Predicting treatment plan approval probability for high-dose-rate brachytherapy of cervical cancer using adversarial deep learning.

Objective.Predicting the probability of having the plan approved by the physician is important for automatic treatment planning. Driven by the mathematical foundation of deep learning that can use a deep neural network to represent functions accurately and flexibly, we developed a deep-learning framework that learns the probability of plan approval for cervical cancer high-dose-rate brachytherapy (HDRBT).Approach.The system consisted of a dose prediction network (DPN) and a plan-approval probability network (PPN). DPN predicts organs at risk (OAR)D2ccand CTVD90%of the current fraction from the patient's current anatomy and prescription dose of HDRBT. PPN outputs the probability of a given plan being acceptable to the physician based on the patients anatomy and the total dose combining HDRBT and external beam radiotherapy sessions. Training of the networks was achieved by first training them separately for a good initialization, and then jointly via an adversarial process. We collected approved treatment plans of 248 treatment fractions from 63 patients. Among them, 216 plans from 54 patients were employed in a four-fold cross validation study, and the remaining 32 plans from other 9 patients were saved for independent testing.Main results.DPN predicted equivalent dose of 2 Gy for bladder, rectum, sigmoidD2ccand CTVD90%with a relative error of 11.51% ± 6.92%, 8.23% ± 5.75%, 7.12% ± 6.00%, and 10.16% ± 10.42%, respectively. In a task that differentiates clinically approved plans and disapproved plans generated by perturbing doses in ground truth approved plans by 20%, PPN achieved accuracy, sensitivity, specificity, and area under the curve 0.70, 0.74, 0.65, and 0.74.Significance.We demonstrated the feasibility of developing a novel deep-learning framework that predicts a probability of plan approval for HDRBT of cervical cancer, which is an essential component in automatic treatment planning.

Definitive radiation for advanced cervix cancer is not associated with vaginal shortening-a prospective vaginal length and dose correlation.

PURPOSE: Prospectively measure change in vaginal length after definitive chemoradiation (C-EBRT) with Intracavitary Brachytherapy (ICBT) for locally advanced cervix cancer (LACC) and correlate with vaginal dose (VD). MATERIALS AND METHODS: Twenty one female patients with LACC receiving C-EBRT and ICBT underwent serial vaginal length (VL) measurements. An initial measurement was made at the time of the first ICBT procedure and subsequently at 3 month intervals up to 1 year post radiation. The vagina was contoured as a 3-dimensional structure for each brachytherapy plan. The difference in VL before and at least 6 months after the last fraction of brachytherapy was considered as an indicator of toxicity. RESULTS: The mean initial VL was 8.7 cm (6.5-12) with median value of 8.5 cm. The mean VL after 6 months was 8.6 cm (6.5-12) and VL change was not found to be statistically significant. The median values (interquartile ranges) for vaginal D0.1cc, D1cc, and D2cc were 129.2 Gy (99.6-252.2), 96.9 Gy (84.2-114.9), and 89.6 Gy (82.4-102.2), respectively. No significant correlation was found between vaginal length change and the dosimetric parameters calculated for all patients. CONCLUSION: Definitive C-EBRT and ICBT did not significantly impact VL in this prospective cohort probably related to acceptable doses per ICRU constraints. Estimate of vaginal stenosis and sexual function was not performed in this cohort which is a limitation of this study and which we hope to study prospectively going forward.

A Tale of Two Hospitals: Effect of Access to Care Through a Safety Net Hospital on Adjuvant Therapy, Imaging Compliance and 5-Year Survival Rates Compared to the University Hospital Served by the Same Breast Cancer Clinical Teams.

RATIONALE AND OBJECTIVES: To compare rates of guideline-concordant care, imaging surveillance, recurrence and survival outcomes between a safety-net (SNH) and tertiary-care University Hospital (UH) served by the same breast cancer clinical teams. MATERIALS AND METHODS: 647 women with newly diagnosed breast cancer treated in affiliated SNH and UH between 11.1.2014 and 3.31.2017 were reviewed. Patient demographics, completion of guideline-concordant adjuvant chemotherapy, radiation and hormonal therapy were recorded. Two multivariable logistic regression models were performed to investigate the effect of hospital and race on cancer stage. Kaplan-Meier log-rank and Cox-regression were used to analyze five-year recurrence-free (RFS) and overall survival (OS) between hospitals and races, (p < 0.05 significant). RESULTS: Patients in SNH were younger (mean SNH 53.2 vs UH 57.9, p < 0.001) and had higher rates of cT3/T4 disease (SNH 19% vs UH 5.5%, p < 0.001). Patients in the UH had higher rates of bilateral mastectomy (SNH 17.6% vs UH 40.1% p < 0.001) while there was no difference in the positive surgical margin rate (SNH 5.0% vs UH 7.6%, p = 0.20), completion of adjuvant radiation (SNH 96.9% vs UH 98.7%, p = 0.2) and endocrine therapy (SNH 60.8% vs UH 66.2%, p = 0.20). SNH patients were less compliant with mammography surveillance (SNH 64.1% vs UH 75.1%, p = 0.02) and adjuvant chemotherapy (SNH 79.1% vs UH 96.3%, p < 0.01). RFS was lower in the SNH (SNH 54 months vs UH 57 months, HR 1.90, 95% CI: 1.18-3.94, p = 0.01) while OS was not significantly different (SNH 90.5% vs UH 94.2%, HR 1.78, 95% CI: 0.97-3.26, p = 0.06). CONCLUSION: In patients experiencing health care disparities, having access to guideline-concordant care through SNH resulted in non-inferior OS to those in tertiary-care UH.

