]. Physics in Medicine and Biology,2018, 63(16): 165001. [22] Shin HC, Roth HR, Gao MC, et al.Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning[J]. IEEE Transactions on Medical Imaging, 2016, 35(5): 1285-1298. [23] Sandler M, Howard A, Zhu ML, et al.MobileNetV2: Inverted Residuals and Linear Bottlenecks[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510-4520. [24] Szegedy C, Vanhoucke V, Ioffe S, et al.Rethinking the inception architecture for computer vision[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2016: 2818-2826. [25] Lin Tsungyi, Goyal P, Girshick R, et al.Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2020, 42(2):318-327. [26] Howard AG, Zhu Menglong, Chen Bo, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[EB/OL]. https://arxiv.org/pdf/1704.04861.pdf, 2017-04-17/2021-08-17. [27] Hu J, Shen L, Albanie S, et al.Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023. [28] Kingma DP, Ba JL. Adam: A method for stochastic optimization[EB/OL]. https://arxiv.org/pdf/1412.6980.pdf, 2017-01-30/2021-08-17. [29] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al.Deep residual learning for image recognition.[C]//IEEE Conference on Computer Vision & Pattern Recognition. Las Vegas: IEEE, 2016: 770-778. [30] Tan Mingxing, Le QV.Efficientnet: rethinking model scaling for convolutional neural networks[C]//International Conference on Machine Learning. Long Beach: PMLR, 2019: 6105-6114. [31] Szegedy C, Vanhoucke V, Ioffe S, et al.Rethinking the inception architecture for computer vision[C]//IEEE Conference on Computer Vision & Pattern Recognition.Las Vegas: IEEE,2016: 2818-2826. [32] Selvaraju RR, Cogswell M, Das A, et al.Grad-CAM: visual explanations from deep networks via gradient-based localization[J]. International Journal of Computer Vision, 2020, 128(2): 336-359.
