Automatic segmentation of tumour and organs at risk in 3D MRI for cervical cancer radiation therapy with anatomical variations.

Cervical cancer is a common cancer in women globally, with treatment usually involving radiation therapy (RT). Accurate segmentation for the tumour site and organ-at-risks (OARs) could assist in the reduction of treatment side effects and improve treatment planning efficiency. Cervical cancer Magnetic Resonance Imaging (MRI) segmentation is challenging due to a limited amount of training data available and large inter- and intra- patient shape variation for OARs. The proposed Masked-Net consists of a masked encoder within the 3D U-Net to account for the large shape variation within the dataset, with additional dilated layers added to improve segmentation performance. A new loss function was introduced to consider the bounding box loss during training with the proposed Masked-Net. Transfer learning from a male pelvis MRI data with a similar field of view was included. The approaches were compared to the 3D U-Net which was widely used in MRI image segmentation. The data used consisted of 52 volumes obtained from 23 patients with stage IB to IVB cervical cancer across a maximum of 7 weeks of RT with manually contoured labels including the bladder, cervix, gross tumour volume, uterus and rectum. The model was trained and tested with a 5-fold cross validation. Outcomes were evaluated based on the Dice Similarity Coefficients (DSC), the Hausdorff Distance (HD) and the Mean Surface Distance (MSD). The proposed method accounted for the small dataset, large variations in OAR shape and tumour sizes with an average DSC, HD and MSD for all anatomical structures of 0.790, 30.19mm and 3.15mm respectively.

Cone beam computed tomography image guidance within a magnetic resonance imaging-only planning workflow.

Background and purpose: Magnetic Resonance Imaging (MRI)-only planning workflows offer many advantages but raises challenges regarding image guidance. The study aimed to assess the viability of MRI to Cone Beam Computed Tomography (CBCT) based image guidance for MRI-only planning treatment workflows. Materials and methods: An MRI matching training package was developed. Ten radiation therapists, with a range of clinical image guidance experience and experience with MRI, completed the training package prior to matching assessment. The matching assessment was performed on four match regions: prostate gold seed, prostate soft tissue, rectum/anal canal and gynaecological. Each match region consisted of five patients, with three CBCTs per patient, resulting in fifteen CBCTs for each match region. The ten radiation therapists performed the CBCT image matching to CT and to MRI for all regions and recorded the match values. Results: The median inter-observer variation for MRI-CBCT matching and CT-CBCT matching for all regions were within 2 mm and 1 degree. There was no statistically significant association in the inter-observer variation in mean match values and radiation therapist image guidance experience levels. There was no statistically significant association in inter-observer variation in mean match values for MRI experience levels for prostate soft tissue and gynaecological match regions, while there was a statistically significant difference for prostate gold seed and rectum match regions. Conclusion: The results of this study support the concept that with focussed training, an MRI to CBCT image guidance approach can be successfully implemented in a clinical planning workflow.

Investigation of a water equivalent depth method for dosimetric accuracy evaluation of synthetic CT.

PURPOSE: To provide a metric that reflects the dosimetric utility of the synthetic CT (sCT) and can be rapidly determined. METHODS: Retrospective CT and atlas-based sCT of 62 (53 IMRT and 9 VMAT) prostate cancer patients were used. For image similarity measurements, the sCT and reference CT (rCT) were aligned using clinical registration parameters. Conventional image similarity metrics including the mean absolute error (MAE) and mean error (ME) were calculated. The water equivalent depth (WED) was automatically determined for each patient on the rCT and sCT as the distance from the skin surface to the treatment plan isocentre at 36 equidistant gantry angles, and the mean WED difference (ΔWED¯) between the two scans was calculated. Doses were calculated on each scan pair for the clinical plan in the treatment planning system. The image similarity measurements and ΔWED¯ were then compared to the isocentre dose difference (ΔDiso) between the two scans. RESULTS: While no particular relationship to dose was observed for the other image similarity metrics, the ME results showed a linear trend against ΔDiso with R2 = 0.6, and the 95 % prediction interval for ΔDiso between -1.2 and 1 %. The ΔWED¯ results showed an improved linear trend (R2 = 0.8) with a narrower 95 % prediction interval from -0.8 % to 0.8 %. CONCLUSION: ΔWED¯ highly correlates with ΔDiso for the reference and synthetic CT scans. This is easy to calculate automatically and does not require time-consuming dose calculations. Therefore, it can facilitate the process of developing and evaluating new sCT generation algorithms.

