Artificial intelligence-enhanced automation of left ventricular diastolic assessment: a pilot study for feasibility, diagnostic validation, and outcome prediction.

Background: Evaluating left ventricular diastolic function (LVDF) is crucial in echocardiography; however, the complexity and time demands of current guidelines challenge clinical use. This study aimed to develop an artificial intelligence (AI)-based framework for automatic LVDF assessment to reduce subjectivity and improve accuracy and outcome prediction. Methods: We developed an AI-based LVDF assessment framework using a nationwide echocardiographic dataset from five tertiary hospitals. This framework automatically identifies views, calculates diastolic parameters, including mitral inflow and annular velocities (E/A ratio, e' velocity, and E/e' ratio), maximal tricuspid regurgitation velocity, left atrial (LA) volume index, and left atrial reservoir strain (LARS). Subsequently, it grades LVDF according to guidelines. The AI-framework was validated on an external dataset composed of randomly screened 173 outpatients who underwent transthoracic echocardiography with suspicion for diastolic dysfunction and 33 individuals from medical check-ups with normal echocardiograms at Seoul National University Bundang Hospital, tertiary medical center in Korea, between May 2012 and June 2022. Additionally, we assessed the predictive value of AI-derived diastolic parameters and LVDF grades for a clinical endpoint, defined as a composite of all-cause death and hospitalization for heart failure, using Cox-regression risk modelling. Results: In an evaluation with 200 echocardiographic examinations (167 suspected diastolic dysfunction patients, 33 controls), it achieves an overall accuracy of 99.1% in identifying necessary views. Strong correlations (Pearson coefficient 0.901-0.959) were observed between AI-derived and manually-derived measurements of diastolic parameters, including LARS as well as conventional parameters. When following the guidelines, whether utilizing AI-derived or manually-derived parameters, the evaluation of LVDF consistently showed high concordance rates (94%). However, both methods exhibited lower concordance rates with the clinician's prior assessments (77.5% and 78.5%, respectively). Importantly, both AI-derived and manually-derived LVDF grades independently demonstrated significant prognostic value [adjusted hazard ratio (HR) =3.03; P=0.03 and adjusted HR =2.75; P=0.04, respectively] for predicting clinical outcome. In contrast, the clinician's prior grading lost its significance as a prognostic indicator after adjusting for clinical risk factors (adjusted HR =1.63; P=0.36). AI-derived LARS values significantly decreased with worsening LVDF (P for trend <0.001), and low LARS (<17%) was associated with increased risk for the clinical outcome (Log-rank P=0.04) relative to that for preserved LARS (≥17%). Conclusions: Our AI-based approach for automatic LVDF assessment on echocardiography is feasible, potentially enhancing clinical diagnosis and outcome prediction.

Artificial intelligence-enhanced automation for M-mode echocardiographic analysis: ensuring fully automated, reliable, and reproducible measurements.

To enhance M-mode echocardiography's utility for measuring cardiac structures, we developed and evaluated an artificial intelligence (AI)-based automated analysis system for M-mode images through the aorta and left atrium [M-mode (Ao-LA)], and through the left ventricle [M-mode (LV)]. Our system, integrating two deep neural networks (DNN) for view classification and image segmentation, alongside an auto-measurement algorithm, was developed using 5,958 M-mode images [3,258 M-mode (LA-Ao), and 2,700 M-mode (LV)] drawn from a nationwide echocardiographic dataset collated from five tertiary hospitals. The performance of view classification and segmentation DNNs were evaluated on 594 M-mode images, while automatic measurement accuracy was tested on separate internal test set with 100 M-mode images as well as external test set with 280 images (140 sinus rhythm and 140 atrial fibrillation). Performance evaluation showed the view classification DNN's overall accuracy of 99.8% and segmentation DNN's Dice similarity coefficient of 94.3%. Within the internal test set, all automated measurements, including LA, Ao, and LV wall and cavity, resonated strongly with expert evaluations, exhibiting Pearson's correlation coefficients (PCCs) of 0.81-0.99. This performance persisted in the external test set for both sinus rhythm (PCC, 0.84-0.98) and atrial fibrillation (PCC, 0.70-0.97). Notably, automatic measurements, consistently offering multi-cardiac cycle readings, showcased a stronger correlation with the averaged multi-cycle manual measurements than with those of a single representative cycle. Our AI-based system for automatic M-mode echocardiographic analysis demonstrated excellent accuracy, reproducibility, and speed. This automated approach has the potential to improve efficiency and reduce variability in clinical practice.

