Deep learning for automatic head and neck lymph node level delineation provides expert-level accuracy.

Background: Deep learning-based head and neck lymph node level (HN_LNL) autodelineation is of high relevance to radiotherapy research and clinical treatment planning but still underinvestigated in academic literature. In particular, there is no publicly available open-source solution for large-scale autosegmentation of HN_LNL in the research setting. Methods: An expert-delineated cohort of 35 planning CTs was used for training of an nnU-net 3D-fullres/2D-ensemble model for autosegmentation of 20 different HN_LNL. A second cohort acquired at the same institution later in time served as the test set (n = 20). In a completely blinded evaluation, 3 clinical experts rated the quality of deep learning autosegmentations in a head-to-head comparison with expert-created contours. For a subgroup of 10 cases, intraobserver variability was compared to the average deep learning autosegmentation accuracy on the original and recontoured set of expert segmentations. A postprocessing step to adjust craniocaudal boundaries of level autosegmentations to the CT slice plane was introduced and the effect of autocontour consistency with CT slice plane orientation on geometric accuracy and expert rating was investigated. Results: Blinded expert ratings for deep learning segmentations and expert-created contours were not significantly different. Deep learning segmentations with slice plane adjustment were rated numerically higher (mean, 81.0 vs. 79.6, p = 0.185) and deep learning segmentations without slice plane adjustment were rated numerically lower (77.2 vs. 79.6, p = 0.167) than manually drawn contours. In a head-to-head comparison, deep learning segmentations with CT slice plane adjustment were rated significantly better than deep learning contours without slice plane adjustment (81.0 vs. 77.2, p = 0.004). Geometric accuracy of deep learning segmentations was not different from intraobserver variability (mean Dice per level, 0.76 vs. 0.77, p = 0.307). Clinical significance of contour consistency with CT slice plane orientation was not represented by geometric accuracy metrics (volumetric Dice, 0.78 vs. 0.78, p = 0.703). Conclusions: We show that a nnU-net 3D-fullres/2D-ensemble model can be used for highly accurate autodelineation of HN_LNL using only a limited training dataset that is ideally suited for large-scale standardized autodelineation of HN_LNL in the research setting. Geometric accuracy metrics are only an imperfect surrogate for blinded expert rating.

Low-dose radiotherapy of osteoarthritis: from biological findings to clinical effects-challenges for future studies.

Osteoarthritis (OA) is one of the most common and socioeconomically relevant diseases, with rising incidence and prevalence especially with regard to an ageing population in the Western world. Over the decades, the scientific perception of OA has shifted from a simple degeneration of cartilage and bone to a multifactorial disease involving various cell types and immunomodulatory factors. Despite a wide range of conventional treatment modalities available, a significant proportion of patients remain treatment refractory. Low-dose radiotherapy (LDRT) has been used for decades in the treatment of patients with inflammatory and/or degenerative diseases and has proven a viable option even in cohorts of patients with a rather poor prognosis. While its justification mainly derives from a vast body of empirical evidence, prospective randomized trials have until now failed to prove the effectiveness of LDRT. Nevertheless, over the decades, adaptions of LDRT treatment modalities have evolved using lower dosages with establishment of different treatment schedules for which definitive clinical proof is still pending. Preclinical research has revealed that the immune system is modulated by LDRT and very recently osteoimmunological mechanisms have been described. Future studies and investigations further elucidating the underlying mechanisms are an essential key to clarify the optimal patient stratification and treatment procedure, considering the patients' inflammatory status, age, and sex. The present review aims not only to present clinical and preclinical knowledge about the mechanistic and beneficial effects of LDRT, but also to emphasize topics that will need to be addressed in future studies. Further, a concise overview of the current status of the underlying radiobiological knowledge of LDRT for clinicians is given, while seeking to stimulate further translational research.

Dose-escalated re-irradiation improves outcome in locally recurrent head and neck cancer - Results of a large multicenter analysis.

