Automated hepatobiliary toxicity prediction after liver stereotactic body radiation therapy with deep learning-based portal vein segmentation

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Automated hepatobiliary toxicity prediction after liver stereotactic body radiation therapy with deep learning-based portal vein segmentation. / Ibragimov, Bulat; Toesca, Diego A.S.; Chang, Daniel T.; Yuan, Yixuan; Koong, Albert C.; Xing, Lei.

I: Neurocomputing, Bind 392, 2020, s. 181-188.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Ibragimov, B, Toesca, DAS, Chang, DT, Yuan, Y, Koong, AC & Xing, L 2020, 'Automated hepatobiliary toxicity prediction after liver stereotactic body radiation therapy with deep learning-based portal vein segmentation', Neurocomputing, bind 392, s. 181-188. https://doi.org/10.1016/j.neucom.2018.11.112

APA

Ibragimov, B., Toesca, D. A. S., Chang, D. T., Yuan, Y., Koong, A. C., & Xing, L. (2020). Automated hepatobiliary toxicity prediction after liver stereotactic body radiation therapy with deep learning-based portal vein segmentation. Neurocomputing, 392, 181-188. https://doi.org/10.1016/j.neucom.2018.11.112

Vancouver

Ibragimov B, Toesca DAS, Chang DT, Yuan Y, Koong AC, Xing L. Automated hepatobiliary toxicity prediction after liver stereotactic body radiation therapy with deep learning-based portal vein segmentation. Neurocomputing. 2020;392:181-188. https://doi.org/10.1016/j.neucom.2018.11.112

Author

Ibragimov, Bulat ; Toesca, Diego A.S. ; Chang, Daniel T. ; Yuan, Yixuan ; Koong, Albert C. ; Xing, Lei. / Automated hepatobiliary toxicity prediction after liver stereotactic body radiation therapy with deep learning-based portal vein segmentation. I: Neurocomputing. 2020 ; Bind 392. s. 181-188.

Bibtex

@article{63f599036fdb45e1ac6d8dc28215494e,
title = "Automated hepatobiliary toxicity prediction after liver stereotactic body radiation therapy with deep learning-based portal vein segmentation",
abstract = "Purpose: To develop a framework for automated prediction of hepatobiliary (HB) toxicity after liver stereotactic body radiation therapy (SBRT). Materials and methods: A newly recognized toxicity type, named central or HB liver toxicity, had been reported, manifestation of which strongly correlates with the dose delivered to portal vein (PV) during SBRT. We propose a novel framework for automated HB toxicity prediction by combining deep learning-based auto-segmentation, PV anatomy analysis and the previously reported HB toxicity model. For validation of the framework, an IBR approved representative database of 72 patients treated with SBRT from primary (37) and metastatic (35) liver cancer was assembled. Each case included a pre-treatment CT, manual segmentations of tumor and PV, approved treatment plan, and the record of acute and late post-treatment toxicities. Performance of the developed framework was evaluated by quantitative comparison against manual predictions of HB toxicity, as well as post-treatment toxicity follow-ups. Results: The manual and automated predictions of HB toxicity were in agreement for 94% cases using either VBED1030 ≥ 45 cc or VBED1040 ≥ 37 cc dosimetric predictors. When compared to post-treatment follow-ups for primary liver cancer, the proposed automated framework made 86% and 83% correct predictions in comparison to 83% and 80% correct manual predictions using VBED1030 ≥ 45 cc or VBED1040 ≥ 37 cc, respectively. Conclusion: The proposed framework automates the HB toxicity prediction with the accuracy similar to manual analysis-based HB toxicity prediction. The strategy is quite general and extendable to the automated prediction of toxicities of other organs.",
keywords = "Deep learning, Primary liver cancer, SBRT, Toxicity prediction",
author = "Bulat Ibragimov and Toesca, {Diego A.S.} and Chang, {Daniel T.} and Yixuan Yuan and Koong, {Albert C.} and Lei Xing",
year = "2020",
doi = "10.1016/j.neucom.2018.11.112",
language = "English",
volume = "392",
pages = "181--188",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Automated hepatobiliary toxicity prediction after liver stereotactic body radiation therapy with deep learning-based portal vein segmentation

AU - Ibragimov, Bulat

AU - Toesca, Diego A.S.

