In IEEE journal of biomedical and health informatics

Serra Ginalber L O, Gomes Daiana Caroline Dos Santos

2021-Jan-15

In Journal of magnetic resonance imaging : JMRI

BACKGROUND : Axonal loss denervates muscle, leading to an increase of fat accumulation in the muscle. Therefore, fat fraction (FF) in whole limb muscle using MRI has emerged as a monitoring biomarker for axonal loss in patients with peripheral neuropathies. In this study, we are testing whether deep learning-based model can automate quantification of the FF in individual muscles. While individual muscle is smaller with irregular shape, manually segmented muscle MRI images have been accumulated in this lab; and make the deep learning feasible.

PURPOSE : To automate segmentation on muscle MRI images through deep learning for quantifying individual muscle FF in patients with peripheral neuropathies.

STUDY TYPE : Retrospective.

SUBJECTS : 24 patients and 19 healthy controls.

FIELD STRENGTH/SEQUENCES : 3T; Interleaved 3D GRE.

ASSESSMENT : A 3D U-Net model was implemented in segmenting muscle MRI images. This was enabled by leveraging a large set of manually segmented muscle MRI images. B₁⁺ and B₁^- maps were used to correct image inhomogeneity. Accuracy of the automation was evaluated using Pixel Accuracy (PA), Dice Coefficient (DC) in binary masks; and Bland-Altman and Pearson correlation by comparing FF values between manual and automated methods.

STATISTICAL TESTS : PA and DC were reported with their median value and standard deviation. Two methods were compared using the ± 95% confidence intervals (CI) of Bland-Altman analysis and the Pearson's coefficient (r² ).

RESULTS : DC values were from 0.83 ± 0.17 to 0.98 ± 0.02 in thigh and from 0.63 ± 0.18 to 0.96 ± 0.02 in calf muscles. For FF values, the overall ± 95% CI and r² were [0.49, -0.56] and 0.989 in thigh and [0.84, -0.71] and 0.971 in the calf.

DATA CONCLUSION : Automated results well agreed with the manual results in quantifying FF for individual muscles. This method mitigates the formidable time consumption and intense labor in manual segmentations; and enables the use of individual muscle FF as outcome measures in upcoming longitudinal studies.

LEVEL OF EVIDENCE : 3 TECHNICAL EFFICACY STAGE: 1.

Chen Yongsheng, Moiseev Daniel, Kong Wan Yee, Bezanovski Alexandar, Li Jun

2021-Jan-14

Dixon magnetic resonance imaging, axonal loss, convolutional neural network, fat fraction, muscle, peripheral neuropathy

In Drug delivery and translational research

Sharma Richa, Singh Dhirendra, Gaur Prerna, Joshi Deepak

2021-Jan-14

Biological systems, Cancer treatment, Cardiac ailments, Closed-loop control, Control system, Drug delivery, GI tract, Insulin therapy, Neurological disorders

In European radiology ; h5-index 62.0

OBJECTIVE : To investigate the application of machine learning-based ultrasound radiomics in preoperative classification of primary and metastatic liver cancer.

METHODS : Data of 114 consecutive histopathologically confirmed patients with liver cancer from January 2018 to November 2019 were retrospectively analyzed. All patients underwent liver ultrasonography within 1 week before hepatectomy or fine-needle biopsy. The liver lesions were manually segmented by two experts using ITK-SNAP software. Seven categories of radiomics features, including first-order, two-dimensional shape, gray-level co-occurrence matrices, gray-level run-length matrix, gray-level size-zone matrix, neighboring gray tone difference matrix, and gray-level dependence matrix, were extracted on the Pyradiomics platform. Fourteen filters were applied to the original images, and derived images were obtained. Then, the dimensions of radiomics features were reduced by least absolute shrinkage and selection operator (Lasso) method. Finally, k-nearest neighbor (KNN), logistic regression (LR), multilayer perceptron (MLP), random forest (RF), and support vector machine (SVM) were employed to distinguish primary liver cancer from metastatic liver cancer by a fivefold cross-validation strategy. The performance of the established model was mainly evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and accuracy.

RESULTS : One thousand four hundred nine radiomics features were extracted from the original images and/or derived images for each patient. The mentioned five machine learning classifiers were able to differentiate primary liver cancer from metastatic liver cancer. LR outperformed other classifiers, with the accuracy of 0.843 ± 0.078 (AUC, 0.816 ± 0.088; sensitivity, 0.768 ± 0.232; specificity, 0.880 ± 0.117).

CONCLUSIONS : Machine learning-based ultrasound radiomics features are able to non-invasively distinguish primary liver tumors from metastatic liver tumors.

KEY POINTS : • Ultrasound-based radiomics was initially used for preoperative classification of primary versus metastatic liver cancer. • Multiple machine learning-based algorithms with cross-validation strategy were applied to extract machine learning-based ultrasound radiomics features. • Distinction between primary and metastatic tumors was obtained with a sensitivity of 0.768 and a specificity of 0.880.

Mao Bing, Ma Jingdong, Duan Shaobo, Xia Yuwei, Tao Yaru, Zhang Lianzhong

2021-Jan-14

Liver neoplasms, Machine learning, Radiomics, Ultrasonography

In Journal of the American Medical Informatics Association : JAMIA

Petersen Carolyn, Smith Jeffery, Freimuth Robert R, Goodman Kenneth W, Jackson Gretchen Purcell, Kannry Joseph, Liu Hongfang, Madhavan Subha, Madhavan Subha, Sittig Dean F, Wright Adam

2021-Jan-15

artificial intelligence, clinical decision support, health policy, machine learning, software as a medical device

In International Journal of Cardiology. Hypertension

Background : Artificial intelligence (AI) promises to provide useful information to clinicians specializing in hypertension. Already, there are some significant AI applications on large validated data sets.

Methods and results : This review presents the use of AI to predict clinical outcomes in big data i.e. data with high volume, variety, veracity, velocity and value. Four examples are included in this review. In the first example, deep learning and support vector machine (SVM) predicted the occurrence of cardiovascular events with 56%-57% accuracy. In the second example, in a data base of 378,256 patients, a neural network algorithm predicted the occurrence of cardiovascular events during 10 year follow up with sensitivity (68%) and specificity (71%). In the third example, a machine learning algorithm classified 1,504,437 patients on the presence or absence of hypertension with 51% sensitivity, 99% specificity and area under the curve 87%. In example four, wearable biosensors and portable devices were used in assessing a person's risk of developing hypertension using photoplethysmography to separate persons who were at risk of developing hypertension with sensitivity higher than 80% and positive predictive value higher than 90%. The results of the above studies were adjusted for demographics and the traditional risk factors for atherosclerotic disease.

Conclusion : These examples describe the use of artificial intelligence methods in the field of hypertension.

Amaratunga Dhammika, Cabrera Javier, Sargsyan Davit, Kostis John B, Zinonos Stavros, Kostis William J

2020-Jun

AMI, Acute Myocardial Infarction, CART, Classification and Regression Trees, CNN, Convolution Neural Net, CS/E, Computer Sciences/Engineering, DBP, Diastolic Blood Pressure, Deep neural networks, Disease management, EHR, Electronic Health Record, HF, Heart Failure, Hypertension, ICD, International Classification of Diseases, MIDAS, Myocardial Infarction Data Acquisition System, Machine learning, NPV, Negative Predictive Value, PDN, Personalized Disease Network, PPG, photoplethysmography, PPV, Positive Predictive Value, Personalized disease network, SBP, Systolic Blood Pressure, SVM, Support Vector Machine