Integration of Cine-cardiac Magnetic Resonance Radiomics and Machine Learning for Differentiating Ischemic and Dilated Cardiomyopathy.

RATIONALE AND OBJECTIVES: This study aims to evaluate the capability of machine learning algorithms in utilizing radiomic features extracted from cine-cardiac magnetic resonance (CMR) sequences for differentiating between ischemic cardiomyopathy (ICM) and dilated cardiomyopathy (DCM). MATERIALS AND METHODS: This retrospective study included 115 cardiomyopathy patients subdivided into ICM (n = 64) and DCM cohorts (n = 51). We collected invasive clinical (IC), noninvasive clinical (NIC), and combined clinical (CC) feature subsets. Radiomic features were extracted from regions of interest (ROIs) in the left ventricle (LV), LV cavity (LVC), and myocardium (MYO). We tested 10 classical machine learning classifiers and validated them through fivefold cross-validation. We compared the efficacy of clinical feature-based models and radiomics-based models to identify the superior diagnostic approach. RESULTS: In the validation set, the Gaussian naive Bayes (GNB) model outperformed the other models in all categories, with areas under the curve (AUCs) of 0.879 for IC_GNB, 0.906 for NIC_GNB, and 0.906 for CC_GNB. Among the radiomics models, the MYO_LASSOCV_MLP model demonstrated the highest AUC (0.919). In the test set, the MYO_RFECV_GNB radiomics model achieved the highest AUC (0.857), surpassing the performance of the three clinical feature models (IC_GNB: 0.732; NIC_GNB: 0.75; CC_GNB: 0.786). CONCLUSION: Radiomics models leveraging MYO images from cine-CMR exhibit promising potential for differentiating ICM from DCM, indicating the significant clinical application scope of such models. CLINICAL RELEVANCE STATEMENT: The integration of radiomics models and machine learning methods utilizing cine-CMR sequences enhances the diagnostic capability to distinguish between ICM and DCM, minimizes examination risks for patients, and potentially reduces the duration of medical imaging procedures.

Deep learning-based 3D cerebrovascular segmentation workflow on bright and black blood sequences magnetic resonance angiography.

BACKGROUND: Cerebrovascular diseases have emerged as significant threats to human life and health. Effectively segmenting brain blood vessels has become a crucial scientific challenge. We aimed to develop a fully automated deep learning workflow that achieves accurate 3D segmentation of cerebral blood vessels by incorporating classic convolutional neural networks (CNNs) and transformer models. METHODS: We used a public cerebrovascular segmentation dataset (CSD) containing 45 volumes of 1.5 T time-of-flight magnetic resonance angiography images. We collected data from another private middle cerebral artery (MCA) with lenticulostriate artery (LSA) segmentation dataset (MLD), which encompassed 3.0 T three-dimensional T1-weighted sequences of volumetric isotropic turbo spin echo acquisition MRI images of 107 patients aged 62 ± 11 years (42 females). The workflow includes data analysis, preprocessing, augmentation, model training with validation, and postprocessing techniques. Brain vessels were segmented using the U-Net, V-Net, UNETR, and SwinUNETR models. The model performances were evaluated using the dice similarity coefficient (DSC), average surface distance (ASD), precision (PRE), sensitivity (SEN), and specificity (SPE). RESULTS: During 4-fold cross-validation, SwinUNETR obtained the highest DSC in each fold. On the CSD test set, SwinUNETR achieved the best DSC (0.853), PRE (0.848), SEN (0.860), and SPE (0.9996), while V-Net achieved the best ASD (0.99). On the MLD test set, SwinUNETR demonstrated good MCA segmentation performance and had the best DSC, ASD, PRE, and SPE for segmenting the LSA. CONCLUSIONS: The workflow demonstrated excellent performance on different sequences of MRI images for vessels of varying sizes. This method allows doctors to visualize cerebrovascular structures. CRITICAL RELEVANCE STATEMENT: A deep learning-based 3D cerebrovascular segmentation workflow is feasible and promising for visualizing cerebrovascular structures and monitoring cerebral small vessels, such as lenticulostriate arteries. KEY POINTS: • The proposed deep learning-based workflow performs well in cerebrovascular segmentation tasks. • Among comparison models, SwinUNETR achieved the best DSC, ASD, PRE, and SPE values in lenticulostriate artery segmentation. • The proposed workflow can be used for different MR sequences, such as bright and black blood imaging.

Correlation Between Cognitive Impairment and Lenticulostriate Arteries: A Clinical and Radiomics Analysis.

