Identification of CT radiomic features robust to acquisition and segmentation variations for improved prediction of radiotherapy-treated lung cancer patient recurrence.

The primary objective of the present study was to identify a subset of radiomic features extracted from primary tumor imaged by computed tomography of early-stage non-small cell lung cancer patients, which remain unaffected by variations in segmentation quality and in computed tomography image acquisition protocol. The robustness of these features to segmentation variations was assessed by analyzing the correlation of feature values extracted from lesion volumes delineated by two annotators. The robustness to variations in acquisition protocol was evaluated by examining the correlation of features extracted from high-dose and low-dose computed tomography scans, both of which were acquired for each patient as part of the stereotactic body radiotherapy planning process. Among 106 radiomic features considered, 21 were identified as robust. An analysis including univariate and multivariate assessments was subsequently conducted to estimate the predictive performance of these robust features on the outcome of early-stage non-small cell lung cancer patients treated with stereotactic body radiation therapy. The univariate predictive analysis revealed that robust features demonstrated superior predictive potential compared to non-robust features. The multivariate analysis indicated that linear regression models built with robust features displayed greater generalization capabilities by outperforming other models in predicting the outcomes of an external validation dataset.

Cross-modal tumor segmentation using generative blending augmentation and self-training.

OBJECTIVES: Data scarcity and domain shifts lead to biased training sets that do not accurately represent deployment conditions. A related practical problem is cross-modal image segmentation, where the objective is to segment unlabelled images using previously labelled datasets from other imaging modalities. METHODS: We propose a cross-modal segmentation method based on conventional image synthesis boosted by a new data augmentation technique called Generative Blending Augmentation (GBA). GBA leverages a SinGAN model to learn representative generative features from a single training image to diversify realistically tumor appearances. This way, we compensate for image synthesis errors, subsequently improving the generalization power of a downstream segmentation model. The proposed augmentation is further combined to an iterative self-training procedure leveraging pseudo labels at each pass. RESULTS: The proposed solution ranked first for vestibular schwannoma (VS) segmentation during the validation and test phases of the MICCAI CrossMoDA 2022 challenge, with best mean Dice similarity and average symmetric surface distance measures. CONCLUSION AND SIGNIFICANCE: Local contrast alteration of tumor appearances and iterative self-training with pseudo labels are likely to lead to performance improvements in a variety of segmentation contexts.

Improving abdominal image segmentation with overcomplete shape priors.

The extraction of abdominal structures using deep learning has recently experienced a widespread interest in medical image analysis. Automatic abdominal organ and vessel segmentation is highly desirable to guide clinicians in computer-assisted diagnosis, therapy, or surgical planning. Despite a good ability to extract large organs, the capacity of U-Net inspired architectures to automatically delineate smaller structures remains a major issue, especially given the increase in receptive field size as we go deeper into the network. To deal with various abdominal structure sizes while exploiting efficient geometric constraints, we present a novel approach that integrates into deep segmentation shape priors from a semi-overcomplete convolutional auto-encoder (S-OCAE) embedding. Compared to standard convolutional auto-encoders (CAE), it exploits an over-complete branch that projects data onto higher dimensions to better characterize anatomical structures with a small spatial extent. Experiments on abdominal organs and vessel delineation performed on various publicly available datasets highlight the effectiveness of our method compared to state-of-the-art, including U-Net trained without and with shape priors from a traditional CAE. Exploiting a semi-overcomplete convolutional auto-encoder embedding as shape priors improves the ability of deep segmentation models to provide realistic and accurate abdominal structure contours.

PET/CT-Based Radiogenomics Supports KEAP1/NFE2L2 Pathway Targeting for Non-Small Cell Lung Cancer Treated with Curative Radiotherapy.

