CT imaging markers to improve radiation toxicity prediction in prostate cancer radiotherapy by stacking regression algorithm.

PURPOSE: Radiomic features, clinical and dosimetric factors have the potential to predict radiation-induced toxicity. The aim of this study was to develop prediction models of radiotherapy-induced toxicities in prostate cancer patients based on computed tomography (CT) radiomics, clinical and dosimetric parameters. METHODS: In this prospective study, prostate cancer patients were included, and radiotherapy-induced urinary and gastrointestinal (GI) toxicities were assessed by Common Terminology Criteria for adverse events. For each patient, clinical and dose volume parameters were obtained. Imaging features were extracted from pre-treatment rectal and bladder wall CT scan of patients. Stacking algorithm and elastic net penalized logistic regression were used in order to feature selection and prediction, simultaneously. The models were fitted by imaging (radiomics model) and clinical/dosimetric (clinical model) features alone and in combinations (clinical-radiomics model). Goodness of fit of the models and performance of classifications were assessed using Hosmer and Lemeshow test, - 2log (likelihood) and area under curve (AUC) of the receiver operator characteristic. RESULTS: Sixty-four prostate cancer patients were studied, and 33 and 52 patients developed ≥ grade 1 GI and urinary toxicities, respectively. In GI modeling, the AUC for clinical, radiomics and clinical-radiomics models was 0.66, 0.71 and 0.65, respectively. To predict urinary toxicity, the AUC for radiomics, clinical and clinical-radiomics models was 0.71, 0.67 and 0.77, respectively. CONCLUSIONS: We have shown that CT imaging features could predict radiation toxicities and combination of imaging and clinical/dosimetric features may enhance the predictive performance of radiotoxicity modeling.

MRI Radiomic Analysis of IMRT-Induced Bladder Wall Changes in Prostate Cancer Patients: A Relationship with Radiation Dose and Toxicity.

BACKGROUND: The main purpose of this study was to assess the structural changes in the bladder wall of prostate cancer patients treated with intensity-modulated radiation therapy using magnetic resonance imaging texture features analysis and to correlate image texture changes with radiation dose and urinary toxicity. METHODS: Ethical clearance was granted to enroll 33 patients into this study who were treated with intensity-modulated radiation therapy for prostate cancer. All patients underwent two magnetic resonance imagings before and after radiation therapy (RT). A total of 274 radiomic features were extracted from MR-T2W-weighted images. Wilcoxon singed rank-test was performed to assess significance of the change in mean radiomic features post-RT relative to pre-RT values. The relationship between radiation dose and feature changes was assessed and depicted. Cystitis was recorded as urinary toxicity. Area under receiver operating characteristic curve of a logistic regression-based classifier was used to find correlation between radiomic features with significant changes and radiation toxicity. RESULTS: Thirty-three bladder walls were analyzed, with 11 patients developing grade ≥2 urinary toxicity. We showed that radiomic features may predict radiation toxicity and features including S5.0SumVarnc, S2.2SumVarnc, S1.0AngScMom, S0.4SumAverg, and S5. _5InvDfMom with area under receiver operating characteristic curve 0.75, 0.69, 0.65, 0.63, and 0.62 had highest correlation with toxicity, respectively. The results showed that most of the radiomic features were changed with radiation dose. CONCLUSION: Feature changes have a good correlation with radiation dose and radiation-induced urinary toxicity. These radiomic features can be identified as being potentially important imaging biomarkers and also assessing mechanisms of radiation-induced bladder injuries.

Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer.

OBJECTIVE: To develop different radiomic models based on the magnetic resonance imaging (MRI) radiomic features and machine learning methods to predict early intensity-modulated radiation therapy (IMRT) response, Gleason scores (GS) and prostate cancer (Pca) stages. METHODS: Thirty-three Pca patients were included. All patients underwent pre- and post-IMRT T2-weighted (T2 W) and apparent diffusing coefficient (ADC) MRI. IMRT response was calculated in terms of changes in the ADC value, and patients were divided as responders and non-responders. A wide range of radiomic features from different feature sets were extracted from all T2 W and ADC images. Univariate radiomic analysis was performed to find highly correlated radiomic features with IMRT response, and a paired t test was used to find significant features between responders and non-responders. To find high predictive radiomic models, tenfold cross-validation as the criterion for feature selection and classification was applied on the pre-, post- and delta IMRT radiomic features, and area under the curve (AUC) of receiver operating characteristics was calculated as model performance value. RESULTS: Of 33 patients, 15 patients (45%) were found as responders. Univariate analysis showed 20 highly correlated radiomic features with IMRT response (20 ADC and 20 T2). Two and fifteen T2 and ADC radiomic features were found as significant (P-value ≤ 0.05) features between responders and non-responders, respectively. Several cross-combined predictive radiomic models were obtained, and post-T2 radiomic models were found as high predictive models (AUC 0.632) followed by pre-ADC (AUC 0.626) and pre-T2 (AUC 0.61). For GS prediction, T2 W radiomic models were found as more predictive (mean AUC 0.739) rather than ADC models (mean AUC 0.70), while for stage prediction, ADC models had higher prediction performance (mean AUC 0.675). CONCLUSIONS: Radiomic models developed by MR image features and machine learning approaches are noninvasive and easy methods for personalized prostate cancer diagnosis and therapy.

Randomized, double-blind, placebo-controlled phase II trial of nanocurcumin in prostate cancer patients undergoing radiotherapy.