Lenticulostriate arteries (LSA) are potentially valuable for studying vascular cognitive impairment. This study aims to investigate correlations between cognitive impairment and LSA through clinical and radiomics features analysis. We retrospectively included 102 patients (mean age 62.5±10.3 years, 60 males), including 58 with mild cognitive impairment (MCI) and 44 with moderate or severe cognitive impairment (MSCI). The MRI images of these patients were subjected to z-score preprocessing, manual regions of interest (ROI) outlining, feature extraction (pyradiomics), feature selection [max-relevance and min-redundancy (mRMR), least absolute shrinkage and selection operator (LASSO), and univariate analysis], model construction (multivariate logistic regression), and evaluation [receiver operating characteristic curve (ROC), decision curve analysis (DCA), and calibration curves (CC)]. In the training dataset (71 patients, 44 MCI) and the test dataset (31 patients, 17 MCI), the area under curve (AUC) of the combined model (training 0.88 [95% CI 0.78, 0.97], test 0.76 [95% CI 0.6, 0.93]) was better than that of the clinical model and the radiomics model. The DCA results demonstrated the highest net yield of the combined model relative to the clinical and radiomics models. In addition, we found that LSA total vessel count (0.79 [95% CI 0.08, 1.59], P = 0.038) and wavelet.HLH_glcm_MCC (-1.2 [95% CI -2.2, -0.4], P = 0.008) were independent predictors of MCI. The model that combines clinical and radiomics features of LSA can predict MCI. Besides, LSA vascular parameters may serve as imaging biomarkers of cognitive impairment.

Utility of deep learning for the diagnosis of cochlear malformation on temporal bone CT.

OBJECTIVE: Diagnosis of cochlear malformation on temporal bone CT images is often difficult. Our aim was to assess the utility of deep learning analysis in diagnosing cochlear malformation on temporal bone CT images. METHODS: A total of 654 images from 165 temporal bone CTs were divided into the training set (n = 534) and the testing set (n = 120). A target region that includes the area of the cochlear was extracted to create a diagnostic model. 4 models were used: ResNet10, ResNet50, SE-ResNet50, and DenseNet121. The testing data set was subsequently analyzed using these models and by 4 doctors. RESULTS: The areas under the curve was 0.91, 0.94, 0.93, and 0.73 in ResNet10, ResNet50, SE-ResNet50, and DenseNet121. The accuracy of ResNet10, ResNet50, and SE-ResNet50 is better than chief physician. CONCLUSIONS: Deep learning technique implied a promising prospect for clinical application of artificial intelligence in the diagnosis of cochlear malformation based on CT images.

Automatic multi-label temporal bone computed tomography segmentation with deep learning.

BACKGROUND: Manually segmenting temporal bone computed tomography (CT) images is difficult. Despite accurate automatic segmentation in previous studies using deep learning, they did not consider clinical differences, such as variations in CT scanners. Such differences can significantly affect the accuracy of segmentation. METHODS: Our dataset included 147 scans from three different scanners, and we used Res U-Net, SegResNet, and UNETR neural networks to segment four structures: the ossicular chain (OC), internal auditory canal (IAC), facial nerve (FN), and labyrinth (LA). RESULTS: The experimental results yielded high mean Dice similarity coefficients of 0.8121, 0.8809, 0.6858, 0.9329, and a low mean of 95% Hausdorff distances of 0.1431 mm, 0.1518 mm, 0.2550 mm, and 0.0640 mm for OC, IAC, FN, and LA, respectively. CONCLUSIONS: This study shows that automated deep learning-based segmentation techniques successfully segment temporal bone structures using CT data from different scanners. Our research can further promote its clinical application.

Application of UNETR for automatic cochlear segmentation in temporal bone CTs.

OBJECTIVE: To investigate the feasibility of a deep learning method based on a UNETR model for fully automatic segmentation of the cochlea in temporal bone CT images. METHODS: The normal temporal bone CTs of 77 patients were used in 3D U-Net and UNETR model automatic cochlear segmentation. Tests were performed on two types of CT datasets and cochlear deformity datasets. RESULTS: Through training the UNETR model, when batch_size=1, the Dice coefficient of the normal cochlear test set was 0.92, which was higher than that of the 3D U-Net model; on the GE 256 CT, SE-DS CT and Cochlear Deformity CT dataset tests, the Dice coefficients were 0.91, 0.93, 0 93, respectively. CONCLUSION: According to the anatomical characteristics of the temporal bone, the use of the UNETR model can achieve fully automatic segmentation of the cochlea and obtain an accuracy close to manual segmentation. This method is feasible and has high accuracy.