In lung cancer patients, radiotherapy is associated with a increased risk of local relapse (LR) when compared with surgery but with a preferable toxicity profile. The KEAP1/NFE2L2 mutational status (MutKEAP1/NFE2L2) is significantly correlated with LR in patients treated with radiotherapy but is rarely available. Prediction of MutKEAP1/NFE2L2 with noninvasive modalities could help to further personalize each therapeutic strategy. Methods: Based on a public cohort of 770 patients, model RNA (M-RNA) was first developed using continuous gene expression levels to predict MutKEAP1/NFE2L2, resulting in a binary output. The model PET/CT (M-PET/CT) was then built to predict M-RNA binary output using PET/CT-extracted radiomics features. M-PET/CT was validated on an external cohort of 151 patients treated with curative volumetric modulated arc radiotherapy. Each model was built, internally validated, and evaluated on a separate cohort using a multilayer perceptron network approach. Results: The M-RNA resulted in a C statistic of 0.82 in the testing cohort. With a training cohort of 101 patients, the retained M-PET/CT resulted in an area under the curve of 0.90 (P < 0.001). With a probability threshold of 20% applied to the testing cohort, M-PET/CT achieved a C statistic of 0.7. The same radiomics model was validated on the volumetric modulated arc radiotherapy cohort as patients were significantly stratified on the basis of their risk of LR with a hazard ratio of 2.61 (P = 0.02). Conclusion: Our approach enables the prediction of MutKEAP1/NFE2L2 using PET/CT-extracted radiomics features and efficiently classifies patients at risk of LR in an external cohort treated with radiotherapy.

A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising with Neural Network Approaches.

Low-dose emission tomography (ET) plays a crucial role in medical imaging, enabling the acquisition of functional information for various biological processes while minimizing the patient dose. However, the inherent randomness in the photon counting process is a source of noise which is amplified in low-dose ET. This review article provides an overview of existing post-processing techniques, with an emphasis on deep neural network (NN) approaches. Furthermore, we explore future directions in the field of NN-based low-dose ET. This comprehensive examination sheds light on the potential of deep learning in enhancing the quality and resolution of low-dose ET images, ultimately advancing the field of medical imaging.

Contrastive image adaptation for acquisition shift reduction in medical imaging.

The domain shift, or acquisition shift in medical imaging, is responsible for potentially harmful differences between development and deployment conditions of medical image analysis techniques. There is a growing need in the community for advanced methods that could mitigate this issue better than conventional approaches. In this paper, we consider configurations in which we can expose a learning-based pixel level adaptor to a large variability of unlabeled images during its training, i.e. sufficient to span the acquisition shift expected during the training or testing of a downstream task model. We leverage the ability of convolutional architectures to efficiently learn domain-agnostic features and train a many-to-one unsupervised mapping between a source collection of heterogeneous images from multiple unknown domains subjected to the acquisition shift and a homogeneous subset of this source set of lower cardinality, potentially constituted of a single image. To this end, we propose a new cycle-free image-to-image architecture based on a combination of three loss functions : a contrastive PatchNCE loss, an adversarial loss and an edge preserving loss allowing for rich domain adaptation to the target image even under strong domain imbalance and low data regimes. Experiments support the interest of the proposed contrastive image adaptation approach for the regularization of downstream deep supervised segmentation and cross-modality synthesis models.

Surgical radioguidance with beta-emitting radionuclides; challenges and possibilities: A position paper by the EANM.

Radioguidance that makes use of ß-emitting radionuclides is gaining in popularity and could have potential to strengthen the range of existing radioguidance techniques. While there is a strong tendency to develop new PET radiotracers, due to favorable imaging characteristics and the success of theranostics research, there are practical challenges that need to be overcome when considering use of ß-emitters for surgical radioguidance. In this position paper, the EANM identifies the possibilities and challenges that relate to the successful implementation of ß-emitters in surgical guidance, covering aspects related to instrumentation, radiation protection, and modes of implementation.

Multicentric development and evaluation of [18F]FDG PET/CT and CT radiomic models to predict regional and/or distant recurrence in early-stage non-small cell lung cancer treated by stereotactic body radiation therapy.

PURPOSE: To develop machine learning models to predict regional and/or distant recurrence in patients with early-stage non-small cell lung cancer (ES-NSCLC) after stereotactic body radiation therapy (SBRT) using [18F]FDG PET/CT and CT radiomics combined with clinical and dosimetric parameters. METHODS: We retrospectively collected 464 patients (60% for training and 40% for testing) from University Hospital of Liège and 63 patients from University Hospital of Brest (external testing set) with ES-NSCLC treated with SBRT between 2010 and 2020 and who had undergone pretreatment [18F]FDG PET/CT and planning CT. Radiomic features were extracted using the PyRadiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Clinical, radiomic, and combined models were trained and tested using a neural network approach to predict regional and/or distant recurrence. RESULTS: In the training (n = 273) and testing sets (n = 191 and n = 63), the clinical model achieved moderate performances to predict regional and/or distant recurrence with C-statistics from 0.53 to 0.59 (95% CI, 0.41, 0.67). The radiomic (original_firstorder_Entropy, original_gldm_LowGrayLevelEmphasis and original_glcm_DifferenceAverage) model achieved higher predictive ability in the training set and kept the same performance in the testing sets, with C-statistics from 0.70 to 0.78 (95% CI, 0.63, 0.88) while the combined model performs moderately well with C-statistics from 0.50 to 0.62 (95% CI, 0.37, 0.69). CONCLUSION: Radiomic features extracted from pre-SBRT analog and digital [18F]FDG PET/CT outperform clinical parameters in the prediction of regional and/or distant recurrence and to discuss an adjuvant systemic treatment in ES-NSCLC. Prospective validation of our models should now be carried out.

