浏览全部资源
扫码关注微信
收稿：2020-12-29，
修回：2021-3-30，
录用：2021-4-6，
纸质出版：2021-09-16
移动端阅览
目的
2
大肠息肉和溃疡性结肠炎（ulcerative colitis，UC）是常见的大肠疾病，发病率高，检测需求大，且容易在临床中被漏诊和误诊。因此研究用于内窥镜大肠病变图像分类的计算机辅助诊断（computer-aided diagnosis，CAD）系统十分重要。局域约束线性编码（locality constrained linear coding，LLC）在图像分类领域展现了优异的性能，能够完成对内窥镜中病变图像的分类。但是由于肠胃内窥镜图像中存在的一些微小息肉等病理征状与肠壁十分相似，LLC在这一场景下的性能有待提高。
方法
2
由于码本的设计对细微差别检测能力影响大，本文通过改进LLC中的码本来实现更精确的大肠病变分类，其中原始码本被改进为带有先验权重影响的共享码本。主要思想是尝试尽可能多地使用代表私有部分的码本。本文方法重新排列了码本的列，将较少使用的原子排列在码本的后面，成为共享码本。并利用原子使用的频率计算权重，通过在线字典学习的方法，获得具有先验权重的共享码本。利用这一新码本对特征进行编码能实现更为高效精确的图像分类。
结果
2
为避免过拟合，将部分Kvasir数据集与部分医院合作数据集合并使用。实验在2 600幅内窥镜图像上进行正常、息肉和UC图像的三分类实验，与压缩感知空间金字塔池化（compressed sensing spatial pyramid pooling，CSSPP）方法、私有共享字典学习算法（category-specific dictionary and shared dictionary learning，CSDL）、环形空间金字塔模型方法（circular inner ring partitioning，CIRP）、显著性和自适应局部约束线性编码（saliency and adaptive locality constrained linear coding，SALLC）和AlexNet迁移学习的网络比较，本文方法的总体分类准确率为93.82%，较对比方法分别高了2.33%、2.21%、1.91%、0.8%、0.07%。
结论
2
本文所提出的先验权重共享码本，综合了词汇袋模型和共享字典的思想，使得对内窥镜图像中相似图片的分类更加精确。
Objective
2
Colorectal polyps (CPs) and ulcerative colitis (UC) have been the typical colorectal diseases with high morbidity. Colorectal polyps have become the main factor to trigger colon cancers. UC has been an unidentified colorectal inflammatory disease nowadays. The clinical manifestations illustrate the phenomena in abdominal pain
diarrhea
and bloody stools. UC and CPs regard as one key factor to cause colon cancer. High-intensity endoscopic images analyses have intended physician to fatigued. computer-aided diagnosis(CAD)-based endoscopic colorectal disease image classification system has been the essential demonstration. The bag-of-visual-words (BoVW) model has been qualified in medical image classification for endoscopic lesion detection. Locality constrained linear coding (LLC) has been one good quality coding methodology in the BoVW model due to its coding performance and fast iteration speed. BoVW divide an image into many patches to extract its local features. The local features have become scale-invariant feature transform (SIFT) and histogram of oriented gradient (HOG). These local features have been coded via LLC. Spatial pyramid matching (SPM) and maximum pooling have been used to preserve the spatial information of the image. Some small polyps and unidentified UC have not been leaked out from the intestinal wall in the endoscopic image. The performance of LLC codebook has not been classified the similar endoscope images. To realize category-specific dictionary and shared dictionary learning (CSDL)
this research has aimed to endoscopic colorectal image classification via learning a priori weight shared codebook in the LLC. The priori weight shared codebook has qualified good classification results via the endoscopic images classification.
Method
2
LLC-based priori weight shared codebook has been illustrated. The private features have been represented as much as possible. Two control factors in the LLC cost function have been added in. The rearrangement of the columns for the codebook have been arranged via these rarely used atoms called shared atoms in the bottom of the updated codebook in the coding process. Prior knowledge has been demonstrated to have good performance in image processing. The endoscopic images have potential to the probabilistic priors for image process. A priori diagonal weighting matrix has been added to the shared codebook for the better represent of local features when encoding. The weights have derived from the frequency based on the usage of the atoms. First
the local features have been extracted from image patches. The histogram of local color difference (LCDH) features has been identified the information via the relationship of the color distribution distance instead of the SIFT and HOG features due to the rich color information in the endoscopic images. These features have been clustered into the initial codebook via K-means algorithm. The initial codebook has been updated through online dictionary learning algorithm based on the proposed priori weight shared codebook algorithm. All features have been coded based on the updated codebook. The SPM has been used to preserve the spatial information of the endoscopic images. The support vector machines (SVM) classifier has been trained via the codes to identification the lesion images.