CAN3D: Fast 3D medical image segmentation via compact context aggregation.

Direct automatic segmentation of objects in 3D medical imaging, such as magnetic resonance (MR) imaging, is challenging as it often involves accurately identifying multiple individual structures with complex geometries within a large volume under investigation. Most deep learning approaches address these challenges by enhancing their learning capability through a substantial increase in trainable parameters within their models. An increased model complexity will incur high computational costs and large memory requirements unsuitable for real-time implementation on standard clinical workstations, as clinical imaging systems typically have low-end computer hardware with limited memory and CPU resources only. This paper presents a compact convolutional neural network (CAN3D) designed specifically for clinical workstations and allows the segmentation of large 3D Magnetic Resonance (MR) images in real-time. The proposed CAN3D has a shallow memory footprint to reduce the number of model parameters and computer memory required for state-of-the-art performance and maintain data integrity by directly processing large full-size 3D image input volumes with no patches required. The proposed architecture significantly reduces computational costs, especially for inference using the CPU. We also develop a novel loss function with extra shape constraints to improve segmentation accuracy for imbalanced classes in 3D MR images. Compared to state-of-the-art approaches (U-Net3D, improved U-Net3D and V-Net), CAN3D reduced the number of parameters up to two orders of magnitude and achieved much faster inference, up to 5 times when predicting with a standard commercial CPU (instead of GPU). For the open-access OAI-ZIB knee MR dataset, in comparison with manual segmentation, CAN3D achieved Dice coefficient values of (mean = 0.87 ± 0.02 and 0.85 ± 0.04) with mean surface distance errors (mean = 0.36 ± 0.32 mm and 0.29 ± 0.10 mm) for imbalanced classes such as (femoral and tibial) cartilage volumes respectively when training volume-wise under only 12G video memory. Similarly, CAN3D demonstrated high accuracy and efficiency on a pelvis 3D MR imaging dataset for prostate cancer consisting of 211 examinations with expert manual semantic labels (bladder, body, bone, rectum, prostate) now released publicly for scientific use as part of this work.

Validation of an MRI-only planning workflow for definitive pelvic radiotherapy.

PURPOSE: Previous work on Magnetic Resonance Imaging (MRI) only planning has been applied to limited treatment regions with a focus on male anatomy. This research aimed to validate the use of a hybrid multi-atlas synthetic computed tomography (sCT) generation technique from a MRI, using a female and male atlas, for MRI only radiation therapy treatment planning of rectum, anal canal, cervix and endometrial malignancies. PATIENTS AND METHODS: Forty patients receiving radiation treatment for a range of pelvic malignancies, were separated into male (n = 20) and female (n = 20) cohorts for the creation of gender specific atlases. A multi-atlas local weighted voting method was used to generate a sCT from a T1-weighted VIBE DIXON MRI sequence. The original treatment plans were copied from the CT scan to the corresponding sCT for dosimetric validation. RESULTS: The median percentage dose difference between the treatment plan on the CT and sCT at the ICRU reference point for the male cohort was - 0.4% (IQR of 0 to - 0.6), and - 0.3% (IQR of 0 to - 0.6) for the female cohort. The mean gamma agreement for both cohorts was > 99% for criteria of 3%/2 mm and 2%/2 mm. With dose criteria of 1%/1 mm, the pass rate was higher for the male cohort at 96.3% than the female cohort at 93.4%. MRI to sCT anatomical agreement for bone and body delineated contours was assessed, with a resulting Dice score of 0.91 ± 0.2 (mean ± 1 SD) and 0.97 ± 0.0 for the male cohort respectively; and 0.96 ± 0.0 and 0.98 ± 0.0 for the female cohort respectively. The mean absolute error in Hounsfield units (HUs) within the entire body for the male and female cohorts was 59.1 HU ± 7.2 HU and 53.3 HU ± 8.9 HU respectively. CONCLUSIONS: A multi-atlas based method for sCT generation can be applied to a standard T1-weighted MRI sequence for male and female pelvic patients. The implications of this study support MRI only planning being applied more broadly for both male and female pelvic sites. Trial registration This trial was registered in the Australian New Zealand Clinical Trials Registry (ANZCTR) ( www.anzctr.org.au ) on 04/10/2017. Trial identifier ACTRN12617001406392.