Monte Carlo Dosimetry Validation for X-Ray Guided Endovascular Procedures.

BACKGROUND: Endovascular treatment is continuously gaining ground in vascular surgery procedures. However, current patient radiation dose estimation does not take into account the exact patient morphology and organs' composition. Monte Carlo (MC) simulation can accurately estimate the dose by recreating the irradiation process generated during X-ray-guided interventions. This study aimed to validate the MC simulation models by comparing simulated and measured dose distributions in endovascular aortic aneurysm repair (EVAR) procedures. METHODS: We conducted a clinical study in patients treated for EVAR. Patient dose measurements were taken with passive dosimeters using Optically Stimulated Luminescence technology in 4 specific anatomical points on the skin: xiphoid process, pubic symphysis, right and left iliac crest. Dose measurements were compared to the corresponding simulated doses with the Geant4 Application for Emission Tomography (GATE) and GPU Geant4-based Monte Carlo Simulations (GGEMS) MC simulations softwares. The MC simulation took as input the computed tomography scan of the patient and the parameters of the imaging system (orientation angles, tube voltage, and aluminum filtration) and gives as output the three-dimensional (3D) dose map for each patient and angulation. RESULTS: A good agreement with real doses was found for doses simulated by the MC GATE method (P < 0.0001; r = 0.97; 95% confidence interval [CI] [0.96-0.98]), as well as for doses simulated by the GGEMS method (P < 0.0001; r = 0.96; 95% CI [0.94-0.97]). The mean relative error for all measurements was 5 ± 5% in the MC GATE group and 6 ± 5% in the GGEMS group. Process execution on GGEMS (6 sec) was faster than the GATE MC simulation (5 hr). CONCLUSION: Considering the current imaging settings, this study shows the potential of using the GATE and GGEMS MC simulations platforms to model the 3D dose distributions during EVAR procedures.

Multi-modal medical Transformers: A meta-analysis for medical image segmentation in oncology.

Multi-modal medical image segmentation is a crucial task in oncology that enables the precise localization and quantification of tumors. The aim of this work is to present a meta-analysis of the use of multi-modal medical Transformers for medical image segmentation in oncology, specifically focusing on multi-parametric MR brain tumor segmentation (BraTS2021), and head and neck tumor segmentation using PET-CT images (HECKTOR2021). The multi-modal medical Transformer architectures presented in this work exploit the idea of modality interaction schemes based on visio-linguistic representations: (i) single-stream, where modalities are jointly processed by one Transformer encoder, and (ii) multiple-stream, where the inputs are encoded separately before being jointly modeled. A total of fourteen multi-modal architectures are evaluated using different ranking strategies based on dice similarity coefficient (DSC) and average symmetric surface distance (ASSD) metrics. In addition, cost indicators such as the number of trainable parameters and the number of multiply-accumulate operations (MACs) are reported. The results demonstrate that multi-path hybrid CNN-Transformer-based models improve segmentation accuracy when compared to traditional methods, but come at the cost of increased computation time and potentially larger model size.

["New Modalities in Cancer Imaging and Therapy" XVth edition of the workshop organized by the network "Tumor Targeting, Imaging, Radiotherapies" of the Cancéropôle Grand-Ouest, 5-8 October 2022, France]. / « New Modalities in Cancer Imaging and Therapy ¼ XVe édition de l'atelier organisé par le réseau « Vectorisation, Imagerie, Radiothérapies ¼ du Cancéropôle Grand-Ouest, 5­8 octobre 2022, Erquy, France.

The fifteenth edition of the international workshop organized by the "Tumour Targeting and Radiotherapies network" of the Cancéropôle Grand-Ouest focused on the latest advances in internal and external radiotherapy from different disciplinary angles: chemistry, biology, physics, and medicine. The workshop covered several deliberately diverse topics: the role of artificial intelligence, new tools for imaging and external radiotherapy, theranostic aspects, molecules and contrast agents, vectors for innovative combined therapies, and the use of alpha particles in therapy.

