Exploring Generalization Capacity of Artificial Neural Network for Myelin Water Imaging

Purpose@#To understand the effects of datasets with various parameters on pretrained network performance, the generalization capacity of the artificial neural network for myelin water imaging (ANN-MWI) is explored by testing datasets with various scan protocols (i.e., resolution and refocusing RF pulse shape) and types of disorders (i.e., neuromyelitis optica and edema). @*Materials and Methods@#ANN-MWI was trained to generate a T2 distribution, from which the myelin water fraction value was measured. The training and test datasets were acquired from healthy controls and multiple sclerosis patients using a multiecho gradient and spin-echo sequence with the same scan protocols. To test the generalization capacity of ANN-MWI, datasets with different settings were utilized.The datasets were acquired or generated with different resolutions, refocusing pulse shape, and types of disorders. For all datasets, the evaluation was performed in a white matter mask by calculating the normalized root-mean-squared error (NRMSE) between the results from the conventional method and ANN-MWI. Additionally, for the patient datasets, the NRMSE was calculated in each lesion mask. @*Results@#The results of ANN-MWI showed high reliability in generating myelin water fraction maps from the datasets with different resolutions. However, the increased errors were reported for the datasets with different refocusing pulse shapes and disorder types. Specifically, the region of lesions in edema patients reported high NRMSEs. These increased errors indicate the dependency of ANN-MWI on refocusing pulse flip angles and T 2 characteristics. @*Conclusion@#This study proposes information about the generalization accuracy of a trained network when applying deep learning to processing myelin water imaging.

Exploring Generalization Capacity of Artificial Neural Network for Myelin Water Imaging

Purpose@#To understand the effects of datasets with various parameters on pretrained network performance, the generalization capacity of the artificial neural network for myelin water imaging (ANN-MWI) is explored by testing datasets with various scan protocols (i.e., resolution and refocusing RF pulse shape) and types of disorders (i.e., neuromyelitis optica and edema). @*Materials and Methods@#ANN-MWI was trained to generate a T2 distribution, from which the myelin water fraction value was measured. The training and test datasets were acquired from healthy controls and multiple sclerosis patients using a multiecho gradient and spin-echo sequence with the same scan protocols. To test the generalization capacity of ANN-MWI, datasets with different settings were utilized.The datasets were acquired or generated with different resolutions, refocusing pulse shape, and types of disorders. For all datasets, the evaluation was performed in a white matter mask by calculating the normalized root-mean-squared error (NRMSE) between the results from the conventional method and ANN-MWI. Additionally, for the patient datasets, the NRMSE was calculated in each lesion mask. @*Results@#The results of ANN-MWI showed high reliability in generating myelin water fraction maps from the datasets with different resolutions. However, the increased errors were reported for the datasets with different refocusing pulse shapes and disorder types. Specifically, the region of lesions in edema patients reported high NRMSEs. These increased errors indicate the dependency of ANN-MWI on refocusing pulse flip angles and T 2 characteristics. @*Conclusion@#This study proposes information about the generalization accuracy of a trained network when applying deep learning to processing myelin water imaging.

Osteoporosis Risk Prediction for Bone Mineral Density Assessment of Postmenopausal Women Using Machine Learning

PURPOSE: A number of clinical decision tools for osteoporosis risk assessment have been developed to select postmenopausal women for the measurement of bone mineral density. We developed and validated machine learning models with the aim of more accurately identifying the risk of osteoporosis in postmenopausal women compared to the ability of conventional clinical decision tools. MATERIALS AND METHODS: We collected medical records from Korean postmenopausal women based on the Korea National Health and Nutrition Examination Surveys. The training data set was used to construct models based on popular machine learning algorithms such as support vector machines (SVM), random forests, artificial neural networks (ANN), and logistic regression (LR) based on simple surveys. The machine learning models were compared to four conventional clinical decision tools: osteoporosis self-assessment tool (OST), osteoporosis risk assessment instrument (ORAI), simple calculated osteoporosis risk estimation (SCORE), and osteoporosis index of risk (OSIRIS). RESULTS: SVM had significantly better area under the curve (AUC) of the receiver operating characteristic than ANN, LR, OST, ORAI, SCORE, and OSIRIS for the training set. SVM predicted osteoporosis risk with an AUC of 0.827, accuracy of 76.7%, sensitivity of 77.8%, and specificity of 76.0% at total hip, femoral neck, or lumbar spine for the testing set. The significant factors selected by SVM were age, height, weight, body mass index, duration of menopause, duration of breast feeding, estrogen therapy, hyperlipidemia, hypertension, osteoarthritis, and diabetes mellitus. CONCLUSION: Considering various predictors associated with low bone density, the machine learning methods may be effective tools for identifying postmenopausal women at high risk for osteoporosis.

Development of a New Index for Mortality Prediction Due to Hemorrhagic Shock using Lactate Concentration and Perfusion in S-D Rats

PURPOSE: We proposed a new index for predicting death resulting from hemorrhagic shock, which was calculated by dividing measured lactate concentration by perfusion. METHODS: Using 24 Sprague-Dawley (S-D) rats, we induced uncontrolled hemorrhage and then measured blood lactate concentration and perfusion in addition to vital signs such as heart rate, blood pressure, respiration rate and temperature. Perfusion and lactate concentration were measured by laser Doppler flowmetry and a lactate concentration meter, respectively. We collected the data for 15 min, which consisted of 3 intervals after homeostasis, and thus obtained a new index. RESULTS: The proposed index revealed an earlier death prediction than lactate concentration alone with the same timing as perfusion. The new index showed generally better sensitivity, specificity and accuracy than lactate concentration and perfusion. Using a receiver operating characteristic curve method, the mortality prediction with the proposed index resulted in a sensitivity of 98.0%, specificity of 90.0%, and accuracy of 93.7%. The mortality prediction with the proposed index resulted in a sensitivity of 98.0%, specificity of 90.0% and accuracy of 93.7%. CONCLUSION: This index could provide physicians, in emergency situations, with early and accurate mortality predictions for cases of human hemorrhagic shock.

Development of a New Index for Mortality Prediction Due to Hemorrhagic Shock using Lactate Concentration and Perfusion in S-D Rats

PURPOSE: We proposed a new index for predicting death resulting from hemorrhagic shock, which was calculated by dividing measured lactate concentration by perfusion. METHODS: Using 24 Sprague-Dawley (S-D) rats, we induced uncontrolled hemorrhage and then measured blood lactate concentration and perfusion in addition to vital signs such as heart rate, blood pressure, respiration rate and temperature. Perfusion and lactate concentration were measured by laser Doppler flowmetry and a lactate concentration meter, respectively. We collected the data for 15 min, which consisted of 3 intervals after homeostasis, and thus obtained a new index. RESULTS: The proposed index revealed an earlier death prediction than lactate concentration alone with the same timing as perfusion. The new index showed generally better sensitivity, specificity and accuracy than lactate concentration and perfusion. Using a receiver operating characteristic curve method, the mortality prediction with the proposed index resulted in a sensitivity of 98.0%, specificity of 90.0%, and accuracy of 93.7%. The mortality prediction with the proposed index resulted in a sensitivity of 98.0%, specificity of 90.0% and accuracy of 93.7%. CONCLUSION: This index could provide physicians, in emergency situations, with early and accurate mortality predictions for cases of human hemorrhagic shock.