Search

Purpose: Difficulties remain in dose optimization and evaluation of cervical cancer radiotherapy that combines external beam radiotherapy (EBRT) and brachytherapy (BT). This study estimates and improves the accumulated dose distribution of EBRT and BT with deep learning-based dose prediction. Materials and methods: A total of 30 patients treated with combined cervical cancer radiotherapy were enrolled in this study. The dose distributions of EBRT and BT plans were accumulated using commercial deformable image registration. A ResNet-101-based deep learning model was trained to predict pixel-wise dose distributions. To test the role of the predicted accumulated dose in clinic, each EBRT plan was designed using conventional method and then redesigned referencing the predicted accumulated dose distribution. Bladder and rectum dosimetric parameters and normal tissue complication probability (NTCP) values were calculated and compared between the conventional and redesigned accumulated doses. Results: The redesigned accumulated doses showed a decrease in mean values of V50, V60, and D2cc for the bladder (-3.02%, -1.71%, and -1.19 Gy, respectively) and rectum (-4.82%, -1.97%, and -4.13 Gy, respectively). The mean NTCP values for the bladder and rectum were also decreased by 0.02%0 and 0.98%, respectively. All values had statistically significant differences (p < 0.01), except for the bladder D2cc (p = 0.112). Conclusion: This study realized accumulated dose prediction for combined cervical cancer radiotherapy without knowing the BT dose. The predicted dose served as a reference for EBRT treatment planning, leading to a superior accumulated dose distribution and lower NTCP values. [ABSTRACT FROM AUTHOR]

Introduction: The use of volumetric modulated arc therapy (VMAT) with flattening-filter-free (FFF) beams is becoming more prevalent in lung cancer stereotactic body radiotherapy (SBRT). The aim in this study was to assess the impact of dosimetric and radiobiological differences between FFF and flattening filter (FF) beams for lung SBRT based on the target volume. Methods: A total of 198 lung stereotactic body radiation therapy treatment plans with FFF beams and FF beams were retrospectively selected for this study. For all plans, the prescribed dose was 50 Gy/5 fractions, and the dose volume histogram (DVH) for the target and organs at risk (OAR) and the normal tissue complication probability (NTCP) of the lung were recorded and compared. Moreover, monitor units (MUs), the beam on-time and the treatment time were evaluated. Results: The study was performed following the Radiation Therapy Oncology Group (RTOG) 0813 and 0915 protocols. No significant differences in D90, coverage rate (CR) or conformity index (CI) of the target were observed between FFF beams and FF beams (p>0.05). The D2, R50% and gradient index (GI) for the target improved with FFF beams compared with FF beams (p<0.05). FFF beams also significantly reduced the dose for the lung, heart, spinal cord, esophagus and NTCP of the lung (p<0.05), compared with FF beams. However, there was no significant difference in sparing of the trachea (p>0.05). The mean MUs, beam on-time and treatment time were 1871 ± 278 MUs, 3.2 ± 0.2 min and 3.9 ± 0.3 min for FFF beams, and 1890 ± 260 MUs, 4.2 ± 0.3 min and 4.8 ± 0.4 min for FF beams, respectively. Discussion: The FFF beam technique for lung SBRT with VMAT results in a better dose fall-off, better dose-sparing of OAR, lower NTCP of the lung and a shorter beam on-time compared with the FF beam technique. Additionally, the improvement in target and OAR-sparing for FFF beams was increased with increasing target volume. [ABSTRACT FROM AUTHOR]