Generative adversarial network with radiomic feature reproducibility analysis for computed tomography denoising.

BACKGROUND: Most computed tomography (CT) denoising algorithms have been evaluated using image quality analysis (IQA) methods developed for natural image, which do not adequately capture the texture details in medical imaging. Radiomics is an emerging image analysis technique that extracts texture information to provide a more objective basis for medical imaging diagnostics, overcoming the subjective nature of traditional methods. By utilizing the difficulty of reproducing radiomics features under different imaging protocols, we can more accurately evaluate the performance of CT denoising algorithms. METHOD: We introduced radiomic feature reproducibility analysis as an evaluation metric for a denoising algorithm. Also, we proposed a low-dose CT denoising method based on a generative adversarial network (GAN), which outperformed well-known CT denoising methods. RESULTS: Although the proposed model produced excellent results visually, the traditional image assessment metrics such as peak signal-to-noise ratio and structural similarity failed to show distinctive performance differences between the proposed method and the conventional ones. However, radiomic feature reproducibility analysis provided a distinctive assessment of the CT denoising performance. Furthermore, radiomic feature reproducibility analysis allowed fine-tuning of the hyper-parameters of the GAN. CONCLUSION: We demonstrated that the well-tuned GAN architecture outperforms the well-known CT denoising methods. Our study is the first to introduce radiomics reproducibility analysis as an evaluation metric for CT denoising. We look forward that the study may bridge the gap between traditional objective and subjective evaluations in the clinical medical imaging field.

Deep Learning-Based Computed Tomography Image Standardization to Improve Generalizability of Deep Learning-Based Hepatic Segmentation.

OBJECTIVE: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. MATERIALS AND METHODS: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. RESULTS: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). CONCLUSION: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

Deep Learning-Based Image Conversion Improves the Reproducibility of Computed Tomography Radiomics Features: A Phantom Study.

OBJECTIVES: This study aimed to evaluate the usefulness of deep learning-based image conversion to improve the reproducibility of computed tomography (CT) radiomics features. MATERIALS AND METHODS: This study was conducted using an abdominal phantom with liver nodules. We developed an image conversion algorithm using a residual feature aggregation network to reproduce radiomics features with CT images under various CT protocols and reconstruction kernels. External validation was performed using images from different scanners, consisting of 8 different protocols. To evaluate the variability of radiomics features, regions of interest (ROIs) were drawn by targeting the liver parenchyma, vessels, paraspinal area, and liver nodules. We extracted 18 first-order, 68 second-order, and 688 wavelet radiomics features. Measurement variability was assessed using the concordance correlation coefficient (CCC), compared with the ground-truth image. RESULTS: In the ROI-based analysis, there was an 83.3% improvement of CCC (80/96; 4 ROIs with 3 categories of radiomics features and 8 protocols) in synthetic images compared with the original images. Among them, the 56 CCC pairs showed a significant increase after image synthesis. In the radiomics feature-based analysis, 62.0% (3838 of 6192; 774 radiomics features with 8 protocols) features showed increased CCC after image synthesis, and a significant increase was noted in 26.9% (1663 of 6192) features. In particular, the first-order feature (79.9%, 115/144) showed better improvement in terms of the reproducibility of radiomics feature than the second-order (59.9%, 326/544) or wavelet feature (61.7%, 3397/5504). CONCLUSIONS: Our study demonstrated that a deep learning model for image conversion can improve the reproducibility of radiomics features across various CT protocols, reconstruction kernels, and CT scanners.

Post-traumatic stress symptoms in hemodialysis patients with MERS-CoV exposure.

