CapNet: An Automatic Attention-Based with Mixer Model for Cardiovascular Magnetic Resonance Image Segmentation.

Deep neural networks have shown excellent performance in medical image segmentation, especially for cardiac images. Transformer-based models, though having advantages over convolutional neural networks due to the ability of long-range dependence learning, still have shortcomings such as having a large number of parameters and and high computational cost. Additionally, for better results, they are often pretrained on a larger data, thus requiring large memory size and increasing resource expenses. In this study, we propose a new lightweight but efficient model, namely CapNet, based on convolutions and mixing modules for cardiac segmentation from magnetic resonance images (MRI) that can be trained from scratch with a small amount of parameters. To handle varying sizes and shapes which often occur in cardiac systolic and diastolic phases, we propose attention modules for pooling, spatial, and channel information. We also propose a novel loss called the Tversky Shape Power Distance function based on the shape dissimilarity between labels and predictions that shows promising performances compared to other losses. Experiments on three public datasets including ACDC benchmark, Sunnybrook data, and MS-CMR challenge are conducted and compared with other state of the arts (SOTA). For binary segmentation, the proposed CapNet obtained the Dice similarity coefficient (DSC) of 94% and 95.93% for respectively the Endocardium and Epicardium regions with Sunnybrook dataset, 94.49% for Endocardium, and 96.82% for Epicardium with the ACDC data. Regarding the multiclass case, the average DSC by CapNet is 93.05% for the ACDC data; and the DSC scores for the MS-CMR are 94.59%, 92.22%, and 93.99% for respectively the bSSFP, T2-SPAIR, and LGE sequences of the MS-CMR. Moreover, the statistical significance analysis tests with p-value < 0.05 compared with transformer-based methods and some CNN-based approaches demonstrated that the CapNet, though having fewer training parameters, is statistically significant. The promising evaluation metrics show comparative results in both Dice and IoU indices compared to SOTA CNN-based and Transformer-based architectures.

Risk assessment of 3-MCPD esters and glycidyl esters from the formulas for infants and young children up to 36 months of age.

Esters of 2-monochloropropane-1,2-diol (2-MCPD), 3- monochloropropane-1,2-diol (3-MCPD), and glycidol are present in infant formulas, follow-on foods and similar compositions. They arise mainly from the vegetable oil content and may cause harmful effects in consumers. The contents of these substances in formulas were determined indirectly by converting the esters to the free form, followed by derivatization and analysis by gas chromatography-tandem mass spectrometry (GC-MS/MS). The validation results demonstrate that the method had sufficient specificity and adequate accuracy. The limits of detection (LOD) and limits of quantification (LOQ) for each of 2-MCPDE, 3-MCPDE, and GE were 1.5 and 5 µg/kg, respectively. Formula intake by children up to 36 months of age was surveyed, and the data was used to assess the risks due to 3-MCPD esters (3-MCPDE) and glycidyl esters (GE). The mean exposure dose of 3-MCPDE for different age groups ranged from 0.51 to 1.13 µg/kg bw per day. The corresponding mean GE exposure ranged from 0.031 to 0.069 µg/kg bw per day. Neither mean values nor the percentile 95% values of 3-MCPDE exposure doses exceed the recommended provisional maximum tolerable daily intake (PMTDI).

Diagnosis and Treatment for Pediatric Supracondylar Humerus Fractures with Brachial Artery Injuries.

(1) Background: This study aims to describe the clinical and paraclinical characteristics of and the diagnostic approach to brachial artery injuries in pediatric supracondylar humerus fractures, as well as to evaluate intraoperative vascular anatomical lesions and early postoperative results. (2) Methods: A retrospective, hospital-based analysis of medical records at Viet Duc University Hospital (Vietnam), using a sample of children under 16 years who met the diagnostic criteria for supracondylar humerus fractures with brachial artery injuries between January 2016 and December 2020, was performed. A total of 50 patients were included in the analysis. (3) Results: Out of 50 pediatric patients, 36 patients were male (72%) and the mean age was 5.85 years (range, 1.5-14 years). Before treatment, there were 46 patients with severely displaced fractures which were classified as Gartland type III (92%). Following casting, the percentage of those with severely displaced fractures was reduced significantly to 12%, while there were no patients with Gartland type III fractures after percutaneous pinning. Doppler sonography failed to assess vascular lesions at the fracture site before and after casting in most patients. Two-thirds of surgical cases had only vasospasm, without physical damage to the vessel wall or intravascular thrombosis. Preoperative Doppler spectrum analysis was not consistent with the severity of intraoperative brachial artery injury. Out of 24 patients with vasospasm, we performed vascular blockade using papaverin in 11 cases and intraoperative balloon angioplasty of the brachial artery using the Fogarty catheter in 13 cases. Brachial artery graft was performed with 12 patients who had anatomical damage to the vascular wall. A complication of embolism occurred in one patient immediately after surgery, and two patients had superficial infections. One month following surgery, 2 out of 36 patients had a temporary loss of sensation in the area of incision. (4) Conclusions: Most pediatric patients did not present with symptoms of critical limb ischemia similar to those associated with lower extremity vascular injuries. The diagnosis and treatment of pediatric supracondylar humerus fractures with vascular injury is difficult and time-consuming, especially in cases of transverse fractures.