ABSTRACT
BACKGROUND: Delay in time to treatment initiation (TTI) is associated with worsened survival outcomes in laryngeal squamous cell carcinoma (LSCC). It is unclear whether this is due to tumor growth or an increased risk of metastatic disease. METHODS: This retrospective cohort study at one academic center included patients with LSCC who underwent radiotherapy/chemoradiotherapy between 2005 and 2017. We examined the association between tumor growth rate (TGR) and survival outcomes. RESULTS: Among 105 patients (mean age, 63.8 ± 11.1 years; 72% male), the threshold between "slow-growing" and "fast-growing" tumors was >0.036 mL/day (survival) and >0.082 mL/day (recurrence). Faster growth was associated with worse overall survival (OS) (hazard ratio, 1.97; 95% confidence interval [CI], 0.94-4.13) and increased recurrence (odds ratio, 9.10; 95% CI, 2.40-34.4). CONCLUSIONS: TGR >0.036 mL/day during TTI was associated with decreased OS, and >0.082 mL/day was associated with increased recurrence. Tumor measurement in patients experiencing delay may identify those who could benefit from escalated therapy.
ABSTRACT
BACKGROUND: Multiple artificial intelligence (AI)-based autocontouring solutions have become available, each promising high accuracy and time savings compared with manual contouring. Before implementing AI-driven autocontouring into clinical practice, three commercially available CT-based solutions were evaluated. MATERIALS AND METHODS: The following solutions were evaluated in this work: MIM-ProtégéAI+ (MIM), Radformation-AutoContour (RAD), and Siemens-DirectORGANS (SIE). Sixteen organs were identified that could be contoured by all solutions. For each organ, ten patients that had manually generated contours approved by the treating physician (AP) were identified, totaling forty-seven different patients. CT scans in the supine position were acquired using a Siemens-SOMATOMgo 64-slice helical scanner and used to generate autocontours. Physician scoring of contour accuracy was performed by at least three physicians using a five-point Likert scale. Dice similarity coefficient (DSC), Hausdorff distance (HD) and mean distance to agreement (MDA) were calculated comparing AI contours to "ground truth" AP contours. RESULTS: The average physician score ranged from 1.00, indicating that all physicians reviewed the contour as clinically acceptable with no modifications necessary, to 3.70, indicating changes are required and that the time taken to modify the structures would likely take as long or longer than manually generating the contour. When averaged across all sixteen structures, the AP contours had a physician score of 2.02, MIM 2.07, RAD 1.96 and SIE 1.99. DSC ranged from 0.37 to 0.98, with 41/48 (85.4%) contours having an average DSC ≥ 0.7. Average HD ranged from 2.9 to 43.3 mm. Average MDA ranged from 0.6 to 26.1 mm. CONCLUSIONS: The results of our comparison demonstrate that each vendor's AI contouring solution exhibited capabilities similar to those of manual contouring. There were a small number of cases where unusual anatomy led to poor scores with one or more of the solutions. The consistency and comparable performance of all three vendors' solutions suggest that radiation oncology centers can confidently choose any of the evaluated solutions based on individual preferences, resource availability, and compatibility with their existing clinical workflows. Although AI-based contouring may result in high-quality contours for the majority of patients, a minority of patients require manual contouring and more in-depth physician review.
Subject(s)
Artificial Intelligence , Radiotherapy Planning, Computer-Assisted , Tomography, X-Ray Computed , Humans , Radiotherapy Planning, Computer-Assisted/methods , Organs at Risk/radiation effects , Algorithms , Image Processing, Computer-Assisted/methodsABSTRACT
PURPOSE: Radiotherapy (RT) treatment and treatment planning is a complex process prepared and delivered by a multidisciplinary team of specialists. Efficient communication and notification systems among different team members are therefore essential to ensure the safe, timely delivery of treatments to patients. METHOD: To address this issue, we developed and implemented automated notification systems and an electronic whiteboard to track every CT simulation, contouring task, the new-start schedule, and physician's appointments and tasks, and notify team members of overdue and missing tasks and appointments. The electronic whiteboard was developed to have a straightforward view of current patients' planning workflow and to help different team members coordinate with each other. The systems were implemented and have been used at our center to monitor the progress of treatment-planning tasks for over 2 years. RESULTS: The last-minute plans were relatively reduced by about 40% in 2023 compared to 2021 and 2022 with a p-value < 0.05. The overdue contouring tasks of more than 1 day decreased from 46.8% in 2019 and 33.6% in 2020 to 20%-26.4% in 2021-2023 with a p-value < 0.05 after the implementation of the notification system. The rate of plans with 1-3 day planning time decreased by 20.31%, 39.32%, and 24.08% with a p-value < 0.05 and the rate of plans with 1-3 day planning time due to the contouring task overdue more than 1 day decreased by 49.49%, 56.89%, and 46.52% with a p-value < 0.05 after the implementation. The rate of outstanding appointments that are overdue by more than 7 days decreased by more than 5% with a p-value < 0.05 following the implementation of the system. CONCLUSIONS: Our experience shows that this system requires minimal human intervention, improves the treatment planning workflow and process by reducing errors and delays in the treatment planning process, positively impacts on-time treatment plan completion, and reduces the need for compressed or rushed treatment planning timelines.
