Computer-Aided Diagnosis of Focal Liver Lesions Using Contrast-Enhanced Ultrasonography With Perflubutane Microbubbles

被引:75
作者
Kondo, Satoshi [1 ]
Takagi, Kazuya [2 ]
Nishida, Mutsumi [3 ]
Iwai, Takahito [3 ]
Kudo, Yusuke [3 ]
Ogawa, Kouji [3 ]
Kamiyama, Toshiya [3 ]
Shibuya, Hitoshi [3 ]
Kahata, Kaoru [3 ]
Shimizu, Chikara [3 ]
机构
[1] Konica Minolta Inc, Osaka 5698503, Japan
[2] Konica Minolta Inc, Tokyo 1918511, Japan
[3] Hokkaido Univ Hosp, Sapporo, Hokkaido 0608648, Japan
关键词
Computer-aided diagnosis; contrast-enhanced ultrasonography; focal liver lesion; time intensity curve; support vector machine; HEPATOCELLULAR-CARCINOMA; DIFFERENTIAL-DIAGNOSIS; NODULAR HYPERPLASIA; ULTRASOUND; CLASSIFICATION; HEMANGIOMAS; SONOGRAPHY; EFFICACY; SONOVUE; MASSES;
D O I
10.1109/TMI.2017.2659734
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This paper proposes an automatic classification method based on machine learning in contrast-enhanced ultrasonography (CEUS) of focal liver lesions using the contrast agent Sonazoid. This method yields spatial and temporal features in the arterial phase, portal phase, and post-vascular phase, as well as max-hold images. The lesions are classified as benign or malignant and again as benign, hepatocellular carcinoma (HCC), or metastatic liver tumor using support vector machines (SVM) with a combination of selected optimal features. Experimental results using 98 subjects indicated that the benign and malignant classification has 94.0% sensitivity, 87.1% specificity, and 91.8% accuracy, and the accuracy of the benign, HCC, and metastatic liver tumor classifications are 84.4%, 87.7%, and 85.7%, respectively. The selected features in the SVM indicate that combining features from the three phases are important for classifying FLLs, especially, for the benign and malignant classifications. The experimental results are consistent with CEUS guidelines for diagnosing FLLs. This research can be considered to be a validation study, that confirms the importance of using features from these phases of the examination in a quantitative manner. In addition, the experimental results indicate that for the benign and malignant classifications, the specificity without the post-vascular phase features is significantly lower than the specificity with the post-vascular phase features. We also conducted an experiment on the operator dependency of setting regions of interest and observed that the intra-operator and inter-operator kappa coefficients were 0.45 and 0.77, respectively.
引用
收藏
页码:1427 / 1437
页数:11
相关论文
共 49 条
[1]  
Ambai M, 2011, IEEE I CONF COMP VIS, P97, DOI 10.1109/ICCV.2011.6126230
[2]   Differentiation of Focal Liver Lesions: Usefulness of Parametric Imaging with Contrast-enhanced US [J].
Anaye, Anass ;
Perrenoud, Genevieve ;
Rognin, Nicolas ;
Arditi, Marcel ;
Mercier, Laurent ;
Frinking, Peter ;
Ruffieux, Christiane ;
Peetrons, Philippe ;
Meuli, Reto ;
Meuwly, Jean-Yves .
RADIOLOGY, 2011, 261 (01) :300-310
[3]   Contrast-enhanced ultrasound using a time-intensity curve for the diagnosis of renal cell carcinoma [J].
Aoki, Shigeyuki ;
Hattori, Ryohei ;
Yamamoto, Tokunori ;
Funahashi, Yasuhito ;
Matsukawa, Yoshihisa ;
Gotoh, Momokazu ;
Yamada, Yoshiaki ;
Honda, Nobuaki .
BJU INTERNATIONAL, 2011, 108 (03) :349-354
[4]  
Bakas S., 2014, EUR C RAD, P1
[5]  
Bakas S., 2015, COMPUT METHOD BIOMEC, P1
[6]  
BAKAS S, 2012, ANN BMVA, V7, P1
[7]   Spot the Best Frame: Towards Intelligent Automated Selection of the Optimal Frame for Initialisation of Focal Liver Lesion Candidates in Contrast-Enhanced Ultrasound Video Sequences [J].
Bakas, Spyridon ;
Hunter, Gordon ;
Makris, Dimitrios ;
Thiebaud, Celia .
NINTH INTERNATIONAL CONFERENCE ON INTELLIGENT ENVIRONMENTS (IE 2013), 2013, :196-203
[8]  
Bakas S, 2012, LECT NOTES COMPUT SC, V7431, P32, DOI 10.1007/978-3-642-33179-4_4
[9]   New potential and applications of contrast-enhanced ultrasound of the breast: Own investigations and review of the literature [J].
Balleyguier, Corinne ;
Opolon, Paule ;
Mathieu, Marie Christine ;
Athanasiou, Alexandra ;
Garbay, Jean Remi ;
Delaloge, Suzette ;
Drornain, Clarisse .
EUROPEAN JOURNAL OF RADIOLOGY, 2009, 69 (01) :14-23
[10]  
Caleanu C. D., 2014, P INT S EL TEL ISETC, P1, DOI DOI 10.1109/ISETC.2014.7010799