Classification guided thick fog removal network for drone imaging: ClassifyCycle.

The foggy images captured by drones are nonuniform due to inhomogeneous distribution of fog in higher altitude, leading to the obvious fog thickness differences in the images. This paper proposes a classification guided thick fog removal network for drone imaging, termed ClassifyCycle. The drone images are input into the proposed classification module (ICLFn) to enhance the reliability of follow-up learning network. The style migration module (ISMn) is introduced to reduce the image distortion, such as hue artifact and texture distort. The proposed network ClassifyCycle does not require paired foggy and corresponding fog-free datasets, avoiding the phenomena of overexposure, distortion, color deviation and fog residue after defogging. Extensive experimental results show that the proposed ClassifyCycle network surpasses the state-of-the-art algorithms on synthetic and realistic drone images captured in thick fog weather.

Deep learning-based diagnosis of disease activity in patients with Graves' orbitopathy using orbital SPECT/CT.

PURPOSE: Orbital [99mTc]TcDTPA orbital single-photon emission computed tomography (SPECT)/CT is an important method for assessing inflammatory activity in patients with Graves' orbitopathy (GO). However, interpreting the results requires substantial physician workload. We aim to propose an automated method called GO-Net to detect inflammatory activity in patients with GO. MATERIALS AND METHODS: GO-Net had two stages: (1) a semantic V-Net segmentation network (SV-Net) that extracts extraocular muscles (EOMs) in orbital CT images and (2) a convolutional neural network (CNN) that uses SPECT/CT images and the segmentation results to classify inflammatory activity. A total of 956 eyes from 478 patients with GO (active: 475; inactive: 481) at Xiangya Hospital of Central South University were investigated. For the segmentation task, five-fold cross-validation with 194 eyes was used for training and internal validation. For the classification task, 80% of the eye data were used for training and internal fivefold cross-validation, and the remaining 20% of the eye data were used for testing. The EOM regions of interest (ROIs) were manually drawn by two readers and reviewed by an experienced physician as ground truth for segmentation GO activity was diagnosed according to clinical activity scores (CASs) and the SPECT/CT images. Furthermore, results are interpreted and visualized using gradient-weighted class activation mapping (Grad-CAM). RESULTS: The GO-Net model combining CT, SPECT, and EOM masks achieved a sensitivity of 84.63%, a specificity of 83.87%, and an area under the receiver operating curve (AUC) of 0.89 (p < 0.01) on the test set for distinguishing active and inactive GO. Compared with the CT-only model, the GO-Net model showed superior diagnostic performance. Moreover, Grad-CAM demonstrated that the GO-Net model placed focus on the GO-active regions. For EOM segmentation, our segmentation model achieved a mean intersection over union (IOU) of 0.82. CONCLUSION: The proposed Go-Net model accurately detected GO activity and has great potential in the diagnosis of GO.

Automatic reorientation by deep learning to generate short-axis SPECT myocardial perfusion images.

BACKGROUND: Single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) can be displayed both in traditional short-axis (SA) cardiac planes and polar maps for interpretation and quantification. It is essential to reorient the reconstructed transaxial SPECT MPI into standard SA slices. This study is aimed to develop a deep-learning-based approach for automatic reorientation of MPI. METHODS: A total of 254 patients were enrolled, including 226 stress SPECT MPIs and 247 rest SPECT MPIs. Fivefold cross-validation with 180 stress and 201 rest MPIs was used for training and internal validation; the remaining images were used for testing. The rigid transformation parameters (translation and rotation) from manual reorientation were annotated by an experienced nuclear cardiologist and used as the reference standard. A convolutional neural network (CNN) was designed to predict the transformation parameters. Then, the derived transform was applied to the grid generator and sampler in spatial transformer network (STN) to generate the reoriented image. A loss function containing mean absolute errors for translation and mean square errors for rotation was employed. A three-stage optimization strategy was adopted for model optimization: (1) optimize the translation parameters while fixing the rotation parameters; (2) optimize rotation parameters while fixing the translation parameters; (3) optimize both translation and rotation parameters together. RESULTS: In the test set, the Spearman determination coefficients of the translation distances and rotation angles between the model prediction and the reference standard were 0.993 in X axis, 0.992 in Y axis, 0.994 in Z axis, 0.987 along X axis, 0.990 along Y axis and 0.996 along Z axis, respectively. For the 46 stress MPIs in the test set, the Spearman determination coefficients were 0.858 in percentage of profusion defect (PPD) and 0.858 in summed stress score (SSS); for the 46 rest MPIs in the test set, the Spearman determination coefficients were 0.9 in PPD and 0.9 in summed rest score (SRS). CONCLUSIONS: Our deep learning-based LV reorientation method is able to accurately generate the SA images. Technical validations and subsequent evaluations of measured clinical parameters show that it has great promise for clinical use.