Subject(s)
Neoplasms , Radiotherapy Dosage , Radiotherapy Planning, Computer-Assisted , Humans , Radiotherapy Planning, Computer-Assisted/methods , Neoplasms/radiotherapy , Radiotherapy, Intensity-Modulated/methods , Workflow , Tomography, X-Ray Computed/methodsABSTRACT
Importance: Toxic effects of concurrent chemoradiotherapy (CRT) can cause treatment interruptions and hospitalizations, reducing treatment efficacy and increasing health care costs. Physical activity monitoring may enable early identification of patients at high risk for hospitalization who may benefit from proactive intervention. Objective: To develop and validate machine learning (ML) approaches based on daily step counts collected by wearable devices on prospective trials to predict hospitalizations during CRT. Design, Setting, and Participants: This study included patients with a variety of cancers enrolled from June 2015 to August 2018 on 3 prospective, single-institution trials of activity monitoring using wearable devices during CRT. Patients were followed up during and 1 month following CRT. Training and validation cohorts were generated temporally, stratifying for cancer diagnosis (70:30). Random forest, neural network, and elastic net-regularized logistic regression (EN) were trained to predict short-term hospitalization risk based on a combination of clinical characteristics and the preceding 2 weeks of activity data. To predict outcomes of activity data, models based only on activity-monitoring features and only on clinical features were trained and evaluated. Data analysis was completed from January 2022 to March 2023. Main Outcomes and Measures: Model performance was evaluated in terms of the receiver operating characteristic area under curve (ROC AUC) in the stratified temporal validation cohort. Results: Step counts from 214 patients (median [range] age, 61 [53-68] years; 113 [52.8%] male) were included. EN based on step counts and clinical features had high predictive ability (ROC AUC, 0.83; 95% CI, 0.66-0.92), outperforming random forest (ROC AUC, 0.76; 95% CI, 0.56-0.87; P = .02) and neural network (ROC AUC, 0.80; 95% CI, 0.71-0.88; P = .36). In an ablation study, the EN model based on only step counts demonstrated greater predictive ability than the EN model with step counts and clinical features (ROC AUC, 0.85; 95% CI, 0.70-0.93; P = .09). Both models outperformed the EN model trained on only clinical features (ROC AUC, 0.53; 95% CI, 0.31-0.66; P < .001). Conclusions and Relevance: This study developed and validated a ML model based on activity-monitoring data collected during prospective clinical trials. Patient-generated health data have the potential to advance predictive ability of ML approaches. The resulting model from this study will be evaluated in an upcoming multi-institutional, cooperative group randomized trial.
Subject(s)
Chemoradiotherapy , Hospitalization , Machine Learning , Neoplasms , Humans , Male , Female , Chemoradiotherapy/adverse effects , Middle Aged , Aged , Neoplasms/drug therapy , Neoplasms/therapy , Prospective Studies , ExerciseABSTRACT
Background: Apicoectomy conceptualizes surgically maintaining a tooth with an endodontic lesion that cannot be resolved by conventional endodontic (re-) treatment. To achieve this, continuous improvement in surgical techniques, materials and instruments is being done to enhance the outcome of periapical endodontic surgeries. The purpose of this study was to compare, radiographically, the healing kinetics of platelet-rich fibrin (PRF) and mineralized freeze-dried bone allograft (FDBA) in patients undergoing apicoectomy. Materials and Methods: Nineteen patients (aged 18-40 years) were included in the study and randomly assigned to groups A or B, where they received PRF or FDBA, respectively. Following apicoectomy, PRF gel and FDBA graft were prepared and placed in the osseous defect followed by placement of PRF membrane for graft stabilization and flap closure. Radiographic follow-up was done at the 1st, 3rd, 6th and 12th months for evaluation of healing using Molven's criteria. Statistical analysis was done with Pearson's and McNemar's Chi-square tests. Results: A highly significant difference (P = 0.002) in radiographic healing was observed at 6 months. Complete healing was observed in 50% of cases in Group A whereas in Group B, none of the cases presented with complete radiographic healing. However, at the end of 12 months, complete radiographic healing was observed in both groups. Conclusion: Our data suggest that PRF accelerates bone healing as compared to FDBA and is both time and cost-efficient.