Purpose: Difficulties remain in dose optimization and evaluation of cervical cancer radiotherapy that combines external beam radiotherapy (EBRT) and brachytherapy (BT). This study estimates and improves the accumulated dose distribution of EBRT and BT with deep learning-based dose prediction., Materials and Methods: A total of 30 patients treated with combined cervical cancer radiotherapy were enrolled in this study. The dose distributions of EBRT and BT plans were accumulated using commercial deformable image registration. A ResNet-101-based deep learning model was trained to predict pixel-wise dose distributions. To test the role of the predicted accumulated dose in clinic, each EBRT plan was designed using conventional method and then redesigned referencing the predicted accumulated dose distribution. Bladder and rectum dosimetric parameters and normal tissue complication probability (NTCP) values were calculated and compared between the conventional and redesigned accumulated doses., Results: The redesigned accumulated doses showed a decrease in mean values of V 50 , V 60 , and D 2cc for the bladder (-3.02%, -1.71%, and -1.19 Gy, respectively) and rectum (-4.82%, -1.97%, and -4.13 Gy, respectively). The mean NTCP values for the bladder and rectum were also decreased by 0.02‰ and 0.98%, respectively. All values had statistically significant differences (p < 0.01), except for the bladder D 2cc (p = 0.112)., Conclusion: This study realized accumulated dose prediction for combined cervical cancer radiotherapy without knowing the BT dose. The predicted dose served as a reference for EBRT treatment planning, leading to a superior accumulated dose distribution and lower NTCP values., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Fu, Chen, Liu, Zhang, Xu, Yang, Huang, Men and Dai.)

Purpose: To investigate the potential clinical benefit of utilizing intensity-modulated proton therapy (IMPT) to reduce acute hematologic toxicity for locally advanced non-small cell lung cancer (LA-NSCLC) patients and explore the feasibility of a model-based patient selection approach via the normal tissue complication probability (NTCP). Methods: Twenty patients with LA-NSCLC were retrospectively selected. Volumetric modulated arc photon therapy (VMAT) and IMPT plans were generated with a prescription dose of 60 Gy in 30 fractions. A wide range of cases with varied tumor size, location, stations of metastatic lymph nodes were selected to represent the general cancer group. Contouring and treatment planning followed RTOG-1308 protocol. Doses to thoracic vertebral bodies (TVB) and other organ at risks were compared. Risk of grade ≥ 3 acute hematologic toxicity (HT3+) were calculated based on the NTCP model, and patients with a reduction on NTCP of HT3+ from VMAT to IMPT (△NTCP_HT3+) ≥ 10% were considered to 'significantly benefit from proton therapy.' Results: Compared to VMAT, IMPT significantly reduced the dose to the TVB, the lung, the heart, the esophagus and the spinal cord. Tumor distance to TVB was significantly associated with △NTCP _HT3+ ≥ 10%. For the patients with tumor distance ≤ 0.7 cm to TVB, the absolute reduction of dose (mean, V30 and V40) to TVB was significantly lower than that in patients with tumor distance > 0.7 cm. Conclusion: IMPT decreased the probability of HT3+ compared to VMAT by reducing the dose to the TVB in LA-NSCLC patients. Patients with tumor distance to TVB less than 0.7 cm are likely to benefit most from proton over photon therapy. [ABSTRACT FROM AUTHOR]

PurposeTo investigate the potential clinical benefit of utilizing intensity-modulated proton therapy (IMPT) to reduce acute hematologic toxicity for locally advanced non-small cell lung cancer (LA-NSCLC) patients and explore the feasibility of a model-based patient selection approach via the normal tissue complication probability (NTCP).MethodsTwenty patients with LA-NSCLC were retrospectively selected. Volumetric modulated arc photon therapy (VMAT) and IMPT plans were generated with a prescription dose of 60 Gy in 30 fractions. A wide range of cases with varied tumor size, location, stations of metastatic lymph nodes were selected to represent the general cancer group. Contouring and treatment planning followed RTOG-1308 protocol. Doses to thoracic vertebral bodies (TVB) and other organ at risks were compared. Risk of grade ≥ 3 acute hematologic toxicity (HT3+) were calculated based on the NTCP model, and patients with a reduction on NTCP of HT3+ from VMAT to IMPT (△NTCP_HT3+) ≥ 10% were considered to ‘significantly benefit from proton therapy.’ResultsCompared to VMAT, IMPT significantly reduced the dose to the TVB, the lung, the heart, the esophagus and the spinal cord. Tumor distance to TVB was significantly associated with △NTCP _HT3+ ≥ 10%. For the patients with tumor distance ≤ 0.7 cm to TVB, the absolute reduction of dose (mean, V30 and V40) to TVB was significantly lower than that in patients with tumor distance > 0.7 cm.ConclusionIMPT decreased the probability of HT3+ compared to VMAT by reducing the dose to the TVB in LA-NSCLC patients. Patients with tumor distance to TVB less than 0.7 cm are likely to benefit most from proton over photon therapy.