Automatic Head and Neck Tumor segmentation and outcome prediction relying on FDG-PET/CT images: Findings from the second edition of the HECKTOR challenge.

By focusing on metabolic and morphological tissue properties respectively, FluoroDeoxyGlucose (FDG)-Positron Emission Tomography (PET) and Computed Tomography (CT) modalities include complementary and synergistic information for cancerous lesion delineation and characterization (e.g. for outcome prediction), in addition to usual clinical variables. This is especially true in Head and Neck Cancer (HNC). The goal of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge was to develop and compare modern image analysis methods to best extract and leverage this information automatically. We present here the post-analysis of HECKTOR 2nd edition, at the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2021. The scope of the challenge was substantially expanded compared to the first edition, by providing a larger population (adding patients from a new clinical center) and proposing an additional task to the challengers, namely the prediction of Progression-Free Survival (PFS). To this end, the participants were given access to a training set of 224 cases from 5 different centers, each with a pre-treatment FDG-PET/CT scan and clinical variables. Their methods were subsequently evaluated on a held-out test set of 101 cases from two centers. For the segmentation task (Task 1), the ranking was based on a Borda counting of their ranks according to two metrics: mean Dice Similarity Coefficient (DSC) and median Hausdorff Distance at 95th percentile (HD95). For the PFS prediction task, challengers could use the tumor contours provided by experts (Task 3) or rely on their own (Task 2). The ranking was obtained according to the Concordance index (C-index) calculated on the predicted risk scores. A total of 103 teams registered for the challenge, for a total of 448 submissions and 29 papers. The best method in the segmentation task obtained an average DSC of 0.759, and the best predictions of PFS obtained a C-index of 0.717 (without relying on the provided contours) and 0.698 (using the expert contours). An interesting finding was that best PFS predictions were reached by relying on DL approaches (with or without explicit tumor segmentation, 4 out of the 5 best ranked) compared to standard radiomics methods using handcrafted features extracted from delineated tumors, and by exploiting alternative tumor contours (automated and/or larger volumes encompassing surrounding tissues) rather than relying on the expert contours. This second edition of the challenge confirmed the promising performance of fully automated primary tumor delineation in PET/CT images of HNC patients, although there is still a margin for improvement in some difficult cases. For the first time, the prediction of outcome was also addressed and the best methods reached relatively good performance (C-index above 0.7). Both results constitute another step forward toward large-scale outcome prediction studies in HNC.

Fast dose calculation in x-ray guided interventions by using deep learning.

Objective.Patient dose estimation in x-ray-guided interventions is essential to prevent radiation-induced biological side effects. Current dose monitoring systems estimate the skin dose based in dose metrics such as the reference air kerma. However, these approximations do not take into account the exact patient morphology and organs composition. Furthermore, accurate organ dose estimation has not been proposed for these procedures. Monte Carlo simulation can accurately estimate the dose by recreating the irradiation process generated during the x-ray imaging, but at a high computation time, limiting an intra-operative application. This work presents a fast deep convolutional neural network trained with MC simulations for patient dose estimation during x-ray-guided interventions.Approach.We introduced a modified 3D U-Net that utilizes a patient's CT scan and the numerical values of imaging settings as input to produce a Monte Carlo dose map. To create a dataset of dose maps, we simulated the x-ray irradiation process for the abdominal region using a publicly available dataset of 82 patient CT scans. The simulation involved varying the angulation, position, and tube voltage of the x-ray source for each scan. We additionally conducted a clinical study during endovascular abdominal aortic repairs to validate the reliability of our Monte Carlo simulation dose maps. Dose measurements were taken at four specific anatomical points on the skin and compared to the corresponding simulated doses. The proposed network was trained using a 4-fold cross-validation approach with 65 patients, and evaluating the performance on the remaining 17 patients during testing.Main results.The clinical validation demonstrated a average error within the anatomical points of 5.1%. The network yielded test errors of 11.5 ± 4.6% and 6.2 ± 1.5% for peak and average skin doses, respectively. Furthermore, the mean errors for the abdominal region and pancreas doses were 5.0 ± 1.4% and 13.1 ± 2.7%, respectively.Significance.Our network can accurately predict a personalized 3D dose map considering the current imaging settings. A short computation time was achieved, making our approach a potential solution for dose monitoring and reporting commercial systems.