Subject(s)
Platelet-Rich Fibrin , Humans , Allografts/pathology , Allografts/transplantation , Apicoectomy , Wound HealingABSTRACT
Importance: For many types of epithelial malignant neoplasms that are treated with definitive radiotherapy (RT), treatment prolongation and interruptions have an adverse effect on outcomes. Objective: To analyze the association between RT duration and outcomes in patients with esophageal cancer who were treated with definitive chemoradiotherapy (CRT). Design, Setting, and Participants: This study was an unplanned, post hoc secondary analysis of 3 prospective, multi-institutional phase 3 randomized clinical trials (Radiation Therapy Oncology Group [RTOG] 8501, RTOG 9405, and RTOG 0436) of the National Cancer Institute-sponsored NRG Oncology (formerly the National Surgical Adjuvant Breast and Bowel Project, RTOG, and Gynecologic Oncology Group). Enrolled patients with nonmetastatic esophageal cancer underwent definitive CRT in the trials between 1986 and 2013, with follow-up occurring through 2014. Data analyses were conducted between March 2022 to February 2023. Exposures: Treatment groups in the trials used standard-dose RT (50 Gy) and concurrent chemotherapy. Main Outcomes and Measures: The outcomes were local-regional failure (LRF), distant failure, disease-free survival (DFS), and overall survival (OS). Multivariable models were used to examine the associations between these outcomes and both RT duration and interruptions. Radiotherapy duration was analyzed as a dichotomized variable using an X-Tile software to choose a cut point and its median value as a cut point, as well as a continuous variable. Results: The analysis included 509 patients (median [IQR] age, 64 [57-70] years; 418 males [82%]; and 376 White individuals [74%]). The median (IQR) follow-up was 4.01 (2.93-4.92) years for surviving patients. The median cut point of RT duration was 39 days or less in 271 patients (53%) vs more than 39 days in 238 patients (47%), and the X-Tile software cut point was 45 days or less in 446 patients (88%) vs more than 45 days in 63 patients (12%). Radiotherapy interruptions occurred in 207 patients (41%). Female (vs male) sex and other (vs White) race and ethnicity were associated with longer RT duration and RT interruptions. In the multivariable models, RT duration longer than 45 days was associated with inferior DFS (hazard ratio [HR], 1.34; 95% CI, 1.01-1.77; P = .04). The HR for OS was 1.33, but the results were not statistically significant (95% CI, 0.99-1.77; P = .05). Radiotherapy duration longer than 39 days (vs ≤39 days) was associated with a higher risk of LRF (HR, 1.32; 95% CI, 1.06-1.65; P = .01). As a continuous variable, RT duration (per 1 week increase) was associated with DFS failure (HR, 1.14; 95% CI, 1.01-1.28; P = .03). The HR for LRF 1.13, but the result was not statistically significant (95% CI, 0.99-1.28; P = .07). Conclusions and Relevance: Results of this study indicated that in patients with esophageal cancer receiving definitive CRT, prolonged RT duration was associated with inferior outcomes; female patients and those with other (vs White) race and ethnicity were more likely to have longer RT duration and experience RT interruptions. Radiotherapy interruptions should be minimized to optimize outcomes.
Subject(s)
Esophageal Neoplasms , Humans , Male , Female , Middle Aged , Prospective Studies , Randomized Controlled Trials as Topic , Esophageal Neoplasms/drug therapy , Esophageal Neoplasms/radiotherapy , Disease-Free Survival , Progression-Free SurvivalABSTRACT
BACKGROUND: Data for proton therapy in high-risk prostate cancer (HRPC) are limited. Using the Proton Collaborative Group prospective registry, we evaluated outcomes for HRPC patients treated with proton therapy. METHODS: A totsl of 605 men with localized HRPC treated with proton therapy from 8/2009 to 3/2019 at nine institutions were selected. Outcomes examined included freedom from progression (FFP), metastasis free survival (MFS), overall survival (OS), and toxicity. Multivariable cox/binomial regression models were used to assess predictors of FFP and toxicity. RESULTS: Median age was 71 years. Gleason grade groups 4 (49.4%) and 5 (31.7%) were most common, as were clinical stage T1c (46.1%) and cT2 (41.3%). The median pretreatment prostate specific antigen (PSA) was 9.18 and median International Prostate Symptom Score (IPSS) was 6. Androgen deprivation therapy was given in 63.6%. Median dose was 79.2 GyE in 44 fractions. Pelvic lymph nodes were treated in 58.2% of cases. Pencil beam scanning was used in 54.5%, uniform scanning in 38.8%, and a rectal spacer in 14.2%. At a median followup of 22 months, the 3- and 5-year FFP were 90.7% and 81.4%, respectively. Five-year MFS and OS were 92.8% and 95.9%, respectively. Independent correlates of FFP included Gleason ≥8, PSA > 10, and cT2 (all p < 0.05). No grade 4 or 5 adverse events were reported. There were 23 (5%) grade 2 and 0 grade 3 gastrointestinal events. Prevalence of late grade 3, late grade 2, acute grade 3, and acute grade 2 genitourinary toxicity was 1.7%, 5.8%, 0%, and 21.8%, respectively. Prevalence of grade 2 and 3 erectile dysfunction at 2 years was 48.4% and 8.4%, respectively. CONCLUSIONS: In the largest series published to date, our results suggest early outcomes using proton therapy for HRPC are encouraging for both safety and efficacy. Further evaluation is needed to determine if an advantage exists to use protons over other radiation techniques in this population.
