Symtosis: A liver ultrasound tissue characterization and risk stratification in optimized deep learning paradigm

Entropy is a quantitative measure of signal uncertainty and has been widely applied to ultrasound tissue characterization. Ultrasound assessment of hepatic steatosis typically involves a backscattered statistical analysis of signals based on information entropy. Deep learning extracts features for classification without any physical assumptions or considerations in acoustics. In this study, we assessed clinical values of information entropy and deep learning in the grading of hepatic steatosis. A total of 205 participants underwent ultrasound examinations. The image raw data were used for Shannon entropy imaging and for training and testing by the pretrained VGG-16 model, which has been employed for medical data analysis. The entropy imaging and VGG-16 model predictions were compared with histological examinations. The diagnostic performances in grading hepatic steatosis were evaluated using receiver operating characteristic (ROC) curve analysis and the DeLong test. The areas under the ROC curves when using the VGG-16 model to grade mild, moderate, and severe hepatic steatosis were 0.71, 0.75, and 0.88, respectively; those for entropy imaging were 0.68, 0.85, and 0.9, respectively. Ultrasound entropy, which varies with fatty infiltration in the liver, outperformed VGG-16 in identifying participants with moderate or severe hepatic steatosis (p < 0.05). The results indicated that physics-based information entropy for backscattering statistics analysis can be recommended for ultrasound diagnosis of hepatic steatosis, providing not only improved performance in grading but also clinical interpretations of hepatic steatosis.

Download Full-text

The Role of AI in Characterizing the DCM Phenotype

Frontiers in Cardiovascular Medicine ◽

10.3389/fcvm.2021.787614 ◽

2021 ◽

Vol 8 ◽

Author(s):

Clint Asher ◽

Esther Puyol-Antón ◽

Maleeha Rizvi ◽

Bram Ruijsink ◽

Amedeo Chiribiri ◽

...

Keyword(s):

Artificial Intelligence ◽

Deep Learning ◽

Risk Stratification ◽

Dilated Cardiomyopathy ◽

Tissue Characterization ◽

Left Ventricular ◽

Muscle Disease ◽

Left Ventricular Ejection ◽

Ventricular Ejection Fraction ◽

Care Assessment

Dilated Cardiomyopathy is conventionally defined by left ventricular dilatation and dysfunction in the absence of coronary disease. Emerging evidence suggests many patients remain vulnerable to major adverse outcomes despite clear therapeutic success of modern evidence-based heart failure therapy. In this era of personalized medical care, the conventional assessment of left ventricular ejection fraction falls short in fully predicting evolution and risk of outcomes in this heterogenous group of heart muscle disease, as such, a more refined means of phenotyping this disease appears essential. Cardiac MRI (CMR) is well-placed in this respect, not only for its diagnostic utility, but the wealth of information captured in global and regional function assessment with the addition of unique tissue characterization across different disease states and patient cohorts. Advanced tools are needed to leverage these sensitive metrics and integrate with clinical, genetic and biochemical information for personalized, and more clinically useful characterization of the dilated cardiomyopathy phenotype. Recent advances in artificial intelligence offers the unique opportunity to impact clinical decision making through enhanced precision image-analysis tasks, multi-source extraction of relevant features and seamless integration to enhance understanding, improve diagnosis, and subsequently clinical outcomes. Focusing particularly on deep learning, a subfield of artificial intelligence, that has garnered significant interest in the imaging community, this paper reviews the main developments that could offer more robust disease characterization and risk stratification in the Dilated Cardiomyopathy phenotype. Given its promising utility in the non-invasive assessment of cardiac diseases, we firstly highlight the key applications in CMR, set to enable comprehensive quantitative measures of function beyond the standard of care assessment. Concurrently, we revisit the added value of tissue characterization techniques for risk stratification, showcasing the deep learning platforms that overcome limitations in current clinical workflows and discuss how they could be utilized to better differentiate at-risk subgroups of this phenotype. The final section of this paper is dedicated to the allied clinical applications to imaging, that incorporate artificial intelligence and have harnessed the comprehensive abundance of data from genetics and relevant clinical variables to facilitate better classification and enable enhanced risk prediction for relevant outcomes.

