Atomic Valence Reversal-Induced Polarization Resonance Spurs Highly Efficient Electromagnetic Wave Absorption in α-Fe2O3@Carbon Microtubes.

Variegation and complexity of polarization relaxation loss in many heterostructured materials provide available mechanisms to seek a strong electromagnetic wave (EMW) absorption performance. Here we construct a unique heterostructured compound that bonds α-Fe2O3 nanosheets of the (110) plane on carbon microtubes (CMTs). Through effective alignment between the Fermi energy level of CMTs and the conduction band position of α-Fe2O3 nanosheets at the interface, we attain substantial polarization relaxation loss via novel atomic valence reversal between Fe(III) ↔ Fe(III-) induced with periodic electron injection from conductive CMTs under EMW irradiation to give α-Fe2O3 nanosheets. Such heterostructured materials possess currently reported minimum reflection loss of -84.01 dB centered at 10.99 GHz at a thickness of 3.19 mm and an effective absorption bandwidth (reflection loss ≤ -10 dB) of 7.17 GHz (10.83-18 GHz) at 2.65 mm. This work provides an effective strategy for designing strong EMW absorbers by combining highly efficient electron injection and atomic valence reversal.

Heart failure classifications via non-invasive pressure volume loops from echocardiography.

BACKGROUND: Left ventricular pressure-volume (LV-PV) loops provide comprehensive characterization of cardiovascular system in both health and disease, which are the essential element of the hemodynamic evaluation of heart failure (HF). This study attempts to achieve more detailed HF classifications by non-invasive LV-PV loops from echocardiography and analyzes contribution of parameters to HF classifications. METHODS: Firstly, non-invasive PV loops are established by time-varying elastance model where LV volume curves were extracted from apical-four-chambers view of echocardiographic videos. Then, 16 parameters related to cardiac structure and functions are automatically acquired from PV loops. Next, we applied six machine learning (ML) methods to divide four categories. On this premise, we choose the best performing classifier among machine learning approaches for feature ranking. Finally, we compare the contributions of different parameters to HF classifications. RESULTS: By the experimental, the PV loops were successfully acquired in 1076 cases. When single left ventricular ejection fraction (LVEF) is used for HF classifications, the accuracy of the model is 91.67%. When added parameters extracted from ML-derived LV-PV loops, the classification accuracy is 96.57%, which improved by 5.1%. Especially, our parameters have a great improvement in the classification of non-HF controls and heart failure with preserved ejection fraction (HFpEF). CONCLUSIONS: We successfully presented the classification of HF by machine derived non-invasive LV-PV loops, which has the potential to improve the diagnosis and management of heart failure in clinic. Moreover, ventriculo-arterial (VA) coupling and ventricular efficiency were demonstrated important factors for ML-based HF classification model besides LVEF.

Diagnosis of fetal total anomalous pulmonary venous connection based on the post-left atrium space ratio using artificial intelligence.

OBJECTIVE: To explore whether the post-left atrium space (PLAS) ratio would be useful for prenatal diagnosis of total anomalous pulmonary venous connection (TAPVC) using echocardiography and artificial intelligence. METHODS: We retrospectively included 642 frames of four-chamber views from 319 fetuses (32 with TAPVC and 287 without TAPVC) in end-systolic and end-diastolic periods with multiple apex directions. The average gestational age was 25.6 ± 2.7 weeks. No other cardiac or extracardiac malformations were observed. The dataset was divided into a training set (n = 540; 48 with TAPVC and 492 without TAPVC) and test set (n = 102; 20 with TAPVC and 82 without TAPVC). The PLAS ratio was defined as the ratio of the epicardium-descending aortic distance to the center of the heart-descending aortic distance. Supervised learning was used in DeepLabv3+, FastFCN, PSPNet, and DenseASPP segmentation models. The area under the curve (AUC) was used on the test set. RESULTS: Expert annotations showed that this ratio was not related to the period or apex direction. It was higher in the TAPVC group than in the control group detected by the expert and the four models. The AUC of expert annotations, DeepLabv3+, FastFCN, PSPNet, and DenseASPP were 0.977, 0.941, 0.925, 0.856, and 0.887, respectively. CONCLUSION: Segmentation models achieve good diagnostic accuracy for TAPVC based on the PLAS ratio.

Differential diagnosis of fetal large ventricular septal defect and tetralogy of Fallot based on big data analysis.

