First Report On Physician Assessment and Clinical Acceptability of Custom-Retrained Artificial Intelligence Models for Clinical Target Volume and Organs-at-Risk Auto-Delineation for Postprostatectomy Patients.

PURPOSE: To assess the clinical acceptability of a commercial deep-learning-based auto-segmentation (DLAS) prostate model that was retrained using institutional data for delineation of the clinical target volume (CTV) and organs-at-risk (OARs) for postprostatectomy patients, accounting for clinical and imaging protocol variations. METHODS AND MATERIALS: CTV and OARs of 109 prostate-bed patients were used to evaluate the performance of the vendor-trained model and custom retrained DLAS models using different training quantities. Two new models for OAR structures were retrained (n = 30, 60 data sets), while separate models were trained for a new CTV structure (n = 30, 60, 90 data sets), with the remaining data sets used for testing (n = 49, 19). The dice similarity coefficient (DSC), Hausdorff distance, and mean surface distance were evaluated. Six radiation oncologists performed a qualitative evaluation scoring both preference and clinical utility for blinded structure sets. Physician consensus data sets identified from the qualitative evaluation were used toward a separate CTV model. RESULTS: Both the 30- and 60-case retrained OAR models had median DSC values between 0.91 to 0.97, improving significantly over the vendor-trained model for all OARs except the penile bulb. The brand new 60-case CTV model had a median DSC of 0.70 improving significantly over the 30-case model. DLAS (60-case model) and manual contours were blinded and evaluated by physicians with contours deemed acceptable or precise for 87% and 94% of cases for DLAS and manual delineations, respectively. DLAS-generated CTVs were scored precise or acceptable in 54% of cases, compared with the manual delineation value of 73%. The 30-case physician consensus CTV model did not show a significant difference compared with the randomly selected models. CONCLUSIONS: Custom retraining using institutional data leads to performance improvement in the clinical utility and accuracy of DLAS for postprostatectomy patients. A small number of data sets are sufficient for building an institutional site-specific DLAS OAR model, as well as for training new structures. Data indicates the workload for identifying training data sets could be shared among groups for the male pelvic region, making it accessible to clinics of all sizes.

Response assessment in pediatric craniopharyngioma: recommendations from the Response Assessment in Pediatric Neuro-Oncology (RAPNO) Working Group.

BACKGROUND: Craniopharyngioma is a histologically benign tumor of the suprasellar region for which survival is excellent but quality of life is often poor secondary to functional deficits from tumor and treatment. Standard therapy consists of maximal safe resection with or without radiation therapy. Few prospective trials have been performed, and response assessment has not been standardized. METHODS: The Response Assessment in Pediatric Neuro-Oncology (RAPNO) committee devised consensus guidelines to assess craniopharyngioma response prospectively. RESULTS: Magnetic resonance imaging is the recommended radiologic modality for baseline and follow-up assessments. Radiologic response is defined by 2-dimensional measurements of both solid and cystic tumor components. In certain clinical contexts, response to solid and cystic disease may be differentially considered based on their unique natural histories and responses to treatment. Importantly, the committee incorporated functional endpoints related to neuro-endocrine and visual assessments into craniopharyngioma response definitions. In most circumstances, the cystic disease should be considered progressive only if growth is associated with acute, new-onset or progressive functional impairment. CONCLUSIONS: Craniopharyngioma is a common pediatric central nervous system tumor for which standardized response parameters have not been defined. A RAPNO committee devised guidelines for craniopharyngioma assessment to uniformly define response in future prospective trials.

Impact of Patient Stage and Disease Characteristics on the proposed Radiation Oncology Alternative Payment Model (RO-APM).

PURPOSE: The proposed Radiation Oncology Alternative Payment Model (RO-APM) released on July 10, 2019, represents a dramatic shift from fee-for-service (FFS) reimbursement in radiation therapy (RT). This study compares historical revenue at Mayo Clinic to the RO-APM and quantifies the effect that disease characteristics may have on reimbursement. METHODS AND MATERIALS: FFS Medicare reimbursements were determined for patients undergoing RT at Mayo Clinic from 2015 to 2016. Disease categories and payment episodes were defined as per the RO-APM. Average RT episode reimbursements were reported for each disease site, except for lymphoma and metastases, and stratified by stage and disease subcategory. Comparisons with RO-APM reimbursements were made via descriptive statistics. RESULTS: A total of 2098 patients were identified, of whom 1866 (89%) were categorized per the RO-APM; 840 (45%) of those were aged >65 years. Breast (33%), head and neck (HN) (14%), and prostate (11%) cancer were most common. RO-APM base rate reimbursements and sensitivity analysis range were lower than historical reimbursement for bladder (-40%), cervical (-34%), lung (-28%), uterine (-26%), colorectal (-24%), upper gastrointestinal (-24%), HN (-23%), pancreatic (-20%), prostate (-16%), central nervous system (-13%), and anal (-10%) and higher for liver (+24%) and breast (+36%). Historical reimbursement varied with stage (stage III vs stage I) for breast (+57%, P < .01), uterine (+53%, P = .01), lung (+50%, P < .01), HN (+24%, P = .01), and prostate (+13%, P = .01). Overall, for patients older than 65 years of age, the RO-APM resulted in a -9% reduction in total RT reimbursement compared with historical FFS (-2%, -15%, and -27% for high, mid, and low adjusted RO-APM rates). CONCLUSIONS: Our findings indicate that the RO-APM will result in significant reductions in reimbursement at our center, particularly for cancers more common in underserved populations. Practices that care for socioeconomically disadvantaged populations may face significant reductions in revenue, which could further reduce access for this vulnerable population.

Identifying the Most Costly Patients in Radiation Oncology and Predicting the Top Spenders.