Comparison of Synthetic Computed Tomography Generation Methods, Incorporating Male and Female Anatomical Differences, for Magnetic Resonance Imaging-Only Definitive Pelvic Radiotherapy.

PURPOSE: There are several means of synthetic computed tomography (sCT) generation for magnetic resonance imaging (MRI)-only planning; however, much of the research omits large pelvic treatment regions and female anatomical specific methods. This research aimed to apply four of the most popular methods of sCT creation to facilitate MRI-only radiotherapy treatment planning for male and female anorectal and gynecological neoplasms. sCT methods were validated against conventional computed tomography (CT), with regard to Hounsfield unit (HU) estimation and plan dosimetry. METHODS AND MATERIALS: Paired MRI and CT scans of 40 patients were used for sCT generation and validation. Bulk density assignment, tissue class density assignment, hybrid atlas, and deep learning sCT generation methods were applied to all 40 patients. Dosimetric accuracy was assessed by dose difference at reference point, dose volume histogram (DVH) parameters, and 3D gamma dose comparison. HU estimation was assessed by mean error and mean absolute error in HU value between each sCT and CT. RESULTS: The median percentage dose difference between the CT and sCT was <1.0% for all sCT methods. The deep learning method resulted in the lowest median percentage dose difference to CT at -0.03% (IQR 0.13, -0.31) and bulk density assignment resulted in the greatest difference at -0.73% (IQR -0.10, -1.01). The mean 3D gamma dose agreement at 3%/2 mm among all sCT methods was 99.8%. The highest agreement at 1%/1 mm was 97.3% for the deep learning method and the lowest was 93.6% for the bulk density method. Deep learning and hybrid atlas techniques gave the lowest difference to CT in mean error and mean absolute error in HU estimation. CONCLUSIONS: All methods of sCT generation used in this study resulted in similarly high dosimetric agreement for MRI-only planning of male and female cancer pelvic regions. The choice of the sCT generation technique can be guided by department resources available and image guidance considerations, with minimal impact on dosimetric accuracy.

Assessing the impact of magnetic resonance treatment simulation (MRSIM) on target volume delineation and dose to organs at risk for oropharyngeal radiotherapy.

INTRODUCTION: Assessing the use of a radiation therapy (RT) planning MRI performed in the treatment position (pMRI) on target volume delineation and effect on organ at risk dose for oropharyngeal cancer patients planned with diagnostic MRI (dMRI) and CT scan. METHODS: Diagnostic MRI scans were acquired for 26 patients in a neutral patient position using a 3T scanner (dMRI). Subsequent pMRI scans were acquired on the same scanner with a flat couch top and the patient in their immobilisation mask. Each series was rigidly registered to the patients planning CT scan and volumes were first completed with the CT/dMRI. The pMRI was then made available for volume modification. For the group with revised volumes, two IMRT plans were developed to demonstrate the impact of the modification. Image and registration quality was also evaluated. RESULTS: The pMRI registration led to the modification of target volumes for 19 of 26 participants. The pMRI target volumes were larger in absolute volume resulting in reduced capacity for organ sparing. Predominantly, modifications occurred for the primary gross tumour volume (GTVp) with a mean Dice Similarity Coefficient (DSC) of 0.7 and the resulting high risk planning target volume, a mean DSC of 0.89. Both MRIs scored similarly for image quality, with the pMRI demonstrating improved registration quality and efficiency. CONCLUSIONS: A pMRI provides improvement in registration efficiency, quality and a higher degree of oncologist confidence in target delineation. These results have led to a practice change within our department, where a pMRI is acquired for all eligible oropharyngeal cancer patients.

Automated COVID-19 diagnosis and prognosis with medical imaging and who is publishing: a systematic review.

