Evaluating the clinical acceptability of deep learning contours of prostate and organs-at-risk in an automated prostate treatment planning process.

BACKGROUND: Radiation treatment is considered an effective and the most common treatment option for prostate cancer. The treatment planning process requires accurate and precise segmentation of the prostate and organs at risk (OARs), which is laborious and time-consuming when contoured manually. Artificial intelligence (AI)-based auto-segmentation has the potential to significantly accelerate the radiation therapy treatment planning process; however, the accuracy of auto-segmentation needs to be validated before its full clinical adoption. PURPOSE: A commercial AI-based contouring model was trained to provide segmentation of the prostate and surrounding OARs. The segmented structures were input to a commercial auto-planning module for automated prostate treatment planning. This study comprehensively evaluates the performance of this contouring model in the automated prostate treatment planning process. METHODS AND MATERIALS: A 3D U-Net-based model (INTContour, Carina AI) was trained and validated on 84 computed tomography (CT) scans and tested on an additional 23 CT scans from patients treated in our local institution. Prostate and OARs contours generated by the AI model (AI contour) were geometrically evaluated against reference contours. The prostate contours were further evaluated against AI, reference, and two additional observer contours for comparison using inter-observer variation (IOV) and 3D boundaries discrepancy analyses. A blinded evaluation was introduced to assess subjectively the clinical acceptability of the AI contours. Finally, treatment plans were created from an automated prostate planning workflow using the AI contours and were evaluated for their clinical acceptability following the Radiation Therapy Oncology Group-0815 protocol. RESULTS: The AI contours demonstrated good geometric accuracy on OARs and prostate contours, with average Dice similarity coefficients (DSC) for bladder, rectum, femoral heads, seminal vesicles, and penile bulb of 0.93, 0.85, 0.96, 0.72, and 0.53, respectively. The DSC, 95% directed Hausdorff distance (HD95), and mean surface distance for the prostate were 0.83 ± 0.05, 6.07 ± 1.87 mm, and 2.07 ± 0.73 mm, respectively. No significant differences were found when comparing with IOV. In the double-blinded evaluation, 95.7% of the AI contours were scored as either "perfect" (34.8%) or "acceptable" (60.9%), while only one case (4.3%) was scored as "unacceptable with minor changes required." In total, 69.6% of the AI contours were considered equal to or better than the reference contours by an independent radiation oncologist. Automated treatment plans created from the AI contours produced similar and clinically acceptable dosimetric distributions as those from plans created from reference contours. CONCLUSIONS: The investigated AI-based commercial model for prostate segmentation demonstrated good performance in clinical practice. Using this model, the implementation of an automated prostate treatment planning process is clinically feasible.

Prescription Drug Monitoring Programs: Does the Arizona CSPMP Provide More Information than Routinely Collected in an Inpatient Psychiatric Facility?

BACKGROUND: Prescription drug monitoring programs (PDMPs) have been implemented as tools to help identify misuse of prescription medications. There has been mixed data regarding the efficacy of PDMP, and physician attitudes towards it vary. In an inpatient psychiatric hospital, history of substance use, including prescription medications, and results of urine drug screens (UDS) are obtained during the admission interview. OBJECTIVES: The aim was to determine if the substance use history and UDS are sufficient to identify substance use as compared to information obtained by Arizona's Controlled Substance Prescription Monitoring Program (CSPMP) in an inpatient setting. METHODS: A prospective chart review was completed on all newly admitted patients to the behavioral units within a 30-day period to identify those that had substance use disorder. CSPMP records were checked for all subjects for patterns of misuse. The test results were not normally distributed, so non-parametric tests were chosen for analyses. RESULTS: Of the 220 patients admitted, 127 patients had a substance use diagnosis. Out of the 127 patients, 67(30.5 %) were diagnosed with either opioid, benzodiazepine or amphetamine and stimulant use disorder. Of the 125 (56.8%) patients who had a substance use disorder, the substance abuse diagnosis had been made by the psychiatrist in the medical chart. CSPMP identified only 2 (0.8%) additional patients that were missed during the intake. CONCLUSIONS: The CSPMP provided little benefit to improving substance abuse detection when compared with the clinical interview and UDS results. This is attributed to the comprehensive evaluation done during the intake.

Laser in the management of burn scars.

BACKGROUND AND OBJECTIVE: Burn scars are associated with significant morbidity ranging from contractures, pruritus, and disfigurement to psychosocial impairment. Traditional therapies include silicone gel, compression garments, corticosteroid injections, massage therapy, and surgical procedures, however, newer and advanced therapies for the treatment of burn scars have been developed. Lasers, specifically ablative fractional lasers, show potential for the treatment of burn scars. METHODS: Both MeSH and keyword searches of the PubMed, Medline and Embase databases were performed and relevant articles were read in full for the compilation of this review. RESULTS: Fifty-one relevant observational studies, clinical trials, and systematic reviews published in English from 2006 to 2016 were reviewed and summarized. CONCLUSION: Laser therapy is effective for the treatment of burn scar appearance, including measures such as pigmentation, vascularity, pliability, and thickness. Ablative fractional laser therapy, in particular, shows significant potential for the release of contractures allowing for improved range of motion of affected joints. Patients may benefit from the use of lasers in the treatment of burn scars, and the safety profile of lasers allows the benefits of treatment to outweigh the risks. Laser therapy should be included in burn scar treatment protocols as an adjuvant therapy to traditional interventions.

The potential role of magnetic resonance spectroscopy in image-guided radiotherapy.

Magnetic resonance spectroscopy (MRS) is a non-invasive technique to detect metabolites within the normal and tumoral tissues. The ability of MRS to diagnose areas of high metabolic activity linked to tumor cell proliferation is particularly useful for radiotherapy treatment planning because of better gross tumor volume (GTV) delineation. The GTV may be targeted with higher radiation dose, potentially improving local control without excessive irradiation to the normal adjacent tissues. Prostate cancer and glioblastoma multiforme (GBM) are two tumor models that are associated with a heterogeneous tumor distribution. Preliminary studies suggest that the integration of MRS into radiotherapy planning for these tumors is feasible and safe. Image-guided radiotherapy (IGRT) by virtue of daily tumor imaging and steep dose gradient may allow for tumor dose escalation with the simultaneous integrated boost technique (SIB) and potentially decrease the complications rates in patients with GBM and prostate cancers.