BACKGROUND AND OBJECTIVES: To analyze echocardiographic parameters of fetal large ventricular septal defect (VSD) and tetralogy of Fallot (TOF) in the context of multicenter data and big data analysis because these two diseases are often misdiagnosed in fetuses, and to find the key parameters for the differential diagnosis of these two diseases. METHODS: A total of 305 cases of large VSD and 192 cases of TOF diagnosed by fetal echocardiography from August 2010 to July 2016 from the database of Beijing Key Laboratory of Fetal Heart Defects were analyzed. Quantile regression of the 48 echocardiographic parameters of the 6272 normal fetuses from seven Chinese medical institutions was performed to determine the Q-score. The forward selection method and the naive Bayesian classification method were used to analyze the core differential diagnostic variables of fetal TOF and VSD. RESULTS: The Q-score of the internal diameter of the aorta (AO Q-score), the ratio of the diameter of the pulmonary artery to the internal diameter of the aorta (PA/AO), and the Q-score of the ratio of the diameter of the pulmonary artery to the internal diameter of the aorta (PA/AO Q-score) were key parameters for the differential diagnosis of fetal large VSD and TOF. PA/AO was the primary parameter, with an area under the receiver operating characteristic curve of 0.951. CONCLUSIONS: These findings provide a new method for the prenatal diagnosis of large VSD and TOF and a theoretical basis for the intelligent diagnosis of large VSD and TOF.

[Analysis of association of genetic polymorphisms of microRNAs with ischemic stroke].

OBJECTIVE: To assess the association of single nucleotide polymorphisms of hsa-miR-196a2, hsa-miR-149, hsa-miR-146a, hsa-miR-499 with susceptibility to ischemic stroke. METHODS: Taqman-PCR and DNA sequencing assays were employed to determine the genotypes of the 4 loci among 510 patients and 523 controls. And their association with the disease was assessed. RESULTS: Analysis showed that smoking, diabetes, hypertension, BMI index and abnormal serum lipid metabolism were significantly associated with ischemic stroke, and that rs2910164 was significantly associated with the disease in codominant (CG vs. CC: P=0.002, OR=1.878, 95%CI=1.269-2.789), dominant (P=0.012, OR=1.325, 95%CI=1.110-1.580), recessive (P=0.008, OR=1.630, 95%CI=1.130-2.342) and allele (P=0.002, OR=1.449, 95%CI=1.210-1.731) genetic models. Stratified analysis further showed that the significant association only existed in population with smoking and hypertension. By contrast, no association was found between hsa-miR-196a2 rs11614913, hsa-miR-149 rs2292832 and hsa-miR-499 rs3746444 with the disease. CONCLUSION: Our study indicated that smoking, diabetes, hypertension, fat and hyperlipidemia are risk factors for ischemic stroke. Hsa-miR-146a rs2910164 is significantly associated with the disease in those with smoking and hypertension in Dongyang region and may be involved in the process of the disease. The G allele G, GG and CG+GG genotypes of the locus may underlie the susceptibility to the disease in Dongyang region.

Resistance to the most common optic neuropathy is associated with systemic mitochondrial efficiency.

Glaucomatous optic neuropathy, an important neurodegenerative condition and the commonest optic neuropathy in humans, is the leading cause of irreversible blindness worldwide. Its prevalence and incidence increase exponentially with ageing and raised intraocular pressure (IOP). Using glaucomatous optic neuropathy as an exemplar for neurodegeneration, this study investigates putative factors imparting resistance to neurodegeneration. Systemic mitochondrial function, oxidative stress and vascular parameters were compared from isolated lymphocytes, whole blood and urine samples between 30 patients who have not developed the neuropathy despite being exposed for many years to very high IOP ('resistant'), 30 fast deteriorating glaucoma patients despite having low IOP ('susceptible'), and 30 age-similar controls. We found that 'resistant' individuals showed significantly higher rates of ADP phosphorylation by mitochondrial respiratory complexes I, II and IV, hyperpolarised mitochondrial membrane potential, higher levels of mitochondrial DNA, and enhanced capacity to deal with cytosolic calcium overload and exogenous oxidative stress, as compared to both controls and glaucoma patients. While it has been known for some years that mitochondrial dysfunction is implicated in neurodegeneration, this study provides a fresh perspective to the field of neurodegeneration by providing, for the first time, evidence that systemic mitochondrial efficiency above normal healthy levels is associated with an enhanced ability to withstand optic nerve injury. These results demonstrate the importance of cellular bioenergetics in glaucomatous disease progression, with potential relevance for other neurodegenerative disorders, and raise the possibility for new therapeutic targets in the field of neurodegeneration.

