Bilal Shahine

Background: Accurate CT/MR registration is important in stereotactic brain radiotherapy, where small spatial errors may affect target localization and treatment planning. In many clinical settings, registration quality is still assessed primarily through manual visual inspection. However, time and workflow constraints may limit the consistency and depth of manual evaluation. Purpose: This study aimed to develop a 3D convolutional neural network (3D CNN)‐based quality assurance (QA) method for rigid brain CT/MR registration using paired sub‐volumes and a registration‐level mean probability score ( μ ). The proposed method classifies local CT/MR registration quality, while the final registration‐level assessment is based on μ across the sampled sub‐volumes. Methods: The study included 209 patients. Of these, 202 comprised the primary cohort and were divided patient‐wise into 128 training, 33 validation, and 41 test patients. For each patient, 25 skull‐based CT/MR sub‐volumes of 42 × 42 × 42 voxels were used as a two‐channel CNN input. High‐quality examples were obtained from clinically approved registrations, while low‐quality examples were generated using rigid perturbations of the complete MR volume. The mean predicted probability across the 25 sub‐volumes was used as the registration‐level score μ , and the validation‐derived threshold of 0.5871 was fixed for testing. Seven additional patients, separate from the 202‐patient cohort, were evaluated after model development and threshold selection were completed using registrations before and after physician correction. Results: On the held‐out test set, patch‐level accuracy was 85.90%, with an ROC AUC of 0.929 and average precision of 0.920. At the registration level, accuracy was 97.56% and ROC AUC was 0.999. All 41 low‐quality registrations were correctly flagged, while 39 of 41 high‐quality registrations were correctly accepted. In the additional clinical evaluation, all seven initial registrations requiring correction were classified as low quality, while six of seven corrected registrations were classified as high quality, resulting in an overall accuracy of 92.86%. Conclusions: The proposed method combined local CNN predictions into a registration‐level μ score and showed strong performance on held‐out and clinical cases. It may provide a quantitative screening measure for rigid brain CT/MR registration QA while maintaining clinical review as the final decision step.

PURPOSE: One crucial use of telemedicine that is underreported is its role in providing health services in conflict-affected zones. The aim of this report is to describe the process and challenges of implementing a telemedicine-based radiation oncology (RO) clinic in a war zone in southern Lebanon, and to assess its effectiveness in providing care to patients with cancer residing in this unsafe, resource-limited area. METHODS: After the outbreak of the Lebanese-Israeli war in October 2023, we had to shift our RO clinic in Nabatieh Governmental Hospital to an exclusively remote clinic without on-site physicians. Consultations, treatment planning, and follow-ups were conducted virtually by physicians at the American University of Beirut Medical Center. Patient data and imaging were shared electronically between both hospitals, and treatment was administered locally by trained staff. RESULTS: From October 2023 to September 2024, 669 new patient consultations were completed remotely. Despite infrastructure limitations, including lack of electronic health records and occasional connectivity issues, we developed a model to ensure care continuity was largely maintained for the local patients with cancer. CONCLUSION: Telemedicine can serve as a tool for delivering cancer care in times of war, improving access and equity for underprivileged groups in the face of severe logistical and infrastructural challenges.

Purpose: Improved accuracy in 4DCT imaging and precise targeting of tumors contribute to more effective and targeted radiation therapy. This study focuses on evaluating the accuracy of utilizing the GateCT (VisionRT Ltd, London, United Kingdom) in comparison with a pressure sensor system (ANZAI Medical Co., Ltd., Shinagawa, Tokyo) to provide 4DCT with respiratory information. Methods: A dynamic breathing phantom enclosing three spheres (A, P, and R) of different densities was enrolled to produce breathing patterns tracked by the two systems. Image sets for three breathing phases obtained based on GateCT and ANZAI systems were analyzed using deformable registration by deforming the three‐phase image sets with the static image sets. Our deformable registration approach revealed how far different phase image sets were from the quantified by various metrics, such as dice similarity coefficient (DSC), mean surface distance (MSD), absolute volume estimation, mean Jacobian, and Warp. Results: Results indicated DSC values greater than 0.90 across all phases and spheres for both respiratory systems, with mean DSC values for spheres A, P, and R of 0.980 versus 0.977, 0.977 versus 0.976, and 0.977 versus 0.976 for GateCT and ANZAI systems, respectively. MSDs for both systems were consistently less than 2 mm across all spheres and phases. Furthermore, the mean volume estimation error for both systems, relative to the static, exhibited statistical insignificance ( p > 0.05). Friedman test revealed significant differences in median Jacobian, and median Warping between the two systems ( p < 0.05). Conclusions: In addition to the effectiveness of deformable image registration in the quantification of respiratory system performance, both systems exhibited comparable performance in providing 4DCT with respiratory information.

Introduction: In vivo diode dosimetry proved its efficacy as a patient-specific quality assurance tool for 3DCRT. Its usefulness in IMRT is not sufficiently investigated. Methods: Four step-and-shoot IMRT plans were generated for different treatment sites using an Alderson Rando anthropomorphic phantom. Two in vivo semiconductor diodes were used to perform 33 entrance radiation dose measurements at central axis and max beam point dose on a water-equivalent slabs based on the anthropomorphic plans. Measured values were compared to planned ones, and detailed analysis per segment of each IMRT field was made to infer the reason behind the discrepancies of measurements from expectations. Results: Point dose measurements were performed on a beam and a segment basis. Agreement within ±5% action level with planned dose was 27% of beams at central axis versus 45% at max point dose and 10% of segments at central axis versus 25% at max point dose. For ±10% action level, 70% of beams at central axis versus 73% at max point dose, and 15% of segments at central axis versus 41% at max point dose. Classification of segments resulted in a significance of .021 for measuring at positions unaffected by the MLC partial and total blockage. Conclusion: Diode measurements are recommended at maximum dose coordinates for open beams/segments for more accurate patient dose verification results as part of in vivo dosimetry. This is important for limited resources centres treating with sMLC IMRT.