Result
2
This research has integrated a part of the Kvasir dataset and a part of the hospital cooperation dataset to resolve overfitting issue. First
the classification experiments have been performed based on 800 polyp images and 800 normal images. The size
$$ K$$
of codebook and the size
$$M $$
of the shared atoms have become the main parameters to conduct classification. The results have shown that the classification result played well when
$$ K$$
is 256 and
$$M $$
is 56. The accuracy
sensitivity and specificity have been 97%
96.88% and 97.12% each. The SVM classification accuracy has increased 8.42%
2.58%
1.58% respectively compared with vector quantization (VQ)
sparse coding SPM (ScSPM) and LLC based on the 1 200 images sample. The illustrated algorithm has presented more robust than LLC based on the small-sized images sample. The dataset has performed classification experiments based on 925 polyp images
835 normal images and 840 UC images. The accuracy of the classification result has reached 93.82%. The SVM classified accuracy have increased 2.33%
2.21%
1.91%
0.8%
0.07% respectively compared to compressed sensing spatial pyramid pooling (CSSPP)
CSDL
circular inner ring partitioning (CIRP)
saliency and adaptive LLC(SALLC) and AlenxNet. The running time has reduced 1 957 seconds in the calculation process.
Conclusion
2
A priori weight shared codebook based on locality constrained linear coding has been demonstrated for lesions detection. The qualified classification capabilities have been presented in comparison with BoVW model and other shared dictionary learning. The algorithm has shorten running time to improve the efficiency and accuracy of computer-aided diagnosis to aid clinical diagnosis level. The real-time disease detection based on a completed endoscopic video has been developing further via the applicability of the algorithm murgrading.
Alexandre L A, Nobre N and Casteleiro J. 2008. Color and position versus texture featuresfor endoscopic polyp detection//Proceedings of 2008 International Conference on BioMedical Engineering and Informatics. Sanya, China: IEEE: 38-42[ DOI: 10.1109/BMEI.2008.246 http://dx.doi.org/10.1109/BMEI.2008.246 ]
Csurka G, Dance C R, Fan L X, Willamowski J and Bray C. 2004. Visual categorization with bags of keypoints//Proceedings of European Conference on Workshop on Statistical Learning in Computer Vision. Prague, Czech Republic: Springer: 1-22
Fan S H, Liu S C, Cao E, Fan Y H, Wei K H and Li L H. 2019. Small intestinal polyp detection in wireless capsule endoscopy images. Chinese Journal of Biomedical Engineering, 38(5): 522-532
范姗慧, 刘士臣, 曹鹗, 范一宏, 魏凯华, 厉力华. 2019. 无线胶囊内窥镜图像小肠息肉的自动识别. 中国生物医学工程学报, 38(5): 522-532[DOI: 10.3969/j.issn.0258-8021.2019.05.002]
Gan J C, Zhang M Q, Qin H and Zhang X P. 2019. Application of computer-assisted diagnosis in colonoscopy. Tianjin Medical Journal, 47(6): 580-583
甘建琛, 张明庆, 秦海, 张锡朋. 2019. 计算机辅助诊断在结肠镜检查中的应用. 天津医药, 47(6): 580-583)[DOI: 10.11958/20191016]
Gao S H, Tsang I W H and Ma Y.2014. Learning category-specific dictionary and shared dictionary for fine-grained image categorization. IEEE Transactions on Image Processing, 23(2): 623-634[DOI: 10.1109/TIP.2013.2290593]
Jiang Q R, Li S, Zhu Z H, Bai H, He X X and de Lamare R C. 2020. Design of compressed sensing system with probability-based prior information. IEEE Transactions on Multimedia, 22(3): 594-609[DOI: 10.1109/TMM.2019.2931400]
Karkanis S A, Iakovidis D K, Maroulis D E, Karras D A and Tzivras M. 2003. Computer-aided tumor detection in endoscopic video using color wavelet features. IEEE Transactions on Information Technology in Biomedicine, 7(3): 141-152[DOI: 10.1109/TITB.2003.813794]
Karmakar P, Teng S W, Lu G J and Zhang D S. 2020. An enhancement to the spatial pyramid matching for image classification and retrieval. IEEE Access, 8: 22463-22472[DOI: 10.1109/ACCESS.2020.2969783]
Lazebnik S, Schmid C and Ponce J. 2006. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories//Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE: 2169-2178[ DOI: 10.1109/CVPR.2006.68 http://dx.doi.org/10.1109/CVPR.2006.68 ]
