In this study, a bias field correction workflow was proposed to improve the flexibility and generalizability of the generative adversarial network (GAN) model for abdominal cancer patients treated with a 0.35T magnetic resonance imaging linear accelerator (MR-LINAC) system.
Model training was performed using brain MR images acquired on a 3T diagnostic scanner, while model testing was performed using abdominal MR images obtained using a 0.35T MR-LINAC system. The performance of the proposed workflow was first compared with the GAN model using root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). To assess the impact of the workflow on image segmentation, it was also compared with the N4ITK algorithm. Segmentation was performed using the k-means clustering algorithm with three clusters corresponding to air, fat, and soft tissue. Segmentation accuracy was then evaluated using the Dice similarity coefficient (DSC).
The RMSE values were 30.59, 12.06, 10.37 for the bias field-corrupted images (IIN), GAN-corrected images (IGAN), and images corrected with the proposed workflow (IOUT), respectively. Corresponding PSNR values were 42.34, 46.04, 47.04 dB, and SSIM values were 0.84, 0.96, 0.98. For segmentation accuracy, the mean DSC for air masks was 0.95, 0.97, and 0.97; for fat masks, 0.61, 0.71, and 0.74; and for soft tissue masks, 0.60, 0.68, and 0.69, corresponding to IIN, N4ITK-corrected images (IN4ITK), and IOUT, respectively
By effectively mitigating bias field artifacts, the proposed workflow has the potential to strengthen the clinical utility of MRI-guided adaptive radiotherapy for abdominal cancers, ensuring safer and more accurate radiation delivery.
We report our experience with the implementation of a same-day simulation and treatment C-arm linear accelerator (linac)-based stereotactic program for patients with intracranial and extracranial metastatic disease.
Between May 2021 and October 2023, patients were treated in our same-day program with linac-based SRS/SBRT. Two slots per week were offered. Patients with expedited clinical needs, able to undergo SRS/SBRT simulation and treatment, were considered. Extracranial treatments were required to meet standards for automated intensity modulated radiation therapy (IMRT) optimization. Intracranial treatments were limited to 1–3 lesions and 1–2 isocenters. The day before treatment, the patient needed to be identified, and any diagnostic imaging had to be available for the physician and dosimetrist to discuss the plan. On the day of treatment, simulation was scheduled for 8 AM and treatment at 4 PM by default, with the goal to complete treatment by 6 PM. We analyzed information about each patient's treatment plan and time spent on each step of the workflow.
Ninety-seven patients followed our same-day workflow and were included in the analysis. Seventy-five patients received intracranial SRS (57% to 1 lesion), while 22 patients received extracranial treatments (50% to the extremities). Simulation often required additional time to be completed, finishing a median 18 min (IQR 5–40) after the goal end time. The median time between simulation completion and end of the same-day treatment was 7.8 h (IQR 7.4–8.6). Treatment technique and the number of target volumes had a significant impact on planning time. The median treatment end time was 5:13 PM (IQR 4:46 PM–6:01 PM), with 74% ending by 6 PM.
A linac-based program to treat patients with SRS/SBRT in an expedited fashion was established and successfully treated patients in a same-day timeline. Careful selection of planning techniques to limit plan complexity and adding automation in time-consuming parts of the process are crucial when developing expedited workflows.
This study comprised two cohorts. The first assessed patient and radiation therapist (RTT) perspectives on temporary ink skin markings. The second evaluated whether integrating a six-degree-of-freedom (6D) couch could further improve setup accuracy, setup time, IGRT time, and total treatment time when used with marker-less or marker-based workflows.
Questionnaires were completed by 72 breast cancer patients and 29 radiation therapists (RTTs) using a 6-point Likert scale (0 = never to 5 = always). The questionnaire assessed emotional experiences related to temporary skin markings and the level of interest in a marker-less approach. Forty patients were assigned to four setup groups: markers without 6D couch (M), markers with 6D couch (M_6D), marker-less without 6D couch (ML), and marker-less with 6D couch (ML_6D). Setup accuracy, setup time, image-guided radiotherapy (IGRT) time, and total treatment time were compared.
