Advertisement

Multifeature Fusion Classification Method for Adaptive Endoscopic Ultrasonography Tumor Image

      Abstract

      Endoscopic ultrasonography (EUS) has been found to be of great advantage in the diagnosis of digestive tract submucosal tumors. However, EUS-based diagnosis is limited by variability in subjective interpretation on the part of doctors. Tumor classification of ultrasound images with the computer-aided diagnosis system can significantly improve the diagnostic efficiency and accuracy of doctors. In this study, we proposed a multifeature fusion classification method for adaptive EUS tumor images. First, for different ultrasound tumor images, we selected the region of interest based on prior information to facilitate the estimation in the subsequent works. Second, we proposed a method based on image gray histogram feature extraction with principal component analysis dimensionality reduction, which learns the gray distribution of different tumor images effectively. Third, we fused the reduced grayscale features with the improved local binary pattern features and gray-level co-occurrence matrix features, and then used the multiclassification support vector machine. Finally, in the experiment, we selected the 431 ultrasound images of 109 patients in the hospital and compared the experimental effects of different features and different classifiers. The results revealed that the proposed method performed best, with the highest accuracy of 96.18% and an area under the curve of 99%. It is evident that the method proposed in this study can efficiently contribute to the classification of EUS tumor images.

      Key Words

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Ultrasound in Medicine and Biology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Fugazza A
        • Fabbri C
        • Mitri R D
        • Petrone M C
        • Colombo M
        • Cugia L
        • Amato A
        • Forti E
        • Binda C
        • Maida M.
        EUS-guided choledochoduodenostomy for malignant distal biliary obstruction after failed ERCP: A retrospective nationwide analysis.
        Gastrointest Endosc. 2022; 95: 896-904
        • Teoh A
        • Leung C
        • Tam P
        • Yeung K
        • Mok R
        • Chan D
        • Chan S
        • Yip H
        • Chiu P
        • Ng E.
        EUS-guided gallbladder drainage versus laparoscopic cholecystectomy for acute cholecystitis: A propensity score analysis with 1-year follow-up data.
        Gastrointest Endosc. 2021; 93: 577-583
        • Lefort C
        • Gupta V
        • Lisotti A
        • Palazzo L
        • Fusaroli P
        • Pujol B
        • Gincul R
        • Fumex F
        • Palazzo M
        • Napoleon B
        Diagnosis of gastric submucosal tumors and estimation of malignant risk of GIST by endoscopic ultrasound: Comparison between B mode and contrast-harmonic mode (with videos).
        Digest Liver Dis. 2021; 53: 1486-1491
        • Goto O
        • Kambe H
        • Niimi K
        • Mochizuki S
        • Asada-Hirayama I
        • Minastsuki C
        • Ono S
        • Kodashima S
        • Yamamichi N
        • Yamaji Y
        • Fujishiro M
        • Koike K.
        Discrepancy in diagnosis of gastric submucosal tumor among esophagogastroduodenoscopy, CT, and endoscopic ultrasonography: A retrospective analysis of 93 consecutive cases.
        Abdom Imaging. 2012; 37: 1074-1078
        • Jackson KL
        • Devine JG.
        Endoscopic submucosal tunnel dissection for large esophageal neoplastic lesions.
        Endoscopy. 2013; 45: 60-62
        • Sajda P.
        Machine learning for detection and diagnosis of disease.
        Annu Rev Biomed Eng. 2006; 8: 537
        • Ahmadvazir S
        • Shah B N
        • Zacharias K
        • Senior R.
        Incremental prognostic value of stress echocardiography with carotid ultrasound for suspected CAD.
        JACC Cardiovasc Imaging. 2018; 11: 173-180
        • Berg WA
        • Gur D
        • Bandos AI
        • Nair B
        • Gizienski T
        • Tyma CS
        • Abrams G
        • Davis KM
        • Mehta A S
        • Rathfon G