Subject(s)
Prostatic Neoplasms , Proton Therapy , Male , Humans , Aged , Prostate-Specific Antigen , Protons , Proton Therapy/adverse effects , Proton Therapy/methods , Prostatic Neoplasms/drug therapy , Androgen Antagonists/therapeutic useABSTRACT
BACKGROUND: Residents of the Bronx suffer marked health disparities due to socioeconomic and other factors. The coronavirus disease 2019 pandemic worsened these health outcome disparities and health care access disparities, especially with the abrupt transition to online care. OBJECTIVES: This study classified electronic health literacy (EHL) among patients at an urban, academic hospital in the Bronx, and assessed for associations between EHL levels and various demographic characteristics. METHODS: We designed a cross-sectional, observational study in adults 18 years or older presenting to the Montefiore Einstein Center for Cancer Care (MECCC) Department of Radiation Oncology or the Montefiore Department of Medicine in the Bronx. We assessed EHL using the eHealth Literacy Scale (eHEALS) survey, a previously validated tool, and our newly developed eHealth Literacy Objective Scale-Scenario Based (eHeLiOS-SB) tool. RESULTS: A total of 97 patients recruited from the MECCC and Department of Medicine participated in this study. There was a statistically significant association between age and EHL as assessed by both eHEALS and eHeLiOS-SB, with older adults having lower EHL scores. Additionally, a question designed to assess general attitudes toward digital health technologies found that most participants had a positive attitude toward such applications. CONCLUSION: Many patients, especially older adults, may require additional support to effectively navigate telehealth. Further research is warranted to optimize telemedicine strategies in this potentially-marginalized population and ultimately to create telehealth practices accessible to patients of all ages and demographics.
Subject(s)
COVID-19 , Health Literacy , Telemedicine , Humans , Aged , Cross-Sectional Studies , COVID-19/epidemiology , Electronics , Surveys and Questionnaires , Hospitals , InternetABSTRACT
Purpose: Financial toxicity (FT) is a significant concern for patients with cancer. We reviewed prospectively collected data to explore associations with FT among patients undergoing concurrent, definitive chemoradiation therapy (CRT) within a diverse, urban, academic radiation oncology department. Methods and Materials: Patients received CRT in 1 of 3 prospective trials. FT was evaluated before CRT (baseline) and then weekly using the European Organization for Research and Treatment of Cancer Core Quality of Life Questionnaire Core-30 questionnaire. Patients were classified as experiencing FT if they answered ≥2 on a Likert scale question (1-4 points) asking if they experienced FT. Rate of change of FT was calculated using linear regression; worsening FT was defined as increase ≥1 point per month. χ2, t tests, and logistic regression were used to assess predictors of FT. Results: Among 233 patients, patients attended an average of 9 outpatient and 4 radiology appointments over the 47 days between diagnosis and starting CRT. At baseline, 52% of patients reported experiencing FT. Advanced T stage (odds ratio, 2.47; P = .002) was associated with baseline FT in multivariate analysis. The mean rate of FT change was 0.23 Likert scale points per month. In total, 26% of patients demonstrated worsening FT during CRT. FT at baseline was not associated with worsening FT (P = .98). Hospitalization during treatment was associated with worsening FT (odds ratio, 2.30; P = .019) in multivariate analysis. Conclusions: Most patients reported FT before CRT. These results suggest that FT should be assessed (and, potentially, addressed) before starting definitive treatment because it develops early in a patient's cancer journey. Reducing hospitalizations may mitigate worsening FT. Further research is warranted to design interventions to reduce FT and avoid hospitalizations.
ABSTRACT
The purpose of this study is to investigate the dosimetric accuracy of prostate SBRT when motion is considered. To account for target movement, motion compensation and gating techniques were investigated with PTV margins reduced to 2 mm. To allow for dosimetric measurements a Delta4 phantom, Gafchromic film, and Hexamotion motion platform were utilized. Four motion files were utilized that represent a range of motions. Analysis of measured prostate motions for fifteen patients was performed to ensure detected motions were similar to those previously reported and motion files utilized were suitable. Five patient plans were utilized to allow for the effects of MLC and target motion interplay to be investigated. For both motion compensation and gating techniques, plans were delivered to the stationary phantom and for each of four motion types with/without compensation/gating enabled. Using a 3%, 2 mm and 80% threshold gamma criteria, film measurements had an average pass rate of 80.5% for uncorrected deliveries versus 96.0% for motion compensated deliveries. For gated techniques average pass rates increased from 89.9% for uncorrected to 94.8% with gating enabled. Measurements with the Delta4 arrays were analyzed with a 3%, 2 mm and 10% threshold dose. An average pass rate of 83.8% was measured for uncorrected motions versus 94.8% with motion compensation. For the gated technique an average pass rate of 87.2% was found for uncorrected motions versus 96.9% with gating enabled. These results show that very high gamma pass rates are achievable when motion compensation or gating techniques are applied. When target motion is not accounted for shifts up to 5 mm in planned versus delivered isodose distributions were found. However, when motion compensation, or gated techniques were applied, much smaller differences between planned and delivered isodose distributions were found. With these techniques dose delivery accuracy is greatly improved, allowing for PTV margins to be reduced.