Predicting the Tumour Response to Radiation by Modelling the Five Rs of Radiotherapy Using PET Images.

Despite the intensive use of radiotherapy in clinical practice, its effectiveness depends on several factors. Several studies showed that the tumour response to radiation differs from one patient to another. The non-uniform response of the tumour is mainly caused by multiple interactions between the tumour microenvironment and healthy cells. To understand these interactions, five major biologic concepts called the "5 Rs" have emerged. These concepts include reoxygenation, DNA damage repair, cell cycle redistribution, cellular radiosensitivity and cellular repopulation. In this study, we used a multi-scale model, which included the five Rs of radiotherapy, to predict the effects of radiation on tumour growth. In this model, the oxygen level was varied in both time and space. When radiotherapy was given, the sensitivity of cells depending on their location in the cell cycle was taken in account. This model also considered the repair of cells by giving a different probability of survival after radiation for tumour and normal cells. Here, we developed four fractionation protocol schemes. We used simulated and positron emission tomography (PET) imaging with the hypoxia tracer 18F-flortanidazole (18F-HX4) images as input data of our model. In addition, tumour control probability curves were simulated. The result showed the evolution of tumours and normal cells. The increase in the cell number after radiation was seen in both normal and malignant cells, which proves that repopulation was included in this model. The proposed model predicts the tumour response to radiation and forms the basis for a more patient-specific clinical tool where related biological data will be included.

Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT.

This paper presents an overview of the third edition of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge, organized as a satellite event of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022. The challenge comprises two tasks related to the automatic analysis of FDG-PET/CT images for patients with Head and Neck cancer (H&N), focusing on the oropharynx region. Task 1 is the fully automatic segmentation of H&N primary Gross Tumor Volume (GTVp) and metastatic lymph nodes (GTVn) from FDG-PET/CT images. Task 2 is the fully automatic prediction of Recurrence-Free Survival (RFS) from the same FDG-PET/CT and clinical data. The data were collected from nine centers for a total of 883 cases consisting of FDG-PET/CT images and clinical information, split into 524 training and 359 test cases. The best methods obtained an aggregated Dice Similarity Coefficient (DSCagg) of 0.788 in Task 1, and a Concordance index (C-index) of 0.682 in Task 2.

Multicentric development and evaluation of 18F-FDG PET/CT and MRI radiomics models to predict para-aortic lymph node involvement in locally advanced cervical cancer.

PURPOSE: To develop machine learning models to predict para-aortic lymph node (PALN) involvement in patients with locally advanced cervical cancer (LACC) before chemoradiotherapy (CRT) using 18F-FDG PET/CT and MRI radiomics combined with clinical parameters. METHODS: We retrospectively collected 178 patients (60% for training and 40% for testing) in 2 centers and 61 patients corresponding to 2 further external testing cohorts with LACC between 2010 to 2022 and who had undergone pretreatment analog or digital 18F-FDG PET/CT, pelvic MRI and surgical PALN staging. Only primary tumor volumes were delineated. Radiomics features were extracted using the Radiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Different prediction models were trained using a neural network approach with either clinical, radiomics or combined models. They were then evaluated on the testing and external validation sets and compared. RESULTS: In the training set (n = 102), the clinical model achieved a good prediction of the risk of PALN involvement with a C-statistic of 0.80 (95% CI 0.71, 0.87). However, it performed in the testing (n = 76) and external testing sets (n = 30 and n = 31) with C-statistics of only 0.57 to 0.67 (95% CI 0.36, 0.83). The ComBat-radiomic (GLDZM_HISDE_PET_FBN64 and Shape_maxDiameter2D3_PET_FBW0.25) and ComBat-combined (FIGO 2018 and same radiomics features) models achieved very high predictive ability in the training set and both models kept the same performance in the testing sets, with C-statistics from 0.88 to 0.96 (95% CI 0.76, 1.00) and 0.85 to 0.92 (95% CI 0.75, 0.99), respectively. CONCLUSIONS: Radiomic features extracted from pre-CRT analog and digital 18F-FDG PET/CT outperform clinical parameters in the decision to perform a para-aortic node staging or an extended field irradiation to PALN. Prospective validation of our models should now be carried out.

Design of a generic method for single dual-tracer PET imaging acquisition in clinical routine.