Longitudinal changes of angle configuration in primary angle-closure suspects: the Zhongshan Angle-Closure Prevention Trial.

OBJECTIVE: To determine longitudinal changes in angle configuration in the eyes of primary angle-closure suspects (PACS) treated by laser peripheral iridotomy (LPI) and in untreated fellow eyes. DESIGN: Longitudinal cohort study. PARTICIPANTS: Primary angle-closure suspects aged 50 to 70 years were enrolled in a randomized, controlled clinical trial. METHODS: Each participant was treated by LPI in 1 randomly selected eye, with the fellow eye serving as a control. Angle width was assessed in a masked fashion using gonioscopy and anterior segment optical coherence tomography (AS-OCT) before and at 2 weeks, 6 months, and 18 months after LPI. MAIN OUTCOME MEASURES: Angle width in degrees was calculated from Shaffer grades assessed under static gonioscopy. Angle configuration was also evaluated using angle opening distance (AOD250, AOD500, AOD750), trabecular-iris space area (TISA500, TISA750), and angle recess area (ARA) measured in AS-OCT images. RESULTS: No significant difference was found in baseline measures of angle configuration between treated and untreated eyes. At 2 weeks after LPI, the drainage angle on gonioscopy widened from a mean of 13.5° at baseline to a mean of 25.7° in treated eyes, which was also confirmed by significant increases in all AS-OCT angle width measures (P<0.001 for all variables). Between 2 weeks and 18 months after LPI, a significant decrease in angle width was observed over time in treated eyes (P<0.001 for all variables), although the change over the first 5.5 months was not statistically significant for angle width measured under gonioscopy (P = 0.18), AOD250 (P = 0.167) and ARA (P = 0.83). In untreated eyes, angle width consistently decreased across all follow-up visits after LPI, with a more rapid longitudinal decrease compared with treated eyes (P values for all variables ≤0.003). The annual rate of change in angle width was equivalent to 1.2°/year (95% confidence interval [CI], 0.8-1.6) in treated eyes and 1.6°/year (95% CI, 1.3-2.0) in untreated eyes (P<0.001). CONCLUSIONS: Angle width of treated eyes increased markedly after LPI, remained stable for 6 months, and then decreased significantly by 18 months after LPI. Untreated eyes experienced a more consistent and rapid decrease in angle width over the same time period.

Does the Swedish Interactive Threshold Algorithm (SITA) accurately map visual field loss attributed to vigabatrin?

BACKGROUND: Vigabatrin (VGB) is an anti-epileptic medication which has been linked to peripheral constriction of the visual field. Documenting the natural history associated with continued VGB exposure is important when making decisions about the risk and benefits associated with the treatment. Due to its speed the Swedish Interactive Threshold Algorithm (SITA) has become the algorithm of choice when carrying out Full Threshold automated static perimetry. SITA uses prior distributions of normal and glaucomatous visual field behaviour to estimate threshold sensitivity. As the abnormal model is based on glaucomatous behaviour this algorithm has not been validated for VGB recipients. We aim to assess the clinical utility of the SITA algorithm for accurately mapping VGB attributed field loss. METHODS: The sample comprised one randomly selected eye of 16 patients diagnosed with epilepsy, exposed to VGB therapy. A clinical diagnosis of VGB attributed visual field loss was documented in 44% of the group. The mean age was 39.3 years ± 14.5 years and the mean deviation was -4.76 dB ±4.34 dB. Each patient was examined with the Full Threshold, SITA Standard and SITA Fast algorithm. RESULTS: SITA Standard was on average approximately twice as fast (7.6 minutes) and SITA Fast approximately 3 times as fast (4.7 minutes) as examinations completed using the Full Threshold algorithm (15.8 minutes). In the clinical environment, the visual field outcome with both SITA algorithms was equivalent to visual field examination using the Full Threshold algorithm in terms of visual inspection of the grey scale plots , defect area and defect severity. CONCLUSIONS: Our research shows that both SITA algorithms are able to accurately map visual field loss attributed to VGB. As patients diagnosed with epilepsy are often vulnerable to fatigue, the time saving offered by SITA Fast means that this algorithm has a significant advantage for use with VGB recipients.

