Outcome Prediction

Treatment Outcome and Toxicity Prediction

Predicting treatment outcome and toxicity is critical to select personalized options for an individual cancer patient. Oncologic outcome data is often imbalanced, thus conventional algorithms based on a single objective such as accuracy during model construction may lead to low sensitivity or specificity.

To overcome the limitation of the current single-objective based predictive models, we propose a multi-objective model that explicitly considers both sensitivity and specificity during model optimization. Combined with an artificial immune-based optimization algorithm, the proposed multi-objective model can obtain a solution that balances sensitivity and specificity. 

We have developed models to predictive distant failure for lung and cervical cancer patients after radiation therapy. Additional systemic therapy for those patients at risk for distant failure may reduce the risk and improve overall survival.

We have also developed deep learning based models to predict toxicity for cervical cancer patients after radiotherapy. Special considerations will be given to those patients at high risk for development of treatment-related toxicity during the treatment planning stage.

Publications

  1. Chen L, Zhou Z, Sher D, Zhang Q, Shah J, Pham NL, ... Wang J. (2019) Combining many-objective radiomics and 3-dimensional convolutional neural network through evidential reasoning to predict lymph node metastasis in head and neck cancer. Phys Med Biol. (journal) (arXiv)
  2. Chen X, Zhou Z, Hannan R, Thomas K, Pedrosa I, Kapur P, ... Wang J. (2018) Reliable gene mutation prediction in clear cell renal cell carcinoma through multi-classifier multi-objective radiogenomics model. Phys Med Biol, 63(21), 215008. (journal) (arXiv)
  3. Zhou Z, Sher D, Zhang Q, Yan P, Shah J, Pham NL, ... Wang J. (2018) Multifactorial cancer treatment outcome prediction through multifaceted radiomics. arXiv preprint arXiv:1807.09212. (arXiv)
  4. Zhou Z, Chen L, Sher D, Zhang Q, Shah J, Pham NL, ... Wang J. (2018) Predicting lymph node metastasis in head and neck cancer by combining many-objective radiomics and 3-dimensional convolutional neural network through evidential reasoning. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE. 1-4. (journal)(arXiv)
  5. Chen L, Shen C, Zhou Z, Maquilan G, Thomas K, Folkert MR, ... Wang J. (2018) Accurate segmenting of cervical tumors in PET imaging based on similarity between adjacent slices. Computers in Biology and Medicine, 97, 30-36. (journal)
  6. Hao H, Zhou Z, Li S, Maquilan G, Folkert MR, Iyengar P, ... Timmerman R. (2018) Shell feature: a new radiomics descriptor for predicting distant failure after radiotherapy in non-small cell lung cancer and cervix cancer. Phys Med Biol, 63(9), 095007. (journal) (arXiv)
  7. Zhou Z, Zhou Z J, Hao H, Li S, Chen X, Zhang Y, ... Wang J. (2017) Constructing multi-modality and multi-classifier radiomics predictive models through reliable classifier fusion. arXiv preprint arXiv:1710.01614. (arXiv)
  8. Zhen X, Chen J, Zhong Z, Hrycushko B, Zhou L, Jiang S, ... Gu X. (2017) Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study. Phys Med Biol, 62(21), 8246. (journal)
  9. Zhou Z, Folkert M, Iyengar P, Westover K, Zhang Y, Choy H, ... Wang J. (2017) Multi-objective radiomics model for predicting distant failure in lung SBRT. Phys Med Biol, 62(11), 4460. (journal)
  10. Zhou Z, Folkert M, Cannon N, Iyengar P, Westover K, Zhang Y, ... Jiang S. (2016) Predicting distant failure in early stage NSCLC treated with SBRT using clinical parameters. Radiotherapy and Oncology, 119(3), 501-504. (journal)