Purpose: For prostate cancer treatment, comparable or superior biochemical control was reported when using External-Beam-Radiotherapy (EBRT) with High-Dose-Rate-Brachytherapy (HDRB)-boost, compared to dose-escalation with EBRT alone. The conformal doses produced by HDRB could allow further beneficial prostate dose-escalation, but increase in dose is limited by normal tissue toxicity. Previous works showed correlation between urethral dose and incidence of urinary toxicity, but there is a lack of established guidelines on the dose constraints to this organ. This work aimed at fitting a Normal-Tissue-Complication-Probability model to urethral stricture data collected at one institution and validating it with an external cohort, looking at neo-adjuvant androgen deprivation as dose-modifying factor.Materials and Methods: Clinical and dosimetric data of 258 patients, with a toxicity rate of 12.8%, treated at a single institution with a variety of prescription doses, were collected to fit the Lyman–Kutcher–Burman (LKB) model using the maximum likelihood method. Due to the different fractionations, doses were converted into 2 Gy-equivalent doses (α/β = 5 Gy), and urethral stricture was used as an end-point. For validation, an external cohort of 187 patients treated as part of the TROG (Trans Tasman Radiation Oncology Group) 03.04 RADAR trial with a toxicity rate of 8.7%, was used. The goodness of fit was assessed using calibration plots. The effect of neo-adjuvant androgen deprivation (AD) was analyzed separating patients who had received it prior to treatment from those who did not receive it.Results: The obtained LKB parameters were TD50 = 116.7 Gy and m = 0.23; n was fixed to 0.3, based on numerical optimization of the likelihood. The calibration plot showed a good agreement between the observed toxicity and the probability predicted by the model, confirmed by bootstrapping. For the external validation, the calibration plot showed that the observed toxicity obtained with the RADAR patients was well-represented by the fitted LKB model parameters. When patients were stratified by the use of AD TD50 decreased when AD was not present.Conclusions: Lyman–Kutcher–Burman model parameters were fitted to the risk of urethral stricture and externally validated with an independent cohort, to provide guidance on urethral tolerance doses for patients treated with a HDRB boost. For patients that did not receive AD, model fitting provided a lower TD50 suggesting a protective effect on urethra toxicity.

Purpose: Late gastrointestinal (GI) toxicity after radiotherapy for prostate cancer may have significant impact on the cancer survivor's quality of life. To date, little is known about local dose-effects after modern radiotherapy including hypofractionation. In the current study we related the local spatial distribution of radiation dose in the rectum to late patient-reported gastrointestinal (GI) toxicities for conventionally fractionated (CF) and hypofractionated (HF) modern radiotherapy in the randomized HYPRO trial.Material and Methods: Patients treated to 78 Gy in 2 Gy fractions (n = 298) or 64.6 Gy in 3.4 Gy fractions (n = 295) with available late toxicity questionnaires (n ≥ 2 within 1–5 years post-treatment) and available 3D planning data were eligible for this study. The majority received intensity modulated radiotherapy (IMRT). We calculated two types of dose surface maps: (1) the total delineated rectum with its central axis scaled to unity, and (2) the delineated rectum with a length of 7 cm along its central axis aligned on the prostate's half-height point (prostate-half). For each patient-reported GI symptom, dose difference maps were constructed by subtracting average co-registered EQD2 (equivalent dose in 2 Gy) dose maps of patients with and without the symptom of interest, separately for HF and CF. P-values were derived from permutation tests. We evaluated patient-reported moderate to severe GI symptoms.Results: Observed incidences of rectal bleeding and increased stool frequency were significantly higher in the HF group. For rectal bleeding (p = 0.016), mucus discharge (p = 0.015), and fecal incontinence (p = 0.001), significant local dose-effects were observed in HF patients but not in CF patients. For rectal pain, similar local dose-effects (p < 0.05) were observed in both groups. No significant local dose-effects were observed for increased stool frequency. Total rectum mapping vs. prostate-half mapping showed similar results.Conclusion: We demonstrated significant local dose-effect relationships for patient-reported late GI toxicity in patients treated with modern RT. HF patients were at higher risk for increased stool frequency and rectal bleeding, and showed the most pronounced local dose-effects in intermediate-high dose regions. These findings suggest that improvement of current treatment optimization protocols could lead to clinical benefit, in particular for HF treatment.