Applications of artificial intelligence-powered prenatal diagnosis for congenital heart disease.

Artificial intelligence (AI) has made significant progress in the medical field in the last decade. The AI-powered analysis methods of medical images and clinical records can now match the abilities of clinical physicians. Due to the challenges posed by the unique group of fetuses and the dynamic organ of the heart, research into the application of AI in the prenatal diagnosis of congenital heart disease (CHD) is particularly active. In this review, we discuss the clinical questions and research methods involved in using AI to address prenatal diagnosis of CHD, including imaging, genetic diagnosis, and risk prediction. Representative examples are provided for each method discussed. Finally, we discuss the current limitations of AI in prenatal diagnosis of CHD, namely Volatility, Insufficiency and Independence (VII), and propose possible solutions.

Rethinking Disentanglement in Unsupervised Domain Adaptation for Medical Image Segmentation.

Domain adaptation has become an important topic because the trained neural networks from the source domain generally perform poorly in the target domain due to domain shifts, especially for medical image analysis. Previous DA methods mainly focus on disentangling domain features. However, it is based on feature independence, which often can not be guaranteed in reality. In this work, we present a new DA approach called Dimension-based Disentangled Dilated Domain Adaptation (D4A) to disentangle the storage locations between the features to tackle the problem of domain shift for medical image segmentation tasks without the annotations of the target domain. We use Adaptive Instance Normalization (AdaIN) to encourage the content information to be stored in the spatial dimension, and the style information to be stored in the channel dimension. In addition, we apply dilated convolution to preserve anatomical information avoiding the loss of information due to downsampling. We validate the proposed method for cross-modality medical image segmentation tasks on two public datasets, and the comparison experiments and ablation studies demonstrate the effectiveness of our method, which outperforms the state-of-the-art methods.

Improved Multi-Head Self-Attention Classification Network for Multi-View Fetal Echocardiography Recognition.

The accurate acquisition of multiview fetal cardiac ultrasound images is very important for the diagnosis of fetal congenital heart disease (FCHD). However, these manual clinical procedures have drawbacks, e.g., varying technical capabilities and inefficiency. Therefore, exploring automatic recognition method for multiview images of fetal heart ultrasound scans is highly desirable to improve prenatal diagnosis efficiency and accuracy. In this work, we propose an improved multi-head self-attention mechanism called IMSA combined with residual networks to stably solve the problem of multiview identification and anatomical structure localization. In details, IMSA can capture short- and long-range dependencies from different subspaces and merge them to extract more precise features, thus making use of the correlation between fetal heart structures to make view recognition more focused on anatomical structures rather than disturbing regions, such as artifacts and speckle noises. We validate our proposed method on fetal cardiac ultrasound imaging datasets from a single center and 38 multicenter studies and the results outperform other state-of-the-art networks by 3%-15% of F1 scores in fetal heart six standard view recognition.Clinical Relevance- This technology has great potential in assisting cardiologists to complete the automatic acquisition of multi-section fetal echocardiography images.

FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation.

Medical image segmentation methods normally perform poorly when there is a domain shift between training and testing data. Unsupervised Domain Adaptation (UDA) addresses the domain shift problem by training the model using both labeled data from the source domain and unlabeled data from the target domain. Source-Free UDA (SFUDA) was recently proposed for UDA without requiring the source data during the adaptation, due to data privacy or data transmission issues, which normally adapts the pre-trained deep model in the testing stage. However, in real clinical scenarios of medical image segmentation, the trained model is normally frozen in the testing stage. In this paper, we propose Fourier Visual Prompting (FVP) for SFUDA of medical image segmentation. Inspired by prompting learning in natural language processing, FVP steers the frozen pre-trained model to perform well in the target domain by adding a visual prompt to the input target data. In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model. To our knowledge, FVP is the first work to apply visual prompts to SFUDA for medical image segmentation. The proposed FVP is validated using three public datasets, and experiments demonstrate that FVP yields better segmentation results, compared with various existing methods.

SCCNet: Self-correction boundary preservation with a dynamic class prior filter for high-variability ultrasound image segmentation.

