Treatment Planning Data Research Articles

Utilizing acrylic acid polymer hydrogel for 3-D quality assurance in CyberKnife radiotherapy

Dosimetry tools play a crucial role in radiotherapy as they are essential for recording and validating intricate 3-D dose distributions. This research introduces and examines a novel acrylic acid polymer hydrogel (ACAPHG) dosimeter composition designed for 3-D dose verification and quality assurance in the context of radiotherapy treatment. A phantom made of an 80 mm diameter cylindrical glass container was utilized. The phantom contained the hydrogel, which served as the medium for radiation exposure. The water equivalent hydrogel within the phantom was subjected to irradiation by a CyberKnife robotic radiotherapy system. An optical computed tomography (OCT) scanner with sub-millimeter resolution was used to obtain imaging data. The dose distribution of a CyberKnife robotic SRS/SBRT treatment plan for a brain cancer patient was compared to that of the hydrogel's OCT scan using 2-D and 3-D gamma analysis with a criterion of 3% dose difference and 3 mm distance-to-agreement. A gamma pass rate of 94.1% for the 2-D gamma analysis and a pass rate of 99% for the 3-D gamma analysis were calculated within the region at which the treatment planning system data drops to 20% of the maximum dose. The use of the ACAPHG dosimeter in conjunction with the described setup suggests that it has the potential to offer an accurate 3-D verification of complex dose distributions in SRS/SBRT radiotherapy treatments. By employing the ACAPHG dosimeter and utilizing OCT scanning, this dosimeter enables the assessment and validation of intricate dose distributions in these advanced radiotherapy treatments.

Outcome Measures in Transactional Analysis Clinical Practice: Presentation of Research Methodology

This article introduces the research methodology underpinning a study on how Transactional Analysis practitioners use Outcome Measure data in diagnosis, contracting and treatment planning. After a brief literature review of outcome measures and details of the formulation of the research questions, it continues with the author’s understanding of Interpretative Phenomenological Analysis, which was the methodology used within the research, and how that aligns with transactional analysis. The further focus of this paper includes the ethical considerations, the inclusion criteria for research participants, the structure and planned content of the research interviews, and a description of the data analysis method. The final data analysis stage is still running so detailed findings will follow in later publications. A previous article by the author set out the rationale for the research, and the intention of this article is to present the research method so that it can be critiqued and replicated.

Evaluating Danish Breast Cancer Group locoregional radiotherapy guideline adherence in clinical treatment data 2008–2016: The DBCG RT Nation study

Background and purposeGuideline adherence in radiotherapy is crucial for maintaining treatment quality and consistency, particularly in non-trial patient settings where most treatments occur. The study aimed to assess the impact of guideline changes on treatment planning practices and compare manual registry data accuracy with treatment planning data. Materials and methodsThis study utilised the DBCG RT Nation cohort, a collection of breast cancer radiotherapy data in Denmark, to evaluate adherence to guidelines from 2008 to 2016. The cohort included 7448 high-risk breast cancer patients. National guideline changes included, fractionation, introduction of respiratory gating, irradiation of the internal mammary lymph nodes, use of the simultaneous integrated boost technique and inclusion of the Left Anterior Descending coronary artery in delineation practice. Methods for structure name mapping, laterality detection, detection of temporal changes in population mean lung volume, and dose evaluation were presented and applied. Manually registered treatment characteristic data was obtained from the Danish Breast Cancer Database for comparison. ResultsThe study found immediate and consistent adherence to guideline changes across Danish radiotherapy centres. Treatment practices before guideline implementation were documented and showed a variation among centres. Discrepancies between manual registry data and actual treatment planning data were as high as 10% for some measures. ConclusionNational guideline changes could be detected in the routine treatment data, with a high degree of compliance and short implementation time. Data extracted from treatment planning data files provides a more accurate and detailed characterisation of treatments and guideline adherence than medical register data.

