Early identification of ischemic stroke in noncontrast computed tomography

Lung CT-based multi-lesion radiomic model to differentiate between nontuberculous mycobacteria and Mycobacterium tuberculosis

BACKGROUND

Nontuberculous mycobacterial lung disease (NTM-LD) and Mycobacterium tuberculosis lung disease (MTB-LD) are difficult to distinguish based on conventional imaging examinations. In recent years, radiomics has been used to discriminate them. However, existing radiomic methods mainly focus on specific lesion types, and have limitations in handling the presence of multiple lesion types that vary among different patients.

PURPOSE

We aimed to establish a radiomic model based on multiple lesion types in the patient's CT scans, and analyzed the importance of different lesion types in distinguishing the two diseases.

METHODS

120 NTM-LD and 120 MTB-LD patients were retrospectively enrolled in this study and randomly split into the training (168) and testing (72) sets. A total of 1037 radiomic features were extracted separately for each lesion type. The univariate analysis, least absolute shrinkage, and selection operator were used to select the significant radiomic features. The radiomic signature score (Radscore) from each lesion type was estimated and aggregated to construct the multi-lesion feature vector for each patient. A multi-lesion radiomic (MLR) model was then established using the random forest classifier, which can estimate importance coefficients for different lesion types. The performances of the MLR model and single radomic models were investigated by the receiver operating characteristic curve (ROC). The impact of the predicted lesion importance was also evaluated in subjective imaging diagnosis.

RESULTS

The MLR model achieved an area under the curve (AUC) of 90.2% (95% CI: 86.2% 94.1%) in differentiating NTM-LD and MTB-LD, outperforming the models using specific lesion types following existing radiomic models by 1% to 13%. Among different lesion types, tree-in-bud pattern demonstrated the highest distinguishing value, followed by consolidation, nodules, and lymph node enlargement. Given the estimated lesion importance, two senior radiologists exhibited improved accuracy in diagnosis, with an increased accuracy of 8.33% and 8.34%, respectively.

CONCLUSIONS

This is the first radiomic study to use multiple lesion types to distinguish NTM-LD and MTB-LD. The developed MLR model performed well in differentiating the two diseases, and the lesion types with high importance exhibited the potential to assist experienced radiologists in clinical decision-making.

A new method for predicting the prognosis of ischemic stroke based vascular structure features and lesion location features

OBJECTIVE

Determining the changes in the prognosis of the cerebral infarction area has an important guiding role in the selection of the treatment plan. The goal of this study is to propose a machine learning-based method that can predict the prognosis of stroke effectively and efficiently.

METHODS

97 cases of stroke were analyzed retrospectively. Firstly, we extracted vascular structural features from computed tomography angiography (CTA) images and stroke location features from diffusion-weighted imaging (DWI) images to comprehensively characterize the lesions, respectively. Then, we performed sparse representation-based feature selection and classification to predict the prognosis of stroke based on the extracted features. Finally, we randomly divided the 97 cases into cross-validation set, independent testing set 1 and independent testing set 2 to validate the proposed model.

RESULTS

464 vascular structure features and 116 positional features were extracted. After feature selection, 52 features were finally applied to build the classification model. The proposed model achieved promising prediction performance on the two independent testing sets, with the classification accuracies of 85.19% and 81.25%, respectively.

CONCLUSION

The proposed machine learning approach can effectively mine and accurately quantify the features related to the prognosis, which include the vascular structural features and the stroke location features. In addition, the established prognostic prediction model based on these features has achieved interesting performances, which may provide valuable guidance for the clinical treatment of stroke.

Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography

A non-contrast cranial computer tomography (ncCT) is often employed for the diagnosis of the early stage of the ischemic stroke. However, the number of false negatives is high. More accurate results are obtained by an MRI. However, the MRI is not available in every hospital. Moreover, even if it is available in the clinic for the routine tests, emergency often does not have it. Therefore, this paper proposes an end-to-end framework for detection and segmentation of the brain infarct on the ncCT. The computer tomography perfusion (CTp) is used as the ground truth. The proposed ensemble model employs three deep convolution neural networks (CNNs) to process three end-to-end feature maps and a hand-craft features characterized by specific contra-lateral features. To improve the accuracy of the detected infarct area, the spatial dependencies between neighboring slices are employed at the postprocessing step. The numerical experiments have been performed on 18 ncCT-CTp paired stroke cases (804 image-pairs). The leave-one-out approach is applied for evaluating the proposed method. The model achieves 91.16% accuracy, 65.15% precision, 77.44% recall, 69.97% F1 score, and 0.4536 IoU.