The highly ambiguous nature of boundaries and similar objects is difficult to address in some ultrasound image segmentation tasks, such as neck muscle segmentation, leading to unsatisfactory performance. Thus, this paper proposes a two-stage network called SCCNet (self-correction context network) using a self-correction boundary preservation module and class-context filter to alleviate these problems. The proposed self-correction boundary preservation module uses a dynamic key boundary point (KBP) map to increase the capability of iteratively discriminating ambiguous boundary points segments, and the predicted segmentation map from one stage is used to obtain a dynamic class prior filter to improve the segmentation performance at Stage 2. Finally, three datasets, Neck Muscle, CAMUS and Thyroid, are used to demonstrate that our proposed SCCNet outperforms other state-of-the art methods, such as BPBnet, DSNnet, and RAGCnet. Our proposed network shows at least a 1.2-3.7% improvement on the three datasets, Neck Muscle, Thyroid, and CAMUS. The source code is available at https://github.com/lijixing0425/SCCNet.

Improving the Quality of Fetal Heart Ultrasound Imaging With Multihead Enhanced Self-Attention and Contrastive Learning.

Fetal congenital heart disease (FCHD) is a common, serious birth defect affecting ∼1% of newborns annually. Fetal echocardiography is the most effective and important technique for prenatal FCHD diagnosis. The prerequisites for accurate ultrasound FCHD diagnosis are accurate view recognition and high-quality diagnostic view extraction. However, these manual clinical procedures have drawbacks such as, varying technical capabilities and inefficiency. Therefore, the automatic identification of high-quality multiview fetal heart scan images is highly desirable to improve prenatal diagnosis efficiency and accuracy of FCHD. Here, we present a framework for multiview fetal heart ultrasound image recognition and quality assessment that comprises two parts: a multiview classification and localization network (MCLN) and an improved contrastive learning network (ICLN). In the MCLN, a multihead enhanced self-attention mechanism is applied to construct the classification network and identify six accurate and interpretable views of the fetal heart. In the ICLN, anatomical structure standardization and image clarity are considered. With contrastive learning, the absolute loss, feature relative loss and predicted value relative loss are combined to achieve favorable quality assessment results. Experiments show that the MCLN outperforms other state-of-the-art networks by 1.52-13.61% when determining the F1 score in six standard view recognition tasks, and the ICLN is comparable to the performance of expert cardiologists in the quality assessment of fetal heart ultrasound images, reaching 97% on a test set within 2 points for the four-chamber view task. Thus, our architecture offers great potential in helping cardiologists improve quality control for fetal echocardiographic images in clinical practice.

Novel analytical methods for stratus OCT: alignment of the scan circle.

Measurement of retinal nerve fiber layer (RNFL) thickness using optical coherence tomography (OCT) is commonly used in the detection and management of glaucoma. The Stratus OCT (Carl Zeiss Meditec, Inc., Dublin, CA) is widely used, but image acquisition is subject to artifacts, such as those caused by normal fixational eye movements, and this leads to unreliable measurements. Novel analytical methods have been developed to estimate the amount of misalignment of the circular scanning protocol used by the Stratus OCT. A computer program with a graphical user interface implementing these methods has been written by some of the authors. A case example is presented in this report that shows the effect that vertical displacements of the OCT scan have on measured RNFL thickness. The example is used to demonstrate how the software can be used for estimating the positional alignment of the scan circle. This software can potentially improve the identification of unreliable RNFL thickness measurements and is freely available from the authors.

MSGAN: Multi-Stage Generative Adversarial Networks for Cross-Modality Domain Adaptation.

Domain adaptation has become an important topic because the trained neural networks from the source domain generally perform poorly in the target domain due to domain shifts, especially for cross-modality medical images. In this work, we present a new unsupervised domain adaptation approach called Multi-Stage GAN (MSGAN) to tackle the problem of domain shift for CT and MRI segmentation tasks. We adopt the multi-stage strategy in parallel to avoid information loss and transfer rough styles on low-resolution feature maps to the detailed textures on high-resolution feature maps. In detail, the style layers map the learnt style codes from the Gaussian noise to the input features in order to synthesize images with different styles. We validate the proposed method for cross-modality medical image segmentation tasks on two public datasets, and the results demonstrate the effectiveness of our method. Clinical relevance- This technique paves the way to translate cross-modality images (MRI and CT) and it can also mitigate the performance degradation when applying deep neural networks in a cross-domain scenario.

Strong Out-of-Plane Vibrations and Ultrasensitive Detection of Dopamine-like Neurotransmitters.

The detection of monoamine neurotransmitters has become a vital research subject due to their high correlations with nervous system diseases, but insufficient detection precisions have obstructed diagnosis of some related diseases. Here, we focus on four monoamine neurotransmitters, dopamine, norepinephrine, epinephrine, and serotonin, to conduct their rapid and ultrasensitive detection. We find that the low-frequency (<200 cm-1) Raman vibrations of these molecules show some sharp peaks, and their intensities are significantly stronger than those of the high-frequency side. Theoretical calculations identify these peaks to be from strong out-of-plane vibrations of the C-C single bonds at the joint point of the ring-like molecule and its side chain. Using our surface enhanced low-frequency Raman scattering substrates, we show that the detection limit of dopamine as an example can reach 10 nM in artificial cerebrospinal fluid. This work provides a useful way for ultrasensitive and rapid detection of some neurotransmitters.

Trail-Traced Threshold Test (T4) With a Weighted Binomial Distribution for a Psychophysical Test.

Clinical visual field testing is performed with commercial perimetric devices and employs psychophysical techniques to obtain thresholds of the differential light sensitivity (DLS) at multiple retinal locations. Current thresholding algorithms are relatively inefficient and tough to get satisfied test accuracy, stability concurrently. Thus, we propose a novel Bayesian perimetric threshold method called the Trail-Traced Threshold Test (T4), which can better address the dependence of the initial threshold estimation and achieve significant improvement in the test accuracy and variability while also decreasing the number of presentations compared with Zippy Estimation by Sequential Testing (ZEST) and FT. This study compares T4 with ZEST and FT regarding presentation number, mean absolute difference (MAD between the real Visual field result and the simulate result), and measurement variability. T4 uses the complete response sequence with the spatially weighted neighbor responses to achieve better accuracy and precision than ZEST, FT, SWeLZ, and with significantly fewer stimulus presentations. T4 is also more robust to inaccurate initial threshold estimation than other methods, which is an advantage in subjective methods, such as in clinical perimetry. This method also has the potential for using in other psychophysical tests.

Brain Age Estimation From MRI Using Cascade Networks With Ranking Loss.

Chronological age of healthy people is able to be predicted accurately using deep neural networks from neuroimaging data, and the predicted brain age could serve as a biomarker for detecting aging-related diseases. In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data. Compared with existing methods, TSAN has the following improvements. First, TSAN uses a two-stage cascade network architecture, where the first-stage network estimates a rough brain age, then the second-stage network estimates the brain age more accurately from the discretized brain age by the first-stage network. Second, to our knowledge, TSAN is the first work to apply novel ranking losses in brain age estimation, together with the traditional mean square error (MSE) loss. Third, densely connected paths are used to combine feature maps with different scales. The experiments with 6586 MRIs showed that TSAN could provide accurate brain age estimation, yielding mean absolute error (MAE) of 2.428 and Pearson's correlation coefficient (PCC) of 0.985, between the estimated and chronological ages. Furthermore, using the brain age gap between brain age and chronological age as a biomarker, Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) can be distinguished from healthy control (HC) subjects by support vector machine (SVM). Classification AUC in AD/HC and MCI/HC was 0.904 and 0.823, respectively. It showed that brain age gap is an effective biomarker associated with risk of dementia, and has potential for early-stage dementia risk screening. The codes and trained models have been released on GitHub: https://github.com/Milan-BUAA/TSAN-brain-age-estimation.

A category attention instance segmentation network for four cardiac chambers segmentation in fetal echocardiography.

Fetal echocardiography is an essential and comprehensive examination technique for the detection of fetal heart anomalies. Accurate cardiac chambers segmentation can assist cardiologists to analyze cardiac morphology and facilitate heart disease diagnosis. Previous research mainly focused on the segmentation of single cardiac chambers, such as left ventricle (LV) segmentation or left atrium (LA) segmentation. We propose a generic framework based on instance segmentation to segment the four cardiac chambers accurately and simultaneously. The proposed Category Attention Instance Segmentation Network (CA-ISNet) has three branches: a category branch for predicting the semantic category, a mask branch for segmenting the cardiac chambers, and a category attention branch for learning category information of instances. The category attention branch is used to correct instance misclassification of the category branch. In our collected dataset, which contains echocardiography images with four-chamber views of 319 fetuses, experimental results show our method can achieve superior segmentation performance against state-of-the-art methods. Specifically, using fivefold cross-validation, our model achieves Dice coefficients of 0.7956, 0.7619, 0.8199, 0.7470 for the four cardiac chambers, and with an average precision of 45.64%.