        • Waheed UX
        • Hakim CM.
        Impact of original and artificially improved artificial intelligence-based computer-aided diagnosis on breast US interpretation.
        J Breast Imaging. 2021; 3: 301-311
        • Sudharson S
        • Kokil P.
        Computer-aided diagnosis system for the classification of multi-class kidney abnormalities in the noisy ultrasound images.
        Comput Methods Programs Biomed. 2021; 205106071
        • Cheng JZ
        • Ni D
        • Chou YH
        • Qin J
        • Tiu CM
        • Chang YC
        • Huang CS
        • Shen DG
        • Chen CM.
        Computer-aided diagnosis with deep learning architecture: Applications to breast lesions in US images and pulmonary nodules in CT scans.
        Sci Rep. 2016; 6: 24454
        • Rodriguez-Diaz E
        • Baffy G
        • Lo W K
        • Mashimo H
        • Vidyarthi G
        • Mohapatra S
        • Singh S.
        Real-time artificial intelligence-based histologic classification of colorectal polyps with augmented visualization.
        Gastrointest Endosc. 2020; 93: 662-670
        • Shaharuddin NA
        • Wan M.
        Feature analysis of kidney ultrasound image in four different ultrasound using gray level co-occurrence matrix (GLCM) and intensity histogram (IH).
        Int J Integrated Eng. 2018; 10: 42-47
        • Sharma K
        • Virmani J.
        A decision support system for classification of normal and medical renal disease using ultrasound images: A decision support system for medical renal diseases.
        Int J Ambient Comput Intell. 2017; 8: 52-69
        • Lv Y
        • Liu J
        • Zeng W.
        A method of cattle follicle ultrasound images detection based on HOG + improved LBP + SVM.
        in: 13th IEEE Conference on Industrial Electronics and Applications (ICIEA). IEEE, New York2018: 2176-2181
        • Lili W
        • Zhongliang F
        • Pan T
        • Zhu K.
        TEE standard plane classification based on improved multi-class AdaBoost algorithm.
        J Comput Appl. 2017; 37: 2253-2257
        • Shin YG
        • Yoo J
        • Kwon HJ
        • Hong JH
        • Lee HS
        • Yoon JH
        • Kim EK
        • Moon HJ
        • Han K
        • Kwak JY.
        Histogram and gray level cooccurrence matrix on gray-scale ultrasound images for diagnosing lymphocytic thyroiditis.
        Comput Biol Med. 2016; 75: 257-266
        • Vadhiraj V
        • Simpkin A
        • O'Connell J
        • Ospina N S
        • Maraka S
        • O'Keeffe DT
        Ultrasound image classification of thyroid nodules using machine learning techniques.
        Medicina. 2021; 57: 527
        • Soh LK
        • Tsatsoulis C.
        Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices.
        IEEE Trans Geosci Remote Sensing. 1999; 37: 780-795
        • Haralick R M
        • Shanmugam K
        • Dinstein I.
        Textural features for image classification.
        Studies in Media Commun. 1973; 3: 610-621
        • Ahonen T
        • Hadid A
        • Pietikainen M.
        Face description with local binary patterns: Application to face recognition.
        IEEE Trans Pattern Anal Mach Intell. 2006; 28: 2037-2041
        • Ojala T
        • Pietikainen M
        • Maenpaa T.
        Multiresolution gray-scale and rotation invariant texture classification with local binary patterns.
        IEEE Trans Pattern Anal Mach Intell. 2002; 24: 971-987
        • Zeebaree D Q
        • Haron H
        • Abdulazeez A M
        • Zebari D A
        Trainable model based on new uniform LBP feature to identify the risk of the breast cancer.
        in: 2019 International Conference on Advanced Science and Engineering (ICOASE). IEEE, New York2019: 106-111
        • Jolliffe IT.
        Principal component analysis.
        J Market Res. 2002; 87: 513
        • Chang CC
        • Lin CJ.
        LIBSVM: A library for support vector machines.
        ACM Trans Intell Syst Technol. 2011; 2: 1-27
        • Hsu CW
        • Lin CJ.
        A Comparison of Methods for Multiclass Support Vector Machines.
        IEEE Trans Neural Netw. 2002; 13: 415-425