OBJECTIVES:  To conduct a systematic survey of published techniques for automated diagnosis and prognosis of COVID-19 diseases using medical imaging, assessing the validity of reported performance and investigating the proposed clinical use-case. To conduct a scoping review into the authors publishing such work. METHODS:  The Scopus database was queried and studies were screened for article type, and minimum source normalized impact per paper and citations, before manual relevance assessment and a bias assessment derived from a subset of the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). The number of failures of the full CLAIM was adopted as a surrogate for risk-of-bias. Methodological and performance measurements were collected from each technique. Each study was assessed by one author. Comparisons were evaluated for significance with a two-sided independent t-test. FINDINGS:  Of 1002 studies identified, 390 remained after screening and 81 after relevance and bias exclusion. The ratio of exclusion for bias was 71%, indicative of a high level of bias in the field. The mean number of CLAIM failures per study was 8.3 ± 3.9 [1,17] (mean ± standard deviation [min,max]). 58% of methods performed diagnosis versus 31% prognosis. Of the diagnostic methods, 38% differentiated COVID-19 from healthy controls. For diagnostic techniques, area under the receiver operating curve (AUC) = 0.924 ± 0.074 [0.810,0.991] and accuracy = 91.7% ± 6.4 [79.0,99.0]. For prognostic techniques, AUC = 0.836 ± 0.126 [0.605,0.980] and accuracy = 78.4% ± 9.4 [62.5,98.0]. CLAIM failures did not correlate with performance, providing confidence that the highest results were not driven by biased papers. Deep learning techniques reported higher AUC (p < 0.05) and accuracy (p < 0.05), but no difference in CLAIM failures was identified. INTERPRETATION:  A majority of papers focus on the less clinically impactful diagnosis task, contrasted with prognosis, with a significant portion performing a clinically unnecessary task of differentiating COVID-19 from healthy. Authors should consider the clinical scenario in which their work would be deployed when developing techniques. Nevertheless, studies report superb performance in a potentially impactful application. Future work is warranted in translating techniques into clinical tools.

Measurements of human tolerance to horizontal rotation within an MRI scanner: Towards gantry-free radiation therapy.

INTRODUCTION: Recent advances in image guidance and adaptive radiotherapy could enable gantry-free radiotherapy using patient rotation. Gantry-free radiotherapy could substantially reduce the cost of radiotherapy systems and facilities. MRI guidance complements a gantry-free approach because of its ability to visualise soft tissue deformation during rotation. A potential barrier to gantry-free radiotherapy is patient acceptability, especially when combined with MRI. This study investigates human experiences of horizontal rotation within an MRI scanner. METHODS: Ten healthy human participants and nine participants previously treated with radiotherapy were rotated within an MRI scanner. Participants' anxiety and motion sickness was assessed before being rotated in 45-degree increments and paused, representing a multi-field intensity-modulated radiotherapy treatment. An MR image was acquired at each 45-degree angle. Following imaging, anxiety and motion sickness were re-assessed, followed by a comfort questionnaire and exit interview. The significance of the differences in anxiety and motion sickness pre- versus post-imaging was assessed using Wilcoxon signed-rank tests. Content analysis was performed on exit interview transcripts. RESULTS: Eight of ten healthy and eight of nine patient participants completed the imaging session. Mean anxiety scores before and after imaging were 7.9/100 and 11.8/100, respectively (P = 0.26), and mean motion sickness scores were 5.3/100 and 13.7/100, respectively (P = 0.02). Most participants indicated likely acceptance of rotation if MRI were to be used in a hypothetical treatment. Physical discomfort was reported to be the biggest concern. CONCLUSIONS: Horizontal rotation within an MRI scanner was acceptable for most (17/19) participants.

Deformable image registration in radiation therapy.

Deformable image registration is an increasingly important method to account for soft tissue deformation between image acquisitions. This editorial discusses the clinical need and current status of deformable image registration.

Increased Dose to Organs in Urinary Tract Associates With Measures of Genitourinary Toxicity in Pooled Voxel-Based Analysis of 3 Randomized Phase III Trials.