Download Full-text

Expert camouflage-breakers can accurately localize search targets

Cognitive Research Principles and Implications ◽

10.1186/s41235-021-00290-5 ◽

2021 ◽

Vol 6 (1) ◽

Author(s):

Fallon Branch ◽

Allison JoAnna Lewis ◽

Isabella Noel Santana ◽

Jay Hegdé

Keyword(s):

Deep Learning ◽

Visual Search ◽

Target Localization ◽

Specific Training ◽

Learning Paradigm ◽

Accuracy And Precision ◽

Per Se ◽

Special Case

AbstractCamouflage-breaking is a special case of visual search where an object of interest, or target, can be hard to distinguish from the background even when in plain view. We have previously shown that naive, non-professional subjects can be trained using a deep learning paradigm to accurately perform a camouflage-breaking task in which they report whether or not a given camouflage scene contains a target. But it remains unclear whether such expert subjects can actually detect the target in this task, or just vaguely sense that the two classes of images are somehow different, without being able to find the target per se. Here, we show that when subjects break camouflage, they can also localize the camouflaged target accurately, even though they had received no specific training in localizing the target. The localization was significantly accurate when the subjects viewed the scene as briefly as 50 ms, but more so when the subjects were able to freely view the scenes. The accuracy and precision of target localization by expert subjects in the camouflage-breaking task were statistically indistinguishable from the accuracy and precision of target localization by naive subjects during a conventional visual search where the target ‘pops out’, i.e., is readily visible to the untrained eye. Together, these results indicate that when expert camouflage-breakers detect a camouflaged target, they can also localize it accurately.

Download Full-text

Improved pulmonary lung nodules risk stratification in computed tomography images by fusing shape and texture features in a machine‐learning paradigm

International Journal of Imaging Systems and Technology ◽

10.1002/ima.22539 ◽

2020 ◽

Author(s):

Satya Prakash Sahu ◽

Narendra D. Londhe ◽

Shrish Verma ◽

Bikesh K. Singh ◽

Sumit Kumar Banchhor

Keyword(s):

Machine Learning ◽

Computed Tomography ◽

Risk Stratification ◽

Texture Features ◽

Lung Nodules ◽

Learning Paradigm ◽

Computed Tomography Images

Download Full-text

Introduction of the Grayscale Median for Ultrasound Tissue Characterization of the Transplanted Kidney

Diagnostics ◽

10.3390/diagnostics11030390 ◽

2021 ◽

Vol 11 (3) ◽

pp. 390

Author(s):

Camilo G. Sotomayor ◽

Stan Benjamens ◽

Hildebrand Dijkstra ◽

Derya Yakar ◽

Cyril Moers ◽

...

Keyword(s):

Kidney Transplant ◽

Tissue Characterization ◽

Kidney Transplant Recipients ◽

Systematic Assessment ◽

Ultrasound Tissue Characterization ◽

Adult Kidney ◽

Mersenne Twister ◽

History Of

Ultrasound examination is advised for early post-kidney transplant assessment. Grayscale median (GSM) quantification is novel in the kidney transplant field, with no systematic assessment previously reported. In this prospective cohort study, we measured the post-operative GSM in a large cohort of adult kidney transplant recipients (KTR) who consecutively underwent Doppler ultrasound directly after transplantation (within 24 h), compared it with GSM in nontransplanted patients, and investigated its association with baseline and follow-up characteristics. B-mode images were used to calculate the GSM in KTR and compared with GSM data in nontransplanted patients, as simulated from summary statistics of the literature using a Mersenne twister algorithm. The association of GSM with baseline and 1-year follow-up characteristics were studied by means of linear regression analyses. In 282 KTR (54 ± 15 years old, 60% male), the median (IQR) GSM was 55 (45–69), ranging from 22 to 124 (coefficient of variation = 7.4%), without differences by type of donation (p = 0.28). GSM in KTR was significantly higher than in nontransplanted patients (p < 0.001), and associated with systolic blood pressure, history of cardiovascular disease, and donor age (std. β = 0.12, −0.20, and 0.13, respectively; p < 0.05 for all). Higher early post-kidney transplant GSM was not associated with 1-year post-kidney transplant function parameters (e.g., measured and estimated glomerular filtration rate). The data provided in this study could be used as first step for further research on the application of early postoperative ultrasound in KTR.

Download Full-text