Dataset Information

Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemo-radiotherapy.

ABSTRACT: INTRODUCTION:In this study, we investigate the role of radiomics for prediction of overall survival (OS), locoregional recurrence (LRR) and distant metastases (DM) in stage III and IV HNSCC patients treated by chemoradiotherapy. We hypothesize that radiomic analysis of (peri-)tumoral tissue may detect invasion of surrounding tissues indicating a higher chance of locoregional recurrence and distant metastasis. METHODS:Two comprehensive data sources were used: the Dutch Cancer Society Database (Alp 7072, DESIGN) and "Big Data To Decide" (BD2Decide). The gross tumor volumes (GTV) were delineated on contrast-enhanced CT. Radiomic features were extracted using the RadiomiX Discovery Toolbox (OncoRadiomics, Liege, Belgium). Clinical patient features such as age, gender, performance status etc. were collected. Two machine learning methods were chosen for their ability to handle censored data: Cox proportional hazards regression and random survival forest (RSF). Multivariable clinical and radiomic Cox/ RSF models were generated based on significance in univariable cox regression/ RSF analyses on the held out data in the training dataset. Features were selected according to a decreasing hazard ratio for Cox and relative importance for RSF. RESULTS:A total of 444 patients with radiotherapy planning CT-scans were included in this study: 301 head and neck squamous cell carcinoma (HNSCC) patients in the training cohort (DESIGN) and 143 patients in the validation cohort (BD2DECIDE). We found that the highest performing model was a clinical model that was able to predict distant metastasis in oropharyngeal cancer cases with an external validation C-index of 0.74 and 0.65 with the RSF and Cox models respectively. Peritumoral radiomics based prediction models performed poorly in the external validation, with C-index values ranging from 0.32 to 0.61 utilizing both feature selection and model generation methods. CONCLUSION:Our results suggest that radiomic features from the peritumoral regions are not useful for the prediction of time to OS, LR and DM.

SUBMITTER: Keek S

PROVIDER: S-EPMC7244120 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemo-radiotherapy.

Keek Simon S Sanduleanu Sebastian S Wesseling Frederik F de Roest Reinout R van den Brekel Michiel M van der Heijden Martijn M Vens Conchita C Giuseppina Calareso C Licitra Lisa L Scheckenbach Kathrin K Vergeer Marije M Leemans C René CR Brakenhoff Ruud H RH Nauta Irene I Cavalieri Stefano S Woodruff Henry C HC Poli Tito T Leijenaar Ralph R Hoebers Frank F Lambin Philippe P

PloS one 20200522 5

<h4>Introduction</h4>In this study, we investigate the role of radiomics for prediction of overall survival (OS), locoregional recurrence (LRR) and distant metastases (DM) in stage III and IV HNSCC patients treated by chemoradiotherapy. We hypothesize that radiomic analysis of (peri-)tumoral tissue may detect invasion of surrounding tissues indicating a higher chance of locoregional recurrence and distant metastasis.<h4>Methods</h4>Two comprehensive data sources were used: the Dutch Cancer Socie ...[more]

PMID: 32442178

Similar Datasets

Project description:BackgroundTo identify a computed tomography (CT) derived radiomic signature for the options of concurrent chemo-radiotherapy (CCR) in patients with non-small cell lung cancer (NSCLC).MethodsA total of 226 patients with NSCLC receiving CCR were enrolled from public dataset, and allocated to discovery and validation sets based on patient identification number. Using CT images of 153 patients in the discovery dataset, we pre-selected a list of radiomic features significantly associated with 5-year survival rate and adopted the least absolute shrinkage and selection operator regression to establish a predictive radiomic signature for CCR treatment. We performed transcriptomic analyzes of the signature, and evaluated its association with molecular lesions and immune landscapes in a dataset with matched CT images and transcriptome data. Furthermore, we identified CCR resistant genes positively correlated with resistant scores of radiomic signature and screened essential resistant genes for NSCLC using genome-scale CRIPSR data. Finally, we combined DrugBank and Genomics of Drug Sensitivity in Cancer databases to excavate candidate therapeutic agents for patients with CCR resistance, and validated them using the Connectivity Map dataset.ResultsThe radiomic signature consisting of nine features was established, and then validated in the dataset of 73 patients receiving CCR log-rank P = 0.0005, which could distinguish patients into resistance and sensitivity groups, respectively, with significantly different 5-year survival rate. Furthermore, the novel proposed radiomic nomogram significantly improved the predictive performance (concordance indexes) of clinicopathological factors. Transcriptomic analyzes linked our signature with important tumor biological processes (e.g. glycolysis/glucoseogenesis, ribosome). Then, we identified 36 essential resistant genes, and constructed a gene-agent network including 10 essential resistant genes and 35 candidate therapeutic agents, and excavated AT-7519 as the therapeutic agent for patients with CCR resistance. The therapeutic efficacy of AT-7519 was validated that significantly more resistant genes were down-regulated induced by AT-7519, and the degree gradually increased with the enhanced doses.ConclusionsThis study illustrated that radiomic signature could non-invasively predict therapeutic efficacy of patients with NSCLC receiving CCR, and indicated that patients with CCR resistance might benefit from AT-7519 or CCR treatment combined with AT-7519.