A Deep Learning-based Method to Extract Lumen and Media-Adventitia in Intravascular Ultrasound Images.

Intravascular ultrasound (IVUS) imaging allows direct visualization of the coronary vessel wall and is suitable for assessing atherosclerosis and the degree of stenosis. Accurate segmentation and lumen and median-adventitia (MA) measurements from IVUS are essential for such a successful clinical evaluation. However, current automated segmentation by commercial software relies on manual corrections, which is time-consuming and user-dependent. We aim to develop a deep learning-based method using an encoder-decoder deep architecture to automatically and accurately extract both lumen and MA border. Inspired by the dual-path design of the state-of-the-art model IVUS-Net, our method named IVUS-U-Net++ achieved an extension of the U-Net++ model. More specifically, a feature pyramid network was added to the U-Net++ model, enabling the utilization of feature maps at different scales. Following the segmentation, the Pearson correlation and Bland-Altman analyses were performed to evaluate the correlations of 12 clinical parameters measured from our segmentation results and the ground truth. A dataset with 1746 IVUS images from 18 patients was used for training and testing. Our segmentation model at the patient level achieved a Jaccard measure (JM) of 0.9080 ± 0.0321 and a Hausdorff distance (HD) of 0.1484 ± 0.1584 mm for the lumen border; it achieved a JM of 0.9199 ± 0.0370 and an HD of 0.1781 ± 0.1906 mm for the MA border. The 12 clinical parameters measured from our segmentation results agreed well with those from the ground truth (all p-values are smaller than .01). Our proposed method shows great promise for its clinical use in IVUS segmentation.

Prognostic value of left-ventricular systolic and diastolic dyssynchrony measured from gated SPECT MPI in patients with dilated cardiomyopathy.

BACKGROUND: Left-ventricular systolic dyssynchrony (LVSD) has been an important prognostic factor in the patients with dilated cardiomyopathy (DCM). However, the association between the LV diastolic dyssynchrony (LVDD) and clinical outcome is not well established. This study aims to evaluate the prognostic values of both systolic and diastolic dyssynchrony in patients with DCM. METHODS: Fifty-two patients with DCM were enrolled and divided into two groups according to cardiac deaths from the follow-up data. The phase-analysis technique was applied on resting gated short-axis SPECT MPI images to measure LV systolic and diastolic dyssynchrony, including phase standard deviation (PSD), phase histogram bandwidth (PBW), and phase entropy (PE). Variables with P < 0.10 in the univariate analysis were included in the multivariate cox analysis. RESULTS: During the follow-up period (2.9 ± 1.7 years), 18 (34.6%) cardiac deaths were observed. Compared with survivors, patients with cardiac death had lower LVEF (P = 0.011), and more severe LV systolic and diastolic dyssynchrony. The univariate cox regression analysis showed that hypertension, NT-proBNP, LVEF, systolic PSD, systolic PE, and diastolic PBW were statistically significantly associated with cardiac death. The multivariate cox regression analysis showed that systolic PE and diastolic PE were independent predictive factors for cardiac death. Furthermore, the receiver operating characteristic (ROC) analysis, when applied into the combination of systolic PE and diastolic PE for predicting cardiac death, had an area under curve (AUC) of 0.766, a sensitivity of 0.765, and a specificity of 0.722. CONCLUSIONS: Both the LVSD and LVDD parameters from SPECT MPI have important prognostic values for DCM patients. Both systolic PE and diastolic PE are independent prognostic factors for cardiac death.