Improved outcome models with denoising diffusion

PurposeRadiotherapy outcome modelling often suffers from class imbalance in the modelled endpoints. One of the main options to address this issue is by introducing new synthetically generated datapoints, using generative models, such as Denoising Diffusion Probabilistic Models (DDPM). In this study, we implemented DDPM to improve performance of a tumor local control model, trained on imbalanced dataset, and compare this approach with other common techniques. MethodsA dataset of 535 NSCLC patients treated with SBRT (50 Gy/5 fractions) was used to train a deep learning outcome model for tumor local control prediction. The dataset included complete treatment planning data (planning CT images, 3D planning dose distribution and patient demographics) with sparsely distributed endpoints (6–7 % experiencing local failure). Consequently, we trained a novel conditional 3D DDPM model to generate synthetic treatment planning data. Synthetically generated treatment planning datapoints were used to supplement the real training dataset and the improvement in the model’s performance was studied. Obtained results were also compared to other common techniques for class imbalanced training, such as Oversampling, Undersampling, Augmentation, Class Weights, SMOTE and ADASYN. ResultsSynthetic DDPM-generated data were visually trustworthy, with Fréchet inception distance (FID) below 50. Extending the training dataset with the synthetic data improved the model’s performance by more than 10%, while other techniques exhibited only about 4% improvement. ConclusionsDDPM introduces a novel approach to class-imbalanced outcome modelling problems. The model generates realistic synthetic radiotherapy planning data, with a strong potential to increase performance and robustness of outcome models.

Effect of Brachytherapy Source Dwell Position on Dose Distribution in Cervical Cancer Therapy

To investigate the effect of different source dwell positions on dose distribution in the treatment of cervical cancer with brachytherapy. Treatment planning data for cervical cancer patients were used. Treatment plans were created at 1 mm intervals, varying up to 5 mm. For intracavitary brachytherapy and intracavitary and interstitial brachytherapy, the following dose parameters were evaluated: 90% high-risk clinical target volume (HR-CTV D90%), rectum 2 cm3 dose (Rectum D2 cc), small intestine 2 cm3 dose (Small D2 cc), sigmoid colon 2 cm3 dose (Sigmoid D2 cc), bladder 2 cm3 dose (Bladder D2 cc), point A dose. In intracavitary brachytherapy, the HR-CTV D90%, Rectum D2 cc, Small D2 cc, and Sigmoid D2 cc doses increased as the source dwell position changed in the direction. On the other hand, the dose of Bladder D2 cc increased when the source position changed in the outward direction. The same trend was observed in the case of intracavitary and interstitial brachytherapy. It was shown that a 1 mm change in the source dwell position can affect the dose by up to 2% or more. The accuracy of the source dwell position is very important and should be checked before using the device.

Evaluation of the accuracy of implants using 3D printed surgical guides in implant placement

Background: The optimal position of the implant in 3 dimensions in space is the most important factor to ensure the long - term success of dental implants. Today, advanced technology can simulate the virtual implant position before surgery. Through 3D printing technology, it is possible to transfer the virtual implant position to the surgical field using a static surgical guide. This study aims to evaluate the accuracy of 3D printed surgical guides when performing implant when performed using 3D printed surgical guides. Methods: The study reports a series of clinical cases with 32 implants placed in the maxilla and mandible. The surgical guide is designed using Blue Sky Implant software. Postoperative CBCT data is combined with preoperative treatment plan data to evaluate deviations in implant position, angle between two implants, and vertical deviation. Results: The study showed implant misalignment when using 3D printed surgical guides: misalignment at the implant neck was 1.11 ± 0.67 mm; at the tip is 1.43 ± 1.053 mm; The angle is 3.01 ± 2.53o and the vertical is 0.71 ± 0.57 mm. The study noted that angular deviations, cervical, apical and vertical deviations were not statistically significant according to gender, parts of dental archs and implant position Conclusion: Using a surgical guide can help the implant to be placed more accurately in all 3 dimensions in the maxilla/ mandible. The 3D printed surgical guide has high precision and can be used to support implant surgery.

Multi-planner validation of RapidPlan knowledge-based model for volumetric modulated arc therapy in prostate cancer.