Subject(s)
Radiosurgery , Radiotherapy, Intensity-Modulated , Male , Humans , Prostate , Radiosurgery/methods , Radiotherapy, Intensity-Modulated/methods , Radiotherapy Planning, Computer-Assisted/methods , Motion , Movement , Radiometry/methods , Radiotherapy DosageABSTRACT
PURPOSE: Given the increasing availability of radiation therapy in sub-Saharan Africa, clinical trials that include radiation therapy are likely to grow. Ensuring appropriate delivery of radiation therapy through rigorous quality assurance is an important component of clinical trial execution. We reviewed the process for credentialing radiation therapy sites and radiation therapy quality assurance through the Imaging and Radiation Oncology Core (IROC) Houston Quality Assurance Center for AIDS Malignancy Consortium (AMC)-081, a multicenter study of cisplatin and radiation therapy for women with locally advanced cervical cancer living with HIV, conducted by the AIDS Malignancy Consortium at 2 sites in South Africa and Zimbabwe. METHODS AND MATERIALS: Women living with HIV with newly diagnosed stage IB2, IIA (>4 cm), IIB-IVA cervical carcinoma (per the 2009 International Federation of Gynecology and Obstetrics [FIGO] staging classifications) were enrolled in AMC-081. They received 3-dimensional conformal external beam radiation therapy (EBRT) to the pelvis (41.4-45 Gy) using a linear accelerator, high-dose-rate brachytherapy (6-9 Gy to point A with each fraction and up to 4 fractions), and concurrent weekly cisplatin (40 mg/m2). IROC reviewed EBRT and brachytherapy quality assurance records after treatment. RESULTS: All of the 38 women enrolled in AMC-081 received ±5% of the protocol-specified prescribed dose of EBRT. Geometry of brachytherapy applicator placement was scored as per protocol in all implants. Doses to points A and B, International Commission on Radiation Units and Measurements (ICRU) bladder, or ICRU rectum required correction by IROC in >50% of the implants. In the final evaluation, 58% of participants (n = 22) were treated per protocol, 40% (n = 15) had minor protocol deviations, and 3% (n = 1) had major protocol deviations. No records were received within 60 days of treatment completion as requested in the protocol. CONCLUSIONS: Major radiation therapy deviations were low, but timely submission of radiation therapy data did not occur. Future studies, especially those that include specialized radiation therapy techniques such as stereotactic or intensity-modulated radiation therapy, will require pathways to ensure timely and adequate quality assurance.
Subject(s)
Acquired Immunodeficiency Syndrome , Brachytherapy , Neoplasms , Uterine Cervical Neoplasms , Female , Humans , Cisplatin/therapeutic use , Brachytherapy/methods , Radiotherapy Dosage , Africa South of the Sahara , Neoplasms/pathology , Uterine Cervical Neoplasms/pathology , Neoplasm Staging , Multicenter Studies as TopicABSTRACT
BACKGROUND: We investigate the impact of gender, race, and socioeconomic status on the diagnosis and management of bladder cancer in the United States. METHODS: We utilized the National Cancer Database to stratify cases of urothelial cell carcinoma of the bladder as early (Tis, Ta, T1), muscle invasive (T2-T3, N0), locally advanced (T4, N1-3), and metastatic. Multivariate binomial and multinomial logistic regression analyses identified demographic characteristics associated with stage at diagnosis and receipt of cancer-directed therapies. Odds ratios (OR) are reported with 95% confidence intervals. RESULTS: After exclusions, we identified 331,714 early, 72,154 muscle invasive, 15,579 locally advanced, and 15,161 metastatic cases from 2004-2016. Relative to diagnosis at early stage, the strongest independent predictors of diagnosis at muscle invasive, locally advanced, and metastatic disease included Black race (OR = 1.19 [1.15-1.23], OR = 1.49 [1.40-1.59], OR = 1.66 [1.56-1.76], respectively), female gender (OR = 1.21 [1.18-1.21], OR = 1.16 [1.12-1.20], and OR = 1.34 [1.29-1.38], respectively), and uninsured status (OR = 1.22 [1.15-1.29], OR = 2.09 [1.94-2.25], OR = 2.57 [2.39-2.75], respectively). Additional demographic factors associated with delayed diagnosis included older age, treatment at an academic center, Medicaid insurance and patients from lower income/less educated/more rural areas (all p < 0.01). Treatment at a non-academic center, older age, women, Hispanic and Black patients, lower income and rural areas were all less likely to receive cancer-directed therapies in early stage disease (all p < 0.01). Women, older patients, and Black patients remained less likely to receive treatment in muscle invasive, locally advanced, and metastatic disease (all p < 0.01). CONCLUSION: Black race was the strongest independent predictor of delayed diagnosis and substandard treatment of bladder cancer.
