TY - JOUR
T1 - Tumor Vascular Networks Depicted in Contrast-Enhanced Ultrasound Images as a Predictor for Transarterial Chemoembolization Treatment Response
AU - Oezdemir, Ipek
AU - Wessner, Corrine E.
AU - Shaw, Colette
AU - Eisenbrey, John R.
AU - Hoyt, Kenneth
N1 - Funding Information:
This work was supported in part by National Institutes of Health (NIH) Grants R01 CA194307 and R01 EB025841 and Cancer Prevention Research Institute of Texas (CPIRIT) Grant RP180670. GE Healthcare provided equipment support and Lantheus Medical Imaging provided the Definity. The Texas Advanced Computing Center (TACC) at the University of Texas at Austin provided high-performance computing resources that have contributed to the research results reported within this article. The authors declare that there is no conflict of interest.
Funding Information:
This work was supported in part by National Institutes of Health (NIH) Grants R01 CA194307 and R01 EB025841 and Cancer Prevention Research Institute of Texas (CPIRIT) Grant RP180670. GE Healthcare provided equipment support and Lantheus Medical Imaging provided the Definity. The Texas Advanced Computing Center (TACC) at the University of Texas at Austin provided high-performance computing resources that have contributed to the research results reported within this article.
Publisher Copyright:
© 2020 World Federation for Ultrasound in Medicine & Biology
PY - 2020/9
Y1 - 2020/9
N2 - Hepatocellular carcinoma (HCC) is prevalent worldwide. Among the various therapeutic options, transarterial chemoembolization (TACE) can be applied to the tumor vascular network by restricting the nutrients and oxygen supply to the tumor. Unique morphologic properties of this network may provide information predictive of future therapeutic responses, which would be significant for decision making during treatment planning. The extraction of morphologic features from the tumor vascular network depicted in abdominal contrast-enhanced ultrasound (CEUS) images faces several challenges, such as organ motion, limited resolution caused by clutter signal and segmentation of the vascular structures at multiple scales. In this study, we present an image processing and analysis approach for the prediction of HCC response to TACE treatment using clinical CEUS images and known pathologic responses. This method focuses on addressing the challenges of CEUS by incorporating a two-stage motion correction strategy, clutter signal removal, vessel enhancement at multiple scales and machine learning for predictive modeling. The morphologic features, namely, number of vessels (NV), number of bifurcations (NB), vessel to tissue ratio (VR), mean vessel length, tortuosity and diameter, from tumor architecture were quantified from CEUS images of 36 HCC patients before TACE treatment. Our analysis revealed that NV, NB and VR are the dominant features for the prediction of long-term TACE response. The model had an accuracy of 86% with a sensitivity and specificity of 89% and 82%, respectively. Reliable prediction of the TACE therapy response using CEUS-derived image features may help to provide personalized therapy planning, which will ultimately improve patient outcomes.
AB - Hepatocellular carcinoma (HCC) is prevalent worldwide. Among the various therapeutic options, transarterial chemoembolization (TACE) can be applied to the tumor vascular network by restricting the nutrients and oxygen supply to the tumor. Unique morphologic properties of this network may provide information predictive of future therapeutic responses, which would be significant for decision making during treatment planning. The extraction of morphologic features from the tumor vascular network depicted in abdominal contrast-enhanced ultrasound (CEUS) images faces several challenges, such as organ motion, limited resolution caused by clutter signal and segmentation of the vascular structures at multiple scales. In this study, we present an image processing and analysis approach for the prediction of HCC response to TACE treatment using clinical CEUS images and known pathologic responses. This method focuses on addressing the challenges of CEUS by incorporating a two-stage motion correction strategy, clutter signal removal, vessel enhancement at multiple scales and machine learning for predictive modeling. The morphologic features, namely, number of vessels (NV), number of bifurcations (NB), vessel to tissue ratio (VR), mean vessel length, tortuosity and diameter, from tumor architecture were quantified from CEUS images of 36 HCC patients before TACE treatment. Our analysis revealed that NV, NB and VR are the dominant features for the prediction of long-term TACE response. The model had an accuracy of 86% with a sensitivity and specificity of 89% and 82%, respectively. Reliable prediction of the TACE therapy response using CEUS-derived image features may help to provide personalized therapy planning, which will ultimately improve patient outcomes.
KW - Contrast-enhanced ultrasound
KW - Hepatocellular carcinoma
KW - Machine learning
KW - Transarterial chemoembolization
KW - Tumor vascular networks
UR - http://www.scopus.com/inward/record.url?scp=85086467643&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086467643&partnerID=8YFLogxK
U2 - 10.1016/j.ultrasmedbio.2020.05.010
DO - 10.1016/j.ultrasmedbio.2020.05.010
M3 - Article
C2 - 32561069
AN - SCOPUS:85086467643
SN - 0301-5629
VL - 46
SP - 2276
EP - 2286
JO - Ultrasound in Medicine and Biology
JF - Ultrasound in Medicine and Biology
IS - 9
ER -