To investigate the performance of a model-based optimization process for volumetric modulated arc therapy (VMAT) applied to prostate cancer patients with the multi-planner. The 120 prostate plans for VMAT treatment were entered into the database system of the RapidPlan (RP) knowledge-based treatment planning. The treatment planning data for each plan was used to create and train the RP model. Twelve prostate cancer cases were selected and were used for planning by a manual of 12 planners based on the clinical protocol for dose constraints. Then, the treatment plans for each patient were compared with the RP model plans and analyzed with Wilcoxon tests. On average, the RP models can estimate comparable doses among all planner plans and clinical plans for the PTV, which Dmax , D95% , D98% , HI, and CI were used to evaluate. For the normal organ doses of the bladder, rectum, penile bulb, and femoral head, all RP model plans showed comparable or better dose sparing than all planner plans and clinical plans. Moreover, the average planning time of the RP model was faster than manual plans by about two times. The RP model can significantly reduce the variation dose of the normal organs compared with the manual plans among the planners. The automated plans of the RP model might benefit from further fine-tuning of the dose constraints of the normal organs, although both procedure plans are acceptable and fulfill the clinical protocol goals so that the RP model can enhance the efficacy and quality of plans.

A brain MRI dataset and baseline evaluations for tumor recurrence prediction after Gamma Knife radiotherapy

Prediction and identification of tumor recurrence are critical for brain cancer treatment design and planning. Stereotactic radiation therapy delivered with Gamma Knife has been developed as one of the common treatment approaches combined with others by delivering radiation that targets accurately on the tumor while not affecting nearby healthy tissues. In this paper, we release a fully publicly available brain cancer MRI dataset and the companion Gamma Knife treatment planning and follow-up data for the purpose of tumor recurrence prediction. The dataset contains original patient MRI images, radiation therapy data, and clinical information. Lesion annotations are provided, and inclusive preprocessing steps have been specified to simplify the usage of this dataset. A baseline framework based on a convolutional neural network is proposed companionably with basic evaluations. The release of this dataset will contribute to the future development of automated brain tumor recurrence prediction algorithms and promote the clinical implementations associated with the computer vision field. The dataset is made publicly available on The Cancer Imaging Archive (TCIA) (https://doi.org/10.7937/xb6d-py67).

Theraphosid medicine: what to do when something is peculiar with the tarantula

Background: With over 1060 species reported and a considerable number of these kept in captivity, theraphosid spiders, also known as tarantulas, have become a significant part of private and zoological collections, hence necessitating a greater demand for veterinary expertise.Aim of the article: This comprehensive review addresses the unique challenges in tarantula care. It delves into the application of diagnostic tools like histology, radiography, haematology and microbiology in tarantulas, and discusses how to gather clinically relevant data for effective treatment planning of common conditions. It also outlines adaptations to cater treatments to tarantulas' unique anatomy, and offers guidance on drug selection and veterinary procedures, as well as covering humane euthanasia methods.

Using clinical pathways to identify patient candidates for survivorship in testicular cancer.

492 Background: Dana-Farber Cancer Institute’s (DFCI) Clinical Pathways provide evidence-based decision support for oncologists across a variety of care settings. Data generated by Pathways enable continued cancer care improvement and may also be a tool for identifying patient candidates for survivorship. Here, we explore patients diagnosed with testicular cancer treated with curative intent. Methods: Oncologists at DFCI navigate Clinical Pathways when starting or changing therapies. Each navigation provides discrete clinical data elements about disease (e.g., histology, stage), treatment setting (e.g., line of therapy), and treatment selected. Here, pathway navigation data was used to retrospectively identify patients with testicular cancer who were appropriate for survivorship resources. Eligibility criteria included patients who completed therapy, had not received treatment in 12-24 months since initial therapy navigation, and had a follow-up appointment scheduled. Eligible patients were referred to the testicular cancer survivorship program. Results: Between April 2021 to April 2022, we identified 25 testicular cancer patients treated at DFCI’s primary Longwood campus. Twelve of the 25 patients were identified as eligible for a survivorship referral. Nine of those 12 patients (75%) were successfully identified through the Pathways testicular survival algorithm described above. A Pathways navigation had not been completed by the providers of the 3-remaining survivorship-eligible patients, who were instead identified by EHR treatment plan data. One of the 12 patients screened by the testicular survivorship identification process developed metastatic disease that was not captured by the current algorithm and was then deemed inappropriate for survivorship referral. The remaining 11 patients were contacted and offered survivorship resources. As a reference, the total pathways usage rate between April 2021 to April 2022 for the DFCI genitourinary oncology group was 85% across all GU malignancies, and 74% in testicular cancer. Conclusions: Pathways Navigations can provide robust clinical information about patients, disease, and treatment. This information can be used to identify patients appropriate for survivorship and other clinical resources and trial opportunities in testicular cancer and across other malignancies. The impact of this process requires reliable provider usage of the Clinical Pathways tool.[Table: see text]

