Search

We aimed to develop efficient data labeling strategies for ground truth segmentation in lower-leg magnetic resonance imaging (MRI) of patients with Charcot-Marie-Tooth disease (CMT) and to develop an automated muscle segmentation model using different labeling approaches. The impact of using unlabeled data on model performance was further examined. Using axial T1-weighted MRIs of 120 patients with CMT (60 each with mild and severe intramuscular fat infiltration), we compared the performance of segmentation models obtained using several different labeling strategies. The effect of leveraging unlabeled data on segmentation performance was evaluated by comparing the performances of few-supervised, semi-supervised (mean teacher model), and fully-supervised learning models. We employed a 2D U-Net architecture and assessed its performance by comparing the average Dice coefficients (ADC) using paired t-tests with Bonferroni correction. Among few-supervised models utilizing 10% labeled data, labeling three slices (the uppermost, central, and lowermost slices) per subject exhibited a significantly higher ADC (90.84±3.46%) compared with other strategies using a single image slice per subject (uppermost, 87.79±4.41%; central, 89.42±4.07%; lowermost, 89.29±4.71%, p < 0.0001) or all slices per subject (85.97±9.82%, p < 0.0001). Moreover, semi-supervised learning significantly enhanced the segmentation performance. The semi-supervised model using the three-slices strategy showed the highest segmentation performance (91.03±3.67%) among 10% labeled set models. Fully-supervised model showed an ADC of 91.39±3.76. A three-slice-based labeling strategy for ground truth segmentation is the most efficient method for developing automated muscle segmentation models of CMT lower leg MRI. Additionally, semi-supervised learning with unlabeled data significantly enhances segmentation performance. [ABSTRACT FROM AUTHOR]

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., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://cdt.amegroups.com/article/view/10.21037/cdt-24-25/coif). Y.E.Y. is Chief Medical Officer of Ontact Health, Inc. J.J., Y.J., Y.H., S.H., and S.A.L. are currently affiliated with Ontact Health, Inc. J.J. and J.K. are co-inventors on a patent related to this work filed by Ontact Health (Method And Device For Acquiring Information From Temporal Information Represented Medical Images; Method Of Acquiring Information From Temporal Information Represented Medical Images And Device For The Same). J.J., J.K., and S.H. are co-inventors on a patent related to this work filed by Ontact Health (Method And Device For Providing Information On Ultrasound Image View Based On Out-Of-Distribution Data Detection). Y.J., Y.H., and S.H. are co-inventors on a patent related to this work filed by Ontact Health (Method For Providing Information Of Organ Function And Device For Providing Information Of Organ Function Using The Same). H.J.C. holds stock in Ontact Health, Inc. The other authors have no conflicts of interest to declare., (2024 Cardiovascular Diagnosis and Therapy. All rights reserved.)

This joint feature issue of Optics Express and Applied Optics showcases technical innovations by participants of the 2023 topical meeting on Computational Optical Sensing and Imaging and the computational imaging community. The articles included in the feature issue highlight advances in imaging science that emphasize synergistic activities in optics, signal processing and machine learning. The issue features 26 contributed articles that cover multiple themes including non line-of-sight imaging, imaging through scattering media, compressed sensing, lensless imaging, ptychography, computational microscopy, spectroscopy and optical metrology.

Rolling shutter speckle imaging (RSSI) is a single-shot imaging technique that directly measures the temporal dynamics of the scattering media using a low-cost rolling shutter image sensor and vertically elongated speckles. In this paper, we derive and validate a complete spatiotemporal intensity correlation (STIC) model for RSSI, which describes the row-by-row correlation of the dynamic speckles measured with a rolling shutter in the presence of static scattering. Our new model accounts for the finite exposure time of the detector, which can be longer than the sampling interval in RSSI. We derive a comprehensive model that works for all correlation times of rolling shutter measurements. As a result, we can correctly utilize all data points in RSSI, which improves the measurement accuracy and ranges of speckle decorrelation time and dynamic scattering fraction, as demonstrated by phantom experiments. With simulations and experiments, we provide an understanding of the design parameters of RSSI and the measurement range of the speckle dynamics., Competing Interests: The authors declare no conflicts of interest related to this article., (© 2024 Optica Publishing Group.)