Machine learning for the diagnosis of pulmonary hypertension.

Objective This paper aims to investigate whether machine learning (ML) can be used to predict the state of pulmonary hypertension (PH), including pre-capillary and post-capillary, from echocardiographic data.Methods Two hundred and seventy-five patients with PH who underwent both echocardiography and right heart catheterization were included in the study. Mean pulmonary artery pressure, pulmonary artery wedge pressure measured by right heart catheterization were used as criteria for judging pre-capillary PH and post-capillary PH. Thirteen echocardiographic indicators were used to predict whether the PH was pre-capillary or post-capillary. Nine ML models were used to make predictions. Accuracy was used as the primary reference standard, and the performance of classification model is observed in conjunction with area under curve (AUC), specificity (Sp), sensitivity (Se), Positive Prediction Value (PPV), Negative Prediction Value (NPV), Positive Likelihood Ratio (PLR) and Negative Likelihood Ratio (NLR) and other assessment protocols.Results By comparing the accuracy (ACC), recall rate (Recall) and other model effect evaluation index of the classification under the nine ML models, it can be found that the ML model can effectively identify the pre-capillary PH and the post-capillary PH. LogitBoost performed best in nine ML models (ACC=0.87, Recall=0.83, F1score=0.85, AUC=0.87, Se=0.90, NPV=0.88, PPV=0.87, PLR=8.61 and NLR=0.18, AUC=0.83), it showed good results in identification of the pre-capillary PH (ACC=0.83, Recall=0.87, F-score=0.85); Post-vascular PH (ACC=0.90, Recall=0.88, F-score=0.89). Decision Tree (ACC=0.75, Recall=0.77, F1score=0.78, AUC=0.75, Se=0.72, NPV=0.78, PPV=0.77, PLR=3.66 and NLR=0.29, AUC=0.79) performed worst, and the accuracy of the other seven models was greater than 0.82.Conclusion The classification results of the nine ML models in this paper indicate that the ML method can effectively identify the pre-capillary PH and post-capillary PH from echocardiographic data. Compared with medical diagnosis, ML methods can distinguish between pre-capillary PH and the post-capillary PH under non-invasive conditions.

An automated two-stage approach to kidney and tumor segmentation in CT imaging.

BACKGROUND: The incidence of kidney tumors is progressively increasing each year. The precision of segmentation for kidney tumors is crucial for diagnosis and treatment. OBJECTIVE: To enhance accuracy and reduce manual involvement, propose a deep learning-based method for the automatic segmentation of kidneys and kidney tumors in CT images. METHODS: The proposed method comprises two parts: object detection and segmentation. We first use a model to detect the position of the kidney, then narrow the segmentation range, and finally use an attentional recurrent residual convolutional network for segmentation. RESULTS: Our model achieved a kidney dice score of 0.951 and a tumor dice score of 0.895 on the KiTS19 dataset. Experimental results show that our model significantly improves the accuracy of kidney and kidney tumor segmentation and outperforms other advanced methods. CONCLUSION: The proposed method provides an efficient and automatic solution for accurately segmenting kidneys and renal tumors on CT images. Additionally, this study can assist radiologists in assessing patients' conditions and making informed treatment decisions.

Radiomics Nomogram Derived from Gated Myocardial Perfusion SPECT for Identifying Ischemic Cardiomyopathy.