PURPOSE: Quality payment programs aim to adjust payments on the basis of quality and cost; however, few quality metrics exist in radiation oncology. This study evaluates and predicts the top spenders (TS) after radiation therapy (RT). MATERIALS AND METHODS: Patient characteristics, cancer details, treatments, toxicity, and survival data were collected for patients treated with RT at Mayo Clinic from 2007 to 2016. Standardized costs were obtained and adjusted for inflation. TSs were identified as those with greater than 93rd percentile costs (≥ $120,812). Prediction models were developed to predict TSs using training and validation sets using information available at consultation, after RT, and at last follow-up. RESULTS: A total of 15,131 patients were included and 1,065 TSs identified. Mean cost overall was $55,290 (median, $39,996) for all patients. Prediction models 1, 2, and 3 had concordance statistics of 0.83 to 0.83, 0.85 to 0.85, and 0.87 to 0.88, respectively in training and validation, indicating excellent prediction of TSs. Factors that were most predictive of TSs included stage N/A and stage 4 (v stage 0; odds ratio [OR], 18.23 and 8.44, respectively; P < .001); hematologic, upper GI, skin and lung cancers (v breast; OR, 11.45, 7.69, 3.81, and 2.43, respectively; P < .01); immunotherapy, surgery, and chemotherapy use (OR, 4.36, 2.51, and 1.61, respectively; P < .01); hospitalizations within 90 days of RT (OR, 2.26; P < .01); or death during the episode (OR, 1.56; P < .01). CONCLUSION: This is the first study of its kind to predict with high accuracy the highest spenders in radiation oncology. These patients may benefit from pre-emptive management to mitigate costs, or may require exclusion or adjustment from quality payment programs.

Photon and Proton Radiation Therapy Utilization in a Population of More Than 100 Million Commercially Insured Patients.

PURPOSE: To characterize the changes in the use of radiation therapy (RT), specifically proton beam radiation therapy (PBRT), among adult and pediatric patients over a 11-year period in a very large population of insured patients. METHODS AND MATERIALS: We conducted a retrospective analysis of the OptumLabs Data Warehouse claims database of more than 100 million insured US enrollees. Descriptive analyses were undertaken to evaluate the characteristics of patients receiving RT from 2002 to 2012. RESULTS: There were 474,533 patients treated with RT from 2002 to 2012. The percentage of patients treated with 3-dimensional conformal radiation therapy, 2-dimensional RT/brachytherapy, intensity modulated radiation therapy (IMRT), stereotactic body radiation therapy (SBRT), and PBRT was 34.5%, 63.4%, 2.1%, 0.0%, and 0.1% and 40.4%, 36.0%, 21.9%, 1.1%, and 0.6% in 2002 and 2012, respectively. The greatest increase in utilization was of IMRT for prostate cancer, growing from 3.5% to 64.0%. For non-prostate cancer adults, IMRT use grew from 1.7% to 16.4%. For children, PBRT utilization increased from 0.3% to 9.7%. For prostate cancer patients, PBRT increased from 0.0% to 2.6%. For all patients, advanced technology (SBRT and PBRT) use was very low at <2%, versus 22% for IMRT. CONCLUSIONS: This is the largest and most geographically diverse description of RT utilization. Proton beam RT utilization remains very low and has had little impact on overall RT utilization compared with IMRT. The largest shift has occurred in IMRT for prostate cancer. Our findings indicate that overall utilization of proton therapy has been low and that its use has likely had little impact on national expenditures on cancer care in the current environment.

Proton therapy for sarcomas.

Sarcomas are a heterogeneous group of tumors that can occur in a wide array of anatomic sites and age ranges with varying histologies. Proton beam therapy, as compared with advanced x-ray radiation therapy techniques, can substantially lower dose to nontarget tissues. This dosimetric advantage can potentially allow for improvement of the therapeutic ratio in the treatment of many of the sarcomas by either increasing the local control, via increased dose to the target, or by decreasing the normal tissue complications, via lowered dose to the avoidance structures. This article reviews the key dosimetric studies and clinical outcomes published to date documenting the potential role proton beam therapy may play in the treatment of sarcomas.

Cine-magnetic resonance imaging assessment of intrafraction motion for prostate cancer patients supine or prone with and without a rectal balloon.

PURPOSE: Determine prostate intrafraction motion with Cine-magnetic resonance imaging (MRI) and deformable registration. METHODS: A total of 68 cine-MRI studies were done in 17 different series with 4 scans per series in 7 patients. In without rectal balloon (WORB) scans, 100 mL of water was infused in the rectum. Each series consisted of supine and prone, with a rectal balloon (WRB) and WORB. Each scan was performed over 4 minutes. Automatic deformable registration software developed by View Ray, Inc., Cleveland, Ohio was employed to segment the prostate for each cine-MRI image. A time-based analysis was done for the different positions and the use of the rectal balloon. RESULTS: The variation/standard deviation of the prostate position during 240 seconds was: supine WRB: 0.55 mm, WORB: 1.2 mm, and prone WRB: 1.48 mm, WORB: 2.15 mm (P < 0.001). A strong relationship was observed between time and prostate motion. For the initial 120 s the standard deviation was smaller than for the second 120 s supine WRB 0.54 mm versus 1.37 mm; supine WORB 0.61 mm versus 1.70 mm; prone WRB 0.85 mm versus 1.85 mm; and prone WORB 1.60 mm versus 2.56 mm. The probabilities for prostate staying within +/-2 mm to its initial position are: 94.8% supine WRB; 91.5% supine WORB; 92.3% prone WRB; 79.2% prone WORB. CONCLUSIONS: Intrafraction prostate motion was found dependent on time, patient position, and the use of a rectal balloon. Relatively stable positions can be obtained for 4 minutes or less especially in the supine position with a rectal balloon.