Using different tracers in positron emission tomography (PET) imaging can bring complementary information on tumor heterogeneities. Ideally, PET images of different tracers should be acquired simultaneously to avoid the bias induced by movement and physiological changes between sequential acquisitions. Previous studies have demonstrated the feasibility of recovering separated PET signals or parameters of two or more tracers injected (quasi-)simultaneously in a single acquisition. In this study, a generic framework in the context of dual-tracer PET acquisition is proposed where no strong kinetic assumptions nor specific tuning of parameters are required. The performances of the framework were assessed through simulations involving the combination of [18F]FCH and [18F]FDG injections, two protocols (90 and 60 min acquisition durations) and various activity ratios between the two injections. Preclinical experiments with the same radiotracers were also conducted. Results demonstrate the ability of the method both to extract separated arterial input functions (AIF) from noisy image-derived input function and to separate the dynamic signals and further estimate kinetic parameters. The compromise between bias and variance associated with the estimation of net influx rateKishows that it is preferable to use the second injected radiotracer with twice the activity of the first for both 90 min [18F]FCH+[18F]FDG and 60 min [18F]FDG+[18F]FCH protocols. In these optimal settings, the weighted mean-squared-error of the estimated AIF was always less than 7%. TheKibias was similar to the one of single-tracer acquisitions; below 5%. Compared to single-tracer results, the variance ofKiwas twice more for 90 min dual-tracer scenario and four times more for the 60 min scenario. The generic design of the method makes it easy to use for other pairs of radiotracers and even for more than two tracers. The absence of strong kinetic assumptions and tuning parameters makes it suitable for a possible use in clinical routine.

Radiomics Approaches for the Prediction of Pathological Complete Response after Neoadjuvant Treatment in Locally Advanced Rectal Cancer: Ready for Prime Time?

In recent years, neoadjuvant therapy of locally advanced rectal cancer has seen tremendous modifications. Adding neoadjuvant chemotherapy before or after chemoradiotherapy significantly increases loco-regional disease-free survival, negative surgical margin rates, and complete response rates. The higher complete rate is particularly clinically meaningful given the possibility of organ preservation in this specific sub-population, without compromising overall survival. However, all locally advanced rectal cancer most likely does not benefit from total neoadjuvant therapy (TNT), but experiences higher toxicity rates. Diagnosis of complete response after neoadjuvant therapy is a real challenge, with a risk of false negatives and possible under-treatment. These new therapeutic approaches thus raise the need for better selection tools, enabling a personalized therapeutic approach for each patient. These tools mostly focus on the prediction of the pathological complete response given the clinical impact. In this article, we review the place of different biomarkers (clinical, biological, genomics, transcriptomics, proteomics, and radiomics) as well as their clinical implementation and discuss the most recent trends for future steps in prediction modeling in patients with locally advanced rectal cancer.

Learn2Reg: Comprehensive Multi-Task Medical Image Registration Challenge, Dataset and Evaluation in the Era of Deep Learning.

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods.

PET scatter estimation using deep learning U-Net architecture.

Objective.Positron emission tomography (PET) image reconstruction needs to be corrected for scatter in order to produce quantitatively accurate images. Scatter correction is traditionally achieved by incorporating an estimated scatter sinogram into the forward model during image reconstruction. Existing scatter estimated methods compromise between accuracy and computing time. Nowadays scatter estimation is routinely performed using single scatter simulation (SSS), which does not accurately model multiple scatter and scatter from outside the field-of-view, leading to reduced qualitative and quantitative PET reconstructed image accuracy. On the other side, Monte-Carlo (MC) methods provide a high precision, but are computationally expensive and time-consuming, even with recent progress in MC acceleration.Approach.In this work we explore the potential of deep learning (DL) for accurate scatter correction in PET imaging, accounting for all scatter coincidences. We propose a network based on a U-Net convolutional neural network architecture with 5 convolutional layers. The network takes as input the emission and computed tomography (CT)-derived attenuation factor (AF) sinograms and returns the estimated scatter sinogram. The network training was performed using MC simulated PET datasets. Multiple anthropomorphic extended cardiac-torso phantoms of two different regions (lung and pelvis) were created, considering three different body sizes and different levels of statistics. In addition, two patient datasets were used to assess the performance of the method in clinical practice.Main results.Our experiments showed that the accuracy of our method, namely DL-based scatter estimation (DLSE), was independent of the anatomical region (lungs or pelvis). They also showed that the DLSE-corrected images were similar to that reconstructed from scatter-free data and more accurate than SSS-corrected images.Significance.The proposed method is able to estimate scatter sinograms from emission and attenuation data. It has shown a better accuracy than the SSS, while being faster than MC scatter estimation methods.