Objectives: Moderate hypofractionation for localized prostate cancer has become a standard of care in many radiation therapy centers worldwide. Several fractionation and planning protocols exist, with CHHiP and PROFIT (60 Gy in 20 fractions) being 2 of the most commonly used. We retrospectively compared the doses received by organs at risk (OARs) using these 2 protocols. Materials and Methods: We retrospectively reviewed the charts of 25 randomly selected de-identified patients treated with intensity-modulated radiation therapy (IMRT) for prostate cancer in a single tertiary care center. For each patient, we generated 2 sets of contours for target volumes and OARs in accordance with both CHHiP and PROFIT protocols. A total of 50 IMRT plans, using Prowess Panther software version 5.10, were generated and achieved the respective planning targets and normal tissue constraints. The related-samples Wilcoxon signed-rank test was used to compare the mean dose, V60, V50, and V40 of each of the bladder, rectum, and penile bulb. Results: Patients had a mean age of 73 years, average prostate-specific antigen level of 9.8 ng/mL, mostly a Gleason score of 7, and a clinical stage that ranged from T1c to T2c. In the CHHiP plans, the rectum averaged a significantly lower V60 (0.5% vs 4.5%, P < .001) and V50 (13.1% vs 15.7%, P = .026) than with PROFIT. Similarly, the bladder in CHHiP averaged a significantly lower V60 (1.9% vs 7.7%, P < .001) and V50 (13.2% vs 15.5%, P = .035). The penile bulb received a lower mean dose (21.9 Gy vs 30.5 Gy, P < .001), V50 (5.6% vs 14.4%, P = .037), and V40 (11.4% vs 35.2%, P < .001) on average in the CHHiP plans as well. Conclusion: In our dosimetric comparison, CHHiP spared the OARs to a greater degree than PROFIT. While contouring and planning using the CHHiP protocol are usually more demanding, we expect that greater sparing of OARs will minimize clinical toxicity in patients with prostate cancer receiving moderately hypofractionated radiation therapy.

Introduction: This study explores the feasibility of SRS/SRT treatment with MLC leaves wider than 2.5 mm at isocenter by inter-comparing treatment plans produced with 2.5, 5.0, and 10.0 mm leaves for various target sizes and shapes. Materials and methods: Forty previously treated patients were re-planned using 2.5, 5.0, and 10.0 mm wide MLC leaves. For each patient, all three plans were evaluated and contrasted between them in terms of five metrics: target dose homogeneity, conformity index, organs at risk dose, dose fall off outside the target, and dose to normal tissues. A regularity index RI was introduced that quantified the degree of target shape irregularity. The effect of target size and shape irregularity on feasibility of 5.0 and 10.0 mm leaves was analyzed. Results: Consistent plan degradation was observed for 10.0 mm (sometimes for 5.0 mm) compared to 2.5 mm MLC in terms of the above five plan metrics, but this degradation was small to clinically insignificant. As an exception, when target (PTV) size was smaller than about 1 cm diameter, clinically significant differences were found between 2.5, 5.0, and 10.0 mm MLC. Conclusion: 5.0 and 10.0 mm MLC can be used in SRS/SRT for targets (PTV) diameter larger than 1 cm. For smaller targets, 2.5 mm MLC is clinically superior, 5.0 is acceptable and 10.0 mm MLC is discouraged in terms of PTV dose conformity.

Purpose: The purpose of this study was to evaluate patient-related non-dosimetric predictors of cardiac sparing with the use of deep inspiration breath-hold (DIBH) in patients with left-sided breast cancer undergoing irradiation (RT). Materials and Methods: We retrospectively reviewed charts and treatment plans of one-hundred and three patients with left-sided breast cancer. All patients had both free-breathing (FB) and DIBH (with body surface tracking) plans available. (MHD) and V4 (heart volume receiving at least 4 Gy) were extracted from dose volume histograms. Fisher's exact and Chi-square tests were used to identify predictors of reductions in MHD and V4 after DIBH. Results: One-hundred and three patients were identified and most underwent mastectomy. MHD and V4 decreased significantly in DIBH plans (0.74 ± 0.25 Gy vs. 1.72 ± 0.98 Gy, p < 0.0001 for MHD; 4 ± 4.98 cc vs. 20.79 ± 18.2 cc, p < 0.0001 for V4). Body mass index (BMI), smoking and timing of CT simulation (spring/winter vs. summer/fall) were significant predictors of reduction in MHD whereas BMI, field size, chemotherapy, axillary dissection, and timing of CT simulation predicted reduction in V4. On multivariate analysis, BMI, and timing of CT simulation remained significant predictors of the heart-sparing effect of DIBH. Conclusions: In the setting of limited resources, identifying patients who will benefit the most from DIBH is extremely important. Prior studies have identified multiple dosimetric predictors of cardiac sparing and hereby we identified new non-dosimetric factors such as BMI and timing of treatments.