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.

Joint Progressive and Coarse-to-Fine Registration of Brain MRI via Deformation Field Integration and Non-Rigid Feature Fusion.

Registration of brain MRI images requires to solve a deformation field, which is extremely difficult in aligning intricate brain tissues, e.g., subcortical nuclei, etc. Existing efforts resort to decomposing the target deformation field into intermediate sub-fields with either tiny motions, i.e., progressive registration stage by stage, or lower resolutions, i.e., coarse-to-fine estimation of the full-size deformation field. In this paper, we argue that those efforts are not mutually exclusive, and propose a unified framework for robust brain MRI registration in both progressive and coarse-to-fine manners simultaneously. Specifically, building on a dual-encoder U-Net, the fixed-moving MRI pair is encoded and decoded into multi-scale sub-fields from coarse to fine. Each decoding block contains two proposed novel modules: i) in Deformation Field Integration (DFI), a single integrated deformation sub-field is calculated, warping by which is equivalent to warping progressively by sub-fields from all previous decoding blocks, and ii) in Non-rigid Feature Fusion (NFF), features of the fixed-moving pair are aligned by DFI-integrated deformation field, and then fused to predict a finer sub-field. Leveraging both DFI and NFF, the target deformation field is factorized into multi-scale sub-fields, where the coarser fields alleviate the estimate of a finer one and the finer field learns to make up those misalignments insolvable by previous coarser ones. The extensive and comprehensive experimental results on both private and two public datasets demonstrate a superior registration performance of brain MRI images over progressive registration only and coarse-to-fine estimation only, with an increase by at most 8% in the average Dice.

Accurate Cobb Angle Estimation on Scoliosis X-ray Images via Deeply-coupled Two-stage Network with Differentiable Cropping and Random Perturbation.

Automated Cobb angle estimation on X-ray images is crucial to scoliosis diagnosis. The existing efforts are typically two extremes, which either laboriously detect the raw vertebral landmarks or directly regress Cobb angles from the entire image. In this paper, we propose a novel two-stage end-to-end method as a balanced solution, to avoid vulnerability to false landmarks, and to preserve flexibility in clinical usages. Concretely, we cascade two stages sequentially for detecting vertebrae and then regressing their bending directions instead of raw landmarks. In the detection stage, we combine two networks called LocNet and SegNet to robustly localize vertebrae, and meanwhile to suppress the false positives by additionally segmenting the whole spine. In the subsequent stage, we introduce a regression network named RegNet to accurately regress bending directions of localized vertebrae. Furthermore, the vertebra-aligned local regions on LocNet's intermediate features are cropped via RoIAlign-pooling, and RegNet inherits the cropped regions to learn only feature residuals. By doing so, the regression difficulty can be dramatically alleviated, and the two stages are deeply coupled and mutually guided in an end-to-end training. Moreover, a random perturbation on the inherited features further enhances RegNet's robustness. We benchmark our method on both public and private datasets, and the errors are 2.92 ±2.34 degree and 6.87 ±6.26% in terms of CMAE and SMAPE on the widely-employed AASCE dataset, outperforming other state-of-the-arts by at least 16.81% and 6.15%, respectively. Also, a clinical user study verifies our promising flexibility for allowing convenient rectifications to further decrease errors by a large marge.

Cholecystokinin octapeptide reduces myocardial fibrosis and improves cardiac remodeling in post myocardial infarction rats.

BACKGROUND/AIMS: Myocardial infarction (MI) increases myocardial fibrosis (MF) and subsequent cardiac remodeling. Cholecystokinin octapeptide (CCK-8) is expressed in cardiomyocytes and plays an important role in cardiovascular regulation. In this study, we intend to use a rat model of myocardial infarction to evaluate the effects of CCK-8 on myocardial fibrosis and cardiac remodeling. METHODS: Male Sprague-Dawley rats were separated into 3 groups: sham operation, MI + NaCl, and MI + CCK-8. All rats were subjected to left coronary artery ligation to induce MI or sham operation and then treated with CCK-8 or saline for 28 days. After 4 weeks, echocardiography was performed to assess cardiac function and myocardial fibrosis was evaluated using H&E and Masson's Trichrome-stained sections. The levels of BNP, CCK-8 in the plasma of all rats were detected by ELISA; RNA sequencing (RNA-seq) analysis was also adapted to detect differentially expressed genes in myocardial tissues of each group. Myocardial expression of fibrosis markers was analyzed by western blotting, immunohistochemistry and qRT-PCR. RESULTS: CCK-8 was demonstrated to improve left ventricular function and results of H&E staining, Masson's trichrome staining, immunohistochemistry and western blotting showed that CCK-8 attenuated MF. Gene expression profiles of the left ventricles were analysed by RNA-seq and validated by qRT-PCR. Cardiac fibrosis genes were downregulated by CCK-8 in the left ventricle. SIGNIFICANCE: CCK-8 can alleviate fibrosis in the noninfarcted regions and delay the left ventricular remodeling and the progress of heart failure in a MI rat model.

Role of pyroptosis in normal cardiac response to calorie restriction and starvation.

AIMS: An unhealthy diet is a major risk factor for cardiac diseases. Most researches focus on high fat diet, little is known about the detrimental effects of starvation on heart. METHODS: Mice were fed 100%, 40% and 20% of ad libitum to mimic the situation of moderate and severe caloric restriction (CR). To further evaluate the different effect of CR and starvation on cardiomyocyte, AC16 cells were treated with different concentrations of serum or glucose. TUNEL staining was performed to evaluate DNA damage in AC16 cells. HE and Masson staining were performed to detect the morphology and degree of fibrosis in myocardium from mice. Immunohistochemical staining, immunofluorescence staining, western blot and real-time PCR were used to detect the protein and mRNA expression of caspase-1, IL-1ß and IL-18. RESULTS: CR and starvation decrease body weight of mice in a concentration dependent manner. The starvation group showed a remarkable myocardial fibrosis with no significant alteration between control and CR groups. CR inhibited the activation of caspase-1 as well as the expression of IL-1ß and IL-18. On the contrary, starvation plays completely opposite effects, which was in accordance with histological changes. Similarly, different levels of serum and glucose deprivation were used to mimic the effect of CR and starvation in vitro. Moderate level of serum and glucose deprivation exerts protective effect on AC16 cells through the inhibition of pyroptosis, whereas high level of serum and glucose deprivation induces cell injury through the induction of pyroptosis. CONCLUSION: CR alleviates pyroptosis, whereas starvation promotes the progression of pyroptosis in myocardial tissues and cells.