Identifying patients suitable for targeted adjuvant therapy: advances in the field of developing biomarkers for tumor recurrence following irradiation.

Introduction: Radiation therapy (RT) is commonly used to treat cancer in conjunction with chemotherapy, immunotherapy, and targeted therapies. Despite the effectiveness of RT, tumor recurrence due to treatment resistance still lead to treatment failure. RT-specific biomarkers are currently lacking and remain challenging to investigate with existing data since, for many common malignancies, standard of care (SOC) paradigms involve the administration of RT in conjunction with other agents. Areas Covered: Established clinically relevant biomarkers are used in surveillance, as prognostic indicators, and sometimes for treatment planning; however, the inability to intercept early recurrence or predict upfront resistance to treatment remains a significant challenge that limits the selection of patients for adjuvant therapy. We discuss attempts at intercepting early failure. We examine biomarkers that have made it into the clinic where they are used for treatment monitoring and management alteration, and novel biomarkers that lead the field with targeted adjuvant therapy seeking to harness these. Expert Opinion: Given the growth of data correlating interventions with omic analysis toward identifying biomarkers of radiation resistance, more robust markers of recurrence that link to biology will increasingly be leveraged toward targeted adjuvant therapy to make a successful transition to the clinic in the coming years.

AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models.

The interpretation of imaging in medicine in general and in oncology specifically remains problematic due to several limitations which include the need to incorporate detailed clinical history, patient and disease-specific history, clinical exam features, previous and ongoing treatment, and account for the dependency on reproducible human interpretation of multiple factors with incomplete data linkage. To standardize reporting, minimize bias, expedite management, and improve outcomes, the use of Artificial Intelligence (AI) has gained significant prominence in imaging analysis. In oncology, AI methods have as a result been explored in most cancer types with ongoing progress in employing AI towards imaging for oncology treatment, assessing treatment response, and understanding and communicating prognosis. Challenges remain with limited available data sets, variability in imaging changes over time augmented by a growing heterogeneity in analysis approaches. We review the imaging analysis workflow and examine how hand-crafted features also referred to as traditional Machine Learning (ML), Deep Learning (DL) approaches, and hybrid analyses, are being employed in AI-driven imaging analysis in central nervous system tumors. ML, DL, and hybrid approaches coexist, and their combination may produce superior results although data in this space is as yet novel, and conclusions and pitfalls have yet to be fully explored. We note the growing technical complexities that may become increasingly separated from the clinic and enforce the acute need for clinician engagement to guide progress and ensure that conclusions derived from AI-driven imaging analysis reflect that same level of scrutiny lent to other avenues of clinical research.

Towards effective machine learning in medical imaging analysis: A novel approach and expert evaluation of high-grade glioma 'ground truth' simulation on MRI.

PURPOSE/OBJECTIVE(S): Gliomas are uniformly fatal brain tumours with significant neurological and quality of life detriment to patients. Improvement in outcomes has remained largely unchanged in nearly 20 years. MRI (magnetic resonance imaging) is often used in diagnosis and management. Machine learning analyses of large-scale MRI data are pivotal in advancing the diagnosis, management and improve outcomes in neuro-oncology. A common challenge to robust machine learning approaches is the lack of large 'ground truth' datasets in supervised learning for building classification and prediction models. The creation of these datasets relies on human-expert input and is time-consuming and subjective error-prone, limiting effective machine learning applications. Simulation of mechanistic aspects such as geometry, location and physical properties of brain tumours can generate large-scale ground-truth datasets allowing for comparison of analysis techniques in clinical applications. We aimed to develop a transparent and convenient method for building 'ground truth' presentations of simulated glioma lesions on anatomical MRI. MATERIALS/METHODS: The simulation workflow was created using the Feature Manipulation Engine (FME®), a data integration platform specializing in the spatial data processing. By compiling and integrating FME's functions to read, integrate, transform, validate, save, and display MRI data, and experimenting with ways to manipulate the parameters concerning location, size, shape, and signal intensity with the presentations of glioma, we were able to generate simulated appearances of high-grade gliomas on gadolinium-based high-resolution 3D T1-weighted MRI (1 mm3). Data of patients with canonical high-grade tumours were used as real-world tumours for validating the accuracy of the simulation. Twenty raters who are experienced with brain tumour interpretation on MRI independently completed a survey, designed to distinguish simulated and real-world brain tumours. Sensitivity and specificity were calculated for assessing the performance of the approach with the binary classification of simulated vs real-world tumours. Correlation and regression were used in run time analysis, assessing the software toolset's efficiency in producing different numbers of simulated lesions. Differences in the group means were examined using the non-parametric Kruskal-Wallis test. RESULTS: The simulation method was developed as an interpretable and useful workflow for the easy creation of tumour simulations and incorporation into 3D MRI. A linear increase in the running time and memory usage was observed with an increasing number of generated lesions. The respondents' accuracy rate ranged between 33.3 and 83.3 %. The sensitivity and specificity were low for a human expert to differentiate simulated lesions from real gliomas (0.43 and 0.58) or vice versa (0.65 and 0.62). The mean scores ranking the real-world gliomas did not differ between the simulated and real tumours. CONCLUSION: The reliable and user-friendly software method can allow for robust simulation of high-grade glioma on MRI. Ongoing research efforts include optimizing the workflow for generating glioma datasets as well as adapting it to simulating additional MRI brain changes.