Personalized management involving heart failure (HF) etiology is crucial for better prognoses. We aim to evaluate the utility of a radiomics nomogram based on gated myocardial perfusion imaging (GMPI) in distinguishing ischemic from non-ischemic origins of HF. A total of 172 heart failure patients with reduced left ventricular ejection fraction (HFrEF) who underwent GMPI scan were divided into training (n = 122) and validation sets (n = 50) based on chronological order of scans. Radiomics features were extracted from the resting GMPI. Four machine learning algorithms were used to construct radiomics models, and the model with the best performances were selected to calculate the Radscore. A radiomics nomogram was constructed based on the Radscore and independent clinical factors. Finally, the model performance was validated using operating characteristic curves, calibration curve, decision curve analysis, integrated discrimination improvement values (IDI), and the net reclassification index (NRI). Three optimal radiomics features were used to build a radiomics model. Total perfusion deficit (TPD) was identified as the independent factors of conventional GMPI metrics for building the GMPI model. In the validation set, the radiomics nomogram integrating the Radscore, age, systolic blood pressure, and TPD significantly outperformed the GMPI model in distinguishing ischemic cardiomyopathy (ICM) from non-ischemic cardiomyopathy (NICM) (AUC 0.853 vs. 0.707, p = 0.038). IDI analysis indicated that the nomogram improved diagnostic accuracy by 28.3% compared to the GMPI model in the validation set. By combining radiomics signatures with clinical indicators, we developed a GMPI-based radiomics nomogram that helps to identify the ischemic etiology of HFrEF.

A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images.

Accurate segmentation of the left ventricle (LV) is crucial for evaluating myocardial perfusion SPECT (MPS) and assessing LV functions. In this study, a novel method combining deep learning with shape priors was developed and validated to extract the LV myocardium and automatically measure LV functional parameters. The method integrates a three-dimensional (3D) V-Net with a shape deformation module that incorporates shape priors generated by a dynamic programming (DP) algorithm to guide its output during training. A retrospective analysis was performed on an MPS dataset comprising 31 subjects without or with mild ischemia, 32 subjects with moderate ischemia, and 12 subjects with severe ischemia. Myocardial contours were manually annotated as the ground truth. A 5-fold stratified cross-validation was used to train and validate the models. The clinical performance was evaluated by measuring LV end-systolic volume (ESV), end-diastolic volume (EDV), left ventricular ejection fraction (LVEF), and scar burden from the extracted myocardial contours. There were excellent agreements between segmentation results by our proposed model and those from the ground truth, with a Dice similarity coefficient (DSC) of 0.9573 ± 0.0244, 0.9821 ± 0.0137, and 0.9903 ± 0.0041, as well as Hausdorff distances (HD) of 6.7529 ± 2.7334 mm, 7.2507 ± 3.1952 mm, and 7.6121 ± 3.0134 mm in extracting the LV endocardium, myocardium, and epicardium, respectively. Furthermore, the correlation coefficients between LVEF, ESV, EDV, stress scar burden, and rest scar burden measured from our model results and the ground truth were 0.92, 0.958, 0.952, 0.972, and 0.958, respectively. The proposed method achieved a high accuracy in extracting LV myocardial contours and assessing LV functions.

Automatic identification of end-diastolic and end-systolic cardiac frames from invasive coronary angiography videos.

BACKGROUND: Automatic identification of proper image frames at the end-diastolic (ED) and end-systolic (ES) frames during the review of invasive coronary angiograms (ICA) is important to assess blood flow during a cardiac cycle, reconstruct the 3D arterial anatomy from bi-planar views, and generate the complementary fusion map with myocardial images. The current identification method primarily relies on visual interpretation, making it not only time-consuming but also less reproducible. OBJECITVE: In this paper, we propose a new method to automatically identify angiographic image frames associated with the ED and ES cardiac phases. METHOD: A detection algorithm is first used to detect the key points (i.e. landmarks) of coronary arteries, and then an optical flow method is employed to track the trajectories of the selected key points. The ED and ES frames are identified based on all these trajectories. Our method was tested with 62 ICA videos from two separate medical centers. RESULTS: Comparing consensus interpretations by two human expert readers, excellent agreement was achieved by the proposed algorithm: the agreement rates within a one-frame range were 92.99% and 92.73% for the automatic identification of the ED and ES image frames, respectively. CONCLUSION: The proposed automated method showed great potential for being an integral part of automated ICA image analysis.