Radiation therapy (RT) of thoracic cancers may cause severe radiation dermatitis (RD), which impacts on the quality of a patient's life. Aim of this study was to analyze the incidence of acute RD and develop normal tissue complication probability (NTCP) models for severe RD in thoracic cancer patients treated with Intensity-Modulated RT (IMRT) or Passive Scattering Proton Therapy (PSPT). We analyzed 166 Non-Small-Cell Lung Cancer (NSCLC) patients prospectively treated at a single institution with IMRT (103 patients) or PSPT (63 patients). All patients were treated to a prescribed dose of 60 to 74 Gy in conventional daily fractionation with concurrent chemotherapy. RD was scored according to CTCAE v3 scoring system. For each patient, the epidermis structure (skin) was automatically defined by an in house developed segmentation algorithm. The absolute dose-surface histogram (DSH) of the skin were extracted and normalized using the Body Surface Area (BSA) index as scaling factor. Patient and treatment-related characteristics were analyzed. The Lyman-Kutcher-Burman (LKB) NTCP model recast for DSH and the multivariable logistic model were adopted. Models were internally validated by Leave-One-Out method. Model performance was evaluated by the area under the receiver operator characteristic curve, and calibration plot parameters. Fifteen of 166 (9%) patients developed severe dermatitis (grade 3). RT technique did not impact RD incidence. Total gross tumor volume (GTV) size was the only non dosimetric variable significantly correlated with severe RD (p = 0.027). Multivariable logistic modeling resulted in a single variable model including S20Gy, the relative skin surface receiving more than 20 Gy (OR = 31.4). The cut off for S20Gy was 1.1% of the BSA. LKB model parameters were TD50 = 9.5 Gy, m = 0.24, n = 0.62. Both NTCP models showed comparably high prediction and calibration performances. Despite skin toxicity has long been considered a potential limiting factor in the clinical use of PSPT, no significant differences in RD incidence was found between RT modalities. Once externally validated, the availability of NTCP models for prediction of severe RD may advance treatment planning optimization.