Li J N. 2010. Clinical features and carcinogenesis mechanism of ulcerative colitis-associated colonic cancer. Modern Digestion and Intervention, 15(3): 158-160
李景南. 2010. 溃疡性结肠炎相关结肠癌的临床特点和癌变机制. 现代消化及介入诊疗, 15(3): 158-160[DOI: 10.3969/j.issn.1672-2159.2010.03.010]
Liaqat A, Khan M A, Shah J H, Sharif M, Yasmin M and Fernandes S L. 2018. Automated ulcer and bleeding classification from WCE images using multiple features fusion and selection. Journal of Mechanics in Medicine and Biology, 18(4): #1850038[DOI: 10.1142/S0219519418500380]
Maghsoudi O H. 2017. Superpixel based segmentation and classification of polyps in wireless capsule endoscopy//The 2017 IEEE Signal Processing in Medicine and Biology Symposium. Philadelphia, USA: IEEE: 1-4[ DOI: 10.1109/spmb.2017.8257027 http://dx.doi.org/10.1109/spmb.2017.8257027 ]
Mairal J, Bach F,Ponce J and Sapiro G. 2009. Online dictionary learning for sparse coding//Proceedings of the 26th Annual International Conference on Machine Learning. New York, USA: ACM: 689-696[ DOI: 10.1145/1553374.1553463 http://dx.doi.org/10.1145/1553374.1553463 ]
Nazir S, Yousaf M H and Velastin S A. 2018. Evaluating a bag-of-visual features approach using spatio-temporal features for action recognition. Computers and Electrical Engineering, 72: 660-669[DOI: 10.1016/j.compeleceng.2018.01.037]
Nowak E, Jurie F and Triggs B. 2006. Sampling strategies for bag-of-features image classification//Proceedings of the 9th European Conference on Computer Vision. Graz, Austria: Springer: 490-503[ DOI: 10.1007/11744085_38 http://dx.doi.org/10.1007/11744085_38 ]
Peng S L, Yang Y N, Liu W, Li F and Liao X K. 2019. Discriminant projection shared dictionary learning for classification of tumors using gene expression data. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2019: #2950209[DOI: 10.1109/TCBB.2019.2950209]
Wang J J, Yang J C, Yu K, Lv F J, Huang T and Gong Y H. 2010. Locality-constrained linear coding for image classification//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA: IEEE: 3360-3367[ DOI: 10.1109/CVPR.2010.5540018 http://dx.doi.org/10.1109/CVPR.2010.5540018 ]
Wang X S. 2017. Comparison analysis of epidemiological characteristics and prevention-treatment strategy of colorectal cancer in China and the United States. Chinese Journal of Colorectal Diseases, 6(6): 447-453
王锡山. 2017. 中美结直肠癌流行病学特征及防诊治策略的对比分析. 中华结直肠疾病电子杂志, 6(6): 447-453[DOI: 10.3877/cma.j.issn.2095-3224.2017.06.002]
Wang Y H and Liu H W. 2017. SAR target discrimination based on BOW model with sample-reweighted category-specific and shared dictionary learning. IEEE Geoscience and Remote Sensing Letters, 14(11): 2097-2101[DOI: 10.1109/LGRS.2017.2752763]
Yang H Q and Sun D Y. 2020. Adjunctive diagnosis of ulcerative colitis under compressed sensing. Journal of Image and Graphics, 25(8): 1684-1694
杨海清, 孙道洋. 2020. 压缩感知下溃疡性结肠炎辅助诊断. 中国图象图形学报, 25(8): 1684-1694[DOI: 10.11834/jig.200005]
Yang J C, Yu K, Gong Y H and Huang T. 2009. Linear spatial pyramid matching using sparse coding for image classification//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA: IEEE: 1794-1801[ DOI: 10.1109/CVPR.2009.5206757 http://dx.doi.org/10.1109/CVPR.2009.5206757 ]
Yang J J, Chang L P, Li S, He X X and Zhu T W. 2020. WCE polyp detection based on novel feature descriptor with normalized variance locality-constrained linear coding. International Journal of Computer Assisted Radiology and Surgery, 15(8): 1291-1302[DOI: 10.1007/s11548-020-02190-3]
Yuan Y X, Li B P and Meng M Q H. 2016. Improved bag of feature for automatic polyp detection in wireless capsule endoscopy images. IEEE Transactions on Automation Science and Engineering, 13(2): 529-535[DOI: 10.1109/TASE.2015.2395429]
Yuan Y X, Li B P and Meng M Q H. 2017. WCE abnormality detection based on saliency and adaptive locality-constrained linear coding. IEEE Transactionson Automation Science and Engineering, 14(1): 149-159[DOI:10.1109/TASE.2016.2610579]
相关作者
相关机构
京公网安备11010802024621