The accuracy of artificial intelligence deformed nodal structures in cervical online cone-beam-based adaptive radiotherapy.

Background and Purpose: Online cone-beam-based adaptive radiotherapy (ART) adjusts for anatomical changes during external beam radiotherapy. However, limited cone-beam image quality complicates nodal contouring. Despite this challenge, artificial-intelligence guided deformation (AID) can auto-generate nodal contours. Our study investigated the optimal use of such contours in cervical online cone-beam-based ART. Materials and Methods: From 136 adaptive fractions across 21 cervical cancer patients with nodal disease, we extracted 649 clinically-delivered and AID clinical target volume (CTV) lymph node boost structures. We assessed geometric alignment between AID and clinical CTVs via dice similarity coefficient, and 95% Hausdorff distance, and geometric coverage of clinical CTVs by AID planning target volumes by false positive dice. Coverage of clinical CTVs by AID contour-based plans was evaluated using D100, D95, V100%, and V95%. Results: Between AID and clinical CTVs, the median dice similarity coefficient was 0.66 and the median 95 % Hausdorff distance was 4.0 mm. The median false positive dice of clinical CTV coverage by AID planning target volumes was 0. The median D100 was 1.00, the median D95 was 1.01, the median V100% was 1.00, and the median V95% was 1.00. Increased nodal volume, fraction number, and daily adaptation were associated with reduced clinical CTV coverage by AID-based plans. Conclusion: In one of the first reports on pelvic nodal ART, AID-based plans could adequately cover nodal targets. However, physician review is required due to performance variation. Greater attention is needed for larger, daily-adapted nodes further into treatment.

Transferring care to enhance access to early-phase cancer clinical trials: Protocol to evaluate a novel program.

Involving diverse populations in early-phase (phase I and II) cancer clinical trials is critical to informed therapeutic development. However, given the growing costs and complexities of early-phase trials, trial activation and enrollment barriers may be greatest for these studies at healthcare facilities that provide care to the most diverse patient groups, including those in historically underserved communities (e.g., safety-net healthcare systems). To promote diverse and equitable access to early-phase cancer clinical trials, we are implementing a novel program for the transfer of care to enhance access to early-phase cancer clinical trials. We will then perform a mixed-methods study to determine perceptions and impact of the program. Specifically, we will screen, recruit, and enroll diverse patients from an urban, integrated safety-net healthcare system to open and active early-phase clinical trials being conducted in a university-based cancer center. To evaluate this novel program, we will: (1) determine program impact and efficiency; and (2) determine stakeholder experience with and perceptions of the program. To achieve these goals, we will conduct preliminary cost analyses of the program. We will also conduct surveys and interviews with patients and caregivers to elucidate program impact, challenges, and areas for improvement. We hypothesize that broadening access to early-phase cancer trials conducted at experienced centers may improve equity and diversity. In turn, such efforts may enhance the efficiency and generalizability of cancer clinical research.

Neural network dose prediction for cervical brachytherapy: Overcoming data scarcity for applicator-specific models.