Purpose: For prostate cancer treatment, comparable or superior biochemical control was reported when using External-Beam-Radiotherapy (EBRT) with High-Dose-Rate-Brachytherapy (HDRB)-boost, compared to dose-escalation with EBRT alone. The conformal doses produced by HDRB could allow further beneficial prostate dose-escalation, but increase in dose is limited by normal tissue toxicity. Previous works showed correlation between urethral dose and incidence of urinary toxicity, but there is a lack of established guidelines on the dose constraints to this organ. This work aimed at fitting a Normal-Tissue-Complication-Probability model to urethral stricture data collected at one institution and validating it with an external cohort, looking at neo-adjuvant androgen deprivation as dose-modifying factor. Materials and Methods: Clinical and dosimetric data of 258 patients, with a toxicity rate of 12.8%, treated at a single institution with a variety of prescription doses, were collected to fit the Lyman–Kutcher–Burman (LKB) model using the maximum likelihood method. Due to the different fractionations, doses were converted into 2 Gy-equivalent doses (α/β = 5 Gy), and urethral stricture was used as an end-point. For validation, an external cohort of 187 patients treated as part of the TROG (Trans Tasman Radiation Oncology Group) 03.04 RADAR trial with a toxicity rate of 8.7%, was used. The goodness of fit was assessed using calibration plots. The effect of neo-adjuvant androgen deprivation (AD) was analyzed separating patients who had received it prior to treatment from those who did not receive it. Results: The obtained LKB parameters were TD50 = 116.7 Gy and m = 0.23; n was fixed to 0.3, based on numerical optimization of the likelihood. The calibration plot showed a good agreement between the observed toxicity and the probability predicted by the model, confirmed by bootstrapping. For the external validation, the calibration plot showed that the observed toxicity obtained with the RADAR patients was well-represented by the fitted LKB model parameters. When patients were stratified by the use of AD TD50 decreased when AD was not present. Conclusions: Lyman–Kutcher–Burman model parameters were fitted to the risk of urethral stricture and externally validated with an independent cohort, to provide guidance on urethral tolerance doses for patients treated with a HDRB boost. For patients that did not receive AD, model fitting provided a lower TD50 suggesting a protective effect on urethra toxicity. [ABSTRACT FROM AUTHOR]

Purpose: Late gastrointestinal (GI) toxicity after radiotherapy for prostate cancer may have significant impact on the cancer survivor's quality of life. To date, little is known about local dose-effects after modern radiotherapy including hypofractionation. In the current study we related the local spatial distribution of radiation dose in the rectum to late patient-reported gastrointestinal (GI) toxicities for conventionally fractionated (CF) and hypofractionated (HF) modern radiotherapy in the randomized HYPRO trial. Material and Methods: Patients treated to 78 Gy in 2 Gy fractions (n = 298) or 64.6 Gy in 3.4 Gy fractions (n = 295) with available late toxicity questionnaires (n ≥ 2 within 1–5 years post-treatment) and available 3D planning data were eligible for this study. The majority received intensity modulated radiotherapy (IMRT). We calculated two types of dose surface maps: (1) the total delineated rectum with its central axis scaled to unity, and (2) the delineated rectum with a length of 7 cm along its central axis aligned on the prostate's half-height point (prostate-half). For each patient-reported GI symptom, dose difference maps were constructed by subtracting average co-registered EQD2 (equivalent dose in 2 Gy) dose maps of patients with and without the symptom of interest, separately for HF and CF. P -values were derived from permutation tests. We evaluated patient-reported moderate to severe GI symptoms. Results: Observed incidences of rectal bleeding and increased stool frequency were significantly higher in the HF group. For rectal bleeding (p = 0.016), mucus discharge (p = 0.015), and fecal incontinence (p = 0.001), significant local dose-effects were observed in HF patients but not in CF patients. For rectal pain, similar local dose-effects (p < 0.05) were observed in both groups. No significant local dose-effects were observed for increased stool frequency. Total rectum mapping vs. prostate-half mapping showed similar results. Conclusion: We demonstrated significant local dose-effect relationships for patient-reported late GI toxicity in patients treated with modern RT. HF patients were at higher risk for increased stool frequency and rectal bleeding, and showed the most pronounced local dose-effects in intermediate-high dose regions. These findings suggest that improvement of current treatment optimization protocols could lead to clinical benefit, in particular for HF treatment. [ABSTRACT FROM AUTHOR]