Severity detection of COVID-19 infection with machine learning of clinical records and CT images.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is a deadly viral infection spreading rapidly around the world since its outbreak in 2019. In the worst case a patient's organ may fail leading to death. Therefore, early diagnosis is crucial to provide patients with adequate and effective treatment. OBJECTIVE: This paper aims to build machine learning prediction models to automatically diagnose COVID-19 severity with clinical and computed tomography (CT) radiomics features. METHOD: P-V-Net was used to segment the lung parenchyma and then radiomics was used to extract CT radiomics features from the segmented lung parenchyma regions. Over-sampling, under-sampling, and a combination of over- and under-sampling methods were used to solve the data imbalance problem. RandomForest was used to screen out the optimal number of features. Eight different machine learning classification algorithms were used to analyze the data. RESULTS: The experimental results showed that the COVID-19 mild-severe prediction model trained with clinical and CT radiomics features had the best prediction results. The accuracy of the GBDT classifier was 0.931, the ROUAUC 0.942, and the AUCPRC 0.694, which indicated it was better than other classifiers. CONCLUSION: This study can help clinicians identify patients at risk of severe COVID-19 deterioration early on and provide some treatment for these patients as soon as possible. It can also assist physicians in prognostic efficacy assessment and decision making.

Analyze Informant-Based Questionnaire for The Early Diagnosis of Senile Dementia Using Deep Learning.

OBJECTIVE: This paper proposes a multiclass deep learning method for the classification of dementia using an informant-based questionnaire. METHODS: A deep neural network classification model based on Keras framework is proposed in this paper. To evaluate the advantages of our proposed method, we compared the performance of our model with industry-standard machine learning approaches. We enrolled 6,701 individuals, which were randomly divided into training data sets (6030 participants) and test data sets (671 participants). We evaluated each diagnostic model in the test set using accuracy, precision, recall, and F1-Score. RESULTS: Compared with the seven conventional machine learning algorithms, the DNN showed higher stability and achieved the best accuracy with 0.88, which also showed good results for identifying normal (F1-score = 0.88), mild cognitive impairment (MCI) (F1-score = 0.87), very mild dementia (VMD) (F1-score = 0.77) and Severe dementia (F1-score = 0.94). CONCLUSION: The deep neural network (DNN) classification model can effectively help doctors accurately screen patients who have normal cognitive function, mild cognitive impairment (MCI), very mild dementia (VMD), mild dementia (Mild), moderate dementia (Moderate), and severe dementia (Severe).

Machine Learning for the Preliminary Diagnosis of Dementia.

Objective: The reliable diagnosis remains a challenging issue in the early stages of dementia. We aimed to develop and validate a new method based on machine learning to help the preliminary diagnosis of normal, mild cognitive impairment (MCI), very mild dementia (VMD), and dementia using an informant-based questionnaire. Methods: We enrolled 5,272 individuals who filled out a 37-item questionnaire. In order to select the most important features, three different techniques of feature selection were tested. Then, the top features combined with six classification algorithms were used to develop the diagnostic models. Results: Information Gain was the most effective among the three feature selection methods. The Naive Bayes algorithm performed the best (accuracy = 0.81, precision = 0.82, recall = 0.81, and F-measure = 0.81) among the six classification models. Conclusion: The diagnostic model proposed in this paper provides a powerful tool for clinicians to diagnose the early stages of dementia.

Hypomethylation of the Toll-like receptor-2 gene increases the risk of essential hypertension.

