Radiotherapy and Oncology最新文献

Background and purpose: To develop a normal tissue complication probability (NTCP) model for predicting grade ≥ 2 acute oral mucositis (AOM) in head and neck cancer patients undergoing carbon-ion radiation therapy (CIRT).

Methods and materials: We retrospectively included 178 patients, collecting clinical, dose-volume histogram (DVH), radiomics, and dosiomics data. Patients were randomly divided into training (70%) and test sets (30%). Feature selection involved univariable logistic regression, least absolute shrinkage and selection operator regression, stepwise backward regression, and Spearman's correlation test, with the bootstrap method ensuring reliability. Multivariable models were built on the training set and evaluated using the test set.

Results: The optimal NTCP model incorporated a DVH parameter (V_{37Gy [relative biological effectiveness, RBE]}), radiomics, and dosiomics features, achieving an area under the curve (AUC) of 0.932 in the training set and 0.959 in the test set. This hybrid model outperformed those based on single DVH, radiomics, dosiomics, or clinical data (Bonferroni-adjusted p < 0.001 and ΔAUC > 0 for all comparisons in 1,000 bootstrap validations). Calibration curves showed strong agreement between predictions and outcomes. A 44.0 % AOM risk threshold was proposed, yielding accuracies of 87.1 % in the training set and 90.7 % in the test set.

Conclusions: We developed the first NTCP model for estimating AOM risk in head and neck cancer patients undergoing CIRT and proposed a risk stratification. This model may assist in clinical decision-making and improve treatment planning for AOM prevention and management by identifying high-risk patients.

Background and purpose: Quantifying tumor heterogeneity from various dimensions is crucial for precise treatment. This study aimed to develop and validate multi-omics models based on the computed tomography images, pathological images, dose and clinical information to predict treatment response and overall survival of non-small cell lung cancer (NSCLC) patients undergoing chemotherapy and radiotherapy.

Materials and methods: This retrospective study included 220 NSCLC patients from three centers. Following feature extraction and selection, single-omics and multi-omics models were built for treatment response and overall survival prediction. The performance of treatment response models was evaluated using the area under the curve (AUC) and box plots. For overall survival analysis, the model's evaluation included AUC, concordance index (C-index), Kaplan-Meier curves, and calibration curves. Shapley values were used to assess the contribution of different features to multi-omics models.

Results: Multi-omics models consistently exhibited superior discriminative ability compared to single-omics models in predicting both treatment response and overall survival. For treatment response, the three all-modality models achieved AUC values of 0.87, 0.91, and 0.82 in the external validation set, respectively. In overall survival analysis, the three all-modality models demonstrated AUC values and C-index of 0.73/0.72, 0.80/0.77, 0.79/0.78 in the external validation set, respectively.

Conclusion: Multi-omics prediction models demonstrated superior predictive ability with robustness and interpretability. By predicting treatment response and overall survival in NSCLC patients, these models have the potential to assist clinician optimizing treatment plans, supporting individualized treatment strategies, improving the tumor control probability and prolonging the patients' survival.

Head and neck squamous cell carcinomas (HNSCC) frequently recur, and patients often develop second primary tumors. Their distinction is clinically challenging. TP53 mutational heterogeneity may indicate novel molecular events rather than resistant clones' expansion or persistent disease. Surveillance and therapeutic strategies should be adjusted, especially in the case of a second primary arising in an already irradiated field.

Background and purpose: Radiation-induced hypothyroidism (RIHT) is a late complication of intensity-modulated radiation therapy (IMRT) for nasopharyngeal carcinoma (NPC). We evaluated thyroid protection in NPC patients receiving IMRT using modified delineation (MD) of cervical lymphatic drainage areas, sparing the common carotid artery within the clinical target volume (CTV), to assess its impact on thyroid function and survival outcomes.

Materials and methods: This retrospective cohort study included patients without metastatic lymph nodes at levels III and IV who received neck irradiation. Patients with normal thyroid function before radiotherapy and regular thyroid monitoring thereafter were included in the regular thyroid-function monitoring cohort. MD was used to adjust the medial edge of level III and IVa lymphatic areas from the medial (standard delineation [SD]) to the lateral edge of the common carotid artery.

Results: Among 374 patients (SD: 223; MD: 151), the median Dmean, V45, and V50 were significantly lower in the MD group than in the SD group. In the regular monitoring cohort (SD: 113; MD: 108), the 3-year RIHT incidence was lower in the MD group (23.5 % vs 40.0 %; P = 0.005). MD was associated with a lower risk of RIHT (HR: 0.49; P = 0.004). The 3-year locoregional recurrence-free survival (97.2 % vs. 97.3 %, P = 0.962) and overall survival (96.2 % vs. 92.2 %, P = 0.221) rates were comparable between MD and SD groups.

Conclusions: Sparing the common carotid artery region in the CTV is associated with reduced thyroid radiation dose and a lower RIHT incidence without increasing regional failure risk or affecting overall survival.

Purpose: This study aims to develop a robust, large-scale deep learning model for medical image segmentation, leveraging self-supervised learning to overcome the limitations of supervised learning and data variability in clinical settings.

Methods and materials: We curated a substantial multi-center CT dataset for self-supervised pre-training using masked image modeling with sparse submanifold convolution. We designed a series of Sparse Submanifold U-Nets (SS-UNets) of varying sizes and performed self-supervised pre-training. We fine-tuned the SS-UNets on the TotalSegmentator dataset. The evaluation encompassed robustness tests on four unseen datasets and transferability assessments on three additional datasets.