Radiation therapy (RT) of thoracic cancers may cause severe radiation dermatitis (RD), which impacts on the quality of a patient's life. Aim of this study was to analyze the incidence of acute RD and develop normal tissue complication probability (NTCP) models for severe RD in thoracic cancer patients treated with Intensity-Modulated RT (IMRT) or Passive Scattering Proton Therapy (PSPT). We analyzed 166 Non-Small-Cell Lung Cancer (NSCLC) patients prospectively treated at a single institution with IMRT (103 patients) or PSPT (63 patients). All patients were treated to a prescribed dose of 60 to 74 Gy in conventional daily fractionation with concurrent chemotherapy. RD was scored according to CTCAE v3 scoring system. For each patient, the epidermis structure (skin) was automatically defined by an in house developed segmentation algorithm. The absolute dose-surface histogram (DSH) of the skin were extracted and normalized using the Body Surface Area (BSA) index as scaling factor. Patient and treatment-related characteristics were analyzed. The Lyman-Kutcher-Burman (LKB) NTCP model recast for DSH and the multivariable logistic model were adopted. Models were internally validated by Leave-One-Out method. Model performance was evaluated by the area under the receiver operator characteristic curve, and calibration plot parameters. Fifteen of 166 (9%) patients developed severe dermatitis (grade 3). RT technique did not impact RD incidence. Total gross tumor volume (GTV) size was the only non dosimetric variable significantly correlated with severe RD (p = 0.027). Multivariable logistic modeling resulted in a single variable model including S 20Gy, the relative skin surface receiving more than 20 Gy (OR = 31.4). The cut off for S 20Gy was 1.1% of the BSA. LKB model parameters were TD50 = 9.5 Gy, m = 0.24, n = 0.62. Both NTCP models showed comparably high prediction and calibration performances. Despite skin toxicity has long been considered a potential limiting factor in the clinical use of PSPT, no significant differences in RD incidence was found between RT modalities. Once externally validated, the availability of NTCP models for prediction of severe RD may advance treatment planning optimization. [ABSTRACT FROM AUTHOR]

Objectives: To compare treatment plans of intensity modulated radiotherapy (IMRT), volumetric modulated arc radiotherapy (VMAT), and helical tomotherapy (HT) with simultaneous integrated boost (SIB) technique for esophageal cancer (EC) of different locations using dosimetry and radiobiology. Methods: Forty EC patients were planned for IMRT, VMAT, and HT plans, including 10 cases located in the cervix, upper, middle, and lower thorax, respectively. Dose-volume metrics, conformity index (CI), homogeneity index (HI), tumor control probability (TCP), and normal tissue complication probability (NTCP) were analyzed to evaluate treatment plans. Results: HT showed significant improvement over IMRT and VMAT in terms of CI (p = 0.007), HI (p < 0.001), and TCP (p < 0.001) in cervical EC. IMRT yielded more superior CI, HI and TCP compared with VMAT and HT in upper and middle thoracic EC (all p < 0.05). Additionally, V30 (27.72 ± 8.67%), mean dose (1801.47 ± 989.58cGy), and NTCP (Niemierko model: 0.44 ± 0.55%; Lyman-Kutcher-Burman model: 0.61 ± 0.59%) of heart in IMRT were sharply reduced than VMAT and HT in middle thoracic EC. For lower thoracic EC, the three techniques offered similar CI and HI (all p > 0.05). But VMAT dramatically lowered liver V30 (9.97 ± 2.84%), and reduced NTCP of lungs (Niemierko model: 0.47 ± 0.48%; Lyman-Kutcher-Burman model: 1.41 ± 1.07%) and liver (Niemierko model: 0.10 ± 0.08%; Lyman-Kutcher-Burman model: 0.17 ± 0.17%). Conclusions: HT was a good option for cervical EC with complex target coverage but little lungs and heart involvement as it achieved superior dose conformity and uniformity. Due to potentially improving tumor control and reducing heart dose with acceptable lungs sparing, IMRT was a preferred choice for upper and middle thoracic EC with large lungs involvement. VMAT could ameliorate therapeutic ratio and lower lungs and liver toxicity, which was beneficial for lower thoracic EC with little thoracic involvement but being closer to heart and liver. Individually choosing optimal technique for EC in different location will be warranted. [ABSTRACT FROM AUTHOR]

