HE-Mind: A model for automatically predicting hematoma expansion after spontaneous intracerebral hemorrhage.

PURPOSE: To develop and validate an end-to-end model for automatically predicting hematoma expansion (HE) after spontaneous intracerebral hemorrhage (sICH) using a novel deep learning framework. METHODS: This multicenter retrospective study collected cranial noncontrast computed tomography (NCCT) images of 490 patients with sICH at admission for model training (n = 236), internal testing (n = 60), and external testing (n = 194). A HE-Mind model was designed to predict HE, which consists of a densely connected U-net for segmentation process, a multi-instance learning strategy for resolving label ambiguity and a Siamese network for classification process. Two radiomics models based on support vector machine or logistic regression and two deep learning models based on residual network or Swin transformer were developed for performance comparison. Reader experiments including physician diagnosis mode and artificial intelligence mode were conducted for efficiency comparison. RESULTS: The HE-Mind model showed better performance compared to the comparative models in predicting HE, with areas under the curve of 0.849 and 0.809 in the internal and external test sets respectively. With the assistance of the HE-Mind model, the predictive accuracy and work efficiency of the emergency physician, junior radiologist, and senior radiologist were significantly improved, with accuracies of 0.768, 0.789, and 0.809 respectively, and reporting times of 7.26 s, 5.08 s, and 3.99 s respectively. CONCLUSIONS: The HE-Mind model could rapidly and automatically process the NCCT data and predict HE after sICH within three seconds, indicating its potential to assist physicians in the clinical diagnosis workflow of HE.

A machine learning approach to predicting vascular calcification risk of type 2 diabetes: A retrospective study.

BACKGROUND: Recently, patients with type 2 diabetes mellitus (T2DM) have experienced a higher incidence and severer degree of vascular calcification (VC), which leads to an increase in the incidence and mortality of vascular complications in patients with T2DM. HYPOTHESIS: To construct and validate prediction models for the risk of VC in patients with T2DM. METHODS: Twenty-three baseline demographic and clinical characteristics were extracted from the electronic medical record system. Ten clinical features were screened with least absolute shrinkage and selection operator method and were used to develop prediction models based on eight machine learning (ML) algorithms (k-nearest neighbor [k-NN], light gradient boosting machine, logistic regression [LR], multilayer perception [(MLP], Naive Bayes [NB], random forest [RF], support vector machine [SVM], XGBoost [XGB]). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, and precision. RESULTS: A total of 1407 and 352 patients were retrospectively collected in the training and test sets, respectively. Among the eight models, the AUC value in the NB model was higher than the other models (NB: 0.753, LGB: 0.719, LR: 0.749, MLP: 0.715, RF: 0.722, SVM: 0.689, XGB:0.707, p < .05 for all). The k-NN model achieved the highest sensitivity of 0.75 (95% confidence interval [CI]: 0.633-0.857), the MLP model achieved the highest accuracy of 0.81 (95% CI: 0.767-0.852) and specificity of 0.875 (95% CI: 0.836-0.912). CONCLUSIONS: This study developed a predictive model of VC based on ML and clinical features in type 2 diabetic patients. The NB model is a tool with potential to facilitate clinicians in identifying VC in high-risk patients.

Identifying Pathological Subtypes of Brain Metastasis from Lung Cancer Using MRI-Based Deep Learning Approach: A Multicenter Study.

The aim of this study was to investigate the feasibility of deep learning (DL) based on multiparametric MRI to differentiate the pathological subtypes of brain metastasis (BM) in lung cancer patients. This retrospective analysis collected 246 patients (456 BMs) from five medical centers from July 2016 to June 2022. The BMs were from small-cell lung cancer (SCLC, n = 230) and non-small-cell lung cancer (NSCLC, n = 226; 119 adenocarcinoma and 107 squamous cell carcinoma). Patients from four medical centers were assigned to training set and internal validation set with a ratio of 4:1, and we selected another medical center as an external test set. An attention-guided residual fusion network (ARFN) model for T1WI, T2WI, T2-FLAIR, DWI, and contrast-enhanced T1WI based on the ResNet-18 basic network was developed. The area under the receiver operating characteristic curve (AUC) was used to assess the classification performance. Compared with models based on five single-sequence and other combinations, a multiparametric MRI model based on five sequences had higher specificity in distinguishing BMs from different types of lung cancer. In the internal validation and external test sets, AUCs of the model for the classification of SCLC and NSCLC brain metastasis were 0.796 and 0.751, respectively; in terms of differentiating adenocarcinoma from squamous cell carcinoma BMs, the AUC values of the prediction models combining the five sequences were 0.771 and 0.738, respectively. DL together with multiparametric MRI has discriminatory feasibility in identifying pathology type of BM from lung cancer.