Subject(s)
Carcinoma, Transitional Cell , Urinary Bladder Neoplasms , Humans , Female , United States/epidemiology , Urinary Bladder Neoplasms/diagnosis , Urinary Bladder Neoplasms/therapy , Urinary Bladder Neoplasms/pathology , Medicaid , Hispanic or Latino , Black People , Healthcare DisparitiesABSTRACT
Novel toxicity metrics that account for all adverse event (AE) grades and the frequency of may enhance toxicity reporting in clinical trials. The Toxicity Index (TI) accounts for all AE grades and frequencies for categories of interest. We evaluate the feasibility of using the TI methodology in 2 prospective anal cancer trials and to evaluate whether more conformal radiation (using Intensity Modulated Radiation Therapy) results in improved toxicity as measured by the TI. Patients enrolled on NRG/RTOG 0529 or nonconformal RT enrolled on the 5-Fluorouracil/Mitomycin arm of NRG/RTOG 9811 were compared using the TI. Patients treated on NRG/RTOG 0529 had lower median TI compared with patients treated with nonconformal RT on NRG/RTOG 9811 for combined GI/GU/Heme/Derm events (3.935 vs 3.996, P=0.014). The TI methodology is a feasible method to assess all AEs of interest and may be useful as a composite metric for future efforts aimed at treatment de-escalation or escalation.
Subject(s)
Anus Neoplasms , Radiotherapy, Conformal , Radiotherapy, Intensity-Modulated , Humans , Prospective Studies , Anus Neoplasms/radiotherapy , Radiotherapy, Intensity-Modulated/adverse effects , Radiotherapy, Intensity-Modulated/methods , Fluorouracil/adverse effectsABSTRACT
BACKGROUND: To evaluate the change in parotid glands at mid-treatment during IMRT and the association between radiation dose to the parotid gland stem cell (PGSC) region and patient-reported xerostomia for patients with head and neck cancer (HNC). MATERIAL AND METHODS: Patients who were treated from 2006-2012 at our institution with patient-reported xerostomia outcomes available at least 9 months following RT were included. PG and PGSC regions were delineated and the dose was estimated from the treatment plan dose distribution, using contours from pre- and mid-treatment CT scans. The association between radiation dose and volumetric changes was assessed using linear regression. Univariable logistic regression, logistic dose-response curves, and receiver operating characteristics (ROC) were used to examine the relationship between radiation dose and patient-reported xerostomia. RESULTS: Sixty-three patients were included, most treated with 70 Gy in 33 fractions; 34 patients had mid-treatment CT scans. Both contralateral and ipsilateral PGs had considerable volume reduction from baseline to mid-treatment (25% and 27%, respectively, both p < .001), significantly associated with mean PG dose (-0.44%/Gy, p = .008 and -0.54%/Gy, p < .001, respectively). There was a > 5 Gy difference in mean PG and PGSC dose for 8/34 patients at mid-treatment, with 6/8 (75%) reporting severe xerostomia. Xerostomia prediction based on whole PG or PGSC region dose showed similar performance (ROC AUC 0.754 and 0.749, respectively). The corresponding dose-response models also predicted similar risk of patient-reported xerostomia with mean dose to the contralateral PG (32.5%) or PGSC region (31.4%) at the 20 Gy QUANTEC-recommended sparing level. CONCLUSIONS: The radiation dose to the PGSC region did not show stronger association with patient-reported xerostomia compared to that of whole PG, possibly due to considerable anatomical changes identified at mid-treatment. This shift in the size and position of the PG warrants adaptive planning strategies to evaluate the true benefit of parotid stem cell sparing.