About 90% of both patients and RTTs preferred a marker-less setup. Marker-less techniques combined with 6D couch achieved comparable positioning accuracy to marker-based methods. Maximum mean setup deviations in the longitudinal axis were 3.3 ± 1.3 mm (M), 3.3 ± 1.5 mm (M_6D), 2.8 ± 1.3 mm (ML), and 3.0 ± 1.5 mm (ML_6D). No significant differences were found in setup or IGRT time. Marker-less setups reduced total treatment time by 27.8%.
Marker-less setups using SGRT are feasible for breast radiotherapy, providing comparable accuracy and reduced treatment times. Both patients and RTTs preferred this method over traditional marker-based approaches.
O-ring linac systems improve radiotherapy efficiency but require rigorous pretreatment verification due to increased delivery uncertainty in IMRT/VMAT. Existing methods face limitations: measurement-based approaches incur setup errors, while calculation-based methods (e.g., Monte Carlo) need machine-specific validation per AAPM TG-219.
To commission the O-ring linac model in RadCalc Monte Carlo software and establish its clinical dosimetric accuracy.
The additional radiation to light field offset (ARLFO) parameter in RadCalc was adjusted from −0.08 cm (−0.8 mm) to +0.08 cm (+0.8 mm) (nine sets). TG-119 and clinical benchmark cases were used to design IMRT/VMAT plans. Verification plans were measured experimentally, and all plans were imported into RadCalc for secondary dose calculation. Triangular gamma analysis (3%/2 mm) compared Monte Carlo-simulated, measured, and TPS-calculated doses. The optimal ARLFO was determined by weighted averaging of gamma pass rates. The model was validated on 10 clinical cases per site (head, thorax, abdomen, pelvis).
Commissioning identified the optimal ARLFO parameter as −0.02 cm (−0.02 mm). Under the gamma analysis criterion of 3%/2 mm, the comparison between TPS-calculated doses and Monte Carlo-calculated doses for 10 clinical plans across four anatomical sites yielded: 98.9% ± 0.8% (head and neck), 98.5% ± 0.8% (thorax), 99.6% ± 0.3% (abdomen), and 99.1% ± 0.5% (pelvis). For verification plans, the gamma pass rates between Monte Carlo-calculated doses and measured doses were 97.5% ± 2.8% (head and neck), 95.6% ± 2.8% (thorax), 96.3% ± 2.9% (abdomen), and 99.4% ± 0.5% (pelvis), while comparisons of Monte Carlo-calculated doses versus TPS-calculated doses reached 99.5% ± 0.8% (head and neck), 99.2% ± 1.0% (thorax), 99.5% ± 0.9% (abdomen), and 99.9% ± 0.2% (pelvis), demonstrating consistent dosimetric accuracy of the optimized model across all clinical sites.
This study establishes a commissioning methodology to determine the optimal ARLFO value for RadCalc, enabling clinics to achieve reliable independent plan verification for O-ring linac.
This study aims to enhance the preoperative diagnosis of non-mass breast lesions (NMLs) by validating radiomics-based machine learning models and assessing their performance alone and in combination with clinical ultrasound features to distinguish benign from malignant lesions.
A total of 123 NMLs from 119 patients with confirmed pathology were analyzed. Patients were split into a training cohort (n = 98) and a validation cohort (n = 25). From each ultrasound image, 1558 radiomics features were extracted. After dimensionality reduction and feature selection, 10 key features were retained. Predictive models were developed using logistic regression (LR), linear regression, support vector machine (SVM), random forests, Extremely Randomized Trees (Extra Trees), and Light Gradient Boosting Machine (LightGBM). A clinical model was built using LR based on ultrasound findings such as calcification, high resistance index, and axillary lymph node enlargement. A combined model incorporated both radiomics and clinical features. Model performance was evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA).
The LightGBM model achieved the highest radiomics-only performance (AUC: 0.932 training; 0.867 validation). The clinical model achieved AUCs of 0.837 (training) and 0.790 (validation). The combined model outperformed both, with AUCs of 0.973 (training) and 0.933 (validation), and showed superior clinical benefit in DCA.
Combining radiomics with clinical ultrasound data significantly improves diagnostic accuracy for NMLs, supporting better differentiation between benign and malignant lesions and aiding clinical decision-making.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：