Clinical potential of curcumin in radiotherapy (RT) setting is outstanding and of high interest. The main purpose of this randomized controlled trial (RCT) was to assess the beneficial role of nanocurcumin to prevent and/or mitigate radiation-induced proctitis in prostate cancer patients undergoing RT. In this parallel-group study, 64 eligible patients with prostate cancer were randomized to receive either oral nanocurcumin (120 mg/day) or placebo 3 days before and during the RT course. Acute toxicities including proctitis and cystitis were assessed weekly during the treatment and once thereafter using CTCAE v.4.03 grading criteria. Baseline-adjusted hematologic nadirs were also analyzed and compared between the two groups. The patients undergoing definitive RT were followed to evaluate the tumor response. Nanocurcumin was well tolerated. Radiation-induced proctitis was noted in 18/31 (58.1%) of the placebo-treated patients versus 15/33 (45.5%) of nanocurcumin-treated patients (p = 0.313). No significant difference was also found between the two groups with regard to radiation-induced cystitis, duration of radiation toxicities, hematologic nadirs, and tumor response. In conclusion, this RCT was underpowered to indicate the efficacy of nanocurcumin in this clinical setting but could provide a considerable new translational insight to bridge the gap between the laboratory and clinical practice.

Rectal wall MRI radiomics in prostate cancer patients: prediction of and correlation with early rectal toxicity.

PURPOSE: To investigate MRI radiomic analysis to assess IMRT associated rectal wall changes and also for predicting radiotherapy induced rectal toxicity. MATERIAL AND METHODS: At first, a machine learning radiomic analysis was applied on T2-weighted (T2W) and apparent diffusion coefficient (ADC) rectal wall MR images of prostate cancer patients' pre- and post-IMRT to predict rectal toxicity. Next, Wilcoxon singed ranked test was performed to find radiomic features with significant changes pre- and post-IMRT. A logistic regression classifier was used to find correlation between features with significant changes and radiation toxicity. Area under the curve (AUC) of receiver operating characteristic (ROC) curve was used in two levels of study for finding performances. RESULTS: AUCmean, 0.68 ± 0.086 and 0.61 ± 0.065 were obtained for pre- and post-IMRT T2 radiomic models, respectively. For ADC radiomic models, AUCmean was 0.58 ± 0.034 for pre-IMRT and was 0.56 ± 0.038 for post-IMRT. Wilcoxon-signed rank test revealed that 9 T2 radiomic features vary significantly post-IMRT. The AUC of logistic-regression was in the range of 0.46-0.58 for single significant features and was 0.81 when all significant features were combined. CONCLUSIONS: Pre-IMRT MR image radiomic features could predict rectal toxicity in prostate cancer patients. Radiotherapy associated complications may be assessed by studying the changes in the MR radiomic features.

The role of metabolic syndrome and related clinical variables in determining CEA levels.

OBJECTIVES: The aim of the study was to investigate how metabolic syndrome (MetS) and related clinical variables correlate with high levels of carcinoembryonic antigen (CEA). MATERIAL AND METHODS: Variables related to MetS as well as the serum CEA levels of 366 subjects were assayed. Logistic regression analyses were used to determine the associations between various clinical variables and high CEA levels, which were defined as values greater than the median (i.e., 1.4 ng/mL). RESULTS: MetS, as an entity, and diabetes were more prevalent in subjects with high CEA levels (for MetS: 64.2% in subjects with CEA≥1.4 vs. 51.1% in subjects with CEA<1.4 ng/mL, p<0.05; for diabetes: 72.6% vs. 59.1% respectively, p<0.05). Waist circumference, triglycerides, fasting plasma glucose (FPG), homeostasis-model assessment of insulin resistance index (HOMA-IR), and HbA1c as well as systolic and diastolic blood pressures were directly associated with CEA levels, after adjusting for age and sex (p<0.05). Subjects with a greater number of MetS components tended to have high CEA levels. Multivariate regression analysis revealed that the association of waist circumference and FPG with CEA is independent of other MetS components, age and sex. CONCLUSIONS: MetS and related clinical variables contribute to CEA values. Thus, the reference interval of CEA may differ according to the clinical status of the subjects.

The inverse relation of CA-125 to diabetes, metabolic syndrome, and associated clinical variables.

OBJECTIVE: We aimed to evaluate the association of carbohydrate antigen 125 (CA-125; also known as cancer antigen 125) with various anthropometric and metabolic measures and also with diabetes and metabolic syndrome. METHODS: A total of 357 diabetic and nondiabetic subjects were enrolled. CA-125, anthropometric parameters, lipids, blood pressure, as well as glycemic and insulin resistance measures were assessed. Metabolic syndrome was defined according to the International Diabetes Federation (IDF) criteria. RESULTS: CA-125 was lower in subjects with diabetes and/or metabolic syndrome [median (interquartile range) of 8.20 (5.70-11.57) and 9.55 (6.50-16.25) U/mL for diabetic and nondiabetic subjects, respectively, P<0.05; 8.11 (5.90-11.45) and 9.50 (6.34-14.76) U/mL for subjects with metabolic syndrome and those without metabolic syndrome, respectively, P<0.05]. Anthropometric measures, dyslipidemia, insulin resistance, and blood pressure were inversely associated with CA-125 (P<0.05); waist circumference and body mass index were also identified as the strongest determinants of CA-125 (P<0.001). Using multiple linear regression models, waist circumference (ß=-0.088, P<0.01), apolipoprotein B (ß=-0.027, P<0.05), and systolic blood pressure (ß=-0.054, P<0.05) were independently associated with CA-125. However, none of insulin resistance measures remained in the model after adjusting for other clinical variables. CONCLUSION: CA-125 is inversely correlated with diabetes status, metabolic syndrome, and their associated anthropometric and metabolic measures. Furthermore, CA-125 is independently associated with waist circumference, apolipoprotein B, and systolic blood pressure, but not with any insulin resistance measures.