BACKGROUND: 3D neural network dose predictions are useful for automating brachytherapy (BT) treatment planning for cervical cancer. Cervical BT can be delivered with numerous applicators, which necessitates developing models that generalize to multiple applicator types. The variability and scarcity of data for any given applicator type poses challenges for deep learning. PURPOSE: The goal of this work was to compare three methods of neural network training-a single model trained on all applicator data, fine-tuning the combined model to each applicator, and individual (IDV) applicator models-to determine the optimal method for dose prediction. METHODS: Models were produced for four applicator types-tandem-and-ovoid (T&O), T&O with 1-7 needles (T&ON), tandem-and-ring (T&R) and T&R with 1-4 needles (T&RN). First, the combined model was trained on 859 treatment plans from 266 cervical cancer patients treated from 2010 onwards. The train/validation/test split was 70%/16%/14%, with approximately 49%/10%/19%/22% T&O/T&ON/T&R/T&RN in each dataset. Inputs included four channels for anatomical masks (high-risk clinical target volume [HRCTV], bladder, rectum, and sigmoid), a mask indicating dwell position locations, and applicator channels for each applicator component. Applicator channels were created by mapping the 3D dose for a single dwell position to each dwell position and summing over each applicator component with uniform dwell time weighting. A 3D Cascade U-Net, which consists of two U-Nets in sequence, and mean squared error loss function were used. The combined model was then fine-tuned to produce four applicator-specific models by freezing the first U-Net and encoding layers of the second and resuming training on applicator-specific data. Finally, four IDV models were trained using only data from each applicator type. Performance of these three model types was compared using the following metrics for the test set: mean error (ME, representing model bias) and mean absolute error (MAE) over all dose voxels and ME of clinical metrics (HRCTV D90% and D2cc of bladder, rectum, and sigmoid), averaged over all patients. A positive ME indicates the clinical dose was higher than predicted. 3D global gamma analysis with the prescription dose as reference value was performed. Dice similarity coefficients (DSC) were computed for each isodose volume. RESULTS: Fine-tuned and combined models showed better performance than IDV applicator training. Fine-tuning resulted in modest improvements in about half the metrics, compared to the combined model, while the remainder were mostly unchanged. Fine-tuned MAE = 3.98%/2.69%/5.36%/3.80% for T&O/T&R/T&ON/T&RN, and ME over all voxels = -0.08%/-0.89%/-0.59%/1.42%. ME D2cc were bladder = -0.77%/1.00%/-0.66%/-1.53%, rectum = 1.11%/-0.22%/-0.29%/-3.37%, sigmoid = -0.47%/-0.06%/-2.37%/-1.40%, and ME D90 = 2.6%/-4.4%/4.8%/0.0%. Gamma pass rates (3%/3 mm) were 86%/91%/83%/89%. Mean DSCs were 0.92%/0.92%/0.88%/0.91% for isodoses ≤ 150% of prescription. CONCLUSIONS: 3D BT dose was accurately predicted for all applicator types, as indicated by the low MAE and MEs, high gamma scores and high DSCs. Training on all treatment data overcomes challenges with data scarcity in each applicator type, resulting in superior performance than can be achieved by training on IDV applicators alone. This could presumably be explained by the fact that the larger, more diverse dataset allows the neural network to learn underlying trends and characteristics in dose that are common to all treatment applicators. Accurate, applicator-specific dose predictions could enable automated, knowledge-based planning for any cervical brachytherapy treatment.

Stereotactic Ablative Radiotherapy for Gynecological Oligometastatic and Oligoprogessive Tumors.

Importance: The role of stereotactic ablative radiotherapy (SABR) for gynecologic malignant tumors has yet to be clearly defined despite recent clinical uptake. Objective: To evaluate the outcomes of SABR in patients with oligometastatic and oligoprogressive gynecologic cancers. Design, Setting, and Participants: In this retrospective pooled analysis, patients with oligometastatic and oligoprogressive gynecologic cancers receiving SABR at 5 institutions from Canada and the US were studied. Data were collected from January 2011 to December 2020, and data were analyzed from January to December 2023. Exposure: Stereotactic ablative radiotherapy. Main Outcomes and Measures: Cumulative incidence of local and distant recurrence, chemotherapy-free survival (CFS), and overall survival (OS) probabilities after SABR were calculated using Kaplan-Meier methods. Univariable and multivariable analysis was conducted using Cox regression methods. Results: A total of 215 patients with 320 lesions meeting criteria were included in the analysis; the median (range) age at primary diagnosis was 59 (23-86) years. The median (range) follow-up from SABR was 18.5 (0.1-124.5) months. The primary site included the endometrium (n = 107), ovary (n = 64), cervix (n = 30), and vulva or vagina (n = 14). Local cumulative incidence of recurrence was 13.7% (95% CI, 9.4-18.9) and 18.5% (95% CI, 13.2-24.5) at 1 and 5 years, respectively. Distant cumulative incidence of recurrence was 48.5% (95% CI, 41.4-55.1) and 73.1% (95% CI, 66.0-79.0) at 1 and 5 years, respectively. OS was 75.7% (95% CI, 69.2-81.1) and 33.1% (95% CI, 25.3-41.1) at 1 and 5 years, respectively. The median CFS was 21.7 months (95% CI, 15.4-29.9). On multivariable analysis, local recurrence was significantly associated with nodal metastasis, lesion size, biologically effective dose, treatment indication, institution, and primary disease type. Distant progression-free survival was associated with nodal targets and lesion size. OS and CFS were significantly associated with lesion size. Conclusions and Relevance: In this study, SABR appeared to have excellent local control with minimal toxic effects in this large patient group, and certain patients may achieve durable distant control and OS as well. It may be possible to delay time to chemotherapy in select patient subtypes and therefore reduce associated toxic effects. Prospective multicenter trials will be critical to establish which characteristics procure the greatest benefit from SABR use and to define the ideal time to implement SABR with other oncologic treatments.