Purpose: To test the hypothesis that increasing radiation dose to the thoracic marrow (TM) contributes to the development of hematologic toxicities (HT) in esophageal cancer (EC) patients receiving chemoradiation therapy (CRT). Methods: We identified EC cases treated with curative intent CRT at our institution from 2007 to 2016. The TM was contoured as the union of the vertebral bodies (VB) from T1-L1, the ribs from T1-L1, and the sternum. The TM-mean dose and the TM volume receiving at least 5–50 Gy (V5-V50) were collected. Grade ≥ 3 HT (HT3+) was the primary endpoint. Normal tissue complication probability (NTCP) was evaluated using the Lyman-Kutcher-Burman (LKB) model. Logistic regression was used to test associations between HT3+ and dosimetric parameters. Odds ratios (OR) and 95% confidence intervals (CI) are reported with p < 0.05 considered significant. Receiver operating characteristics analysis was used to determine optimal cut points. Results: We identified 137 EC cases, and most received concurrent carboplatin/paclitaxel (N = 83). Median radiation dose was 50.4 Gy (IQR = 50.4–50.4 Gy). The rate of HT3+ was 39.4%. Optimization of the LKB model yielded the results n = 0.70, m = 0.67, and TD50 = 20.1 Gy. The TM-V30 was most strongly associated with HT3+ and on multivariate analysis, patients with TM-V30 ≥ 14% had a 5.7-fold (95% CI 2.42–14.54, p < 0.001) increased odds of HT3+ in the entire cohort and a 4-fold (95% CI 1.54–11.11, p = 0.006) increased odds of HT3+ in the carboplatin/paclitaxel cohort compared to patients with TM-V30 < 14%. Radiation dose to the VB and rib sub-sites of the TM were also associated with HT3+, particularly VB-V40. Conclusion: We found that increasing TM radiation dose was associated with HT3+ in EC patients treated with CRT. Radiation dose to the VB and rib sub-sites were also associated with HT3+. These findings suggest that limiting radiation dose to the TM (or its sub-sites) may be sufficient to decrease HT3+, but further prospective evaluation of these results is needed. [ABSTRACT FROM AUTHOR]

PurposeThe purpose of this study is to investigate whether machine learning with dosiomic, radiomic, and demographic features allows for xerostomia risk assessment more precise than normal tissue complication probability (NTCP) models based on the mean radiation dose to parotid glands.Material and methodsA cohort of 153 head-and-neck cancer patients was used to model xerostomia at 0–6 months (early), 6–15 months (late), 15–24 months (long-term), and at any time (a longitudinal model) after radiotherapy. Predictive power of the features was evaluated by the area under the receiver operating characteristic curve (AUC) of univariate logistic regression models. The multivariate NTCP models were tuned and tested with single and nested cross-validation, respectively. We compared predictive performance of seven classification algorithms, six feature selection methods, and ten data cleaning/class balancing techniques using the Friedman test and the Nemenyi post hoc analysis.ResultsNTCP models based on the parotid mean dose failed to predict xerostomia (AUCs 0.85), dose gradients in the right–left (AUCs > 0.78), and the anterior–posterior (AUCs > 0.72) direction. Multivariate models of long-term xerostomia were typically based on the parotid volume, the parotid eccentricity, and the dose–volume histogram (DVH) spread with the generalization AUCs ranging from 0.74 to 0.88. On average, support vector machines and extra-trees were the top performing classifiers, whereas the algorithms based on logistic regression were the best choice for feature selection. We found no advantage in using data cleaning or class balancing methods.ConclusionWe demonstrated that incorporation of organ- and dose-shape descriptors is beneficial for xerostomia prediction in highly conformal radiotherapy treatments. Due to strong reliance on patient-specific, dose-independent factors, our results underscore the need for development of personalized data-driven risk profiles for NTCP models of xerostomia. The facilitated machine learning pipeline is described in detail and can serve as a valuable reference for future work in radiomic and dosiomic NTCP modeling.