Deep Learning-Based Automated Quality Assurance for Palliative Spinal Treatment Planning in Radiotherapy

Robustquality assurance (QA) for palliative spine radiation therapy (RT) remains critical due to the risk of wrong anatomic level treatment on account of human error in enumerating vertebral bodies accurately based on morphology with incomplete imaging of the spine and prevalence of anatomic variants (10%). We propose a rapid, fully automated deep learning-based QA (DL-QA) tool for segmenting and enumerating vertebral structures from image data, capable of identifying misalignment based on discrepancies in calculated dose coverage. Ina retrospective cohort of 514 patients who received palliative spine radiation treatment at a single institution for spinal metastases, vertebral volumes for each individual spine level were automatically segmented on RT planning computed tomography scans using a publicly available deep learning algorithm, Total Segmentator (TS) deployed in the treatment planning system (Wasserthal et al, 2022). Departmental policy requires that the prescription/plan name include all spinal levels that receive a prescribed dosimetric threshold of V50% > 50%. By comparing the intended spine level target in the prescription and plan name against the TS volumes, the DL-QA flagged all cases for which any target vertebrae did not receive this threshold dose and/or any non-targeted vertebrae that received V50% > 50%. To detect spine anomalies, cases were also flagged if any vertebrae volume was not within ±1σ of the entire population of vertebrae volumes. Flagged cases were either categorized as: (1) wrong spine level RT error; (2) documentation error, in which treatment was correct but the prescription/plan name did not follow Departmental policy; or (3) potential spinal geometric error. All flagged cases were verified manually by checking the original images and treatment planning data. Outof 514 patients, 29 cases were flagged as potential errors. Manual review revealed that one of these was a previously discovered true treatment error (due to anatomic variant with 4 lumbar bodies) while 10 were treated as intended but showed documentation errors due to variants in the number of vertebral bodies, kyphosis of the spine causing non-targeted vertebrae to appear in the treatment field, or improper observation of the Departmental plan naming policy. The remaining 18 cases were associated with flagged vertebrae volumes. Reviewing those patients, we identified spinal anomalies where TS attempted to account for extra or missing vertebrae (N = 9) and cases where TS made segmentation errors (N = 9). Theproposed automated DL-QA system successfully identified patients with spine anomalies, flagged documentation errors, verified the correct target levels of spine RT treatments, and detected a known misadministration. The next phase will involve prospective testing of the system in a clinical setting upstream of treatment delivery.

The impact of COVID-19 national restrictions on dental antibiotic dispensing trends and treatment activity in England: January 2016 to July 2021.

Reducing inappropriate antibiotic prescribing tempers the growing threat of antimicrobial resistance. We aimed to quantify the associated impact of COVID-19-related national restrictions in England on dental antibiotic dispensing and describe changes in appointments and modes of delivery of care. Interrupted time series analyses were completed using NHS Business Service Authority (NHSBSA) ePACT2 data to measure the associated change in antibiotic dispensing in England following COVID-19-related restrictions (which began March 2020). For face-to-face dental consultations, NHS dental treatment plan (FP17) data were used. For remote consultations during the COVID-19 period, NHSBSA Compass system remote management data were used. Between January 2016 and February 2020, there was a decreasing trend in antibiotic dispensing (-0.02 per 1000 population per month, P < 0.05). In contrast, there was an increase of 0.98 per 1000 population (P < 0.05) in March. The peak in antibiotic use occurred between June 2020 and July 2020, once the restrictions were eased. At the end of the study period (July 2021), the elevated prescribing trend had not returned to pre-pandemic counterfactual levels, although exhibiting a declining trend. A stable trend in dental treatment plans was seen pre-COVID-19, with a sharp decline coinciding with the restrictions. Dental treatment plans had not yet returned to the higher pre-pandemic levels. Dental antibiotic prescribing significantly increased with the national COVID-19 restrictions when service delivery was altered with the closure of dental practices and introduction of remote consultations. Teledentistry was likely associated with inappropriate antibiotic prescribing. Continued antimicrobial stewardship and prudent use of antibiotics in dentistry is important.

An evidence-based stepwise approach to orthopedic treatment

Treatment protocols help organize data for accurate diagnosis and treatment planning. The aim was to develop a logical series of steps predicated on the latest credible body of evidence. The steps were developed for Class II patients with hyperdivergent growth patterns. The steps include establishing 1) the patient's problem list to determine the treatment objectives; 2) the theoretical basis modifying growth; 3) the etiology of the problem 4) the growth mechanisms that produce normal growth, and 5) a practical and realistic treatment approach. Departing from traditional assessments by reverse engineering the problem, potential gaps in the application of knowledge to practice may be recognized and addressed.

Independent reliability and availability analyses of modified classification for migrated lumbar disc herniation

Study designRetrospective cohort study.ObjectiveThe purpose of this study was to evaluate the reliability of modified classification system of migrated nucleus pulposus and its clinical application value.MethodsWe retrieved 1000 lumbar MRI of different patients in Hangzhou Hospital of Traditional Chinese Medicine from January 2016 to December 2019 for interpretation, and screened 105 migrated lumbar MRI for inclusion in the study. Three spinal surgeons made classification according to the modified classification method. Two weeks later, the sorting data of the patients were shuffled and the classification was judged by three doctors again. The consistency and repeatability of the improved classification were evaluated by Kappa coefficient. The general data of the included patients were collected. The patients were followed up for 2 years, and the risk factors of surgical treatment of patients with migrated lumbar disc herniation were analyzed. The treatment plan, surgical approach, operation time, VAS score, ODI score and other relevant data of the included patients were collected to evaluate the guiding effect of the classification system on clinical practice.ResultsIn this study, the incidence of migrated lumbar disc herniation was about 10.5%, and most of the patients were male. Patients with higher BMI are more likely to develop this disease. Our study confirmed that the modified classification has moderate to high confidence. During the 2-year follow-up period, 66 patients (62.9%) were treated conservatively, and the patients with conservative treatment were mainly A2 and B2 type (59.1%). Thirty-nine patients (37.1%) underwent surgical treatment. The patients recovered well after operation, and the low back pain and ODI index were significantly improved at 1 year after operation (P < 0.05). We suggest that type A1 and B1 migrated nucleus pulposus can be removed by posterior approach. For type A2, B2, C1, C2, the lateral approach is recommended to remove the nucleus pulposus directly. Logistic regression and ROC analysis showed that disease duration (≥ 1 year) and BMI (≥ 24) maybe were risk factors for surgical treatment of patients with migrated lumbar disc herniation.ConclusionThe modified classification has good reliability. In the current study, the experience level of spine surgeons does not affect the reliability of the classification system. Our study confirmed that this classification has a good reference value for guiding the treatment plan and the choice of surgical approach.

Novel framework for determining TPS-calculated doses corresponding to detector locations using 3D camera in in vivo surface dosimetry

Purpose. To address the shortcomings of current procedures for evaluating the measured-to-planned dose agreement in in vivo dosimetry (IVD), this study aimed to develop an accurate and efficient novel framework to identify the detector location placed on a patient’s skin surface using a 3D camera and determine the planned dose at the same anatomical position corresponding to the detector location. Methods. Breast cancer treatment was simulated using an anthropomorphic adult female phantom (ATOM 702D; CIRS, Norfolk, VA, USA). An optically stimulated luminescent dosimeter was used for surface dose measurements (MyOSLchip, RadPro International GmbH, Germany) at six IVD points. Three-dimensional surface imaging (3DSI) of the phantom with the detector was performed in the treatment position using a 3D camera. The developed framework, iSMART, was designed to import 3DSI and treatment planning data for determining the position of the IVD detectors in the 3D treatment planning DICOM image. The clinical usefulness of iSMART was evaluated in terms of accuracy and efficiency, for comparison with the results obtained using cone-beam computed tomography (CBCT) image guidance. Results. The relative dose difference between the planned doses determined using iSMART and CBCT images displayed similar accuracies (within approximately ±2.0%) at all detector locations. The relative dose differences between the planned and measured doses at the six detector locations ranged from –4.8% to 3.1% for the CBCT images and –3.5% to 2.1% for iSMART. The total time required to read the planned doses at six detector locations averaged at 8.1 and 0.8 min for the CBCT images and iSMART, respectively. Conclusions. The proposed framework can improve the robustness of IVD analyses and aid in accurate and efficient evaluations of the measured-to-planned dose agreement.

Uncertainty guidance in proton therapy planning visualization

We investigate uncertainty guidance mechanisms to support proton therapy (PT) planning visualization. Uncertainties in the PT workflow pose significant challenges for navigating treatment plan data and selecting the most optimal plan among alternatives. Although guidance techniques have not yet been applied to PT planning scenarios, they have successfully supported sense- and decision-making processes in other contexts. We hypothesize that augmenting PT uncertainty visualization with guidance may influence the intended users’ perceived confidence and provide new insights. To this end, we follow an iterative co-design process with domain experts to develop a visualization dashboard enhanced with distinct level-of-detail uncertainty guidance mechanisms. Our approach classifies uncertainty guidance into two dimensions: degree of intrusiveness and detail-orientation. Our dashboard supports the comparison of multiple treatment plans (i.e., nominal plans with their translational variations) while accounting for multiple uncertainty factors. We subsequently evaluate the designed and developed strategies by assessing perceived confidence and effectiveness during a sense- and decision-making process. Our findings indicate that uncertainty guidance in PT planning visualization does not necessarily impact the perceived confidence of the users in the process. Nonetheless, it provides new insights and raises uncertainty awareness during treatment plan selection. This observation was particularly evident for users with longer experience in PT planning.

Vaginal Toxicity Management in Patients with Locally Advanced Cervical Cancer following Exclusive Chemoradiation-A Nationwide Survey on Knowledge and Attitudes by the Italian Association of Radiotherapy and Clinical Oncology (AIRO) Gynecology Study Group.

Background and Objective: Exclusive radiotherapy, including external beam radiotherapy (EBRT) and interventional radiotherapy/brachytherapy (IRT/BT), with concurrent cisplatin-based chemotherapy, represents the standard of care in patients with locally advanced cervical cancer (LACC). The emerging topic of vaginal toxicity has become a key endpoint in LACC management, although different approaches and non-standardized procedures were available. Our aim was to analyze a nationwide study of the attitudes of Italian gynecological radiation oncology teams in the management of LACC patients' vaginal toxicities. Methods: A nationwide survey of radiation oncologists specializing in the treatment of gynecological malignancies was performed, using the free SurveyMonkey platform, consisting of 26 items. The questionnaire was proposed by the Italian Association of Radiation Oncologists (AIRO) gynecological working group to all 183 Italian radiation oncology institutions, as per AIRO's website. Results: Fifty-eight questionnaires (31%) were completed and returned. The assessment of acute and late vaginal toxicities was systematic in 32 (55.2%) and 26 (44.8%) centers, respectively. In the case of EBRT, 70.7% of centers, according to the contouring and treatment plan data, did not contour the vagina as an organ at risk (OAR). Vaginal dose constraints were heterogeneous for both EBRT and IRT/BT. Local treatment to prevent vaginal toxicity was prescribed by 60.3% of radiation oncologists, mostly vaginal hyaluronic acid cream, and one center recommended vaginal estrogen preparations. During follow-up visits, vaginal toxicity was considered an issue to be investigated always (n = 31) or in sexually active women only (n = 11). Conclusions: This survey showed that wide variation exists with regard to recording and treating vaginal toxicity after exclusive chemoradiation for cervical cancer, underscoring the need to develop more comprehensive guidelines for contouring e-dose reporting of the vagina, so as to implement clinical approaches for vaginal toxicity.

Using a Further Planning MRI after Neoadjuvant Androgen Deprivation Therapy Significantly Reduces the Radiation Exposure of Organs at Risk in External Beam Radiotherapy of Prostate Cancer.

Radiotherapy for prostate cancer is often preceded by neoadjuvant androgen deprivation therapy (ADT), which leads to a reduction in the size of the prostate. This study examines whether it is relevant for treatment planning to acquire a second planning magnetic resonance imaging (MRI) after ADT (=MRI 2) or whether it can be planned without disadvantage based on an MRI acquired before starting ADT (=MRI 1). The imaging data for the radiotherapy treatment planning of 17 patients with prostate cancer who received two planning MRIs (before and after neoadjuvant ADT) were analyzed as follows: detailed comparable radiation plans were created separately, each based on the planning CT scan and either MRI 1 or MRI 2. After ADT for an average of 17.2 weeks, the prostate was reduced in size by an average of 24%. By using MRI 2 for treatment planning, the V60Gy of the rectum could be significantly relieved by an average of 15% with the same coverage of the target volume, and the V70Gy by as much as 33% (compared to using MRI 1 alone). Using a second MRI for treatment planning after neoadjuvant ADT in prostate cancer leads to a significant relief for the organs at risk, especially in the high dose range, with the same irradiation of the target volume, and should therefore be carried out regularly. Waiting for the prostate to shrink after a few months of ADT contributes to relief for the organs at risk and to lowering the toxicity. However, the use of reduced target volumes requires an image-guided application, and the oncological outcome needs to be verified in further studies.

A Deep-Learning Error Detection System in Radiation Therapy.

Delivering radiation therapy based on erroneous or corrupted treatment plan data has previously and unfortunately resulted in severe, sometimes grave patient harm. Aiming to prevent such harm and improve safety in radiation therapy treatment, this work introduces a novel, yet intuitive algorithm for strategically structuring the complex and unstructured data typical of modern treatment plans so their treatment sites may automatically be verified with deep-learning architectures. The proposed algorithm utilizes geometric and dose plan parameters to represent each plan's data as a heat map to feed a deep-learning classifier that will predict the plan's treatment site. Once it is returned by the classifier, a plan's predicted site can be compared to its documented intended site, and a warning raised should the two differ. Using real head-neck, breast, and prostate treatment plan data retrieved at two hospitals in the United States, the algorithm is evaluated by observing the accuracy of convolutional neural networks (ConvNets) in correctly classifying the structured heat map data. Many well-known ConvNet architectures are tested, and ResNet-18 performs the best with a testing accuracy of 97.8% and 0.979 F-1 score. Clearly, the heat maps generated by the proposed algorithm, despite using only a few of the many available plan parameters, retain enough information for correct treatment site classification. The simple construction and ease of interpretation make the heat maps an attractive choice for classification and error detection.

Characterization of a robust probabilistic framework for brain magnetic resonance image data distributions

Probabilistic characterisation of image data for accurate prognosis and treatment planning remains a long‐standing problem in medical research, especially when the data distribution depicts flat‐top and high‐order contact. Such flat‐top distributions are quite common in brain magnetic resonance (MR) image data, where the density drops sharply beyond the flat interval. Intuitively, it would indicate a bipartition of data into positive region containing observations definitely belonging to the image class and boundary region with observations possibly belonging to it. The flat peak would also imply that multiple values are equally most likely to belong to that class. However, the popular probability distributions used in such cases are unimodal, creating ambiguity about the positive region. In this work, we study the statistical properties and develop likelihood‐based iterative estimation method for the parameters of a novel class of platykurtic probability distributions containing normal, called the stomped normal distribution, that provides more accurate modelling to the flat‐top data distributions. The robustness of the proposed stomped normal model has been illustrated with six simulated and nine real brain MR volumes. Our analysis shows substantial improvement in explaining a variety of shapes of data distributions using the proposed probability model.