Quantification of infarct core signal using CT imaging in acute ischemic stroke

In stroke care, the extent of irreversible brain injury, termed infarct core, plays a key role in determining eligibility for acute treatments, such as intravenous thrombolysis and endovascular reperfusion therapies. Many of the pivotal randomized clinical trials testing those therapies used MRI Diffusion-Weighted Imaging (DWI) or CT Perfusion (CTP) to define infarct core. Unfortunately, these modalities are not available 24/7 outside of large stroke centers. As such, there is a need for accurate infarct core determination using faster and more widely available imaging modalities including Non-Contrast CT (NCCT) and CT Angiography (CTA). Prior studies have suggested that CTA provides improved predictions of infarct core relative to NCCT; however, this assertion has never been numerically quantified by automatic medical image computing pipelines using acquisition protocols not confounded by different scanner manufacturers, or other protocol settings such as exposure times, kilovoltage peak, or imprecision due to contrast bolus delays. In addition, single-phase CTA protocols are at present designed to optimize contrast opacification in the arterial phase. This approach works well to maximize the sensitivity to detect vessel occlusions, however, it may not be the ideal timing to enhance the ischemic infarct core signal (ICS). In this work, we propose an image analysis pipeline on CT-based images of 88 acute ischemic stroke (AIS) patients drawn from a single dynamic acquisition protocol acquired at the acute ischemic phase. We use the first scan at the time of the dynamic acquisition as a proxy for NCCT, and the rest of the scans as a proxy for CTA scans, with bolus imaged at different brain enhancement phases. Thus, we use the terms "NCCT" and "CTA" to refer to them. This pipeline enables us to answer the questions "Does the injection of bolus enhance the infarct core signal?" and "What is the ideal bolus timing to enhance the infarct core signal?" without being influenced by aforementioned factors such as scanner model, acquisition settings, contrast bolus delay, and human reader errors. We use reference MRI DWI images acquired after successful recanalization acting as our gold standard for infarct core. The ICS is quantified by calculating the difference in intensity distribution between the infarct core region and its symmetrical healthy counterpart on the contralateral hemisphere of the brain using a metric derived from information theory, the Kullback-Leibler divergence (KL divergence). We compare the ICS provided by NCCT and CTA and retrieve the optimal timing of CTA bolus to maximize the ICS. In our experiments, we numerically confirm that CTAs provide greater ICS compared to NCCT. Then, we find that, on average, the ideal CTA acquisition time to maximize the ICS is not the current target of standard CTA protocols, i.e., during the peak of arterial enhancement, but a few seconds afterward (median of 3 s; 95% CI [1.5, 3.0]). While there are other studies comparing the prediction potential of ischemic infarct core from NCCT and CTA images, to the best of our knowledge, this analysis is the first to perform a quantitative comparison of the ICS among CT based scans, with and without bolus injection, acquired using the same scanning sequence and a precise characterization of the bolus uptake, hence, reducing potential confounding factors.

Evaluating nnU-Net for early ischemic change segmentation on non-contrast computed tomography in patients with Acute Ischemic Stroke

Identifying the presence and extent of early ischemic changes (EIC) on Non-Contrast Computed Tomography (NCCT) is key to diagnosing and making time-sensitive treatment decisions in patients that present with Acute Ischemic Stroke (AIS). Segmenting EIC on NCCT is however a challenging task. In this study, we investigated a 3D CNN based on nnU-Net, a self-adapting CNN technique that has become the state-of-the-art in medical image segmentation, for segmenting EIC in NCCT of AIS patients. We trained and tested this model on a sizeable and heterogenous dataset of 534 patients, split into 438 for training and validation and 96 for testing. On this test set, we additionally assessed the inter-rater performance by comparing the proposed approach against two reference segmentation annotations by expert neuroradiologist readers, using this as the benchmark against which to compare our model. In terms of spatial agreement, we report median Dice Similarity Coefficients (DSCs) of 39.8% for the model vs. Reader-1, 39.4% for the model vs. Reader-2, and 55.6% for Reader-2 vs. Reader-1. In terms of lesion volume agreement, we report Intraclass Correlation Coefficients (ICCs) of 83.4% for model vs. Reader-1, 80.4% for model vs. Reader-2, and 94.8% for Reader-2 vs. Reader-1. Based on these results, we conclude that our model performs well relative to expert human performance and therefore may be useful as a decision-aid for clinicians.