Purpose: The purpose of this study is to investigate whether machine learning with dosiomic, radiomic, and demographic features allows for xerostomia risk assessment more precise than normal tissue complication probability (NTCP) models based on the mean radiation dose to parotid glands. Material and methods: A cohort of 153 head-and-neck cancer patients was used to model xerostomia at 0-6 months (early), 6-15 months (late), 15-24 months (long-term), and at any time (a longitudinal model) after radiotherapy. Predictive power of the features was evaluated by the area under the receiver operating characteristic curve (AUC) of univariate logistic regression models. The multivariate NTCP models were tuned and tested with single and nested cross-validation, respectively. We compared predictive performance of seven classification algorithms, six feature selection methods, and ten data cleaning/class balancing techniques using the Friedman test and the Nemenyi post hoc analysis. Results: NTCP models based on the parotid mean dose failed to predict xerostomia (AUCs<0.60). The most informative predictors were found for late and long-term xerostomia. Late xerostomia correlated with the contralateral dose gradient in the anterior- posterior (AUC=0.72) and the right-left (AUC=0.68) direction, whereas long-term xerostomia was associated with parotid volumes (AUCs>0.85), dose gradients in the right-left (AUCs>0.78), and the anterior-posterior (AUCs>0.72) direction. Multivariate models of long-term xerostomia were typically based on the parotid volume, the parotid eccentricity, and the dose-volume histogram (DVH) spread with the generalization AUCs ranging from 0.74 to 0.88. On average, support vector machines and extra-trees were the top performing classifiers, whereas the algorithms based on logistic regression were the best choice for feature selection. We found no advantage in using data cleaning or class balancing methods. Conclusion: We demonstrated that incorporation of organ- and dose-shape descriptors is beneficial for xerostomia prediction in highly conformal radiotherapy treatments. Due to strong reliance on patient-specific, dose-independent factors, our results underscore the need for development of personalized data-driven risk profiles for NTCP models of xerostomia. The facilitated machine learning pipeline is described in detail and can serve as a valuable reference for future work in radiomic and dosiomic NTCP modeling. [ABSTRACT FROM AUTHOR]

Introduction: The use of volumetric modulated arc therapy (VMAT) with flattening-filter-free (FFF) beams is becoming more prevalent in lung cancer stereotactic body radiotherapy (SBRT). The aim in this study was to assess the impact of dosimetric and radiobiological differences between FFF and flattening filter (FF) beams for lung SBRT based on the target volume., Methods: A total of 198 lung stereotactic body radiation therapy treatment plans with FFF beams and FF beams were retrospectively selected for this study. For all plans, the prescribed dose was 50 Gy/5 fractions, and the dose volume histogram (DVH) for the target and organs at risk (OAR) and the normal tissue complication probability (NTCP) of the lung were recorded and compared. Moreover, monitor units (MUs), the beam on-time and the treatment time were evaluated., Results: The study was performed following the Radiation Therapy Oncology Group (RTOG) 0813 and 0915 protocols. No significant differences in D 90 , coverage rate (CR) or conformity index (CI) of the target were observed between FFF beams and FF beams ( p >0.05). The D 2 , R 50% and gradient index (GI) for the target improved with FFF beams compared with FF beams ( p <0.05). FFF beams also significantly reduced the dose for the lung, heart, spinal cord, esophagus and NTCP of the lung ( p <0.05), compared with FF beams. However, there was no significant difference in sparing of the trachea ( p >0.05). The mean MUs, beam on-time and treatment time were 1871 ± 278 MUs, 3.2 ± 0.2 min and 3.9 ± 0.3 min for FFF beams, and 1890 ± 260 MUs, 4.2 ± 0.3 min and 4.8 ± 0.4 min for FF beams, respectively., Discussion: The FFF beam technique for lung SBRT with VMAT results in a better dose fall-off, better dose-sparing of OAR, lower NTCP of the lung and a shorter beam on-time compared with the FF beam technique. Additionally, the improvement in target and OAR-sparing for FFF beams was increased with increasing target volume., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Wu, Song, Li, Tang and Wu.)