To determine efficacy and prognostic parameters of definitive re-irradiation of locoregionally recurrent squamous cell carcinoma of the head and neck (HNSCC). MATERIALS AND METHODS: Patients with locoregionally recurrent or second primary HNSCC undergoing re-irradiation with modern radiotherapy technique were eligible for this multicentric retrospective analysis. Main endpoints were overall survival (OS), progression-free survival (PFS) and locoregional control (LC). Univariate analyses were performed using the Kaplan Meier Method (log-rank). For multivariable analysis, Cox regression was used. RESULTS: A total of 253 patients treated between 2009 and 2020 at 16 university hospitals in Germany were included. The median follow up was 27.4 months (range 0.5-130). The median OS and PFS were 13.2 (CI: 10.7 - 15.7) months and 7.9 (CI: 6.7 - 9.1) months, respectively, corresponding to two-year OS and PFS rates of 29 % and 19 %. Rates of locoregional progression and "in-field-failure" were 62 % and 51 % after two years. Multivariable Cox regression analysis identified good ECOG performance status and high radiation dose as independent prognostic parameters for OS. Doses above 50 Gy (EQD2) achieved longer median OS of 17.8 months (vs 11.7 months, p < 0.01) and longer PFS of 9.6 months (vs 6.8 months, p < 0.01). In addition, there was a trend for worse survival in patients with tracheostomy (multivariable, p = 0.061). Concomitant systemic therapy did not significantly impact PFS or OS. CONCLUSION: Re-irradiation of locally recurrent or second primary HNSCC is efficient, especially if doses above 50 Gy (EQD2) are delivered. ECOG performance score was the strongest prognostic parameter for OS and PFS.

FSRT vs. SRS in Brain Metastases-Differences in Local Control and Radiation Necrosis-A Volumetric Study.

Background: While the role of stereotactic radiotherapy for brain metastases is increasing, evidence on the comparative efficacy and safety of fractionated stereotactic radiotherapy (FSRT) and single-session radiosurgery (SRS) is scarce. Methods: Longitudinal volumetric analysis was performed in a consecutive cohort of 120 patients and 190 brain metastases (>0.065 cm3 in volume / > ~5 mm in diameter) treated exclusively with FSRT (n = 98) and SRS (n = 92), respectively. A total of 972 tumor segmentations was used, averaging 5.1 time points per metastasis. Progression was defined using a volumetric extension of the RANO-BM criteria. Local control and radionecrosis were compared for lesions treated with FSRT and SRS, respectively. Results: Metastases treated with FSRT were significantly larger at baseline (mean, 4.66 vs. 0.40 cm3, p < 0.001). Biologically effective dose (BED) for metastases (α/ß = 12, linear-quadratic-cubic model) was significantly associated with local control, whereas BED for normal brain (α/ß = 2, linear-quadratic model) was significantly associated with radionecrosis. Median time to local progression was 22.9 months in the FSRT group compared to 14.5 months in the SRS group (p = 0.022). Overall radionecrosis rate at 12 months was 3.4% for FSRT and 14.8% for SRS (p = 0.010). Radionecrosis °IV requiring resection with histologic proof of radiation necrosis also was significantly reduced in the FSRT group (FSRT 0.0% vs. SRS 3.9%, p = 0.041). In multivariate analysis, FSRT was associated with reduced risk of progression (HR 0.47, p = 0.015) and reduced risk of radionecrosis (HR 0.18, p = 0.045). Conclusions: This volumetric study provides initial evidence that the improvements in therapeutic ratio expected for FSRT in larger brain metastases, might equally extend into the domain of smaller metastases, traditionally less considered for fractionated treatment. FSRT might constitute an important tool to further increase local control and reduce radionecrosis risk in stereotactic radiotherapy for brain metastases, that should be assessed in randomized intervention trials.

Volumetric Regression in Brain Metastases After Stereotactic Radiotherapy: Time Course, Predictors, and Significance.

BACKGROUND: There is insufficient understanding of the natural course of volumetric regression in brain metastases after stereotactic radiotherapy (SRT) and optimal volumetric criteria for the assessment of response and progression in radiotherapy clinical trials for brain metastases are currently unknown. METHODS: Volumetric analysis via whole-tumor segmentation in contrast-enhanced 1 mm³-isotropic T1-Mprage sequences before SRT and during follow-up. A total of 3,145 MRI studies of 419 brain metastases from 189 patients were segmented. Progression was defined using a volumetric extension of the RANO-BM criteria. A subset of 205 metastases without progression/radionecrosis during their entire follow-up of at least 3 months was used to study the natural course of volumetric regression after SRT. Predictors for volumetric regression were investigated. A second subset of 179 metastases was used to investigate the prognostic significance of volumetric response at 3 months (defined as ≥20% and ≥65% volume reduction, respectively) for subsequent local control. RESULTS: Median relative metastasis volume post-SRT was 66.9% at 6 weeks, 38.6% at 3 months, 17.7% at 6 months, 2.7% at 12 months and 0.0% at 24 months. Radioresistant histology and FSRT vs. SRS were associated with reduced tumor regression for all time points. In multivariate linear regression, radiosensitive histology (p=0.006) was the only significant predictor for metastasis regression at 3 months. Volumetric regression ≥20% at 3 months post-SRT was the only significant prognostic factor for subsequent control in multivariate analysis (HR 0.63, p=0.023), whereas regression ≥65% was no significant predictor. CONCLUSIONS: Volumetric regression post-SRT does not occur at a constant rate but is most pronounced in the first 6 weeks to 3 months. Despite decreasing over time, volumetric regression continues beyond 6 months post-radiotherapy and may lead to complete resolution of controlled lesions by 24 months. Radioresistant histology is associated with slower regression. We found that a cutoff of ≥20% regression for the volumetric definition of response at 3 months post-SRT was predictive for subsequent control whereas the currently proposed definition of ≥65% was not. These results have implications for standardized volumetric criteria in future radiotherapy trials for brain metastases.

Paragangliomas of the Head and Neck: Local Control and Functional Outcome Following Fractionated Stereotactic Radiotherapy.

OBJECTIVES: To investigate local control and functional outcome following state-of-the-art fractionated stereotactic radiotherapy (FSRT) for paragangliomas of the head and neck. METHODS: In total, 40 consecutive patients with paragangliomas of the head and neck received conventionally FSRT from 2003 to 2016 at the Department of Radiation Oncology of the University Hospital Erlangen. Local control, toxicities, and functional outcome were examined during follow-up. In total, 148 magnetic resonance imaging studies were subjected to longitudinal volumetric analysis using whole tumor segmentation in a subset of 22 patients. RESULTS: A total of 80.0% (32/40) of patients received radiotherapy as part of their primary treatment. In 20.0% (8/40) of patients, radiation was used as salvage treatment after tumor recurrence in patients initially treated with surgery alone. The median dose applied was 54.0 Gy (interdecile range, 50.4 to 56.0 Gy) in single doses of 1.8 or 2 Gy. Local control was 100% after a median imaging follow-up of 52.2 months (range, 0.8 to 152.9 mo). The volumetric analysis confirmed sustained tumor control in a subset of 22 patients and showed transient enlargement (range, 129.6% to 151.2%) in 13.6% of cases (3/22). After a median volumetric follow-up of 24.6 months mean tumor volume had diminished to 86.1% compared with initial volume. In total, 52.5% (21/40) of patients reported improved symptoms after radiotherapy, 40% (16/40) observed no subjective change with only 7.5% (3/40) reporting significant worsening. CONCLUSIONS: State-of-the-art FSRT provides excellent control and favorable functional outcome in patients with paragangliomas of the head and neck. The volumetric analysis provides improved evidence for sustained tumor control.

Influence of inter-observer delineation variability on radiomics stability in different tumor sites.

BACKGROUND: Radiomics is a promising methodology for quantitative analysis and description of radiological images using advanced mathematics and statistics. Tumor delineation, which is still often done manually, is an essential step in radiomics, however, inter-observer variability is a well-known uncertainty in radiation oncology. This study investigated the impact of inter-observer variability (IOV) in manual tumor delineation on the reliability of radiomic features (RF). METHODS: Three different tumor types (head and neck squamous cell carcinoma (HNSCC), malignant pleural mesothelioma (MPM) and non-small cell lung cancer (NSCLC)) were included. For each site, eleven individual tumors were contoured on CT scans by three experienced radiation oncologists. Dice coefficients (DC) were calculated for quantification of delineation variability. RF were calculated with an in-house developed software implementation, which comprises 1404 features: shape (n = 18), histogram (n = 17), texture (n = 137) and wavelet (n = 1232). The IOV of RF was studied using the intraclass correlation coefficient (ICC). An ICC >0.8 indicates a good reproducibility. For the stable RF, an average linkage hierarchical clustering was performed to identify classes of uncorrelated features. RESULTS: Median DC was high for NSCLC (0.86, range 0.57-0.90) and HNSCC (0.72, 0.21-0.89), whereas it was low for MPM (0.26, 0-0.9) indicating substantial IOV. Stability rate of RF correlated with DC and depended on tumor site, showing a high stability in NSCLC (90% of total parameters), acceptable stability in HNSCC (59% of total parameters) and low stability in MPM (36% of total parameters). Shape features showed the weakest stability across all tumor types. Hierarchical clustering revealed 14 groups of correlated and stable features for NSCLC and 6 groups for both HNSCC and MPM. CONCLUSION: Inter-observer delineation variability has a relevant influence on radiomics analysis and is strongly influenced by tumor type. This leads to a reduced number of suitable imaging features.

Potential dosimetric benefits of adaptive tumor tracking over the internal target volume concept for stereotactic body radiation therapy of pancreatic cancer.

BACKGROUND: Radiotherapy for pancreatic cancer has two major challenges: (I) the tumor is adjacent to several critical organs and, (II) the mobility of both, the tumor and its surrounding organs at risk (OARs). A treatment planning study simulating stereotactic body radiation therapy (SBRT) for pancreatic tumors with both the internal target volume (ITV) concept and the tumor tracking approach was performed. The two respiratory motion-management techniques were compared in terms of doses to the target volume and organs at risk. METHODS AND MATERIALS: Two volumetric-modulated arc therapy (VMAT) treatment plans (5 × 5 Gy) were created for each of the 12 previously treated pancreatic cancer patients, one using the ITV concept and one the tumor tracking approach. To better evaluate the overall dose delivered to the moving tumor volume, 4D dose calculations were performed on four-dimensional computed tomography (4DCT) scans. The resulting planning target volume (PTV) size for each technique was analyzed. Target and OAR dose parameters were reported and analyzed for both 3D and 4D dose calculation. RESULTS: Tumor motion ranged from 1.3 to 11.2 mm. Tracking led to a reduction of PTV size (max. 39.2%) accompanied with significant better tumor coverage (p<0.05, paired Wilcoxon signed rank test) both in 3D and 4D dose calculations and improved organ at risk sparing. Especially for duodenum, stomach and liver, the mean dose was significantly reduced (p<0.05) with tracking for 3D and 4D dose calculations. CONCLUSIONS: By using an adaptive tumor tracking approach for respiratory-induced pancreatic motion management, a significant reduction in PTV size can be achieved, which subsequently facilitates treatment planning, and improves organ dose sparing. The dosimetric benefit of tumor tracking is organ and patient-specific.

Risk for surgical complications after previous stereotactic body radiotherapy of the spine.

OBJECT: Stereotactic body radiotherapy (SBRT) for vertebral metastases has emerged as a promising technique, offering high rates of symptom relief and local control combined with low risk of toxicity. Nonetheless, local failure or vertebral instability may occur after spine SBRT, generating the need for subsequent surgery in the irradiated region. This study evaluated whether there is an increased incidence of surgical complications in patients previously treated with SBRT at the index level. METHODS: Based upon a retrospective international database of 704 cases treated with SBRT for vertebral metastases, 30 patients treated at 6 different institutions were identified who underwent surgery in a region previously treated with SBRT. RESULTS: Thirty patients, median age 59 years (range 27-84 years) underwent SBRT for 32 vertebral metastases followed by surgery at the same vertebra. Median follow-up time from SBRT was 17 months. In 17 cases, conventional radiotherapy had been delivered prior to SBRT at a median dose of 30 Gy in median 10 fractions. SBRT was administered with a median prescription dose of 19.3 Gy (range 15-65 Gy) delivered in median 1 fraction (range 1-17) (median EQD2/10 = 44 Gy). The median time interval between SBRT and surgical salvage therapy was 6 months (range 1-39 months). Reasons for subsequent surgery were pain (n = 28), neurological deterioration (n = 15) or fracture of the vertebral body (n = 13). Open surgical decompression (n = 24) and/or stabilization (n = 18) were most frequently performed; Five patients (6 vertebrae) were treated without complications with vertebroplasty only. Increased fibrosis complicating the surgical procedure was explicitly stated in one surgical report. Two durotomies occurred which were closed during the operation, associated with a neurological deficit in one patient. Median blood loss was 500 ml, but five patients had a blood loss of more than 1 l during the procedure. Delayed wound healing was reported in two cases. One patient died within 30 days of the operation. CONCLUSION: In this series of surgical interventions following spine SBRT, the overall complication rate was 19%, which appears comparable to primary surgery without previous SBRT. Prior spine SBRT does not appear to significantly increase the risk of intra- and post-surgical complications.

SBRT in operable early stage lung cancer patients.

Since decades the gold standard for treatment of early stage non-small cell lung cancer (NSCLC) is surgical lobectomy plus mediastinal lymph node dissection. Patients in worse health status are treated with sublobar resection or radiation treatment. With development of stereotactic-body-radiotherapy (SBRT), outcome of patients treated with radiation was substantially improved. Comparison of SBRT and surgical techniques is difficult due to the lack of randomized trials. However, all available evidence in form of case control studies of population based studies show equivalence between sublobar resection and SBRT indicating that SBRT-when performed by a trained and experienced team-should be offered to all high-risk surgical patients. For patients not willing to take the risk of lobectomy and therefore refusing surgery, SBRT is an excellent treatment option.

Dosimetric consequences of translational and rotational errors in frame-less image-guided radiosurgery.

BACKGROUND: To investigate geometric and dosimetric accuracy of frame-less image-guided radiosurgery (IG-RS) for brain metastases. METHODS AND MATERIALS: Single fraction IG-RS was practiced in 72 patients with 98 brain metastases. Patient positioning and immobilization used either double- (n = 71) or single-layer (n = 27) thermoplastic masks. Pre-treatment set-up errors (n = 98) were evaluated with cone-beam CT (CBCT) based image-guidance (IG) and were corrected in six degrees of freedom without an action level. CBCT imaging after treatment measured intra-fractional errors (n = 64). Pre- and post-treatment errors were simulated in the treatment planning system and target coverage and dose conformity were evaluated. Three scenarios of 0 mm, 1 mm and 2 mm GTV-to-PTV (gross tumor volume, planning target volume) safety margins (SM) were simulated. RESULTS: Errors prior to IG were 3.9 mm ± 1.7 mm (3D vector) and the maximum rotational error was 1.7° ± 0.8° on average. The post-treatment 3D error was 0.9 mm ± 0.6 mm. No differences between double- and single-layer masks were observed. Intra-fractional errors were significantly correlated with the total treatment time with 0.7 mm ± 0.5 mm and 1.2 mm ± 0.7 mm for treatment times ≤23 minutes and >23 minutes (p<0.01), respectively. Simulation of RS without image-guidance reduced target coverage and conformity to 75% ± 19% and 60% ± 25% of planned values. Each 3D set-up error of 1 mm decreased target coverage and dose conformity by 6% and 10% on average, respectively, with a large inter-patient variability. Pre-treatment correction of translations only but not rotations did not affect target coverage and conformity. Post-treatment errors reduced target coverage by >5% in 14% of the patients. A 1 mm safety margin fully compensated intra-fractional patient motion. CONCLUSIONS: IG-RS with online correction of translational errors achieves high geometric and dosimetric accuracy. Intra-fractional errors decrease target coverage and conformity unless compensated with appropriate safety margins.