Studies on the etiology of essential hypertension (EH) have demonstrated that chronic inflammation contributes to the onset and development of elevated blood pressure. Toll­like receptors (TLRs), important immune receptors, serve a role in chronic inflammation and are associated with EH. In the present study, 96 patients with EH, and 96 age­ and sex­matched healthy controls were recruited, and eight cytosine­phosphate­guanine (CpG) dinucleotides (CpG1­8) were analyzed using bisulfite pyrosequencing technology. It was observed that the methylation levels of all of the eight CpG dinucleotides were decreased in the EH group compared with the control group; however, only CpG1 (2.83±1.34 vs. 3.44±1.75; P=0.009), CpG6 (3.58±3.64 vs. 8.30±4.13; P<0.001) and CpG8 (8.91±5.32 vs. 11.33±3.87; P<0.001) were significantly different, as demonstrated by paired t­test analysis. In addition, logistic regression analysis demonstrated that CpG6 hypomethylation was a risk factor of EH (odds ratio=1.10; adjusted P=0.009), and CpG6 methylation level was observed to be negatively correlated with systolic blood pressure (r=­0.304; P<0.001) and diastolic blood pressure (r=­0.329; P<0.001). Additionally, receiver operating characteristic curve analysis demonstrated that a methylation level of 7.5% for CpG6 (area under the curve, 0.834; P<0.001) was an appropriate threshold value to predict the risk of EH. With generalized multifactor dimensionality reduction, a potential gene­gene interaction between CpG6 and CpG8 (P=0.001), and gene­environment interactions between smoking, alcohol consumption, CpG6, CpG7 and CpG8 (P=0.011), were observed. In conclusion, the results of the present study demonstrated that hypomethylation of the TLR2 promoter, particularly CpG6, was associated with the risk of EH in this population. Additionally, a gene­gene interaction between CpG6 and CpG8, and interactions between environmental factors, including smoking and alcohol consumption, and CpG6, CpG7 and CpG8, may be associated with the risk of EH.

Interactions between CYP11B2 Promoter Methylation and Smoking Increase Risk of Essential Hypertension.

Aldosterone synthase (CYP11B2) is closely linked to essential hypertension (EH). However, it remains unclear whether the methylation of the CYP11B2 promoter is involved in the development of EH in humans. Our study is aimed at evaluating the contribution of CYP11B2 promoter methylation to the risk of EH. Methylation levels were measured using pyrosequencing technology in 192 participants in a hospital-based case-control study. Logistic regression and multiple linear regression analyses were utilized to adjust for confounding factors and the GMDR method was applied to investigate high-order gene-environment interactions. Although no significant result was observed linking the four analyzed CpG sites to EH, GMDR detected significant interactions among CpG1, CpG3, CpG4, and smoking correlated with an increased risk of EH (OR = 4.62, adjusted P = 0.011). In addition, CpG2 (adjusted P = 0.013) and CpG3 (adjusted P = 0.039) methylation was significantly lower in healthy males than in healthy females. Likewise, after adjusting for confounding factors, CpG2 methylation (adjusted P = 0.007) still showed significant gender-specific differences among the participants of the study. CpG1 (P = 0.009) site was significantly positively correlated with age, and CpG3 (P = 0.007) and CpG4 (P = 0.006) were both inversely linked to smoking. Our findings suggest that gene-environment interactions are associated with the pathogenesis and progression of EH.

Topological Alterations of the Intrinsic Brain Network in Patients with Functional Dyspepsia.

BACKGROUND/AIMS: Previous studies reported that integrated information in the brain ultimately determines the subjective experience of patients with chronic pain, but how the information is integrated in the brain connectome of functional dyspepsia (FD) patients remains largely unclear. The study aimed to quantify the topological changes of the brain network in FD patients. METHODS: Small-world properties, network efficiency and nodal centrality were utilized to measure the changes in topological architecture in 25 FD patients and 25 healthy controls based on functional magnetic resonance imaging. Pearson's correlation assessed the relationship of each topological property with clinical symptoms. RESULTS: FD patients showed an increase of clustering coefficients and local efficiency relative to controls from the perspective of a whole network as well as elevated nodal centrality in the right orbital part of the inferior frontal gyrus, left anterior cingulate gyrus and left hippocampus, and decreased nodal centrality in the right posterior cingulate gyrus, left cuneus, right putamen, left middle occipital gyrus and right inferior occipital gyrus. Moreover, the centrality in the anterior cingulate gyrus was significantly associated with symptom severity and duration in FD patients. Nevertheless, the inclusion of anxiety and depression scores as covariates erased the group differences in nodal centralities in the orbital part of the inferior frontal gyrus and hippocampus. CONCLUSIONS: The results suggest topological disruption of the functional brain networks in FD patients, presumably in response to disturbances of sensory information integrated with emotion, memory, pain modulation, and selective attention in patients.