Perioperative Differences Between Outpatient and Inpatient Pathways Following Hip and Knee Arthroplasty.

Background: Optimization of clinical pathways and logistics led to the introduction of outpatient joint arthroplasty of the hip and knee. Nevertheless, little is known about what these current protocols look like and how they differ from "standard" inpatient protocols. This study aimed to find preoperative, intraoperative, and postoperative differences between outpatient and inpatient pathways. Methods: A questionnaire (ranging between 23 and 37 items) was developed and administered by email to orthopedic surgeons who were a member of the Dutch Hip Society and Dutch Knee Society. Survey response rate was 38% (N = 117). Results: No significant differences were found in preoperative pathway characteristics. The administration regime for tranexamic acid significantly differed between outpatient and inpatient pathways (P < .001 and P = .002 for hip and knee arthroplasty, respectively), with outpatient pathways using a combined (eg, oral and intravenous) administration regime more frequently. The perioperative antibiotic prophylaxis regime also significantly differed between outpatient and inpatient pathways (P < .001 and P = .014, respectively), with outpatient pathways more frequently incorporating fewer antibiotic doses. Same-day postoperative mobilization significantly less often occurred if surgery took place later that day in inpatient hip arthroplasty pathways (24%; P = .034). Postoperative hemoglobin-check occurred significantly more often on indication in outpatient than in inpatient hip and knee arthroplasty pathways (∼75% vs ∼25%; P = .001). Conclusions: Few intraoperative and postoperative differences in outpatient and inpatient pathways were found and probably mainly relied on logistical grounds. Nonetheless, findings suggested that outpatient pathways tended to be more up-to-date and innovative than inpatient pathways.

Deep learning for automated contouring of neurovascular structures on magnetic resonance imaging for prostate cancer patients.

Background and purpose: Manual contouring of neurovascular structures on prostate magnetic resonance imaging (MRI) is labor-intensive and prone to considerable interrater disagreement. Our aim is to contour neurovascular structures automatically on prostate MRI by deep learning (DL) to improve workflow and interrater agreement. Materials and methods: Segmentation of neurovascular structures was performed on pre-treatment 3.0 T MRI data of 131 prostate cancer patients (training [n = 105] and testing [n = 26]). The neurovascular structures include the penile bulb (PB), corpora cavernosa (CCs), internal pudendal arteries (IPAs), and neurovascular bundles (NVBs). Two DL networks, nnU-Net and DeepMedic, were trained for auto-contouring on prostate MRI and evaluated using volumetric Dice similarity coefficient (DSC), mean surface distances (MSD), Hausdorff distances, and surface DSC. Three radiation oncologists evaluated the DL-generated contours and performed corrections when necessary. Interrater agreement was assessed and the time required for manual correction was recorded. Results: nnU-Net achieved a median DSC of 0.92 (IQR: 0.90-0.93) for the PB, 0.90 (IQR: 0.86-0.92) for the CCs, 0.79 (IQR: 0.77-0.83) for the IPAs, and 0.77 (IQR: 0.72-0.81) for the NVBs, which outperformed DeepMedic for each structure (p < 0.03). nnU-Net showed a median MSD of 0.24 mm for the IPAs and 0.71 mm for the NVBs. The median interrater DSC ranged from 0.93 to 1.00, with the majority of cases (68.9%) requiring manual correction times under two minutes. Conclusions: DL enables reliable auto-contouring of neurovascular structures on pre-treatment MRI data, easing the clinical workflow in neurovascular-sparing MR-guided radiotherapy.

Orthopaedic surgeons' perspective on the implementation of outpatient hip and knee arthroplasty - Results of a nationwide survey.

