Dataset Information

Machine Learning for Diagnosis of Hematologic Diseases in Magnetic Resonance Imaging of Lumbar Spines.

ABSTRACT: We aimed to assess feasibility of a support vector machine (SVM) texture classifier to discriminate pathologic infiltration patterns from the normal bone marrows in MRI. This retrospective study included 467 cases, which were split into a training (n = 360) and a test set (n = 107). A sagittal T1-weighted lumbar spinal MR image was normalized by an intervertebral disk, and bone marrows were segmented. The various kernel functions and SVM input dimensions were experimented to construct the most optimal classifier model. The accuracy and sensitivity increased as the number of training set sizes increased from 180 to 360. The test set was analyzed by SVM and two independent readers, and the accuracy and sensitivity of the SVM classifier, reader 1 and reader 2 were 82.2% and 85.5%, 79.4% and 82.3%, and 82.2% and 83.9%, respectively. The area under receiver operating characteristic curve (AUC) of the SVM classifier, reader 1 and reader 2 were 0.895, 0.879 and 0.880, respectively. The SVM texture classifier produced comparable performance to radiologists in isolating the hematologic diseases, which could support inexperienced physicians with spinal MRI to screen patients with marrow diseases, who need further diagnostic work-ups to make final decisions.

SUBMITTER: Hwang EJ

PROVIDER: S-EPMC6465258 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning for Diagnosis of Hematologic Diseases in Magnetic Resonance Imaging of Lumbar Spines.

Hwang Eo-Jin EJ Jung Joon-Yong JY Lee Seul Ki SK Lee Sung-Eun SE Jee Won-Hee WH

Scientific reports 20190415 1

We aimed to assess feasibility of a support vector machine (SVM) texture classifier to discriminate pathologic infiltration patterns from the normal bone marrows in MRI. This retrospective study included 467 cases, which were split into a training (n = 360) and a test set (n = 107). A sagittal T1-weighted lumbar spinal MR image was normalized by an intervertebral disk, and bone marrows were segmented. The various kernel functions and SVM input dimensions were experimented to construct the most o ...[more]

PMID: 30988360

Similar Datasets

Project description:PurposeThis study aimed to develop machine learning models for the diagnosis of Parkinson's disease (PD) using multiple structural magnetic resonance imaging (MRI) features and validate their performance.MethodsBrain structural MRI scans of 60 patients with PD and 56 normal controls (NCs) were enrolled as development dataset and 69 patients with PD and 71 NCs from Parkinson's Progression Markers Initiative (PPMI) dataset as independent test dataset. First, multiple structural MRI features were extracted from cerebellar, subcortical, and cortical regions of the brain. Then, the Pearson's correlation test and least absolute shrinkage and selection operator (LASSO) regression were used to select the most discriminating features. Finally, using logistic regression (LR) classifier with the 5-fold cross-validation scheme in the development dataset, the cerebellar, subcortical, cortical, and a combined model based on all features were constructed separately. The diagnostic performance and clinical net benefit of each model were evaluated with the receiver operating characteristic (ROC) analysis and the decision curve analysis (DCA) in both datasets.ResultsAfter feature selection, 5 cerebellar (absolute value of left lobule crus II cortical thickness (CT) and right lobule IV volume, relative value of right lobule VIIIA CT and lobule VI/VIIIA gray matter volume), 3 subcortical (asymmetry index of caudate volume, relative value of left caudate volume, and absolute value of right lateral ventricle), and 4 cortical features (local gyrification index of right anterior circular insular sulcus and anterior agranular insula complex, local fractal dimension of right middle insular area, and CT of left supplementary and cingulate eye field) were selected as the most distinguishing features. The area under the curve (AUC) values of the cerebellar, subcortical, cortical, and combined models were 0.679, 0.555, 0.767, and 0.781, respectively, for the development dataset and 0.646, 0.632, 0.690, and 0.756, respectively, for the independent test dataset, respectively. The combined model showed higher performance than the other models (Delong's test, all p-values < 0.05). All models showed good calibration, and the DCA demonstrated that the combined model has a higher net benefit than other models.ConclusionThe combined model showed favorable diagnostic performance and clinical net benefit and had the potential to be used as a non-invasive method for the diagnosis of PD.

Project description:BackgroundThe effect of diagnosing Graves' ophthalmopathy (GO) through traditional measurement and observation in medical imaging is not ideal. This study aimed to develop and validate deep learning (DL) models that could be applied to the diagnosis of GO based on magnetic resonance imaging (MRI) and compare them to traditional measurement and judgment of radiologists.MethodsA total of 199 clinically verified consecutive GO patients and 145 normal controls undergoing MRI were retrospectively recruited, of whom 240 were randomly assigned to the training group and 104 to the validation group. Areas of superior, inferior, medial, and lateral rectus muscles and all rectus muscles on coronal planes were calculated respectively. Logistic regression models based on areas of extraocular muscles were built to diagnose GO. The DL models named ResNet101 and Swin Transformer with T1-weighted MRI without contrast as input were used to diagnose GO and the results were compared to the radiologist's diagnosis only relying on MRI T1-weighted scans.ResultsAreas on the coronal plane of each muscle in the GO group were significantly greater than those in the normal group. In the validation group, the areas under the curve (AUCs) of logistic regression models by superior, inferior, medial, and lateral rectus muscles and all muscles were 0.897 [95% confidence interval (CI): 0.833-0.949], 0.705 (95% CI: 0.598-0.804), 0.799 (95% CI: 0.712-0.876), 0.681 (95% CI: 0.567-0.776), and 0.905 (95% CI: 0.843-0.955). ResNet101 and Swin Transformer achieved AUCs of 0.986 (95% CI: 0.977-0.994) and 0.936 (95% CI: 0.912-0.957), respectively. The accuracy, sensitivity, and specificity of ResNet101 were 0.933, 0.979, and 0.869, respectively. The accuracy, sensitivity, and specificity of Swin Transformer were 0.851, 0.817, and 0.898, respectively. The ResNet101 model yielded higher AUC than models of all muscles and radiologists (0.986 vs. 0.905, 0.818; P<0.001).ConclusionsThe DL models based on MRI T1-weighted scans could accurately diagnose GO, and the application of DL systems in MRI may improve radiologists' performance in diagnosing GO and early detection.

Dataset Information

Machine Learning for Diagnosis of Hematologic Diseases in Magnetic Resonance Imaging of Lumbar Spines.

Publications

Machine Learning for Diagnosis of Hematologic Diseases in Magnetic Resonance Imaging of Lumbar Spines.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets