Comparison of different deep learning architectures for synthetic CT generation from MR images

PurposeAmong the different available methods for synthetic CT generation from MR images for the task of MR-guided radiation planning, the deep learning algorithms have and do outperform their conventional counterparts. In this study, we investigated the performance of some most popular deep learning architectures including eCNN, U-Net, GAN, V-Net, and Res-Net for the task of sCT generation. As a baseline, an atlas-based method is implemented to which the results of the deep learning-based model are compared.MethodsA dataset consisting of 20 co-registered MR-CT pairs of the male pelvis is applied to assess the different sCT production methods' performance. The mean error (ME), mean absolute error (MAE), Pearson correlation coefficient (PCC), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR) metrics were computed between the estimated sCT and the ground truth (reference) CT images.ResultsThe visual inspection revealed that the sCTs produced by eCNN, V-Net, and ResNet, unlike the other methods, were less noisy and greatly resemble the ground truth CT image. In the whole pelvis region, the eCNN yielded the lowest MAE (26.03 ± 8.85 HU) and ME (0.82 ± 7.06 HU), and the highest PCC metrics were yielded by the eCNN (0.93 ± 0.05) and ResNet (0.91 ± 0.02) methods. The ResNet model had the highest PSNR of 29.38 ± 1.75 among all models. In terms of the Dice similarity coefficient, the eCNN method revealed superior performance in major tissue identification (air, bone, and soft tissue).ConclusionsAll in all, the eCNN and ResNet deep learning methods revealed acceptable performance with clinically tolerable quantification errors.     

DeepWL: Robust EPID based Winston-Lutz analysis using deep learning,synthetic image generation and optical path-tracing

Radiation therapy requires clinical linear accelerators to be mechanically and dosimetrically calibrated to a high standard. One important quality assurance test is the Winston-Lutz test which localises the radiation isocentre of the linac.In the current work we demonstrate a novel method of analysing EPID based Winston-Lutz QA images using a deep learning model trained only on synthetic image data. In addition, we propose a novel method of generating the synthetic WL images and associated ‘ground-truth’ masks using an optical path-tracing engine to ‘fake’ mega-voltage EPID images.The model called DeepWL was trained on 1500 synthetic WL images using data augmentation techniques for 180 epochs. The model was built using Keras with a TensorFlow backend on an Intel Core i5-6500T CPU and trained in approximately 15 h. DeepWL was shown to produce ball bearing and multi-leaf collimator field segmentations with a mean dice coefficient of 0.964 and 0.994 respectively on previously unseen synthetic testing data. When DeepWL was applied to WL data measured on an EPID, the predicted mean displacements were shown to be statistically similar to the Canny Edge detection method. However, the DeepWL predictions for the ball bearing locations were shown to correlate better with manual annotations compared with the Canny edge detection algorithm.DeepWL was demonstrated to analyse Winston-Lutz images with an accuracy suitable for routine linac quality assurance with some statistical evidence that it may outperform Canny Edge detection methods in terms of segmentation robustness and the resultant displacement predictions.     

Central nervous system metastasis from osteosarcoma: Case report and literature review

Osteosarcoma is the most common primary malignancy of bone in children and young adults, the highest incidence peak is during adolescence and doesn’t have any gender predominance. The main site of metastasis are the lungs and extrapulmonary cases are occasional. The incidence of metastasis in the Central Nervous System (CNS) is 2–6.5%, increase to 10–15% in patients with pulmonary metastases. Therefore, metastatic disease of the CNS is rare and the information on such patients is limited. Here, we describe a case of a 20-year old patient diagnosed with osteosarcoma in the left distal femur stage IIB, he developed pulmonary disease, during palliative chemotherapy experienced relapse to the brain classified as recursive partitioning analysis (RPA) class II, and was treated with external radiotherapy (30?Gy in 10 fractions) and later he had a poor evolution and died.     

环状RNA计算预测方法的研究进展

环状RNA(circular RNA,circRNA)是一类具有重要生物作用的内源性RNA,大多在可变剪接过程中通过5'端和3'端反向共价连接形成闭合环状结构.目前,环状RNA的识别策略主要分为两大类:一类方法从高通量测序(RNA-seq)数据中检测反向剪接位点,另一类直接从RNA序列中检测成环特征.由于数据本身和识别...     

Artificial intelligence and machine learning for medical imaging: A technology review

Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.     

A review of dose calculation approaches with cone beam CT in photon and proton therapy

Background and purposeThe use of cone beam computed tomography (CBCT) for performing dose calculations in radiation therapy has been widely investigated as it could provide a quantitative analysis of the dosimetric impact of changes in patients during the treatment. The aim of this review was to classify different techniques adopted to perform CBCT dose calculation and to report their dosimetric accuracy with respect to the metrics used.Methods and materialsA literature search was carried out in PubMed and ScienceDirect databases, based upon the following keywords: “cone beam computed tomography”, “CBCT”, “cone beam CT”, “dose calculation”, “accuracy”. Sixty-nine peer-reviewed relevant articles were included in this review: thirty-one patient studies, fifteen phantom studies and twenty-three patient & phantom studies. Most studies were found to have focused on head and neck, lung and prostate cancers.ResultsThe techniques adopted to perform CBCT dose calculation have been grouped in six categories labelled as (1) pCT calibration, (2) CBCT calibration, (3) HU override, (4) Deformable image registration, (5) Dose deformation, and (6) Combined techniques. Differences between CBCT dose and reference dose were reported both for target volumes and OARs.ConclusionsA comparison among the available techniques for CBCT dose calculations is challenging as many variables are involved. Therefore, a set of reporting standards is recommended to enable meaningful comparisons among different studies. The accuracy of the results was strongly dependent on the image quality, regardless of the methods used, highlighting the need for dose validation and quality assurance standards.     

Task-based characterization of a deep learning image reconstruction and comparison with filtered back-projection and a partial model-based iterative reconstruction in abdominal CT: A phantom study

PurposeWe aimed to thoroughly characterize image quality of a novel deep learning image reconstruction (DLIR), and investigate its potential for dose reduction in abdominal CT in comparison with filtered back-projection (FBP) and a partial model-based iterative reconstruction (ASiR-V).MethodsWe scanned a phantom at three dose levels: regular (7 mGy), low (3 mGy) and ultra-low (1 mGy). Images were reconstructed using DLIR (low, medium and high levels) and ASiR-V (0% = FBP, 50% and 100%). Noise and contrast-dependent spatial resolution were characterized by computing noise power spectra and target transfer functions, respectively. Detectability indexes of simulated acute appendicitis or colonic diverticulitis (low contrast), and calcium-containing urinary stones (high contrast) (|ΔHU| = 50 and 500, respectively) were calculated using the nonprewhitening with eye filter model observer.ResultsAt all dose levels, increasing DLIR and ASiR-V levels both markedly decreased noise magnitude compared with FBP, with DLIR low and medium maintaining noise texture overall. For both low- and high-contrast spatial resolution, DLIR not only maintained, but even slightly enhanced spatial resolution in comparison with FBP across all dose levels. Conversely, increasing ASiR-V impaired low-contrast spatial resolution compared with FBP. Overall, DLIR outperformed ASiR-V in all simulated clinical scenarios. For both low- and high-contrast diagnostic tasks, increasing DLIR substantially enhanced detectability at any dose and contrast levels for any simulated lesion size.ConclusionsUnlike ASiR-V, DLIR substantially reduces noise while maintaining noise texture and slightly enhancing spatial resolution overall. DLIR outperforms ASiR-V by enabling higher detectability of both low- and high-contrast simulated abdominal lesions across all investigated dose levels.     

Advanced dose calculation algorithms in lung cancer radiotherapy: Implications for SBRT and locally advanced disease in deep inspiration breath hold

PurposeEvaluating performance of modern dose calculation algorithms in SBRT and locally advanced lung cancer radiotherapy in free breathing (FB) and deep inspiration breath hold (DIBH).MethodsFor 17 patients with early stage and 17 with locally advanced lung cancer, a plan in FB and in DIBH were generated with Anisotropic Analytical Algorithm (AAA). Plans for early stage were 3D-conformal SBRT, 45 Gy in 3 fractions, prescribed to 95% isodose covering 95% of PTV and aiming for 140% dose centrally in the tumour. Locally advanced plans were volumetric modulated arc therapy, 66 Gy in 33 fractions, prescribed to mean PTV dose. Calculation grid size was 1 mm for SBRT and 2.5 mm for locally advanced plans. All plans were recalculated with AcurosXB with same MU as in AAA, for comparison on target coverage and dose to risk organs.ResultsLung volume increased in DIBH, resulting in decreased lung density (6% for early and 13% for locally-advanced group).In SBRT, AAA overestimated mean and near-minimum PTV dose (p-values < 0.01) compared to AcurosXB, with largest impact in DIBH (differences of up to 11 Gy). These clinically relevant differences may be a combination of small targets and large dose gradients within the PTV.In locally advanced group, AAA overestimated mean GTV, CTV and PTV doses by median less than 0.8 Gy and near-minimum doses by median 0.4–2.7 Gy.No clinically meaningful difference was observed for lung and heart dose metrics between the algorithms, for both FB and DIBH.ConclusionsAAA overestimated target coverage compared to AcurosXB, especially in DIBH for SBRT.     

A review on gold nanoparticles radiosensitization effect in radiation therapy of cancer

In the recent years, application of nanoparticles in diagnosis and treatment of cancer has been the issue of extensive research. Among these studies some have focused on the dose enhancement effect of gold nanoparticles (GNPs) in radiation therapy of cancer. On the other hand, some studies indicated energy dependency of dose enhancement effect, and the others have studied the GNP size effect in association with photon energy. However, in some aspects of GNP-based radiotherapy the results of recent studies do not seem very conclusive in spite of relative agreement on the basic physical interaction of photoelectric between GNPs and low energy photons. The main idea behind the GNP dose enhancement in some studies is not able to explain the results especially in recent investigation on cell lines and animal models radiation therapy using GNPs. In the present article the results of the available reports and articles were analyzed and compared and the final status of the GNP-RT was discussed.     

Cumulative radiation dose estimates from medical imaging in paediatric patients with non-oncologic chronic illnesses. A systematic review

Paediatric patients with non-oncologic chronic illnesses often require ongoing care that may result in repeated imaging and exposure to ionizing radiation from both diagnostic and interventional procedures. In this study the scientific literature on cumulative effective dose (CED) of radiation accrued from medical imaging among specific cohorts of paediatric, non-oncologic chronic patients (inflammatory bowel disease, cystic fibrosis, congenital heart disease, shunt-treated hydrocephalus, hemophilia, spinal dysraphism) was systematically reviewed.We conducted PubMed/Medline, Scopus and EMBASE searches of peer-reviewed papers on CED from diagnostic and therapeutic radiological examinations. No time restriction was introduced in the search. Only studies reporting CEDs accrued for a period >1 year were included.We found that the annual CED was relatively low (<3 mSv/year) in cystic fibrosis, congenital heart disease, patients with cerebrospinal fluid shunts and hemophilia, while being moderate (>3–20 mSv/year) in Crohn's patients.This extra yearly radiation exposure accrues over the lifetime and can reach high values (>100 mSv) in selected cohorts of paediatric chronic patients.     

Deep learning representations to support COVID-19 diagnosis on CT slices

Introduction: The coronavirus disease 2019 (COVID-19) has become a significant public health problem worldwide. In this context, CT-scan automatic analysis has emerged as a COVID-19 complementary diagnosis tool allowing for radiological finding characterization, patient categorization, and disease follow-up. However, this analysis depends on the radiologist’s expertise, which may result in subjective evaluations.Objective: To explore deep learning representations, trained from thoracic CT-slices, to automatically distinguish COVID-19 disease from control samples.Materials and methods: Two datasets were used: SARS-CoV-2 CT Scan (Set-1) and FOSCAL clinic’s dataset (Set-2). The deep representations took advantage of supervised learning models previously trained on the natural image domain, which were adjusted following a transfer learning scheme. The deep classification was carried out: (a) via an end-to-end deep learning approach and (b) via random forest and support vector machine classifiers by feeding the deep representation embedding vectors into these classifiers.Results: The end-to-end classification achieved an average accuracy of 92.33% (89.70% precision) for Set-1 and 96.99% (96.62% precision) for Set-2. The deep feature embedding with a support vector machine achieved an average accuracy of 91.40% (95.77% precision) and 96.00% (94.74% precision) for Set-1 and Set-2, respectively.Conclusion: Deep representations have achieved outstanding performance in the identification of COVID-19 cases on CT scans demonstrating good characterization of the COVID-19 radiological patterns. These representations could potentially support the COVID-19 diagnosis in clinical settings.     

A deep learning approach to gold nanoparticle quantification in computed tomography

IntroductionDeep learning (DL) is used to classify, detect, and quantify gold nanoparticles (AuNPs) in a human-sized phantom with a clinical MDCT scanner.MethodsAuNPs were imaged at concentrations between 0.0274 and 200 mgAu/mL in a 33 cm phantom. 1 mm-thick CT image slices were acquired at 120 kVp with a CTDI_vol of 23.6 mGy. A convolutional neural network (CNN) was trained on 544 images to classify 17 different tissue types and AuNP concentrations. A second set of 544 images was then used for testing.ResultsAuNPs were classified with 95% accuracy at 0.1095 mgAu/mL and 97% accuracy at 0.2189 mgAu/mL. Both these concentrations are lower than what humans can visually perceive (0.3–1.4 mgAu/mL). AuNP concentrations were also classified with 95% accuracy at 150 and 200 mgAu/mL. These high concentrations result in CT numbers that are at or above the 12-bit limit for CT’s dynamic range where extended Hounsfield scales are otherwise required for measuring differences in contrast.ConclusionsWe have shown that DL can be used to detect AuNPs at concentrations lower than what humans can visually perceive and can also quantify very high AuNP concentrations that exceed the typical 12-bit dynamic range of clinical MDCT scanners. This second finding is possible due to inhomogeneous AuNP distributions and characteristic streak artifacts. It may even be possible to extend this approach beyond AuNP imaging in CT for quantifying high density objects without extended Hounsfield scales.     

Prostate embryonal rhabdomyosarcoma in adults: Case report and review of literature

Introduction

Prostate embryonal rhabdomyosarcoma (ERMS) is a common tumour in infants and children, with a median occurrence age of 5 years, but it is rare in adults. It is characterized by a high degree of malignancy, both local rapid growth with formation of large pelvic masses, often leading to renal failure due to urethral obstruction, and systemic spread, commonly to the lungs, liver and bone. Several therapeutic approaches have been employed in the effort to treat prostate ERMS, but all of them have failed to gain a significant survival benefit in adult patients.

Case report

We report on a case of a stage IV prostate ERMS, approached with combined-modality treatment, with the administration of 5 courses of doxorubicin, ifosfamide and 2-mercaptoethane sulfonate sodium (mesna), and, subsequent radiotherapy to the prostatic bed (60 Gy/30 fxs). The patient remained free of progression of disease for about 1 year to finally experience a systemic relapse with multiple lung metastases and pleural effusion. The patient died for metastatic disease 27 months following the initial diagnosis.

Conclusion

While it remains questionable which therapeutic approach for prostate ERMS in adults is the most appropriate, our report demonstrates that a chemo-radiation combined treatment can control the prostate disease, reducing the symptoms and improving the quality of life of these patients, for the most part destined to die for systemic progression of disease.     

Estimation and reduction of the radiation dose to the fetus from external-beam radiotherapy

The appearance of a malignant disease during pregnancy is relatively rare. The use of external-beam radiation therapy is limited to non-pelvic tumors which are usually located above the diaphragm. However, supradiaphragmatic radiotherapy unavoidably exposes the fetus to secondary radiation due to head leakage, scatter from the machine and scatter produced inside the patient. This fetal exposure may be associated with an elevated risk for the development of deterministic harmful effects and/or carcinogenesis. The decision about the administration of radiotherapy in a pregnant patient is influenced by the fetal dose which must always be estimated before the patient’s treatment course. The methods employed for fetal dosimetry in external-beam radiotherapy are described in this review study. Direct dose measurements using thermoluminescent dosemeters or large ionization chambers placed on physical phantoms may be used. Monte Carlo simulations on computational phantoms may also provide accurate fetal dose calculations. The physical and/or computational phantoms need to simulate the full-scatter geometry of the pregnant patient. Typical fetal dose values attributable to radiation therapy for brain tumors, head and neck cancer, breast carcinoma and Hodgkin lymphoma at the first, second and third trimesters of gestation are presented. The effectiveness of different shielding devices for fetal dose reduction in radiotherapy is discussed. The effect of the dimensions and setup of the shielding material on the radiation dose received by the fetus is described. Moreover, practical methods for reducing the fetal dose by selecting the appropriate irradiation parameters are presented.     

A novel fast kilovoltage switching dual-energy CT with deep learning: Accuracy of CT number on virtual monochromatic imaging and iodine quantification

PurposeA novel fast kilovoltage switching dual-energy CT with deep learning [Deep learning based-spectral CT (DL-Spectral CT)], which generates a complete sinogram for each kilovolt using deep learning views that complement the measured views at each energy, was commercialized in 2020. The purpose of this study was to evaluate the accuracy of CT numbers in virtual monochromatic images (VMIs) and iodine quantifications at various radiation doses using DL-Spectral CT.Materials and methodsTwo multi-energy phantoms (large and small) using several rods representing different materials (iodine, calcium, blood, and adipose) were scanned by DL-Spectral CT at varying radiation doses. Images were reconstructed using three reconstruction parameters (body, lung, bone). The absolute percentage errors (APEs) for CT numbers on VMIs at 50, 70, and 100 keV and iodine quantification were compared among different radiation dose protocols.ResultsThe APEs of the CT numbers on VMIs were <15% in both the large and small phantoms, except at the minimum dose in the large phantom. There were no significant differences among radiation dose protocols in computed tomography dose index volumes of 12.3 mGy or larger. The accuracy of iodine quantification provided by the body parameter was significantly better than those obtained with the lung and bone parameters. Increasing the radiation dose did not always improve the accuracy of iodine quantification, regardless of the reconstruction parameter and phantom size.ConclusionThe accuracy of iodine quantification and CT numbers on VMIs in DL-Spectral CT was not affected by the radiation dose, except for an extremely low radiation dose for body size.     

Artificial intelligence: Deep learning in oncological radiomics and challenges of interpretability and data harmonization

Over the last decade there has been an extensive evolution in the Artificial Intelligence (AI) field. Modern radiation oncology is based on the exploitation of advanced computational methods aiming to personalization and high diagnostic and therapeutic precision. The quantity of the available imaging data and the increased developments of Machine Learning (ML), particularly Deep Learning (DL), triggered the research on uncovering “hidden” biomarkers and quantitative features from anatomical and functional medical images. Deep Neural Networks (DNN) have achieved outstanding performance and broad implementation in image processing tasks. Lately, DNNs have been considered for radiomics and their potentials for explainable AI (XAI) may help classification and prediction in clinical practice. However, most of them are using limited datasets and lack generalized applicability. In this study we review the basics of radiomics feature extraction, DNNs in image analysis, and major interpretability methods that help enable explainable AI. Furthermore, we discuss the crucial requirement of multicenter recruitment of large datasets, increasing the biomarkers variability, so as to establish the potential clinical value of radiomics and the development of robust explainable AI models.     

Machine learning for metabolic engineering: A review

Machine learning provides researchers a unique opportunity to make metabolic engineering more predictable. In this review, we offer an introduction to this discipline in terms that are relatable to metabolic engineers, as well as providing in-depth illustrative examples leveraging omics data and improving production. We also include practical advice for the practitioner in terms of data management, algorithm libraries, computational resources, and important non-technical issues. A variety of applications ranging from pathway construction and optimization, to genetic editing optimization, cell factory testing, and production scale-up are discussed. Moreover, the promising relationship between machine learning and mechanistic models is thoroughly reviewed. Finally, the future perspectives and most promising directions for this combination of disciplines are examined.     

DeepCPI:A Deep Learning-based Framework for Large-scale in silico Drug Screening

Accurate identification of compound–protein interactions(CPIs) in silico may deepen our understanding of the underlying mechanisms of drug action and thus remarkably facilitate drug discovery and development.Conventional similarity-or docking-based computational methods for predicting CPIs rarely exploit latent features from currently available large-scale unlabeled compound and protein data and often limit their usage to relatively small-scale datasets.In the present study,we propose Deep CPI,a novel general and scalable computational framework that combines effective feature embedding(a technique of representation learning) with powerful deep learning methods to accurately predict CPIs at a large scale.Deep CPI automatically learns the implicit yet expressive low-dimensional features of compounds and proteins from a massive amount of unlabeled data.Evaluations of the measured CPIs in large-scale databases,such as Ch EMBL and Binding DB,as well as of the known drug–target interactions from Drug Bank,demonstrated the superior predictive performance of Deep CPI.Furthermore,several interactions among smallmolecule compounds and three G protein-coupled receptor targets(glucagon-like peptide-1 receptor,glucagon receptor,and vasoactive intestinal peptide receptor) predicted using Deep CPI were experimentally validated.The present study suggests that Deep CPI is a useful and powerful tool for drug discovery and repositioning.The source code of Deep CPI can be downloaded from https://github.com/Fangping Wan/Deep CPI.     

DeepWILD: Wildlife Identification,Localisation and estimation on camera trap videos using Deep learning

Videos and images from camera traps are more and more used by ecologists to estimate the population of species on a territory. It is a laborious work since experts have to analyse massive data sets manually. This takes also a lot of time to filter these videos when many of them do not contain animals or are with human presence. Fortunately, deep learning algorithms for object detection can help ecologists to identify multiple relevant species on their data and to estimate their population. In this study, we propose to go even further by using object detection model to detect, classify and count species on camera traps videos. To this end, we developed a 3-step process: (i) At the first stage, after splitting videos into images, we annotate images by associating bounding boxes to each label thanks to MegaDetector algorithm; (ii) then, we extend MegaDetector based on Faster R-CNN architecture with backbone Inception-ResNet-v2 in order to not only detect the 13 relevant classes but also to classify them; (iii) finally, we design a method to count individuals based on the maximum number of bounding boxes detected. This final stage of counting is evaluated in two different contexts: first including only detection results (i.e. comparing our predictions against the right number of individuals, no matter their true class), then an evolved version including both detection and classification results (i.e. comparing our predictions against the right number in the right class). The results obtained during the evaluation of our model on the test data set are: (i) 73,92% mAP for classification, (ii) 96,88% mAP for detection with a ratio Intersection-Over-Union (IoU) of 0.5 (overlapping ratio between groundtruth bounding box and the detected one), and (iii) 89,24% mAP for detection at IoU = 0.75. Highly represented classes, like humans, have highest values of mAP around 81% whereas less represented classes in the train data set, such as dogs, have lowest values of mAP around 66%. Regarding the proposed counting method, we predicted a count either exact or $\pm$ 1 unit for 87% with detection results and for 48% with detection and classification results of our test data set. Our model is also able to detect empty videos. To the best of our knowledge, this is the first study in France about the use of object detection model on a French national park to locate, identify and estimate the population of species from camera trap videos.     

Simple low-cost approaches to semantic segmentation in radiation therapy planning for prostate cancer using deep learning with non-contrast planning CT images

PurposeDeep learning has shown great efficacy for semantic segmentation. However, there are difficulties in the collection, labeling and management of medical imaging data, because of ethical complications and the limited number of imaging studies available at a single facility.This study aimed to find a simple and low-cost method to increase the accuracy of deep learning semantic segmentation for radiation therapy of prostate cancer.MethodsIn total, 556 cases with non-contrast CT images for prostate cancer radiation therapy were examined using a two-dimensional U-Net. Initially, all slices were used for the input data. Then, we removed slices of the cranial portions, which were beyond the margins of the bladder and rectum. Finally, the ground truth labels for the bladder and rectum were added as channels to the input for the prostate training dataset.ResultsThe highest mean dice similarity coefficients (DSCs) for each organ in the test dataset of 56 cases were 0.85 ± 0.05, 0.94 ± 0.04 and 0.85 ± 0.07 for the prostate, bladder and rectum, respectively. Removal of the cranial slices from the original images significantly increased the DSC of the rectum from 0.83 ± 0.09 to 0.85 ± 0.07 (p < 0.05). Adding bladder and rectum information to prostate training without removing the slices significantly increased the DSC of the prostate from 0.79 ± 0.05 to 0.85 ± 0.05 (p < 0.05).ConclusionsThese cost-free approaches may be useful for new applications, which may include updated models and datasets. They may be applicable to other organs at risk (OARs) and clinical targets such as elective nodal irradiation.