The addition of Valproic acid to concurrent radiation therapy and temozolomide improves patient outcome: a Correlative analysis of RTOG 0525, SEER and a Phase II NCI trial.

PURPOSE/OBJECTIVES: Valproic Acid (VPA) is an antiepileptic agent with HDACi (histone deacetylase inhibitor) activity shown to radiosensitize glioblastoma (GBM) cells. We evaluated the addition of VPA to standard radiation therapy (RT) and temozolomide (TMZ) in an open-label, phase II study (NCI-06-C-0112). The intent of the current study was to compare our patient outcomes with modern era standard of care data (RTOG 0525) and general population data (SEER 2006-2013). MATERIALS/METHODS: 37 patients with newly diagnosed GBM were treated in a phase II NCI trial with daily VPA (25 mg/kg) in addition to concurrent RT and TMZ (2006 - 2013) and 411 patients with newly diagnosed GBM were treated in the standard TMZ dose arm of RTOG 0525 (2006 - 2008). Using the SEER database, adult patients (age > 15) with diagnostic codes 9440-9443 (third edition (IDC-O-3) diagnosed between 2006 - 2013 were identified and 6083 were included in the analysis. Kaplan-Meier method was used to estimate OS and PFS. The effect of patient characteristics and clinical factors on OS and PFS was analyzed using univariate analysis and a Cox regression model. A landmark analysis was performed to correlate recurrence to OS and conditional probabilities of surviving an additional 12 months at diagnosis, 6, 12, 18, 24 and 30 months were calculated for both the trial data and the SEER data. RESULTS: Updated median OS in the NCI cohort was 30.9m (22.2- 65.6m), compared to RTOG 0525 18.9m (16.8-20.3m) (p= 0.007) and the SEER cohort of 11m. Median PFS in the NCI cohort was 11.1m (6.6 - 49.6m) compared to RTOG 0525 with a median PFS of 7.5m (6.9-8.2m) (p = 0.004). Younger age, class V RPA and MGMT status were significant for PFS in both the NCI cohort and the RTOG 0525 cohort, in addition KPS was also significant for OS. In comparison to RTOG 0525, the population in the NCI cohort had a more favorable KPS and RPA, and a higher proportion of patients receiving bevacizumab after protocol therapy however with the exception of RPA (V) (8% vs 18%) (0.026), the effects of these factors on PFS and OS were not significantly different between the two cohorts. CONCLUSION: Previously reported improvements in PFS and OS with the addition of VPA to concurrent RT and TMZ in the NCI phase II study were confirmed by comparison to both a trial population receiving standard of care (RTOG 0525) and a contemporary SEER cohort. These results provide further justification of a phase III trial of VPA/RT/TMZ.

Quality-of-life outcomes in high-risk prostate cancer patients treated with helical tomotherapy in a hypofractionated radiation schedule with long-term androgen suppression.

PURPOSE: We examined the impact of hypofractionated radiation therapy and androgen suppression therapy (AST) on quality of life (QOL) in high-risk prostate cancer patients. METHODS: Between March 2005 and March 2007, 60 patients with high-risk prostate cancer were enrolled in a prospective phase ii study. All patients received 68 Gy (2.72 Gy per fraction) to the prostate gland and 45 Gy (1.8 Gy per fraction) to the pelvic lymph nodes in 25 fractions over 5 weeks. Of the 60 patients, 58 received ast. The University of California-Los Angeles Prostate Cancer Index questionnaire was used to prospectively measure QOL at baseline (month 0) and at 1, 6, 12, 18, 24, 30, and 36 months after radiation treatment. The generalized estimating equation approach was used to compare the QOL scores at 1, 6, 12, 18, 24, 30, and 36 months with those at baseline. RESULTS: We observed a significant decrease in QOL items related to bowel and sexual function. Several QOL items related to bowel function were significantly adversely affected at both 1 and 6 months, with improvement toward 6 months. Although decreased QOL scores persisted beyond the 6-month mark, they began to re-approach baseline at the 18- to 24-month mark. Most sexual function items were significantly adversely affected at both 1 and 6 months, but the effects were not considered to be a problem by most patients. A complete return to baseline was not observed for either bowel or sexual function. Urinary function items remained largely unaffected, with overall urinary function being the only item adversely affected at 6 months, but not at 1 month. Urinary function returned to baseline and remained unimpaired from 18 months onwards. CONCLUSIONS: In our study population, who received hypofractionated radiation delivered using dynamic intensity-modulated radiotherapy with inclusion of the pelvic lymph nodes, and 2-3 years of ast prescription, QOL with respect to bowel and sexual function was significantly affected; QOL with respect to urinary function was largely unaffected. Our results are comparable to those in other published studies.