Results: Our SS-UNets exhibited superior performance in comparison to state-of-the-art self-supervised methods, demonstrating higher Dice Similarity Coefficient (DSC) and Surface Dice Coefficient (SDC) metrics. SS-UNet-B achieved 84.3 % DSC and 88.0 % SDC in TotalSegmentator. We further demonstrated the scalability of our networks, with segmentation performance increasing with model size, demonstrated from 58 million to 1.4 billion parameters:4.6 % DSC and 3.2 % SDC improvement in TotalSegmentator from SS-UNet-B to SS-UNet-H.

Conclusions: We demonstrate the efficacy of self-supervised learning for medical image segmentation in the CT, MRI and PET domains. Our approach significantly reduces reliance on extensively labeled data, mitigates risks of overfitting, and enhances model generalizability. Future applications may allow accurate segmentation of organs and lesions across several imaging domains, potentially streamlining cancer detection and radiotherapy treatment planning.

Background and purpose: Few studies have examined the factors associated with xerostomia during proton and carbon ion radiotherapy for head and neck cancer (HNC), which are reported to have fewer toxic effects compared to traditional photon-based radiotherapy. This study aims to evaluate the performance of machine learning approaches in predicting grade 2 + xerostomia in adults with HNC receiving proton and carbon ion radiotherapy.

Materials and methods: A retrospective study involving 1,769 adults with HNC who completed proton or carbon ion radiotherapy was conducted. Xerostomia was graded using the Radiation Therapy Oncology Group criteria. Eight machine learning models with different combinations sampling methods and class weights were compared to identify the model with the highest balanced accuracy.

Results: The mean age of patients was 47.8 years (range 18-80), with 33.5 % female. The average total radiation dose was 71.0 GyE (SD = 5.7). Grade 1 xerostomia was recorded in 572 patients (32.3 %) and grade 2 in 103 patients (5.8 %). No cases of grade 3 or higher xerostomia were reported. A support vector machine with a linear kernel, a 1:2 positive-to-negative class weight, and SMOTE oversampling achieved the highest balanced accuracy (0.66) and AUC-ROC (0.69) for predicting grade 2 xerostomia, outperforming the logistic regression model (balanced accuracy:0.50, AUC-ROC. 0.67).

Conclusion: The prevalence of grade 2 radiation-induced xerostomia during proton and carbon ion radiotherapy was low in adults with HNC, posing challenges for accurate prediction. Further research is needed to develop improved methods for predicting xerostomia during proton and carbon ion radiotherapy.

Background and purpose: Daily online adaptive radiotherapy (DART) increases treatment accuracy by crafting daily customized plans that adjust to the patient's daily setup and anatomy. The routine application of DART is limited by its resource-intensive processes. This study proposes a novel DART strategy for head and neck squamous cell carcinoma (HNSCC), automizing the process by propagating physician-edited treatment contours for each fraction.

Materials and methods: This study retrospectively analyzed 24 HNSCC patients treated with DART, encompassing 810 fractions. Both weekly and daily offline editing of the contours were emulated, propagating them to subsequent fractions using rigid and deformable image registration (DIR), respectively. Contour margins (CM) of 1, 2, and 3 mm were applied to create an adaptive gross tumor volume (aGTV) /adaptive clinical target volume (aCTV). Geometric coverage of the aGTV/aCTV relative to the ground-truth GTV/CTV were assessed. Additionally, adaptive dose distributions were predicted based on the aGTV/aCTV, and the dosimetric coverage of these predictions on the ground-truth GTV/CTV was evaluated. The recommended CM was identified by comparing the geometric and dosimetric accuracy across different combinations of CM, registration methods, and contour update frequencies.

Results: Rigid registration failed to accurately propagate most targets, even with a 3 mm CM. With DIR and a 2 mm CM, weekly or daily contour propagation achieved ≥ 98 % geometric coverage for gross tumor/nodal targets and ≥ 94 % for small suspicious nodes. DIR with weekly and daily contours achieved target dose coverage: V95% ≥ 99 % and V100% ≥ 95 % to the aGTV.

Conclusion: This study shows that DIR can effectively propagate periodically edited treatment contours for HNSCC patients, provided the correct CM is used. By adjusting contours weekly offline and using DIR at the console, the need for daily physician attendance can be eliminated.

Background and purpose: Late toxicity is substantial after chemotherapy for anal cancer. This study aimed to investigate the relationship between radiation dose to lower urinary tract sub-structures and the risk of late urinary toxicities, in patients with anal cancer treated with chemoradiotherapy or radiotherapy.

Materials and methods: From 2015 to 2021, 314 patients with localized anal cancer were included in a national prospective registration study. Urinary toxicity (CTCAE) was scored during treatment (acute toxicity) and at one- and three-years follow-up (late toxicity). Lower urinary tract sub-structures (bladder, bladder neck, bladder trigone, and urethra) were contoured post-hoc on the planning-CT and dosimetric variables extracted. Logistic regression was used to evaluate the association between clinical and dosimetric variables and registered toxicity.

Results: There was an increase in late toxicity from baseline of 15 % for both urgency and frequency, and 25 % for incontinence. The most common late toxicity was urinary frequency, with 40 % of patients experiencing grade 1 and 2 % experiencing grade 2 toxicity. A dose-effect relationship was found for late urinary urgency and increasing D0.1 cm3 of the urethra (p = 0.01). Increased late urinary frequency was correlated to increasing D2cm3 of the urethra (p = 0.007), and bladder neck V30Gy (p = 0.03). Patients with acute toxicity had up to three times increased risk of corresponding late toxicity.

Conclusion: We found a significant dose-effect relationship between radiation dose to urethra and bladder neck and late urinary toxicity. These findings warrant more focus on these structures when optimizing radiotherapy for anal cancer. Furthermore, a strong association between having acute toxicity and developing late toxicity was shown.