AU - Chang, Daniel T.

AU - Yuan, Yixuan

AU - Koong, Albert C.

AU - Xing, Lei

PY - 2020

Y1 - 2020

N2 - Purpose: To develop a framework for automated prediction of hepatobiliary (HB) toxicity after liver stereotactic body radiation therapy (SBRT). Materials and methods: A newly recognized toxicity type, named central or HB liver toxicity, had been reported, manifestation of which strongly correlates with the dose delivered to portal vein (PV) during SBRT. We propose a novel framework for automated HB toxicity prediction by combining deep learning-based auto-segmentation, PV anatomy analysis and the previously reported HB toxicity model. For validation of the framework, an IBR approved representative database of 72 patients treated with SBRT from primary (37) and metastatic (35) liver cancer was assembled. Each case included a pre-treatment CT, manual segmentations of tumor and PV, approved treatment plan, and the record of acute and late post-treatment toxicities. Performance of the developed framework was evaluated by quantitative comparison against manual predictions of HB toxicity, as well as post-treatment toxicity follow-ups. Results: The manual and automated predictions of HB toxicity were in agreement for 94% cases using either VBED1030 ≥ 45 cc or VBED1040 ≥ 37 cc dosimetric predictors. When compared to post-treatment follow-ups for primary liver cancer, the proposed automated framework made 86% and 83% correct predictions in comparison to 83% and 80% correct manual predictions using VBED1030 ≥ 45 cc or VBED1040 ≥ 37 cc, respectively. Conclusion: The proposed framework automates the HB toxicity prediction with the accuracy similar to manual analysis-based HB toxicity prediction. The strategy is quite general and extendable to the automated prediction of toxicities of other organs.

AB - Purpose: To develop a framework for automated prediction of hepatobiliary (HB) toxicity after liver stereotactic body radiation therapy (SBRT). Materials and methods: A newly recognized toxicity type, named central or HB liver toxicity, had been reported, manifestation of which strongly correlates with the dose delivered to portal vein (PV) during SBRT. We propose a novel framework for automated HB toxicity prediction by combining deep learning-based auto-segmentation, PV anatomy analysis and the previously reported HB toxicity model. For validation of the framework, an IBR approved representative database of 72 patients treated with SBRT from primary (37) and metastatic (35) liver cancer was assembled. Each case included a pre-treatment CT, manual segmentations of tumor and PV, approved treatment plan, and the record of acute and late post-treatment toxicities. Performance of the developed framework was evaluated by quantitative comparison against manual predictions of HB toxicity, as well as post-treatment toxicity follow-ups. Results: The manual and automated predictions of HB toxicity were in agreement for 94% cases using either VBED1030 ≥ 45 cc or VBED1040 ≥ 37 cc dosimetric predictors. When compared to post-treatment follow-ups for primary liver cancer, the proposed automated framework made 86% and 83% correct predictions in comparison to 83% and 80% correct manual predictions using VBED1030 ≥ 45 cc or VBED1040 ≥ 37 cc, respectively. Conclusion: The proposed framework automates the HB toxicity prediction with the accuracy similar to manual analysis-based HB toxicity prediction. The strategy is quite general and extendable to the automated prediction of toxicities of other organs.

KW - Deep learning

KW - Primary liver cancer

KW - SBRT

KW - Toxicity prediction

UR - http://www.scopus.com/inward/record.url?scp=85066833513&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2018.11.112

DO - 10.1016/j.neucom.2018.11.112

M3 - Journal article

AN - SCOPUS:85066833513

VL - 392

SP - 181

EP - 188

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -

ID: 223679972