A deep learning model integrating multisequence MRI to predict EGFR mutation subtype in brain metastases from non-small cell lung cancer.

BACKGROUND: To establish a predictive model based on multisequence magnetic resonance imaging (MRI) using deep learning to identify wild-type (WT) epidermal growth factor receptor (EGFR), EGFR exon 19 deletion (19Del), and EGFR exon 21-point mutation (21L858R) simultaneously. METHODS: A total of 399 patients with proven brain metastases of non-small cell lung cancer (NSCLC) were retrospectively enrolled and divided into training (n = 306) and testing (n = 93) cohorts separately based on two timepoints. All patients underwent 3.0-T brain MRI including T2-weighted, T2-weighted fluid-attenuated inversion recovery, diffusion-weighted imaging, and contrast-enhanced T1-weighted sequences. Radiomics features were extracted from each lesion based on four sequences. An algorithm combining radiomics approach with graph convolutional networks architecture (Radio-GCN) was designed for the prediction of EGFR mutation status and subtype. The area under the curve (AUC) at receiver operating characteristic analysis was used to evaluate the predication capabilities of each model. RESULTS: We extracted 1,290 radiomics features from each MRI sequence. The AUCs of the Radio-GCN model for identifying EGFR 19Del, 21L858R, and WT for the lesion-wise analysis were 0.996 ± 0.004, 0.971 ± 0.013, and 1.000 ± 0.000 on the independent testing cohort separately. It also yielded AUCs of 1.000 ± 0.000, 0.991 ± 0.009, and 1.000 ± 0.000 for predicting EGFR mutations respectively for the patient-wise analysis. The κ coefficients were 0.735 and 0.812, respectively. CONCLUSIONS: The constructed Radio-GCN model is a new potential tool to predict the EGFR mutation status and subtype in NSCLC patients with brain metastases. RELEVANCE STATEMENT: The study demonstrated that a deep learning approach based on multisequence MRI can help to predict the EGFR mutation status in NSCLC patients with brain metastases, which is beneficial to guide a personalized treatment. KEY POINTS: • This is the first study to predict the EGFR mutation subtype simultaneously. • The Radio-GCN model holds the potential to be used as a diagnostic tool. • This study provides an imaging surrogate for identifying the EGFR mutation subtype.

A weakly supervised deep learning model integrating noncontrasted computed tomography images and clinical factors facilitates haemorrhagic transformation prediction after intravenous thrombolysis in acute ischaemic stroke patients.

BACKGROUND: Haemorrhage transformation (HT) is a serious complication of intravenous thrombolysis (IVT) in acute ischaemic stroke (AIS). Accurate and timely prediction of the risk of HT before IVT may change the treatment decision and improve clinical prognosis. We aimed to develop a deep learning method for predicting HT after IVT for AIS using noncontrast computed tomography (NCCT) images. METHODS: We retrospectively collected data from 828 AIS patients undergoing recombinant tissue plasminogen activator (rt-PA) treatment within a 4.5-h time window (n = 665) or of undergoing urokinase treatment within a 6-h time window (n = 163) and divided them into the HT group (n = 69) and non-HT group (n = 759). HT was defined based on the criteria of the European Cooperative Acute Stroke Study-II trial. To address the problems of indiscernible features and imbalanced data, a weakly supervised deep learning (WSDL) model for HT prediction was constructed based on multiple instance learning and active learning using admission NCCT images and clinical information in addition to conventional deep learning models. Threefold cross-validation and transfer learning were performed to confirm the robustness of the network. Of note, the predictive value of the commonly used scales in clinics associated with NCCT images (i.e., the HAT and SEDAN score) was also analysed and compared to measure the feasibility of our proposed DL algorithms. RESULTS: Compared to the conventional DL and ML models, the WSDL model had the highest AUC of 0.799 (95% CI 0.712-0.883). Significant differences were observed between the WSDL model and five ML models (P < 0.05). The prediction performance of the WSDL model outperforms the HAT and SEDAN scores at the optimal operating point (threshold = 1.5). Further subgroup analysis showed that the WSDL model performed better for symptomatic intracranial haemorrhage (AUC = 0.833, F1 score = 0.909). CONCLUSIONS: Our WSDL model based on NCCT images had relatively good performance for predicting HT in AIS and may be suitable for assisting in clinical treatment decision-making.