Purpose: Dose information from organ sub-regions has been shown to be more predictive of genitourinary toxicity than whole organ dose volume histogram information. This study aimed to identify anatomically-localized regions where 3D dose is associated with genitourinary toxicities in healthy tissues throughout the pelvic anatomy. Methods and Materials: Dose distributions for up to 656 patients of the Trans-Tasman Radiation Oncology Group 03.04 RADAR trial were deformably registered onto a single exemplar CT dataset. Voxel- based multiple comparison permutation dose difference testing, Cox regression modeling and LASSO feature selection were used to identify regions where 3D dose-increase was associated with late grade ≥ 2 genitourinary dysuria, incontinence and frequency, and late grade ≥ 1 haematuria. This was externally validated by registering dose distributions from the RT01 (up to n = 388) and CHHiP (up to n = 247) trials onto the same exemplar and repeating the voxel-based tests on each of these data sets. All three datasets were then combined, and the tests repeated. Results: Voxel-based Cox regression and multiple comparison permutation dose difference testing revealed regions where increased dose was correlated with genitourinary toxicity. Increased dose in the vicinity of the membranous and spongy urethra was associated with dysuria for all datasets. Haematuria was similarly correlated with increased dose at the membranous and spongy urethra, for the RADAR, CHHiP, and combined datasets. Some evidence was found for the association between incontinence and increased dose at the internal and external urethral sphincter for RADAR and the internal sphincter alone for the combined dataset. Incontinence was also strongly correlated with dose from posterior oblique beams. Patients with fields extending inferiorly and posteriorly to the CTV, adjacent to the membranous and spongy urethra, were found to experience increased frequency. Conclusions: Anatomically-localized dose-toxicity relationships were determined for late genitourinary symptoms in the urethra and urinary sphincters. Low-intermediate doses to the extraprostatic urethra were associated with risk of late dysuria and haematuria, while dose to the urinary sphincters was associated with incontinence.

Relationships between rectal and perirectal doses and rectal bleeding or tenesmus in pooled voxel-based analysis of 3 randomised phase III trials.

BACKGROUND AND PURPOSE: This study aimed to identify anatomically-localised regions where planned radiotherapy dose is associated with gastrointestinal toxicities in healthy tissues throughout the pelvic anatomy. MATERIALS AND METHODS: Planned dose distributions for up to 657 patients of the Trans Tasman Radiation Oncology Group 03.04 RADAR trial were deformably registered onto a single exemplar computed tomography dataset. Voxel-based multiple comparison permutation dose difference testing, Cox regression modelling and LASSO feature selection were used to identify regions where dose-increase was associated with grade ≥2 rectal bleeding (RB) or tenesmus, according to the LENT/SOMA scale. This was externally validated by registering dose distributions from the RT01 (n = 388) and CHHiP (n = 241) trials onto the same exemplar and repeating the tests on each of these data sets, and on all three datasets combined. RESULTS: Voxel-based Cox regression and permutation dose difference testing revealed regions where increased dose was correlated with gastrointestinal toxicity. Grade ≥2 RB was associated with posteriorly extended lateral beams that manifested high doses (>55 Gy) in a small rectal volume adjacent to the clinical target volume. A correlation was found between grade ≥2 tenesmus and increased low-intermediate dose (∼25 Gy) at the posterior beam region, including the posterior rectum and perirectal fat space (PRFS). CONCLUSIONS: The serial response of the rectum with respect to RB has been demonstrated in patients with posteriorly extended lateral beams. Similarly, the parallel response of the PRFS with respect to tenesmus has been demonstrated in patients treated with the posterior beam.

Reduced Dose Posterior to Prostate Correlates With Increased PSA Progression in Voxel-Based Analysis of 3 Randomized Phase 3 Trials.

PURPOSE: Reducing margins during treatment planning to decrease dose to healthy organs surrounding the prostate can risk inadequate treatment of subclinical disease. This study aimed to investigate whether lack of dose to subclinical disease is associated with increased disease progression by using high-quality prostate radiation therapy clinical trial data to identify anatomically localized regions where dose variation is associated with prostate-specific antigen progression (PSAP). METHODS AND MATERIALS: Planned dose distributions for 683 patients of the Trans-Tasman Radiation Oncology Group 03.04 Randomized Androgen Deprivation and Radiotherapy (RADAR) trial were deformably registered onto a single exemplar computed tomography data set. These were divided into high-risk and intermediate-risk subgroups for analysis. Three independent voxel-based statistical tests, using permutation testing, Cox regression modeling, and least absolute shrinkage selection operator feature selection, were applied to identify regions where dose variation was associated with PSAP. Results from the intermediate-risk RADAR subgroup were externally validated by registering dose distributions from the RT01 (n = 388) and Conventional or Hypofractionated High Dose Intensity Modulated Radiotherapy for Prostate Cancer Trial (CHHiP) (n = 253) trials onto the same exemplar and repeating the tests on each of these data sets. RESULTS: Voxel-based Cox regression revealed regions where reduced dose was correlated with increased prostate-specific androgen progression. Reduced dose in regions associated with coverage at the posterior prostate, in the immediate periphery of the posterior prostate, and in regions corresponding to the posterior oblique beams or posterior lateral beam boundary, was associated with increased PSAP for RADAR and RT01 patients, but not for CHHiP patients. Reduced dose to the seminal vesicle region was also associated with increased PSAP for RADAR intermediate-risk patients. CONCLUSIONS: Ensuring adequate dose coverage at the posterior prostate and immediately surrounding posterior region (including the seminal vesicles), where aggressive cancer spread may be occurring, may improve tumor control. It is recommended that particular care be taken when defining margins at the prostate posterior, acknowledging the trade-off between quality of life due to rectal dose and the preferences of clinicians and patients.