Background: Outpatient joint arthroplasty (OJA) for the hip and knee is gaining popularity among orthopaedic surgeons worldwide. The purposes of this study were to (1) assess the proportion of Dutch orthopaedic surgeons who perform OJA; (2) identify surgeons' willingness to implement OJA in the future; (3) identify reasons and barriers to implement OJA; and (4) gather surgeon's perspective on the implementation of OJA. Methods: A 20-item survey was developed and administered by email to orthopaedic surgeons who are a member of the Dutch Hip Society and Dutch Knee Society. Survey response rate was 40% (N = 123). Results: Twenty-two respondents (18%) already implemented OJA, and 46% of respondents (who don't perform OJA) were interested to implement OJA in the future. Reasons to perform OJA included own positive experiences (82%), available evidence (77%) and patients' request (77%). Proponents' and opponents' view on safety and added value conflicted with each other. Other barriers included patient selection and organizational related (e.g., multidisciplinary support). Surgeons' view on evolution and relevance of OJA significantly differed by respondents who perform OJA versus respondents who don't perform OJA. Most respondents agreed with one another that the healthcare institution benefits most from OJA, and that optimization of the arthroplasty pathway could be reached through better patient education and -participation (e.g., eHealth, wearables). Conclusion: One in five respondents currently implement OJA pathways, and about half of the remaining respondents are interested to implement OJA in the future. OJA-opponents aren't convinced of the value and safety of OJA, despite accumulating evidence supporting OJA. Future research should inform patient-selection and -acceptance and organizational implementation.

Clinical utility of convolutional neural networks for treatment planning in radiotherapy for spinal metastases.

BACKGROUND AND PURPOSE: Spine delineation is essential for high quality radiotherapy treatment planning of spinal metastases. However, manual delineation is time-consuming and prone to interobserver variability. Automatic spine delineation, especially using deep learning, has shown promising results in healthy subjects. We aimed to evaluate the clinical utility of deep learning-based vertebral body delineations for radiotherapy planning purposes. MATERIALS AND METHODS: A multi-scale convolutional neural network (CNN) was used for automatic segmentation and labeling. Two approaches were tested: the combined approach using one CNN for both segmentation and labeling, and the sequential approach using separate CNN's for these tasks. Training and internal validation data included 580 vertebrae, external validation data included 202 vertebrae. For quantitative assessment, Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used. Axial slices from external images were presented to radiation oncologists for subjective evaluation. RESULTS: Both approaches performed comparably during the internal validation (DSC: 96.7%, HD: 3.6 mm), but the sequential approach proved more robust during the external validation (DSC: 94.5% vs 94.4%, p < 0.001, HD: 4.5 vs 7.1 mm, p < 0.001). Subsequently, subjective evaluation of this sequential approach showed that experienced radiation oncologists could distinguish automatic from human-made contours in 63% of cases. They rated automatic contours clinically acceptable in 77% of cases, compared to 88% of human-made contours. CONCLUSION: We present a feasible approach for automatic vertebral body delineation using two variants of a multi-scale CNN. This approach generates high quality automatic delineations, which can save time in a clinical radiotherapy workflow.

Rates and Causes of 90-day Complications and Readmissions Following Outpatient Hip and Knee Arthroplasty: A Retrospective Analysis of 525 Patients in a Single Institution.

BACKGROUND: Outpatient joint arthroplasty (OJA) has gained increasing popularity and success in a well-defined population. Safety concerns, in terms of complications and readmissions, however still exist. PATIENTS AND METHODS: This retrospective study included 525 patients (90 primary THAs, 277 primary TKAs, and 158 primary UKAs), initially planned for OJA. All complications and readmissions were evaluated for timing and cause (surgical vs medical) within a 90-day followup. Complications and readmissions were compared by the length of stay (LOS): same-day discharge (SDD) vs ≥1 day. Differences were assessed by the log-rank test. Complications and readmission risk were assessed using multivariable logistic regression analysis. RESULTS: The complication rate was 9.9% at 30 days and 15% at 90 days. The readmission rate was 2.5% at 30 days and 4.2% at 90 days. The majority of surgical complications and readmissions were the result of wound discharge (43% and 56%, respectively). Overall, we did not observe different rates between SDD and LOS ≥1. Following THA, but not TKA or UKA, the 90-day complication rate was significantly lower in patients that underwent SDD compared with LOS ≥1. The risk of complications was positively associated with TKA (vs THA and UKA), ASA III (vs ASA I), and Charnley C (vs Charnley A). The risk of readmissions was negatively associated with a BMI ranging from 25-29.9 kg/m2 (vs BMI <25 kg/m2). CONCLUSION: SDD following OJA did not result in more complications and hospital readmissions compared to a prolonged hospital stay. The majority of complications and readmissions were due to noninfected wound discharge.

Differential Response of Gestational Tissues to TLR3 Viral Priming Prior to Exposure to Bacterial TLR2 and TLR2/6 Agonists.

Background: Infection/inflammation is an important causal factor in spontaneous preterm birth (sPTB). Most mechanistic studies have concentrated on the role of bacteria, with limited focus on the role of viruses in sPTB. Murine studies support a potential multi-pathogen aetiology in which a double or sequential hit of both viral and bacterial pathogens leads to a higher risk preterm labour. This study aimed to determine the effect of viral priming on bacterial induced inflammation in human in vitro models of ascending and haematogenous infection. Methods: Vaginal epithelial cells, and primary amnion epithelial cells and myocytes were used to represent cell targets of ascending infection while interactions between peripheral blood mononuclear cells (PBMCs) and placental explants were used to model systemic infection. To model the effect of viral priming upon the subsequent response to bacterial stimuli, each cell type was stimulated first with a TLR3 viral agonist, and then with either a TLR2 or TLR2/6 agonist, and responses compared to those of each agonist alone. Immunoblotting was used to detect cellular NF-κB, AP-1, and IRF-3 activation. Cellular TLR3, TLR2, and TLR6 mRNA was quantified by RT-qPCR. Immunoassays were used to measure supernatant cytokine, chemokine and PGE2 concentrations. Results: TLR3 ("viral") priming prior to TLR2/6 agonist ("bacterial") exposure augmented the pro-inflammatory, pro-labour response in VECs, AECs, myocytes and PBMCs when compared to the effects of agonists alone. In contrast, enhanced anti-inflammatory cytokine production (IL-10) was observed in placental explants. Culturing placental explants in conditioned media derived from PBMCs primed with a TLR3 agonist enhanced TLR2/6 agonist stimulated production of IL-6 and IL-8, suggesting a differential response by the placenta to systemic inflammation compared to direct infection as a result of haematogenous spread. TLR3 agonism generally caused increased mRNA expression of TLR3 and TLR2 but not TLR6. Conclusion: This study provides human in vitro evidence that viral infection may increase the susceptibility of women to bacterial-induced sPTB. Improved understanding of interactions between viral and bacterial components of the maternal microbiome and host immune response may offer new therapeutic options, such as antivirals for the prevention of PTB.

Deep learning-based synthetic CT generation for paediatric brain MR-only photon and proton radiotherapy.

BACKGROUND AND PURPOSE: To enable accurate magnetic resonance imaging (MRI)-based dose calculations, synthetic computed tomography (sCT) images need to be generated. We aim at assessing the feasibility of dose calculations from MRI acquired with a heterogeneous set of imaging protocol for paediatric patients affected by brain tumours. MATERIALS AND METHODS: Sixty paediatric patients undergoing brain radiotherapy were included. MR imaging protocols varied among patients, and data heterogeneity was maintained in train/validation/test sets. Three 2D conditional generative adversarial networks (cGANs) were trained to generate sCT from T1-weighted MRI, considering the three orthogonal planes and its combination (multi-plane sCT). For each patient, median and standard deviation (σ) of the three views were calculated, obtaining a combined sCT and a proxy for uncertainty map, respectively. The sCTs were evaluated against the planning CT in terms of image similarity and accuracy for photon and proton dose calculations. RESULTS: A mean absolute error of 61 ± 14 HU (mean±1σ) was obtained in the intersection of the body contours between CT and sCT. The combined multi-plane sCTs performed better than sCTs from any single plane. Uncertainty maps highlighted that multi-plane sCTs differed at the body contours and air cavities. A dose difference of -0.1 ± 0.3% and 0.1 ± 0.4% was obtained on the D > 90% of the prescribed dose and mean γ2%,2mm pass-rate of 99.5 ± 0.8% and 99.2 ± 1.1% for photon and proton planning, respectively. CONCLUSION: Accurate MR-based dose calculation using a combination of three orthogonal planes for sCT generation is feasible for paediatric brain cancer patients, even when training on a heterogeneous dataset.

Clinical implementation of MRI-based organs-at-risk auto-segmentation with convolutional networks for prostate radiotherapy.

BACKGROUND: Structure delineation is a necessary, yet time-consuming manual procedure in radiotherapy. Recently, convolutional neural networks have been proposed to speed-up and automatise this procedure, obtaining promising results. With the advent of magnetic resonance imaging (MRI)-guided radiotherapy, MR-based segmentation is becoming increasingly relevant. However, the majority of the studies investigated automatic contouring based on computed tomography (CT). PURPOSE: In this study, we investigate the feasibility of clinical use of deep learning-based automatic OARs delineation on MRI. MATERIALS AND METHODS: We included 150 patients diagnosed with prostate cancer who underwent MR-only radiotherapy. A three-dimensional (3D) T1-weighted dual spoiled gradient-recalled echo sequence was acquired with 3T MRI for the generation of the synthetic-CT. The first 48 patients were included in a feasibility study training two 3D convolutional networks called DeepMedic and dense V-net (dV-net) to segment bladder, rectum and femurs. A research version of an atlas-based software was considered for comparison. Dice similarity coefficient, 95% Hausdorff distances (HD95), and mean distances were calculated against clinical delineations. For eight patients, an expert RTT scored the quality of the contouring for all the three methods. A choice among the three approaches was made, and the chosen approach was retrained on 97 patients and implemented for automatic use in the clinical workflow. For the successive 53 patients, Dice, HD95 and mean distances were calculated against the clinically used delineations. RESULTS: DeepMedic, dV-net and the atlas-based software generated contours in 60 s, 4 s and 10-15 min, respectively. Performances were higher for both the networks compared to the atlas-based software. The qualitative analysis demonstrated that delineation from DeepMedic required fewer adaptations, followed by dV-net and the atlas-based software. DeepMedic was clinically implemented. After retraining DeepMedic and testing on the successive patients, the performances slightly improved. CONCLUSION: High conformality for OARs delineation was achieved with two in-house trained networks, obtaining a significant speed-up of the delineation procedure. Comparison of different approaches has been performed leading to the succesful adoption of one of the neural networks, DeepMedic, in the clinical workflow. DeepMedic maintained in a clinical setting the accuracy obtained in the feasibility study.

Reasons for Unsuccessful Same-Day Discharge Following Outpatient Hip and Knee Arthroplasty: 5½ Years' Experience From a Single Institution.

BACKGROUND: Outpatient joint arthroplasty (OJA) is considered safe and feasible in selected patients but should be further optimized to improve success rates. The purposes of this study are to (1) identify the main reasons of unsuccessful same-day discharge (SDD) following hip and knee arthroplasty; (2) determine the hospital length of stay (LOS) following unsuccessful SDD; and (3) assess which independent variables are related to specific reasons for unsuccessful SDD. METHODS: Five hundred twenty-five patients undergoing total hip arthroplasty (THA), total knee arthroplasty (TKA), and unicompartmental knee arthroplasty between 2013 and 2019 were retrospectively identified. SDD to home was planned in all patients. Specific reasons for unsuccessful SDD and LOS were assessed. Bivariate analysis was performed to find differences in independent variables between patients experiencing a specific reason for unsuccessful SDD and control patients. RESULTS: One hundred ten patients (21%) underwent unsuccessful SDD. The main reason was postoperative reduced motor function and sensory disturbances (33%). The mean LOS in the unsuccessful SDD group was 1.7 days (standard deviation ± 1.0 days). Postoperative transient reduced motor function and sensory disturbances occurred more often in patients undergoing TKA (P < .001). CONCLUSION: An option for overnight stay should be available when performing outpatient hip and knee arthroplasty. The main reason for unsuccessful SDD in this study was transient postoperative reduced motor function and sensory disturbance, most likely due to intraoperative local infiltration analgesia in TKA. No other studies have found local infiltration analgesia to be an issue preventing SDD.

Deep learning-based reconstruction of in vivo pelvis conductivity with a 3D patch-based convolutional neural network trained on simulated MR data.

PURPOSE: To demonstrate that mapping pelvis conductivity at 3T with deep learning (DL) is feasible. METHODS: 210 dielectric pelvic models were generated based on CT scans of 42 cervical cancer patients. For all dielectric models, electromagnetic and MR simulations with realistic accuracy and precision were performed to obtain B1+ and transceive phase (ϕ± ). Simulated B1+ and ϕ± served as input to a 3D patch-based convolutional neural network, which was trained in a supervised fashion to retrieve the conductivity. The same network architecture was retrained using only ϕ± in input. Both network configurations were tested on simulated MR data and their conductivity reconstruction accuracy and precision were assessed. Furthermore, both network configurations were used to reconstruct conductivity maps from a healthy volunteer and two cervical cancer patients. DL-based conductivity was compared in vivo and in silico to Helmholtz-based (H-EPT) conductivity. RESULTS: Conductivity maps obtained from both network configurations were comparable. Accuracy was assessed by mean error (ME) with respect to ground truth conductivity. On average, ME < 0.1 Sm-1 for all tissues. Maximum MEs were 0.2 Sm-1 for muscle and tumour, and 0.4 Sm-1 for bladder. Precision was indicated with the difference between 90th and 10th conductivity percentiles, and was below 0.1 Sm-1 for fat, bone and muscle, 0.2 Sm-1 for tumour and 0.3 Sm-1 for bladder. In vivo, DL-based conductivity had median values in agreement with H-EPT values, but a higher precision. CONCLUSION: Anatomically detailed, noise-robust 3D conductivity maps with good sensitivity to tissue conductivity variations were reconstructed in the pelvis with DL.

Predictors of (Un)successful Same-Day Discharge in Selected Patients Following Outpatient Hip and Knee Arthroplasty.

BACKGROUND: It is generally accepted that only selected patients are suitable for outpatient joint arthroplasty (OJA); however, no consensus exists on the optimal selection criteria. We believe patients undergoing OJA should undergo risk stratification and mitigation in an attempt to optimize quality and minimize costs. METHODS: Patient factors of 525 patients who were selected to have primary elective unicompartmental knee arthroplasty (N = 158), total knee arthroplasty (N = 277), or total hip arthroplasty (N = 90) in an outpatient setting were retrospectively reviewed. A complete case multivariable logistic regression analysis of 440 patients was conducted to identify factors that were independently associated with (un)successful same-day discharge (SDD). RESULTS: One hundred ten patients (21%) were not able to be discharged on the day of surgery. Charnley class B2 was associated with a higher chance of successful SDD (odds ratio [OR], 0.29; 95% confidence interval [CI], 0.12-0.72), whereas female gender (OR, 1.7; 95% CI, 1.0-2.8), total knee arthroplasty (OR, 1.9; 95% CI, 1.1-3.4), and a higher American Society of Anesthesiologists (ASA) physical function score (ASA II: OR, 1.9; 95% CI, 1.1-3.3; ASA III: OR, 3.9; 95% CI, 1.1-13) were associated with a higher risk of unsuccessful SDD. CONCLUSION: These results in a preselected population suggest the need for further specifying and improving selection criteria for patients undergoing OJA and emphasize the importance of an in-hospital backup plan for patients at risk of unsuccessful SDD. Previous contralateral joint arthroplasty is a protective factor for successful SDD.

PROMIS PF correlates with HOOS, JR in patients with hip pain.

BACKGROUND: Patient-reported outcome measures (PROMs) are increasingly integrated into reporting requirements tied to reimbursement. There may be advantages to computer adaptive tests that apply to many different anatomical regions and diseases, provided that important information is not lost. QUESTIONS: 1) Does the Patient-Reported Outcomes Measurement Information System Physical Function (PROMIS PF) computer adaptive test correlate with the Hip injury and Osteoarthritis Outcome Score for Joint Replacement (HOOS, JR: a hip-specific PROM); 2) Is there any difference in the amount of variation explained by various factors (e.g. age, BMI, presence of concomitant knee pain) for both measures? METHODS: In this prospective, cross-sectional study of 213 patients, we assessed the Pearson correlation of PROMIS PF and HOOS, JR. To investigate the variation explained by various patient-level factors, we constructed two multivariable linear regression models. RESULTS: We found a large correlation between PROMIS PF and HOOS, JR (r 0.58, P < 0.001). Disabled or unemployed status was independently associated with both lower PROMIS PF and HOOS, JR scores (regression coefficient [ß] -3.4; 95% confidence interval [CI] -5.8 to -1.0; P = 0.006 and ß -11; 95% CI -17 to -5.0; P < 0.001, respectively). Private rather than public insurance was associated with both higher PROMIS PF and HOOS, JR scores (ß 4.5; 95% CI 2.2 to 6.8; P < 0.001 and ß 6.4; 95% CI 0.49 to 12; P = 0.034, respectively). No floor or ceiling effects were observed for PROMIS PF. HOOS, JR scores showed 4.2% floor and 0.5% ceiling effect. CONCLUSIONS: This study adds to the evidence that general measures of physical limitations may provide similar information as joint- or region-specific measures. LEVEL OF EVIDENCE: Level III.

A single neural network for cone-beam computed tomography-based radiotherapy of head-and-neck, lung and breast cancer.

Background and purpose Adaptive radiotherapy based on cone-beam computed tomography (CBCT) requires high CT number accuracy to ensure accurate dose calculations. Recently, deep learning has been proposed for fast CBCT artefact corrections on single anatomical sites. This study investigated the feasibility of applying a single convolutional network to facilitate dose calculation based on CBCT for head-and-neck, lung and breast cancer patients. Materials and Methods Ninety-nine patients diagnosed with head-and-neck, lung or breast cancer undergoing radiotherapy with CBCT-based position verification were included in this study. The CBCTs were registered to planning CT according to clinical procedures. Three cycle-consistent generative adversarial networks (cycle-GANs) were trained in an unpaired manner on 15 patients per anatomical site generating synthetic-CTs (sCTs). Another network was trained with all the anatomical sites together. Performances of all four networks were compared and evaluated for image similarity against rescan CT (rCT). Clinical plans were recalculated on rCT and sCT and analysed through voxel-based dose differences and γ -analysis. Results A sCT was generated in 10 s. Image similarity was comparable between models trained on different anatomical sites and a single model for all sites. Mean dose differences < 0.5 % were obtained in high-dose regions. Mean gamma (3%, 3 mm) pass-rates > 95 % were achieved for all sites. Conclusion Cycle-GAN reduced CBCT artefacts and increased similarity to CT, enabling sCT-based dose calculations. A single network achieved CBCT-based dose calculation generating synthetic CT for head-and-neck, lung, and breast cancer patients with similar performance to a network specifically trained for each anatomical site.

PROMIS Physical Function Correlates with KOOS, JR in Patients with Knee Pain.

Using Patient-Reported Outcomes Measurement Information System Physical Function (PROMIS PF) computerized adaptive test instead of the Knee injury and Osteoarthritis Outcome Score for Joint Replacement (KOOS, JR) could reduce question burden for patients with knee pain. We aimed to prospectively determine the correlation between PROMIS PF and KOOS, JR to assess whether PROMIS PF could be a useful alternative measure for both research and clinical care of patients with knee pain. This was a cross-sectional study of 88 patients. We assessed the correlation between PROMIS PF and KOOS, JR using a Pearson's correlation test. Two multivariable linear regression models were used to determine the amount of variation explained by various patient-level factors. There was a strong correlation between PROMIS PF and KOOS, JR (r = 0.74, p < 0.001). KOOS, JR was an independent predictor of PROMIS PF when controlling for patient-level factors (ß 0.26; p < 0.001). The results of this study support the idea of using PROMIS PF in place of joint-specific measures such as KOOS, JR for clinical care of patients with knee pain. The level of evidence for this study is Level III.

[Suspected traumatic posterior shoulder luxation]. / Een vermeende traumatische posterieure schouderluxatie.

BACKGROUND An obstetric brachial plexus lesion arises during childbirth as a consequence of excessive lateral traction of the neonate's head during shoulder dystocia. A small number of patients do not experience spontaneous recovery and secondary glenohumeral deformities can arise due to rotator cuff imbalance. CASE DESCRIPTION A 34-year-old man of Syrian descent with a history of a conservatively treated right-sided obstetric brachial plexus lesion went to the accident and emergency department (A and E) with acute pain in the right shoulder. Additional X-ray diagnostics suggested a posterior shoulder luxation, but attempts to relocate the glenohumeral joint in A and E failed. An additional CT scan of the shoulders revealed a severe right-sided dysplasia of the glenohumeral joint, with severe retroversion and posterior luxation of a rotated humeral head. After 3 weeks of relative rest through use of a sling and pain relief with an NSAID the pain had diminished and the patient had resumed his daily activities. CONCLUSION Posterior shoulder luxation can occur as a complication of obstetric brachial plexus lesion. Closed reduction is not of any use in these cases. The expertise of a specialized multidisciplinary team is indispensable for providing a patient with obstetric brachial plexus lesion with the best advice on treatment.

CBCT correction using a cycle-consistent generative adversarial network and unpaired training to enable photon and proton dose calculation.

In presence of inter-fractional anatomical changes, clinical benefits are anticipated from image-guided adaptive radiotherapy. Nowadays, cone-beam CT (CBCT) imaging is mostly utilized during pre-treatment imaging for position verification. Due to various artifacts, image quality is typically not sufficient for photon or proton dose calculation, thus demanding accurate CBCT correction, as potentially provided by deep learning techniques. This work aimed at investigating the feasibility of utilizing a cycle-consistent generative adversarial network (cycleGAN) for prostate CBCT correction using unpaired training. Thirty-three patients were included. The network was trained to translate uncorrected, original CBCT images (CBCTorg) into planning CT equivalent images (CBCTcycleGAN). HU accuracy was determined by comparison to a previously validated CBCT correction technique (CBCTcor). Dosimetric accuracy was inferred for volumetric-modulated arc photon therapy (VMAT) and opposing single-field uniform dose (OSFUD) proton plans, optimized on CBCTcor and recalculated on CBCTcycleGAN. Single-sided SFUD proton plans were utilized to assess proton range accuracy. The mean HU error of CBCTcycleGAN with respect to CBCTcor decreased from 24 HU for CBCTorg to -6 HU. Dose calculation accuracy was high for VMAT, with average pass-rates of 100%/89% for a 2%/1% dose difference criterion. For proton OSFUD plans, the average pass-rate for a 2% dose difference criterion was 80%. Using a (2%, 2 mm) gamma criterion, the pass-rate was 96%. 93% of all analyzed SFUD profiles had a range agreement better than 3 mm. CBCT correction time was reduced from 6-10 min for CBCTcor to 10 s for CBCTcycleGAN. Our study demonstrated the feasibility of utilizing a cycleGAN for CBCT correction, achieving high dose calculation accuracy for VMAT. For proton therapy, further improvements may be required. Due to unpaired training, the approach does not rely on anatomically consistent training data or potentially inaccurate deformable image registration. The substantial speed-up for CBCT correction renders the method particularly interesting for adaptive radiotherapy.

Dosimetric evaluation of synthetic CT for head and neck radiotherapy generated by a patch-based three-dimensional convolutional neural network.

PURPOSE: To develop and evaluate a patch-based convolutional neural network (CNN) to generate synthetic computed tomography (sCT) images for magnetic resonance (MR)-only workflow for radiotherapy of head and neck tumors. A patch-based deep learning method was chosen to improve robustness to abnormal anatomies caused by large tumors, surgical excisions, or dental artifacts. In this study, we evaluate whether the generated sCT images enable accurate MR-based dose calculations in the head and neck region. METHODS: We conducted a retrospective study on 34 patients with head and neck cancer who underwent both CT and MR imaging for radiotherapy treatment planning. To generate the sCTs, a large field-of-view T2-weighted Turbo Spin Echo MR sequence was used from the clinical protocol for multiple types of head and neck tumors. To align images as well as possible on a voxel-wise level, CT scans were nonrigidly registered to the MR (CTreg ). The CNN was based on a U-net architecture and consisted of 14 layers with 3 × 3 × 3 filters. Patches of 48 × 48 × 48 were randomly extracted and fed into the training. sCTs were created for all patients using threefold cross validation. For each patient, the clinical CT-based treatment plan was recalculated on sCT using Monaco TPS (Elekta). We evaluated mean absolute error (MAE) and mean error (ME) within the body contours and dice scores in air and bone mask. Also, dose differences and gamma pass rates between CT- and sCT-based plans inside the body contours were calculated. RESULTS: sCT generation took 4 min per patient. The MAE over the patient population of the sCT within the intersection of body contours was 75 ± 9 Hounsfield Units (HU) (±1 SD), and the ME was 9 ± 11 HU. Dice scores of the air and bone masks (CTreg vs sCT) were 0.79 ± 0.08 and 0.70 ± 0.07, respectively. Dosimetric analysis showed mean deviations of -0.03% ± 0.05% for dose within the body contours and -0.07% ± 0.22% inside the >90% dose volume. Dental artifacts obscuring the CT could be circumvented in the sCT by the CNN-based approach in combination with Turbo Spin Echo (TSE) magnetic resonance imaging (MRI) sequence that typically is less prone to susceptibility artifacts. CONCLUSIONS: The presented CNN generated sCTs from conventional MR images without adding scan time to the acquisition. Dosimetric evaluation suggests that dose calculations performed on the sCTs are accurate, and can therefore be used for MR-only radiotherapy treatment planning of the head and neck.

Does resiliency mediate the association of psychological adaptability with disability and pain in patients with an upper extremity injury or illness?

OBJECTIVE: Symptom intensity and magnitude of limitations are highly variable for a given nociception and pathophysiology. As psychological determinants are of great influence to physical wellbeing, we assessed the influence of the protective factor measured and labelled as resilience in upper extremity illness. METHODS: One hundred and six patients completed a survey of demographics, the Brief Resilience Scale (BRS), the Psychological Adaptation Scale (PAS), an 11-point ordinal measure of pain intensity, and the PROMIS Physical Function (PROMIS PF) Computer Adaptive Test (CAT). Measures of pain intensity and PROMIS PF were repeated 3 months later. We created mediation models using structural equation modeling (SEM) to assess the mediation effect of BRS on the association of PAS and other confounding variables with disability and pain at initial assessment and 3 months later. RESULTS: Resiliency does not mediate the association of psychological adaptability with physical limitations and pain intensity at baseline (P = .89 and .82 respectively) or 3 months after enrollment (P = .65 and .72 respectively). CONCLUSIONS: Positive and protective factors promote beneficial resilience mechanisms that strengthen coping responses to pain and disability. In future studies we should either include more patients to improve power and provide more information about the health benefits of resilience or focus more on mood and self-efficacy on symptoms and limitations in patients with musculoskeletal illness. LEVEL OF EVIDENCE: Prospective, longitudinal cohort study; Level II.

MR-Only Brain Radiation Therapy: Dosimetric Evaluation of Synthetic CTs Generated by a Dilated Convolutional Neural Network.

PURPOSE: This work aims to facilitate a fast magnetic resonance (MR)-only workflow for radiation therapy of intracranial tumors. Here, we evaluate whether synthetic computed tomography (sCT) images generated with a dilated convolutional neural network (CNN) enable accurate MR-based dose calculations in the brain. METHODS AND MATERIALS: We conducted a retrospective study of 52 patients with brain tumors who underwent both computed tomography (CT) and MR imaging for radiation therapy treatment planning. To generate the sCTs, a T1-weighted gradient echo MR sequence was selected from the clinical protocol for multiple types of brain tumors. sCTs were created for all 52 patients with a dilated CNN using 2-fold cross validation; in each fold, 26 patients were used for training and the remaining 26 patients were used for evaluation. For each patient, the clinical CT-based treatment plan was recalculated on sCT. We calculated dose differences and gamma pass rates between CT- and sCT-based plans inside body and planning target volume. Geometric fidelity of the sCT and differences in beam depth and equivalent path length were assessed between both treatment plans. RESULTS: sCT generation took 1 minute per patient. Over the patient population, the mean absolute error of the sCT within the intersection of body contours was 67 ± 11 HU (±1 standard deviation [SD], range: 51-117 HU), and the mean error was 13 ± 9 HU (±1 SD, range: -2 to 38 HU). Dosimetric analysis showed mean deviations of 0.00% ± 0.02% (±1 SD, range: -0.05 to 0.03) for dose within the body contours and -0.13% ± 0.39% (±1 SD, range: -1.43 to 0.80) inside the planning target volume. Mean γ1mm/1% was 98.8% ± 2.2% for doses >50% of the prescribed dose. CONCLUSIONS: The presented dilated CNN generated sCTs from conventional MR images without adding scan time to the acquisition. Dosimetric evaluation suggests that dose calculations performed on the sCTs are accurate and can therefore be used for MR-only intracranial radiation therapy treatment planning.