Non-contrast CT radiomics and machine learning for outcomes prediction of patients with acute ischemic stroke receiving conventional treatment.

PURPOSE: Accurate prediction of outcomes for patients with acute ischemic stroke (AIS) is crucial for clinical decision-making. In this study, we developed prediction models based on non-contrast computed tomography (NCCT) radiomics and clinical features to predict the modified Rankin Scale (mRS) six months after hospital discharge. METHOD: A two-center retrospective cohort of 240 AIS patients receiving conventional treatment was included. Radiomics features of the infarct area were extracted from baseline NCCT scans. We applied Kruskal-Wallis (KW) test and recursive feature elimination (RFE) to select features for developing clinical, radiomics, and fusion models (with clinical data and radiomics features), using support vector machine (SVM) algorithm. The prediction performance of the models was assessed by accuracy, sensitivity, specificity, F1 score, and receiver operating characteristic (ROC) curve. Shapley Additive exPlanations (SHAP) was applied to analyze the interpretability and predictor importance of the model. RESULTS: A total of 1454 texture features were extracted from the NCCT images. In the test cohort, the ROC analysis showed that the radiomics model and the fusion model showed AUCs of 0.705 and 0.857, which outperformed the clinical model (0.643), with the fusion model exhibiting the best performance. Additionally, the accuracy and sensitivity of the fusion model were also the best among the models (84.8% and 93.8%, respectively). CONCLUSIONS: The model based on NCCT radiomics and machine learning has high predictive efficiency for the prognosis of AIS patients receiving conventional treatment, which can be used to assist early personalized clinical therapy.

Improving the malignancy prediction of breast cancer based on the integration of radiomics features from dual-view mammography and clinical parameters.

Radiomics has been a promising imaging biomarker for many malignant diseases. We developed a novel radiomics strategy that incorporating radiomics features extracted from dual-view mammograms and clinical parameters for identifying benign and malignant breast lesions, and validated whether the radiomics assessment could improve the accurate diagnosis of breast cancer. A total of 380 patients (mean age, 52 ± 7 years) with 621 breast lesions utilizing mammograms on craniocaudal (CC) and mediolateral oblique (MLO) views were randomly allocated into the training (n = 486) and testing (n = 135) sets in this retrospective study. A total of 1184 and 2368 radiomics features were extracted from single-position region of interest (ROI) and position-paired ROI, separately. Clinical parameters were then combined for better prediction. Recursive feature elimination and least absolute shrinkage and selection operator methods were applied to select optimal predictive features. Random forest was used to conduct the predictive model. Intraclass correlation coefficient test was used to assess repeatability and reproducibility of features. After preprocessing, 467 radiomics features and clinical parameters remained in the single-view and dual-view models. The performance and significance of models were quantified by the area under the curve (AUC), sensitivity, specificity, and accuracy. The correlation analysis between variables was evaluated using the correlation ratio and Pearson correlation coefficient. The model using a combination of dual-view radiomics and clinical parameters achieved a favorable performance (AUC: 0.804, 95% CI: 0.668-0.916), outperformed single-view model and model without clinical parameters. Incorporating with radiomics features of dual-view (CC&MLO) mammogram, age, breast density, and type of suspicious lesions can provide a noninvasive approach to evaluate the malignancy of breast lesions and facilitate clinical decision-making.

Using combined CT-clinical radiomics models to identify epidermal growth factor receptor mutation subtypes in lung adenocarcinoma.