Subject(s)
Head and Neck Neoplasms , Radiotherapy, Intensity-Modulated , Xerostomia , Humans , Parotid Gland/diagnostic imaging , Radiotherapy, Intensity-Modulated/adverse effects , Radiotherapy Dosage , Head and Neck Neoplasms/radiotherapy , Xerostomia/etiology , Stem CellsABSTRACT
PURPOSE: Liver-directed therapy after transarterial chemoembolization (TACE) can lead to improvement in survival for selected patients with unresectable hepatocellular carcinoma (HCC). However, there is uncertainty in the appropriate application and modality of therapy in current clinical practice guidelines. The aim of this study was to develop a proof-of-concept, machine learning (ML) model for treatment recommendation in patients previously treated with TACE and select patients who might benefit from additional treatment with combination stereotactic body radiotherapy (SBRT) or radiofrequency ablation (RFA). METHODS: This retrospective observational study was based on data from an urban, academic hospital system selecting for patients diagnosed with stage I-III HCC from January 1, 2008, to December 31, 2018, treated with TACE, followed by adjuvant RFA, SBRT, or no additional liver-directed modality. A feedforward, ML ensemble model provided a treatment recommendation on the basis of pairwise assessments evaluating each potential treatment option and estimated benefit in survival. RESULTS: Two hundred thirty-seven patients met inclusion criteria, of whom 54 (23%) and 49 (21%) received combination of TACE and SBRT or TACE and RFA, respectively. The ML model suggested a different consolidative modality in 32.7% of cases among patients who had previously received combination treatment. Patients treated in concordance with model recommendations had significant improvement in progression-free survival (hazard ratio 0.5; P = .007). The most important features for model prediction were cause of cirrhosis, stage of disease, and albumin-bilirubin grade (a measure of liver function). CONCLUSION: In this proof-of-concept study, an ensemble ML model was able to provide treatment recommendations for HCC who had undergone prior TACE. Additional treatment in line with model recommendations was associated with significant improvement in progression-free survival, suggesting a potential benefit for ML-guided medical decision making.
Subject(s)
Carcinoma, Hepatocellular , Chemoembolization, Therapeutic , Liver Neoplasms , Artificial Intelligence , Carcinoma, Hepatocellular/pathology , Carcinoma, Hepatocellular/therapy , Chemoembolization, Therapeutic/adverse effects , Combined Modality Therapy , Humans , Liver Neoplasms/therapyABSTRACT
OBJECTIVE: To quantify the clinical performance of a machine learning (ML) algorithm for organ-at-risk (OAR) dose prediction for lung stereotactic body radiation therapy (SBRT) and estimate the treatment planning benefit from having upfront access to these dose predictions. METHODS: ML models were trained using multi-center data consisting of 209 patients previously treated with lung SBRT. Two prescription levels were investigated, 50 Gy in five fractions and 54 Gy in three fractions. Models were generated using a gradient-boosted regression tree algorithm using grid searching with fivefold cross-validation. Twenty patients not included in the training set were used to test OAR dose prediction performance, ten for each prescription. We also performed blinded re-planning based on OAR dose predictions but without access to clinically delivered plans. Differences between predicted and delivered doses were assessed by root-mean square deviation (RMSD), and statistical differences between predicted, delivered, and re-planned doses were evaluated with one-way analysis of variance (ANOVA) tests. RESULTS: ANOVA tests showed no significant differences between predicted, delivered, and replanned OAR doses (all p ≥ 0.36). The RMSD was 2.9, 3.9, 4.3, and 1.7Gy for max dose to the spinal cord, great vessels, heart, and trachea, respectively, for 50 Gy in five fractions. Average improvements of 1.0, 1.4, and 2.0 Gy were seen for spinal cord, esophagus, and trachea max doses in blinded replans compared to clinically delivered plans with 54 Gy in three fractions, and 1.8, 0.7, and 1.5 Gy, respectively, for the esophagus, heart and bronchus max doses with 50 Gy in five fractions. Target coverage was similar with an average PTV V100% of 94.7% for delivered plans compared to 97.3% for blinded re-plans for 50 Gy in five fractions, and respectively 98.4% versus 99.2% for 54 Gy in three fractions. CONCLUSION: This study validated ML-based OAR dose prediction for lung SBRT, showing potential for improved OAR dose sparing and more consistent plan quality using dose predictions for patient-specific planning guidance.
Subject(s)
Lung Neoplasms , Radiosurgery , Radiotherapy, Intensity-Modulated , Algorithms , Humans , Lung , Lung Neoplasms/radiotherapy , Lung Neoplasms/surgery , Machine Learning , Organs at Risk , Radiotherapy Dosage , Radiotherapy Planning, Computer-AssistedABSTRACT
BACKGROUND AND PURPOSE: Disease recurrence and distant metastases (DM) are major concerns for oropharyngeal cancer (OPC) patients receiving definitive chemo-radiotherapy. Here, we investigated whether pre-treatment primary tumor positron emission tomography (PET) features could predict progression-free survival (PFS) or DM. METHODS AND MATERIALS: Primary tumors were delineated on pre-treatment PET scans for patients treated between 2005 and 2018 using gradient-based segmentation. Radiomic image features were extracted, along with SUV metrics. Features with zero variance and strong correlation to tumor volume, stage, p16 status, age or smoking were excluded. A random forest model was used to identify features associated with PFS. Kaplan-Meier methods, Cox regression and logistic regression with receiver operating characteristics (ROC) and 5-fold cross-validated areas-under-the-curve (CV-AUCs) were used. RESULTS: A total of 114 patients were included. With median follow-up 40 months (range: 3-138 months), 14 patients had local recurrence, 21 had DM and 38 died. Two-year actuarial local control, distant control, PFS and overall survival was 89%, 84%, 70% and 84%, respectively. The wavelet_LHL_GLDZM_LILDE feature slightly improved PFS prediction compared to clinical features alone (CV-AUC 0.73 vs. 0.71). Age > 65 years (HR = 2.64 (95%CI: 1.36-5.2), p = 0.004) and p16-negative disease (HR = 3.38 (95%CI: 1.72-6.66), p < 0.001) were associated with poor PFS. A binary radiomic classifier strongly predicted DM with multivariable HR = 3.27 (95%CI: 1.15-9.31), p = 0.027, specifically for patients with p16-negative disease with 2-year DM-free survival 83% for low-risk vs. 38% for high-risk patients (p = 0.004). CONCLUSIONS: A radiomics signature strongly associated with DM risk could provide a tool for improved risk stratification, potentially adding adjuvant immunotherapy for high-risk patients.