Project description:Background: Prostate cancer (PCa) influences its surrounding habitat, which tends to manifest as different phenotypic appearances on magnetic resonance imaging (MRI). This region surrounding the PCa lesion, or the peri-tumoral region, may encode useful information that can complement intra-tumoral information to enable better risk stratification. Purpose: To evaluate the role of peri-tumoral radiomic features on bi-parametric MRI (T2-weighted and Diffusion-weighted) to distinguish PCa risk categories as defined by D'Amico Risk Classification System. Materials and Methods: We studied a retrospective, HIPAA-compliant, 4-institution cohort of 231 PCa patients (n = 301 lesions) who underwent 3T multi-parametric MRI prior to biopsy. PCa regions of interest (ROIs) were delineated on MRI by experienced radiologists following which peri-tumoral ROIs were defined. Radiomic features were extracted within the intra- and peri-tumoral ROIs. Radiomic features differentiating low-risk from: (1) high-risk (L-vs.-H), and (2) (intermediate- and high-risk (L-vs.-I + H)) lesions were identified. Using a multi-institutional training cohort of 151 lesions (D1, N = 116 patients), machine learning classifiers were trained using peri- and intra-tumoral features individually and in combination. The remaining 150 lesions (D2, N = 115 patients) were used for independent hold-out validation and were evaluated using Receiver Operating Characteristic (ROC) analysis and compared with PI-RADS v2 scores. Results: Validation on D2 using peri-tumoral radiomics alone resulted in areas under the ROC curve (AUCs) of 0.84 and 0.73 for the L-vs.-H and L-vs.-I + H classifications, respectively. The best combination of intra- and peri-tumoral features resulted in AUCs of 0.87 and 0.75 for the L-vs.-H and L-vs.-I + H classifications, respectively. This combination improved the risk stratification results by 3-6% compared to intra-tumoral features alone. Our radiomics-based model resulted in a 53% accuracy in differentiating L-vs.-H compared to PI-RADS v2 (48%), on the validation set. Conclusion: Our findings suggest that peri-tumoral radiomic features derived from prostate bi-parametric MRI add independent predictive value to intra-tumoral radiomic features for PCa risk assessment.

Project description:BackgroundThe 21-gene recurrence score (RS) predicts risk of locoregional recurrence (LRR) in node-negative, estrogen receptor (ER)-positive breast cancer. We evaluated the association between RS and LRR in node-positive, ER-positive patients treated with adjuvant chemotherapy plus tamoxifen in National Surgical Adjuvant Breast and Bowel Project B-28.MethodsB-28 compared doxorubicin/cyclophosphamide (AC X 4) with AC X 4 followed by paclitaxel X 4. Tamoxifen was given to patients age 50 years or older and those younger than age 50 years with ER-positive and/or progesterone receptor-positive tumors. Lumpectomy patients received breast radiotherapy. Mastectomy patients received no radiotherapy. The present study includes 1065 ER-positive, tamoxifen-treated patients with RS assessment. Cumulative incidence functions and subdistribution hazard regression models were used for LRR to account for competing risks including distant recurrence, second primary cancers, and death from other causes. Median follow-up was 11.2 years. All statistical tests were one-sided.ResultsThere were 80 LRRs (7.5%) as first events (68% local/32% regional). RS was low: 36.2%; intermediate: 34.2%; and high: 29.6%. RS was a statistically significant predictor of LRR in univariate analyses (10-year cumulative incidence of LRR = 3.3%, 7.2%, and 12.2% for low, intermediate, and high RS, respectively, P < .001). In multivariable regression analysis, RS remained an independent predictor of LRR (hazard ratio [HR] = 2.59, 95% confidence interval [CI] = 1.28 to 5.26, for a 50-point difference, P = .008) along with pathologic nodal status (HR = 1.91, 95% CI = 1.20 to 3.03, for four or more vs one to three positive nodes, P = .006) and tumor size (HR = 1.28, 95% CI = 1.05 to 1.55, for a 1 cm difference, P = .02).ConclusionsRS statistically significantly predicts risk of LRR in node-positive, ER-positive breast cancer patients after adjuvant chemotherapy plus tamoxifen. These findings can help in the selection of appropriate candidates for comprehensive radiotherapy.

Dataset Information

Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemo-radiotherapy.

Publications

Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemo-radiotherapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets