Ciro Franzese1,2, Luca Cozzi3,4, Marco Badalamenti1, Davide Baldaccini1, Giuseppe D'Agostino1, Antonella Fogliata1, Pierina Navarria1, Davide Franceschini1, Tiziana Comito1, Elena Clerici1, Giacomo Reggiori1, Stefano Tomatis1, Marta Scorsetti1,2. 1. Radiotherapy and Radiosurgery Department, Humanitas Clinical and Research Center-IRCCS, via Manzoni 56, 20089, Rozzano (Mi), Italy. 2. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, 20090, Pieve Emanuele (Mi), Italy. 3. Radiotherapy and Radiosurgery Department, Humanitas Clinical and Research Center-IRCCS, via Manzoni 56, 20089, Rozzano (Mi), Italy. luca.cozzi@humanitas.it. 4. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, 20090, Pieve Emanuele (Mi), Italy. luca.cozzi@humanitas.it.
Abstract
OBJECTIVE: The present study aimed to investigate if CT-based radiomics features could correlate to the risk of metastatic progression in high-risk prostate cancer patients treated with radical RT and long-term androgen deprivation therapy (ADT). MATERIALS AND METHODS: A total of 157 patients were investigated and radiomics features extracted from the contrast-free treatment planning CT series. Three volumes were segmented: the prostate gland only (CTV_p), the prostate gland with seminal vesicles (CTV_psv), and the seminal vesicles only (CTV_sv). The patients were split into two subgroups of 100 and 57 patients for training and validation. Five clinical and 62 radiomics features were included in the analysis. Considering metastases-free survival (MFS) as an endpoint, the predictive model was used to identify the subgroups with favorable or unfavorable prognoses (separated by a threshold selected according to the Youden method). Pure clinical, pure radiomic, and combined predictive models were investigated. RESULTS: With a median follow-up of 30.7 months, the MFS at 1 and 3 years was 97.2% ± 1.5 and 92.1% ± 2.0, respectively. Univariate analysis identified seven potential predictors for MFS in the CTV_p group, 11 in the CTV_psv group, and 9 in the CTV_sv group. After elastic net reduction, these were 4 predictors for MFS in the CTV_p group (positive lymph nodes, Gleason score, H_Skewness, and NGLDM_Contrast), 5 in the CTV_psv group (positive lymph nodes, Gleason score, H_Skewnesss, Shape_Surface, and NGLDM_Contrast), and 6 in the CTV_sv group (positive lymph nodes, Gleason score, H_Kurtosis, GLCM_Correlation, GLRLM_LRHGE, and GLZLM_SZLGE). The patients' group of the training and validation cohorts were stratified into favorable and unfavorable prognosis subgroups. For the combined model, for CTV_p, the mean MFS was 134 ± 14.5 vs. 96.9 ± 22.2 months for the favorable and unfavorable subgroups, respectively, and 136.5 ± 14.6 vs. 70.5 ± 4.3 months for CTV_psv and 150.0 ± 4.2 vs. 91.1 ± 8.6 months for CTV_sv, respectively. CONCLUSION: Radiomic features were able to predict the risk of metastatic progression in high-risk prostate cancer. Combining the radiomic features and clinical characteristics can classify high-risk patients into favorable and unfavorable prognostic groups.
OBJECTIVE: The present study aimed to investigate if CT-based radiomics features could correlate to the risk of metastatic progression in high-risk prostate cancer patients treated with radical RT and long-term androgen deprivation therapy (ADT). MATERIALS AND METHODS: A total of 157 patients were investigated and radiomics features extracted from the contrast-free treatment planning CT series. Three volumes were segmented: the prostate gland only (CTV_p), the prostate gland with seminal vesicles (CTV_psv), and the seminal vesicles only (CTV_sv). The patients were split into two subgroups of 100 and 57 patients for training and validation. Five clinical and 62 radiomics features were included in the analysis. Considering metastases-free survival (MFS) as an endpoint, the predictive model was used to identify the subgroups with favorable or unfavorable prognoses (separated by a threshold selected according to the Youden method). Pure clinical, pure radiomic, and combined predictive models were investigated. RESULTS: With a median follow-up of 30.7 months, the MFS at 1 and 3 years was 97.2% ± 1.5 and 92.1% ± 2.0, respectively. Univariate analysis identified seven potential predictors for MFS in the CTV_p group, 11 in the CTV_psv group, and 9 in the CTV_sv group. After elastic net reduction, these were 4 predictors for MFS in the CTV_p group (positive lymph nodes, Gleason score, H_Skewness, and NGLDM_Contrast), 5 in the CTV_psv group (positive lymph nodes, Gleason score, H_Skewnesss, Shape_Surface, and NGLDM_Contrast), and 6 in the CTV_sv group (positive lymph nodes, Gleason score, H_Kurtosis, GLCM_Correlation, GLRLM_LRHGE, and GLZLM_SZLGE). The patients' group of the training and validation cohorts were stratified into favorable and unfavorable prognosis subgroups. For the combined model, for CTV_p, the mean MFS was 134 ± 14.5 vs. 96.9 ± 22.2 months for the favorable and unfavorable subgroups, respectively, and 136.5 ± 14.6 vs. 70.5 ± 4.3 months for CTV_psv and 150.0 ± 4.2 vs. 91.1 ± 8.6 months for CTV_sv, respectively. CONCLUSION: Radiomic features were able to predict the risk of metastatic progression in high-risk prostate cancer. Combining the radiomic features and clinical characteristics can classify high-risk patients into favorable and unfavorable prognostic groups.
Authors: Stephanie Tanadini-Lang; Marta Bogowicz; Patrick Veit-Haibach; Martin Huellner; Chantal Pauli; Vyoma Shukla; Matthias Guckenberger; Oliver Riesterer Journal: Anticancer Res Date: 2018-02 Impact factor: 2.480