Background: To investigate the value of computed tomography (CT)-based radiomics signatures in combination with clinical and CT morphological features to identify epidermal growth factor receptor (EGFR)-mutation subtypes in lung adenocarcinoma (LADC). Methods: From February 2012 to October 2019, 608 patients were confirmed with LADC and underwent chest CT scans. Among them, 307 (50.5%) patients had a positive EGFR-mutation and 301 (49.5%) had a negative EGFR-mutation. Of the EGFR-mutant patients, 114 (37.1%) had a 19del -mutation, 155 (50.5%) had a L858R-mutation, and 38 (12.4%) had other rare mutations. Three combined models were generated by incorporating radiomics signatures, clinical, and CT morphological features to predict EGFR-mutation status. Patients were randomly split into training and testing cohorts, 80% and 20%, respectively. Model 1 was used to predict positive and negative EGFR-mutation, model 2 was used to predict 19del and non-19del mutations, and model 3 was used to predict L858R and non-L858R mutations. The receiver operating characteristic curve and the area under the curve (AUC) were used to evaluate their performance. Results: For the three models, model 1 had AUC values of 0.969 and 0.886 in the training and validation cohorts, respectively. Model 2 had AUC values of 0.999 and 0.847 in the training and validation cohorts, respectively. Model 3 had AUC values of 0.984 and 0.806 in the training and validation cohorts, respectively. Conclusion: Combined models that incorporate radiomics signature, clinical, and CT morphological features may serve as an auxiliary tool to predict EGFR-mutation subtypes and contribute to individualized treatment for patients with LADC.

Transformer-Based Deep-Learning Algorithm for Discriminating Demyelinating Diseases of the Central Nervous System With Neuroimaging.

Background: Differential diagnosis of demyelinating diseases of the central nervous system is a challenging task that is prone to errors and inconsistent reading, requiring expertise and additional examination approaches. Advancements in deep-learning-based image interpretations allow for prompt and automated analyses of conventional magnetic resonance imaging (MRI), which can be utilized in classifying multi-sequence MRI, and thus may help in subsequent treatment referral. Methods: Imaging and clinical data from 290 patients diagnosed with demyelinating diseases from August 2013 to October 2021 were included for analysis, including 67 patients with multiple sclerosis (MS), 162 patients with aquaporin 4 antibody-positive (AQP4+) neuromyelitis optica spectrum disorder (NMOSD), and 61 patients with myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD). Considering the heterogeneous nature of lesion size and distribution in demyelinating diseases, multi-modal MRI of brain and/or spinal cord were utilized to build the deep-learning model. This novel transformer-based deep-learning model architecture was designed to be versatile in handling with multiple image sequences (coronal T2-weighted and sagittal T2-fluid attenuation inversion recovery) and scanning locations (brain and spinal cord) for differentiating among MS, NMOSD, and MOGAD. Model performances were evaluated using the area under the receiver operating curve (AUC) and the confusion matrices measurements. The classification accuracy between the fusion model and the neuroradiological raters was also compared. Results: The fusion model that was trained with combined brain and spinal cord MRI achieved an overall improved performance, with the AUC of 0.933 (95%CI: 0.848, 0.991), 0.942 (95%CI: 0.879, 0.987) and 0.803 (95%CI: 0.629, 0.949) for MS, AQP4+ NMOSD, and MOGAD, respectively. This exceeded the performance using the brain or spinal cord MRI alone for the identification of the AQP4+ NMOSD (AUC of 0.940, brain only and 0.689, spinal cord only) and MOGAD (0.782, brain only and 0.714, spinal cord only). In the multi-category classification, the fusion model had an accuracy of 81.4%, which was significantly higher compared to rater 1 (64.4%, p=0.04<0.05) and comparable to rater 2 (74.6%, p=0.388). Conclusion: The proposed novel transformer-based model showed desirable performance in the differentiation of MS, AQP4+ NMOSD, and MOGAD on brain and spinal cord MRI, which is comparable to that of neuroradiologists. Our model is thus applicable for interpretating conventional MRI in the differential diagnosis of demyelinating diseases with overlapping lesions.