Interpretable Machine Learning for Characterization of Focal Liver Lesions by Contrast-Enhanced Ultrasound

被引:26
|
作者
Turco, Simona [1 ]
Tiyarattanachai, Thodsawit [2 ]
Ebrahimkheil, Kambez [1 ]
Eisenbrey, John [3 ]
Kamaya, Aya [2 ]
Mischi, Massimo [1 ]
Lyshchik, Andrej [3 ]
El Kaffas, Ahmed [2 ]
机构
[1] Eindhoven Univ Technol, Dept Elect Engn, NL-5612 AZ Eindhoven, Netherlands
[2] Stanford Med, Dept Radiol, Stanford, CA 94305 USA
[3] Thomas Jefferson Univ, Dept Radiol, Philadelphia, PA 19107 USA
关键词
Feature extraction; Lesions; Cancer; Frequency locked loops; Liver; Ultrasonic imaging; Spatiotemporal phenomena; Medical imaging; medical signal and image processing; medical tissue characterization; ultrasound (US) contrast agents; COMPUTER-AIDED DIAGNOSIS; HEPATOCELLULAR-CARCINOMA; DCE-US; QUANTIFICATION; CEUS; ULTRASONOGRAPHY; CLASSIFICATION; ANGIOGENESIS; EFSUMB; AGENT;
D O I
10.1109/TUFFC.2022.3161719
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
This work proposes an interpretable radiomics approach to differentiate between malignant and benign focal liver lesions (FLLs) on contrast-enhanced ultrasound (CEUS). Although CEUS has shown promise for differential FLLs diagnosis, current clinical assessment is performed only by qualitative analysis of the contrast enhancement patterns. Quantitative analysis is often hampered by the unavoidable presence of motion artifacts and by the complex, spatiotemporal nature of liver contrast enhancement, consisting of multiple, overlapping vascular phases. To fully exploit the wealth of information in CEUS, while coping with these challenges, here we propose combining features extracted by the temporal and spatiotemporal analysis in the arterial phase enhancement with spatial features extracted by texture analysis at different time points. Using the extracted features as input, several machine learning classifiers are optimized to achieve semiautomatic FLLs characterization, for which there is no need for motion compensation and the only manual input required is the location of a suspicious lesion. Clinical validation on 87 FLLs from 72 patients at risk for hepatocellular carcinoma (HCC) showed promising performance, achieving a balanced accuracy of 0.84 in the distinction between benign and malignant lesions. Analysis of feature relevance demonstrates that a combination of spatiotemporal and texture features is needed to achieve the best performance. Interpretation of the most relevant features suggests that aspects related to microvascular perfusion and the microvascular architecture, together with the spatial enhancement characteristics at wash-in and peak enhancement, are important to aid the accurate characterization of FLLs.
引用
收藏
页码:1670 / 1681
页数:12
相关论文
共 50 条
  • [31] Our experiences using contrast-enhanced ultrasound in focal liver lesions
    Rettenbacher, T
    EUROPEAN RADIOLOGY, 2005, 15 : E93 - E97
  • [32] Deep CNN for Contrast-Enhanced Ultrasound Focal Liver Lesions Diagnosis
    Sirbu, Cristina Laura
    Simion, Georgiana
    Caleanu, Catalin Daniel
    2020 14TH INTERNATIONAL SYMPOSIUM ON ELECTRONICS AND TELECOMMUNICATIONS (ISETC), 2020, : 3 - 6
  • [33] Challenges in Diagnosing Focal Liver Lesions Using Contrast-Enhanced Ultrasound
    Moga, Tudor Voicu
    Lupusoru, Raluca
    Danila, Mirela
    Ghiuchici, Ana Maria
    Popescu, Alina
    Miutescu, Bogdan
    Ratiu, Iulia
    Burciu, Calin
    Bizerea-Moga, Teofana
    Voron, Anca
    Sporea, Ioan
    Sirli, Roxana
    DIAGNOSTICS, 2025, 15 (01)
  • [34] Contrast-enhanced ultrasound of the liver: basics and interpretation of common focal lesions
    Zadeh, Ehsan Safai
    Prosch, Helmut
    Ba-Ssalamah, Ahmed
    Findeisen, Hajo
    Alhyari, Amjad
    Raab, Nils
    Goerg, Christian
    ROFO-FORTSCHRITTE AUF DEM GEBIET DER RONTGENSTRAHLEN UND DER BILDGEBENDEN VERFAHREN, 2024, 196 (08): : 807 - 818
  • [35] Contrast-enhanced ultrasound for characterisation of focal liver lesions, practical advice
    Froehlich, E.
    Jenssen, C.
    Schuler, A.
    Dietrich, C. F.
    ZEITSCHRIFT FUR GASTROENTEROLOGIE, 2015, 53 (09): : 1099 - 1107
  • [36] ACCURACY OF CONTRAST ENHANCED ULTRASOUND IN CHARACTERIZATION OF FOCAL LIVER LESIONS
    Monteiro, Sara
    Magalhaes, Joana
    Leite, Slvia
    de Castro, Francisca Dias
    Carvalho, Pedro Boal
    Marinho, Carla M.
    Cotter, Jose
    GASTROENTEROLOGY, 2017, 152 (05) : S1184 - S1184
  • [37] Role of contrast enhanced ultrasound in characterization of focal liver lesions
    Thakur, Shruti
    Jhobta, Anupam
    Dhiman, D. S.
    Sood, R. G.
    Chauhan, Arun
    Thakur, Charu S.
    EGYPTIAN JOURNAL OF RADIOLOGY AND NUCLEAR MEDICINE, 2014, 45 (01): : 7 - 17
  • [38] CONTRAST-ENHANCED ULTRASOUND OF LIVER LESIONS
    Cosgrove, David O.
    ULTRASOUND IN MEDICINE AND BIOLOGY, 2010, 36 (12): : 2146 - 2146
  • [39] Characterization of focal liver lesions with contrast-enhanced low MI real time ultrasound and SonoVue
    Hohmann, J
    Skrok, J
    Puls, R
    Albrecht, T
    ROFO-FORTSCHRITTE AUF DEM GEBIET DER RONTGENSTRAHLEN UND DER BILDGEBENDEN VERFAHREN, 2003, 175 (06): : 835 - 843
  • [40] Undetermined focal liver lesions on gray-scale ultrasound in patients with fatty liver: Characterization with contrast-enhanced ultrasound
    Wang, Zhi-Li
    Tang, Jie
    Weskott, Hance Peter
    Li, Jun-Lai
    Wang, Wei
    Luo, Yu-Kun
    An, Li-Chun
    Xu, Jian-Hong
    JOURNAL OF GASTROENTEROLOGY AND HEPATOLOGY, 2008, 23 (10) : 1511 - 1519