Development of deep neural network for individualized hepatobiliary toxicity prediction after liver SBRT

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

97 Scopus Citations
View graph of relations

Author(s)

  • Bulat Ibragimov
  • Diego Toesca
  • Daniel Chang
  • Albert Koong
  • Lei Xing

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)4763-4774
Journal / PublicationMedical Physics
Volume45
Issue number10
Online published11 Aug 2018
Publication statusPublished - Oct 2018

Abstract

Background :  Accurate prediction of radiation toxicity of healthy organs‐at‐risks (OARs) critically determines the radiation therapy (RT) success. The existing dose volume histogram‐based metric may grossly under/over‐estimate the therapeutic toxicity after 27% in liver RT and 50% in head‐and‐neck RT. We propose the novel paradigm for toxicity prediction by leveraging the enormous potential of deep learning and go beyond the existing dose/volume histograms.

Experimental Design :  We employed a database of 125 liver stereotactic body RT (SBRT) cases with follow‐up data to train deep learning‐based toxicity predictor. Convolutional neural networks (CNNs) were applied to discover the consistent patterns in 3D dose plans associated with toxicities. To enhance the predicting power, we first pre‐train the CNNs with transfer learning from 3D CT images of 2644 human organs. CNNs were then trained on liver SBRT cases. Furthermore, non‐dosimetric pre‐treatment features, such as patients’ demographics, underlying liver diseases, liver‐directed therapies, were inputted into the fully‐connected neural network for more comprehensive prediction. The saliency maps of CNNs were used to estimate the toxicity risks associated with irradiation of anatomical regions of specific OARs. In addition, we applied machine learning solutions to map numerical pre‐treatment features with hepatobiliary toxicity manifestation.

Results : Among 125 liver SBRT patients, 58 were treated for liver metastases, 36 for hepatocellular carcinoma, 27 for cholangiocarcinoma and 4 for other histologies. We observed that CNN we able to achieve accurate hepatobiliary toxicity prediction with the AUC of 0.79, whereas combining CNN for 3D dose plan analysis and fully‐connected neural networks for numerical feature analysis resulted in AUC of 0.85. Deep learning produces almost 2 times fewer false positive toxicity predictions in comparison to DVH‐based predictions, when the number of false negatives, i.e. missed toxicities, was minimized. The CNN saliency maps automatically estimated the toxicity risks for portal vein (PV) regions. We discovered that irradiation of the proximal portal vein is associated with two‐times higher toxicity risks (risk score: 0.66) that irradiation of the left portal vein (risk score: 0.31).

Conclusions :  The framework offers clinically accurate tools for hepatobiliary toxicity prediction and automatic identification of anatomical regions that are critical to spare during SBRT.

Research Area(s)

  • Convolutional neural networks, liver cancer, SBRT, toxicity prediction

Citation Format(s)

Development of deep neural network for individualized hepatobiliary toxicity prediction after liver SBRT. / Ibragimov, Bulat; Toesca, Diego; Chang, Daniel et al.
In: Medical Physics, Vol. 45, No. 10, 10.2018, p. 4763-4774.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review