Comparison of Deep Learning-Based and Patch-Based Methods for Pseudo-CT Generation in MRI-Based Prostate Dose Planning.

PURPOSE: Deep learning methods (DLMs) have recently been proposed to generate pseudo-CT (pCT) for magnetic resonance imaging (MRI) based dose planning. This study aims to evaluate and compare DLMs (U-Net and generative adversarial network [GAN]) using various loss functions (L2, single-scale perceptual loss [PL], multiscale PL, weighted multiscale PL) and a patch-based method (PBM). METHODS AND MATERIALS: Thirty-nine patients received a volumetric modulated arc therapy for prostate cancer (78 Gy). T2-weighted MRIs were acquired in addition to planning CTs. The pCTs were generated from the MRIs using 7 configurations: 4 GANs (L2, single-scale PL, multiscale PL, weighted multiscale PL), 2 U-Net (L2 and single-scale PL), and the PBM. The imaging endpoints were mean absolute error and mean error, in Hounsfield units, between the reference CT (CTref) and the pCT. Dose uncertainties were quantified as mean absolute differences between the dose volume histograms (DVHs) calculated from the CTref and pCT obtained by each method. Three-dimensional gamma indexes were analyzed. RESULTS: Considering the image uncertainties in the whole pelvis, GAN L2 and U-Net L2 showed the lowest mean absolute error (≤34.4 Hounsfield units). The mean errors were not different than 0 (P ≤ .05). The PBM provided the highest uncertainties. Very few DVH points differed when comparing GAN L2 or U-Net L2 DVHs and CTref DVHs (P ≤ .05). Their dose uncertainties were ≤0.6% for the prostate planning target Volume V95%, ≤0.5% for the rectum V70Gy, and ≤0.1% for the bladder V50Gy. The PBM, U-Net PL, and GAN PL presented the highest systematic dose uncertainties. The gamma pass rates were >99% for all DLMs. The mean calculation time to generate 1 pCT was 15 s for the DLMs and 62 min for the PBM. CONCLUSIONS: Generating pCT for MRI dose planning with DLMs and PBM provided low-dose uncertainties. In particular, the GAN L2 and U-Net L2 provided the lowest dose uncertainties together with a low computation time.

Multi-observer contouring of male pelvic anatomy: Highly variable agreement across conventional and emerging structures of interest.

INTRODUCTION: This study quantified inter-observer contouring variations for multiple male pelvic structures, many of which are of emerging relevance for prostate cancer radiotherapy progression and toxicity response studies. METHODS: Five prostate cancer patient datasets (CT and T2-weighted MR) were distributed to 13 observers for contouring. CT structures contoured included the clinical target volume (CTV), seminal vesicles, rectum, colon, bowel bag, bladder and peri-rectal space (PRS). MR contours included CTV, trigone, membranous urethra, penile bulb, neurovascular bundle and multiple pelvic floor muscles. Contouring variations were assessed using the intraclass correlation coefficient (ICC), Dice similarity coefficient (DSC), and multiple additional metrics. RESULTS: Clinical target volume (CT and MR), bladder, rectum and PRS contours showed excellent inter-observer agreement (median ICC = 0.97; 0.99; 1.00; 0.95; 0.90, DSC = 0.83 ± 0.05; 0.88 ± 0.05; 0.93 ± 0.03; 0.81 ± 0.07; 0.80 ± 0.06, respectively). Seminal vesicle contours were more variable (ICC = 0.75, DSC = 0.73 ± 0.14), while colon and bowel bag contoured volumes were consistent (ICC = 0.97; 0.97), but displayed poor overlap (DSC = 0.58 ± 0.22; 0.67 ± 0.21). Smaller MR structures showed significant inter-observer variations, with poor overlap for trigone, membranous urethra, penile bulb, and left and right neurovascular bundles (DSC = 0.44 ± 0.22; 0.41 ± 0.21; 0.66 ± 0.21; 0.16 ± 0.17; 0.15 ± 0.15). Pelvic floor muscles recorded moderate to strong inter-observer agreement (ICC = 0.50-0.97), although large outlier variations were observed. CONCLUSIONS: Inter-observer contouring variation was significant for multiple pelvic structures contoured on MR.

Pseudo-CT Generation for MRI-Only Radiation Therapy Treatment Planning: Comparison Among Patch-Based, Atlas-Based, and Bulk Density Methods.

PURPOSE: Methods have been recently developed to generate pseudo-computed tomography (pCT) for dose calculation in magnetic resonance imaging (MRI)-only radiation therapy. This study aimed to propose an original nonlocal mean patch-based method (PBM) and to compare this PBM to an atlas-based method (ABM) and to a bulk density method (BDM) for prostate MRI-only radiation therapy. MATERIALS AND METHODS: Thirty-nine patients received a volumetric modulated arc therapy for prostate cancer. In addition to the planning computed tomography (CT) scans, T2-weighted MRI scans were acquired. pCTs were generated from MRIs using 3 methods: an original nonlocal mean PBM, ABM, and BDM. The PBM was performed using feature extraction and approximate nearest neighbor search in a training cohort. The PBM accuracy was evaluated in a validation cohort by using imaging and dosimetric endpoints. Imaging endpoints included mean absolute error and mean error between Hounsfield units of the pCT and the reference CT (CTref). Dosimetric endpoints were based on dose-volume histograms calculated from the CTref and the pCTs for various volumes of interest and on 3-dimensional gamma analyses. The PBM uncertainties were compared with those of the ABM and BDM. RESULTS: The mean absolute error and mean error obtained from the PBM were 41.1 and -1.1 Hounsfield units. The PBM dose-volume histogram differences were 0.7% for prostate planning target volume V95%, 0.5% for rectum V70Gy, and 0.2% for bladder V50Gy. Compared with ABM and BDM, PBM provided significantly lower dose uncertainties for the prostate planning target volume (70-78 Gy), the rectum (8.5-29 Gy, 40-48 Gy, and 61-73 Gy), and the bladder (12-78 Gy). The PBM mean gamma pass rate (99.5%) was significantly higher than that of ABM (94.9%) or BDM (96.1%). CONCLUSIONS: The proposed PBM provides low uncertainties with dose planned on CTref. These uncertainties were smaller than those of ABM and BDM and are unlikely to be clinically significant.

Dedicated MRI simulation for cervical cancer radiation treatment planning: Assessing the impact on clinical target volume delineation.

INTRODUCTION: Magnetic Resonance Imaging (MRI) provides excellent soft tissue definition of pelvic tumours and organs. The aim of this study was to quantify differences in delineated clinical target volumes (CTVs) between computed tomography (CT) and MRI. METHODS: Twenty patients with locally advanced gynaecological malignancies were recruited. Patients underwent dedicated MRI simulation following CT simulation. Four clinicians independently contoured each CT and MRI. CTV structures were contoured using the Radiation Therapy Oncology Group (RTOG) guidelines and lymph node CTV (LN-CTV) according to published guidelines. Interobserver variability was analysed using the dice similarity coefficient (DSC) and mean absolute surface distance (MASD). RESULTS: Gross tumour volume delineation was more consistent on MRI compared to CT, the DSC improved from 0.77 on CT to 0.81 on MRI, P < 0.01. GTV volumes were significantly smaller on MRI compared to CT (MRI 92 cc vs. CT 117 cc, P < 0.01). The LN-CTV and combined CTV volumes were both significantly smaller on MRI compared to CT (LN-CTV: MRI 324 cc vs CT 354 cc, P < 0.01 and combined CTV: MRI 560 cc vs CT 600 cc, P < 0.01). The LN-CTV DSC was 0.75 for both MRI and CT, and the combined CTV DSC was 0.81 for MRI and 0.80 for CT, P = 0.27. Vagina and parametria volumes exhibited more variability compared to other structures. CONCLUSIONS: Magnetic Resonance Imaging contouring resulted in smaller and more consistently delineated volumes when compared to CT for most CTV structures. An MRI contouring atlas is provided to complement the existing RTOG contouring guidelines.

Comparative study of algorithms for synthetic CT generation from MRI: Consequences for MRI-guided radiation planning in the pelvic region.

PURPOSE: Magnetic resonance imaging (MRI)-guided radiation therapy (RT) treatment planning is limited by the fact that the electron density distribution required for dose calculation is not readily provided by MR imaging. We compare a selection of novel synthetic CT generation algorithms recently reported in the literature, including segmentation-based, atlas-based and machine learning techniques, using the same cohort of patients and quantitative evaluation metrics. METHODS: Six MRI-guided synthetic CT generation algorithms were evaluated: one segmentation technique into a single tissue class (water-only), four atlas-based techniques, namely, median value of atlas images (ALMedian), atlas-based local weighted voting (ALWV), bone enhanced atlas-based local weighted voting (ALWV-Bone), iterative atlas-based local weighted voting (ALWV-Iter), and a machine learning technique using deep convolution neural network (DCNN). RESULTS: Organ auto-contouring from MR images was evaluated for bladder, rectum, bones, and body boundary. Overall, DCNN exhibited higher segmentation accuracy resulting in Dice indices (DSC) of 0.93 ± 0.17, 0.90 ± 0.04, and 0.93 ± 0.02 for bladder, rectum, and bones, respectively. On the other hand, ALMedian showed the lowest accuracy with DSC of 0.82 ± 0.20, 0.81 ± 0.08, and 0.88 ± 0.04, respectively. DCNN reached the best performance in terms of accurate derivation of synthetic CT values within each organ, with a mean absolute error within the body contour of 32.7 ± 7.9 HU, followed by the advanced atlas-based methods (ALWV: 40.5 ± 8.2 HU, ALWV-Iter: 42.4 ± 8.1 HU, ALWV-Bone: 44.0 ± 8.9 HU). ALMedian led to the highest error (52.1 ± 11.1 HU). Considering the dosimetric evaluation results, ALWV-Iter, ALWV, DCNN and ALWV-Bone led to similar mean dose estimation within each organ at risk and target volume with less than 1% dose discrepancy. However, the two-dimensional gamma analysis demonstrated higher pass rates for ALWV-Bone, DCNN, ALMedian and ALWV-Iter at 1%/1 mm criterion with 94.99 ± 5.15%, 94.59 ± 5.65%, 93.68 ± 5.53% and 93.10 ± 5.99% success, respectively, while ALWV and water-only resulted in 86.91 ± 13.50% and 80.77 ± 12.10%, respectively. CONCLUSIONS: Overall, machine learning and advanced atlas-based methods exhibited promising performance by achieving reliable organ segmentation and synthetic CT generation. DCNN appears to have slightly better performance by achieving accurate automated organ segmentation and relatively small dosimetric errors (followed closely by advanced atlas-based methods, which in some cases achieved similar performance). However, the DCNN approach showed higher vulnerability to anatomical variation, where a greater number of outliers was observed with this method. Considering the dosimetric results obtained from the evaluated methods, the challenge of electron density estimation from MR images can be resolved with a clinically tolerable error.

A lightweight rapid application development framework for biomedical image analysis.

Biomedical imaging analysis typically comprises a variety of complex tasks requiring sophisticated algorithms and visualising high dimensional data. The successful integration and deployment of the enabling software to clinical (research) partners, for rigorous evaluation and testing, is a crucial step to facilitate adoption of research innovations within medical settings. In this paper, we introduce the Simple Medical Imaging Library Interface (SMILI), an object oriented open-source framework with a compact suite of objects geared for rapid biomedical imaging (cross-platform) application development and deployment. SMILI supports the development of both command-line (shell and Python scripting) and graphical applications utilising the same set of processing algorithms. It provides a substantial subset of features when compared to more complex packages, yet it is small enough to ship with clinical applications with limited overhead and has a license suitable for commercial use. After describing where SMILI fits within the existing biomedical imaging software ecosystem, by comparing it to other state-of-the-art offerings, we demonstrate its capabilities in creating a clinical application for manual measurement of cam-type lesions of the femoral head-neck region for the investigation of femoro-acetabular impingement (FAI) from three dimensional (3D) magnetic resonance (MR) images of the hip. This application for the investigation of FAI proved to be convenient for radiological analyses and resulted in high intra (ICC=0.97) and inter-observer (ICC=0.95) reliabilities for measurement of α-angles of the femoral head-neck region. We believe that SMILI is particularly well suited for prototyping biomedical imaging applications requiring user interaction and/or visualisation of 3D mesh, scalar, vector or tensor data.