ABSTRACT
PURPOSE: To assess clinically relevant image quality metrics (IQMs) of helical fan beam kilovoltage (kV) fan beam computed tomography (CT). METHODS AND MATERIALS: kVCT IQMs were evaluated on an Accuray Radixact unit equipped with helical fan beam kVCT to assess the capabilities of this newly available modality. kVCT IQMs were evaluated and compared to a kVCT simulator and linear accelerator-based cone beam CTs (CBCT) using a commercial CBCT image quality phantom. kVCTs were acquired on the Accuray Radixact for all combinations of kVp and mAs in fine mode using a 440-mm field of view (FOV). Evaluated IQMs were spatial resolution, overall uniformity, subject contrast, contrast-to-noise ratio (CNR), and effective slice thickness. Imaging dose was assessed for planar kV imaging. RESULTS: On this kVCT system spatial resolution and contrast were consistent across all settings with 0.28 ± 0.03 lp/mm and 9.8% ± 0.7% (both 95% confidence interval). CNR strongly depended on selected mode (views per rotation) and body size (mA per view) and ranged between 7.9 and 34.9. Overall uniformity was greater than 97% for all settings. Large FOV was not found to substantially affect the IQMs whereas small FOV affected IQMs due to its effect on pitch. Technique-matched CT simulator scans were comparable for uniformity and contrast, while spatial resolution was higher (0.43 ± 0.06 lp/mm), and CNR was between 4% (140 kVp) and 51% (100 kVp) lower. For kV-CBCT, spatial resolutions ranging from 0.37 to 0.44 lp/mm were achieved with comparable contrast, CNR, and uniformity to kVCT. All kVCT scans exhibit imaging artifacts due to helical acquisition. Clinical acquisitions of megavoltage (MV) CT, kV-CBCT, and kVCT on the same patient showed improved and comparable image quality of kVCT compared to MVCT and kV-CBCT, respectively. CONCLUSIONS: Helical fan beam kVCT allows for daily image guidance for localization and setup verification with comparable performance to existing kV-CBCT systems. Scan parameters must be selected carefully to maximize image quality for the desired tasks. Due to the large effective slice thicknesses for all parameter combinations, kVCT scans should not be used for simulation or planning of stereotactic procedures. Finally, improved image quality over MVCT has the potential to greatly improve manual and automated adaptive monitoring and planning.
ABSTRACT
Objectives This study aimed to evaluate quantitative and qualitative screening measures for anomalous computed tomography (CT) scans in cancer patients with potential coronavirus disease 2019 (COVID-19) as an automated detection tool in a radiation oncology treatment setting. Methods We identified a non-COVID-19 cohort and patients with suspected COVID-19 with chest CT scans from February 1, 2020 to June 30, 2020. Lungs were segmented, and a mean normal Hounsfield Unit (HU) histogram was generated for the non-COVID-19 CT scans; these were used to define thresholds for designating the COVID-19-suspected histograms as normal or abnormal. Statistical measures were computed and compared to the threshold levels, and density maps were generated to examine the difference between lungs with and without COVID-19 qualitatively. Results The non-COVID-19 cohort consisted of 70 patients with 70 CT scans, and the cohort of suspected COVID-19 patients consisted of 59 patients with 80 CT scans. Sixty-two patients were positive for COVID-19. The mean HUs and skewness of the intensity histogram discriminated between COVID-19 positive and negative cases, with an area under the curve of 0.948 for positive and 0.944 for negative cases. Skewness correctly identified 57 of 62 positive cases, whereas mean HUs correctly identified 17 of 18 negative cases. Density maps allowed for visualization of the temporal evolution of COVID-19 disease. Conclusions The statistical measures and density maps evaluated here could be employed in an automated screening algorithm for COVID-19 infection. The accuracy is high enough for a simple and rapid screening tool for early identification of suspected infection in patients treated with chemotherapy and radiation therapy already receiving CT scans as part of clinical care. This screening tool could also identify other infections that present critical risks for patients undergoing chemotherapy and radiation therapy, such as pneumonitis.