Dataset Information

Radiomics-Based Outcome Prediction for Pancreatic Cancer Following Stereotactic Body Radiotherapy.

ABSTRACT: (1) Background: Radiomics use high-throughput mining of medical imaging data to extract unique information and predict tumor behavior. Currently available clinical prediction models poorly predict treatment outcomes in pancreatic adenocarcinoma. Therefore, we used radiomic features of primary pancreatic tumors to develop outcome prediction models and compared them to traditional clinical models. (2) Methods: We extracted and analyzed radiomic data from pre-radiation contrast-enhanced CTs of 74 pancreatic cancer patients undergoing stereotactic body radiotherapy. A panel of over 800 radiomic features was screened to create overall survival and local-regional recurrence prediction models, which were compared to clinical prediction models and models combining radiomic and clinical information. (3) Results: A 6-feature radiomic signature was identified that achieved better overall survival prediction performance than the clinical model (mean concordance index: 0.66 vs. 0.54 on resampled cross-validation test sets), and the combined model improved the performance slightly further to 0.68. Similarly, a 7-feature radiomic signature better predicted recurrence than the clinical model (mean AUC of 0.78 vs. 0.66). (4) Conclusion: Overall survival and recurrence can be better predicted with models based on radiomic features than with those based on clinical features for pancreatic cancer.

SUBMITTER: Parr E

PROVIDER: S-EPMC7226523 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Radiomics-Based Outcome Prediction for Pancreatic Cancer Following Stereotactic Body Radiotherapy.

Parr Elsa E Du Qian Q Zhang Chi C Lin Chi C Kamal Ahsan A McAlister Josiah J Liang Xiaoying X Bavitz Kyle K Rux Gerard G Hollingsworth Michael M Baine Michael M Zheng Dandan D

Cancers 20200424 4

(1) Background: Radiomics use high-throughput mining of medical imaging data to extract unique information and predict tumor behavior. Currently available clinical prediction models poorly predict treatment outcomes in pancreatic adenocarcinoma. Therefore, we used radiomic features of primary pancreatic tumors to develop outcome prediction models and compared them to traditional clinical models. (2) Methods: We extracted and analyzed radiomic data from pre-radiation contrast-enhanced CTs of 74 p ...[more]

PMID: 32344538

Similar Datasets

Project description:Prostate cancer is the most common non-cutaneous cancer in males. There are a number of options for patients with localized early stage disease, including active surveillance for low-risk disease, surgery, brachytherapy, and external beam radiotherapy. Increasingly, external beam radiotherapy, in the form of dose-escalated and moderately hypofractionated regimens, is being utilized in prostate cancer, with randomized evidence to support their use. Stereotactic body radiotherapy, which is a form of extreme hypofractionation, delivered with high precision and conformality typically over 1 to 5 fractions, offers a more contemporary approach with several advantages including being non-invasive, cost-effective, convenient for patients, and potentially improving patient access. In fact, one study has estimated that if half of the patients currently eligible for conventional fractionated radiotherapy in the United States were treated instead with stereotactic body radiotherapy, this would result in a total cost savings of US$250 million per year. There is also a strong radiobiological rationale to support its use, with prostate cancer believed to have a low α/β ratio and therefore being preferentially sensitive to larger fraction sizes. To date, there are no published randomized trials reporting on the comparative efficacy of stereotactic body radiotherapy compared to alternative treatment modalities, although multiple randomized trials are currently accruing. Yet, early results from the randomized phase III study of HYPOfractionated RadioTherapy of intermediate risk localized Prostate Cancer (HYPO-RT-PC) trial, as well as multiple single-arm phase I/II trials, indicate low rates of late adverse effects with this approach. In patients with low- to intermediate-risk disease, excellent biochemical relapse-free survival outcomes have been reported, albeit with relatively short median follow-up times. These promising early results, coupled with the enormous potential cost savings and implications for resource availability, suggest that stereotactic body radiotherapy will take center stage in the treatment of prostate cancer in the years to come.

Dataset Information

Radiomics-Based Outcome Prediction for Pancreatic Cancer Following Stereotactic Body Radiotherapy.

Publications

Radiomics-Based Outcome Prediction for Pancreatic Cancer Following Stereotactic Body Radiotherapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets