Clinical target volume delineation quality assurance for MRI-guided prostate radiotherapy using deep learning with uncertainty estimation.

BACKGROUND AND PURPOSE: Previous studies on automatic delineation quality assurance (QA) have mostly focused on CT-based planning. As MRI-guided radiotherapy is increasingly utilized in prostate cancer treatment, there is a need for more research on MRI-specific automatic QA. This work proposes a clinical target volume (CTV) delineation QA framework based on deep learning (DL) for MRI-guided prostate radiotherapy. MATERIALS AND METHODS: The proposed workflow utilized a 3D dropblock ResUnet++ (DB-ResUnet++) to generate multiple segmentation predictions via Monte Carlo dropout which were used to compute an average delineation and area of uncertainty. A logistic regression (LR) classifier was employed to classify the manual delineation as pass or discrepancy based on the spatial association between the manual delineation and the network's outputs. This approach was evaluated on a multicentre MRI-only prostate radiotherapy dataset and compared with our previously published QA framework based on AN-AG Unet. RESULTS: The proposed framework achieved an area under the receiver operating curve (AUROC) of 0.92, a true positive rate (TPR) of 0.92 and a false positive rate of 0.09 with an average processing time per delineation of 1.3 min. Compared with our previous work using AN-AG Unet, this method generated fewer false positive detections at the same TPR with a much faster processing speed. CONCLUSION: To the best of our knowledge, this is the first study to propose an automatic delineation QA tool using DL with uncertainty estimation for MRI-guided prostate radiotherapy, which can potentially be used for reviewing prostate CTV delineation in multicentre clinical trials.

Magnetic resonance imaging organ at risk delineation for nasopharyngeal radiotherapy: Measuring the effectiveness of an educational intervention.

INTRODUCTION: Magnetic resonance imaging (MRI) demonstrates superior soft tissue contrast and is increasingly being used in radiotherapy planning. This study evaluated the impact of an education workshop in minimising inter-observer variation (IOV) for nasopharyngeal organs at risk (OAR) delineation on MRI. METHODS: Ten observers delineated 14 OARs on 4 retrospective nasopharyngeal MRI data sets. Standard contouring guidelines were provided pre-workshop. Following an education workshop on MRI OAR delineation, observers blinded to their original contours repeated the 14 OAR delineations. For comparison, reference volumes were delineated by two head and neck radiation oncologists. IOV was evaluated using dice similarity coefficient (DSC), Hausdorff distance (HD) and relative volume. Location of largest deviations was evaluated with centroid values. Observer confidence pre- and post-workshop was also recorded using a 6-point Likert scale. The workshop was deemed beneficial for an OAR if ≥50% of observers mean scores improved in any metric and ≥50% of observers' confidence improved. RESULTS: All OARs had ≥50% of observers improve in at least one metric. Base of tongue, larynx, spinal cord and right temporal lobe were the only OARs achieving a mean DSC score of ≥0.7. Base of tongue, left and right lacrimal glands, larynx, left optic nerve and right parotid gland all exhibited statistically significant HD improvements post-workshop (P < 0.05). Brainstem and left and right temporal lobes all had statistically significant relative volume improvements post-workshop (P < 0.05). Post-workshop observer confidence improvement was observed for all OARs (P < 0.001). CONCLUSIONS: The educational workshop reduced IOV and improved observers' confidence when delineating nasopharyngeal OARs on MRI.

Implementing online position monitoring for prostate radiotherapy using an in-house position monitoring system: User experience and impact on workforce.

INTRODUCTION: To evaluate the feasibility of prostate intrafraction motion monitoring using the SeedTracker real-time image guidance system in order to improve targeting accuracy in prostate radiotherapy. METHODS: SeedTracker was used to monitor prostate gold fiducial seeds with kV x-ray imaging during radiotherapy in 30 patients. Feedback from radiation therapists was collected via the use of a user evaluation form. The impact on treatment time was established by using a record and verify system. The effective dose and a risk of exposure-induced cancer death (REID) were estimated for a 60-year-old patient when using the SeedTracker system. RESULTS: A total of 22 radiation therapists completed user evaluation forms. The time taken to prepare a reference data set for one patient varied with three (13.6%) radiation therapists taking less than 2 min, 10 (45.5%) between 2 and 4 min, eight (36.4%) between 4 and 6 min and one (4.5%) between 6 and 8 min. The useability of the SeedTracker system was reported as 'easy' by 21 (95.5%) radiation therapists and 'hard' by 1 (4.5%) radiation therapist. Mean treatment time changed from 6 to 7 min with prostate-only radiotherapy treatment and from 6.9 to 10.2 min with prostate and whole pelvis radiotherapy treatments. The maximum effective dose with the SeedTracker was 1.6276 mSv, and increase in REID was 0.007%. CONCLUSION: The SeedTracker real-time image guidance system is a feasible tool to use in radiotherapy departments to monitor and correct for prostate intrafraction motion.

Mechanisms, mitigation, and management of urinary toxicity from prostate radiotherapy.

Urinary toxicity is common following pelvic radiotherapy and can have a substantial negative effect on survivorship. Due to its prevalence and the increasing number of related clinical trials, localised prostate cancer radiotherapy is a useful illustrative tool to explore urinary toxicity. A good understanding of the interplay between anatomy, radiation-sensitive cell populations, and treatment sequencing is necessary for optimal outcomes. Emerging evidence suggests that the prostatic urethra is a radiation-sensitive structure, not only for stricture development, but also chronic irritative symptoms. Tools now exist not only to identify the urethra, but also to direct radiation dose away from the urethra, with early data suggesting that this reduces moderate-to-severe late urinary toxicity. Coupled with new evidence supporting dominant nodule microboosting and ultrahypofractionation as emerging standards of care, urethral sparing radiotherapy is a powerful tool against radiation induced urinary toxicity while also maximising disease control.

Interim Prostate-Specific Antigen: Predicting for Biochemical Failure During Salvage Radiation Therapy After Prostatectomy.

PURPOSE: A subset of patients treated with postprostatectomy radiation therapy for biochemical recurrence after surgery fail to respond because of microscopic disease beyond the irradiated prostate bed. This work aims to determine whether a rising interim prostate-specific antigen (PSA) during radiation therapy can predict the likelihood of subsequent biochemical recurrence. METHODS AND MATERIALS: Between 2010 and 2016, 185 patients had salvage radiation therapy to a dose of 68 Gy without androgen deprivation therapy for a rising PSA level after radical prostatectomy. Patients had their PSA recorded on the first day of radiation therapy and again after completing the 25th fraction (of 34 total fractions). Biochemical failure after radiation therapy was defined as a PSA value ≥0.2 ng/mL within 2 years after radiation therapy. Both univariate and multivariate Cox regression models were used for statistical analysis. Factors with a P value of <.2 in univariate analysis were then used in a multivariate analysis. RESULTS: The 2-year freedom from biochemical failure was 60% (95% confidence interval, 53%-67%). When assessing the interim PSA, 143 patients (77%) had a drop in interim PSA; of these patients, 71% had 2-year biochemical control. Forty-two patients (23%) had a stable or rising interim PSA, and only 24% of these patients had 2-year biochemical control. On multivariate analysis, a drop in PSA during radiation therapy (P < .0001) and a positive surgical margin (P < .0001) were significant factors for freedom from subsequent biochemical failure, and seminal vesicle invasion was associated with biochemical failure at 2 years (P = .019). All patients with a rising interim PSA, negative surgical margin, and seminal vesicle invasion ultimately had biochemical failure at 2 years. CONCLUSIONS: A PSA rise during salvage radiation therapy is prognostic of biochemical failure at 2 years. Factors such as seminal vesicle invasion and a negative surgical margin also predict for poor responders to salvage radiation therapy.

Evaluating diffusion-weighted magnetic resonance imaging for target volume delineation in head and neck radiotherapy.

INTRODUCTION: Inter-observer variability (IOV) in target volume delineation is a source of error in head and neck radiotherapy. Diffusion-weighted imaging (DWI) has been shown to be useful in detecting recurrent head and neck cancer. This study aims to determine whether DWI improves target volume delineation and IOV. METHODS: Four radiation oncologists delineated the gross tumour volume (GTV) for ten head and neck cancer patients. Delineation was performed on CT alone as well as fused image sets which incorporated fluorodeoxyglucose (FDG)-positron emission tomography (PET) and magnetic resonance imaging (MRI) in the form of CT/PET, CT/PET/T2W and CT/PET/T2W/DWI image sets. Analysis of the variability of contour volumes was completed by comparison to the simultaneous truth and performance level estimation (STAPLE) volumes. The DICE Similarity Coefficient (DSC) and other IOV metrics for each observer's contour were compared to the STAPLE for each patient and image dataset. A DWI usability scoresheet for delineation was completed. RESULTS: The CT/PET/T2W/DWI mean GTV volume of 13.37 (10.35-16.39)cm3 was shown to be different to the mean GTV of 10.92 (8.32-13.51)cm3 when using CT alone (P < 0.001). The GTV DSC amongst observers for CT alone was 0.72 (0.65-0.79), CT/PET was 0.73 (0.67-0.80), CT/PET/T2W was 0.71 (0.64-0.77) and CT/PET/T2W/DWI was 0.69 (0.61-0.75). CONCLUSION: Mean GTVs with the addition of DWI had slightly larger volumes compared to standard CT and CT/PET volumes. DWI may add supplemental visual information for GTV delineation while having a small impact on IOV, therefore potentially improving target volume delineation.

Surface dosimetry for breast radiotherapy in the presence of immobilization cast material.

Curative breast radiotherapy typically leaves patients with varying degrees of cosmetic damage. One problem interfering with cosmetically acceptable breast radiotherapy is the external contour for large pendulous breasts which often results in high doses to skin folds. Thermoplastic casts are often employed to secure the breasts to maintain setup reproducibility and limit the presence of skin folds. This paper aims to determine changes in surface dose that can be attributed to the use of thermoplastic immobilization casts. Skin dose for a clinical hybrid conformal/IMRT breast plan was measured using radiochromic film and MOSFET detectors at a range of water equivalent depths representative of the different skin layers. The radiochromic film was used as an integrating dosimeter, while the MOSFETs were used for real-time dosimetry to isolate the contribution of skin dose from individual IMRT segments. Strips of film were placed at various locations on the breast and the MOSFETs were used to measure skin dose at 16 positions spaced along the film strips for comparison of data. The results showed an increase in skin dose in the presence of the immobilization cast of up to 45.7% and 62.3% of the skin dose without the immobilization cast present as measured with Gafchromic EBT film and MOSFETs, respectively. The increase in skin dose due to the immobilization cast varied with the angle of beam incidence and was greatest when the beam was normally incident on the phantom. The increase in surface dose with the immobilization cast was greater under entrance dose conditions compared to exit dose conditions.