BACKGROUND: Post-traumatic stress symptoms can occur in patients with medical illness. During the Middle East Respiratory Syndrome (MERS) outbreak in South Korea in 2015, some dialysis patients in three centers who were incidentally exposed to patients or medical staff with confirmed MERS-CoV infection were isolated to interrupt the spread of the infection. We aimed to investigate post-traumatic stress symptoms and risk factors among these patients. MATERIALS AND METHODS: In total, 116 hemodialysis (HD) patients in contact with MERS-CoV-confirmed subjects were isolated using three strategies, namely, single room isolation, cohort isolation, and self-quarantine. We used the Impact of Event Scale-Revised-Korean (IES-R-K) to examine post-traumatic stress symptoms at 12 months after the isolation period. RESULTS: Of the 116 HD patients, 27 were lost to follow-up. Of the 89 patients, 67 (75.3%) completed the questionnaires. Single room isolation was used on 40 (58.8%) of the patients, cohort isolation on 20 (29.4%), and self-imposed quarantine on 8 (11.8%). In total, 17.9% of participants (n = 12) reported post-traumatic stress symptoms exceeding the IES-R-K's cutoff point (≧18). Prevalence rates of IES-R-K ≧18 did not differ significantly according to isolation method. However, isolation duration was linearly associated with the IES-R-K score (standardized ß coefficient - 0.272, P = 0.026). Scores in Avoidance, Emotional numbing and Dissociation subscale were higher in patients with longer isolation period. CONCLUSION: MERS was a traumatic experience for quarantined HD patients. IES-R-K scores were not significantly different by isolation methods. However, short isolation was associated with post-traumatic stress symptoms.

Effect of isolation practice on the transmission of middle east respiratory syndrome coronavirus among hemodialysis patients: A 2-year prospective cohort study.

Hemodialysis (HD) patients had a high rate of infection transmission and mortality during the middle east respiratory syndrome coronavirus (MERS-CoV) outbreak in Saudi Arabia. A standardized guideline on isolation technique for exposed HD patients is not available. Thus, this study aimed to evaluate the effect of different isolation strategies on the prevention of secondary viral transmission and clinical outcomes among exposed HD patients.During the 2015 MERS-CoV outbreak in Korea, 116 patients in 3 HD units were incidentally exposed to individuals with confirmed MERS-CoV infection and underwent different types of isolation, which were as follows: single-room isolation (n = 54, 47%), cohort isolation (n = 46, 40%), and self-imposed quarantine (n = 16, 13%). The primary outcome was rate of secondary viral transmission. The secondary outcome measures were changes in clinical and biochemical markers during the isolation period, difference in clinical and biochemical markers according to the types of isolation practice, and effect of isolation practice on patient survival.During a mean isolation period of 15 days, no further cases of secondary transmission were detected among HD patients. Plasma hemoglobin, serum calcium, and serum albumin levels and single-pool Kt/V decreased during the isolation period but normalized thereafter. Patients who were subjected to self-imposed quarantine had higher systolic and diastolic blood pressure, lower total cholesterol level, and lower Kt/V than those who underwent single-room or cohort isolation. During the 24-month follow-up period, 12 patients died. However, none of the deaths occurred during the isolation period, and no differences were observed in patient survival rate according to different isolation strategies.Although 116 participants in 3 HD units were incidentally exposed to MERS-CoV during the 2015 outbreak in Korea, strict patient surveillance and proper isolation practice prevented secondary transmission of the virus. Thus, a renal disaster protocol, which includes proper contact surveillance and isolation practice, must be established in the future to accommodate the needs of HD patients during disasters or outbreaks.

Inevitable isolation and the change of stress markers in hemodialysis patients during the 2015 MERS-CoV outbreak in Korea.

During the outbreak of Middle East respiratory syndrome coronavirus(MERS-CoV) in 2015, one hemodialysis patient was infected with MERS-CoV, and the remaining hemodialysis(HD) patients (n = 83) and medical staff (n = 12) had to undergo dialysis treatment in an isolated environment. This study was performed to investigate the effects of stress caused by dialysis treatment under isolation. Plasma samples from the HD patients and medical staff were collected at the time of isolation(M0), the following month(M1), and three months after isolation(M3). Parameters for stress included circulating cell-free genomic DNA(ccf-gDNA), circulating cell-free mitochondria DNA(ccf-mtDNA), and pentraxin-3(PTX-3). Decreased values of Hct, kt/v and ca x p were recovered after the end of two weeks of isolation. The levels of ccf-gDNA and ccf-mtDNA were the highest at M0 and decreased gradually in both HD patients and the medical staff. The normalization of ccf-gDNA and ccf-mtDNA was significantly delayed in HD patients compared with the response in the medical staff. PTX-3 increased only in HD patients and was highest at M0, and it then gradually decreased. Medical isolation and subnormal quality of care during the MERS outbreak caused extreme stress in HD patients. Plasma cell-free DNA and PTX-3 seems to be good indicators of stress and quality of care in HD patients.