Multi-Order Brain Functional Connectivity Network-Based Machine Learning Method for Recognition of Delayed Neurocognitive Recovery in Older Adults Undergoing Non-cardiac Surgery

Objectives: Delayed neurocognitive recovery (DNR) seriously affects the post-operative recovery of elderly surgical patients, but there is still a lack of effective methods to recognize high-risk patients with DNR. This study proposed a machine learning method based on a multi-order brain functional connectivity (FC) network to recognize DNR.

Method: Seventy-four patients who completed assessments were included in this study, in which 16/74 (21.6%) had DNR following surgery. Based on resting-state functional magnetic resonance imaging (rs-fMRI), we first constructed low-order FC networks of 90 brain regions by calculating the correlation of brain region signal changing in the time dimension. Then, we established high-order FC networks by calculating correlations among each pair of brain regions. Afterward, we built sparse representation-based machine learning model to recognize DNR on the extracted multi-order FC network features. Finally, an independent testing was conducted to validate the established recognition model.

Results: Three hundred ninety features of FC networks were finally extracted to identify DNR. After performing the independent-sample T test between these features and the categories, 15 features showed statistical differences (P < 0.05) and 3 features had significant statistical differences (P < 0.01). By comparing DNR and non-DNR patients’ brain region connection matrices, it is found that there are more connections among brain regions in DNR patients than in non-DNR patients. For the machine learning recognition model based on multi-feature combination, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the classifier reached 95.61, 92.00, 66.67, and 100.00%, respectively.

Conclusion: This study not only reveals the significance of preoperative rs-fMRI in recognizing post-operative DNR in elderly patients but also establishes a promising machine learning method to recognize DNR.

Rapid Assessment of Acute Ischemic Stroke by Computed Tomography Using Deep Convolutional Neural Networks

Acute stroke is one of the leading causes of disability and death worldwide. Regarding clinical diagnoses, a rapid and accurate procedure is necessary for patients suffering from acute stroke. This study proposes an automatic identification scheme for acute ischemic stroke using deep convolutional neural networks (DCNNs) based on non-contrast computed tomographic (NCCT) images. Our image database for the classification model was composed of 1254 grayscale NCCT images from 96 patients (573 images) with acute ischemic stroke and 121 normal controls (681 images). According to the consensus of critical stroke findings by two neuroradiologists, a gold standard was established and used to train the proposed DCNN using machine-generated image features. Including the earliest DCNN, AlexNet, the popular Inception-v3, and ResNet-101 were proposed. To train the limited data size, transfer learning with ImageNet parameters was also used. The established models were evaluated by tenfold cross-validation and tested on an independent dataset containing 50 patients with acute ischemic stroke (108 images) and 58 normal controls (117 images) from another institution. AlexNet without pretrained parameters achieved an accuracy of 97.12%, a sensitivity of 98.11%, a specificity of 96.08%, and an area under the receiver operating characteristic curve (AUC) of 0.9927. Using transfer learning, transferred AlexNet, transferred Inception-v3, and transferred ResNet-101 achieved accuracies between 90.49 and 95.49%. Tested with a dataset from another institution, AlexNet showed an accuracy of 60.89%, a sensitivity of 18.52%, and a specificity of 100%. Transferred AlexNet, Inception-v3, and ResNet-101 achieved accuracies of 81.77%, 85.78%, and 80.89%, respectively. The proposed DCNN architecture as a computer-aided diagnosis system showed that training from scratch can generate a customized model for a specific scanner, and transfer learning can generate a more generalized model to provide diagnostic suggestions of acute ischemic stroke to radiologists.

Detecting the Early Infarct Core on Non-Contrast CT Images with a Deep Learning Residual Network

PURPOSE

To explore a new approach mainly based on deep learning residual network (ResNet) to detect infarct cores on non-contrast CT images and improve the accuracy of acute ischemic stroke diagnosis.

METHODS

We continuously enrolled magnetic resonance diffusion weighted image (MR-DWI) confirmed first-episode ischemic stroke patients (onset time: less than 9 h) as well as some normal individuals in this study. They all underwent CT plain scan and MR-DWI scan with same scanning range, layer thickness (4 mm) and interlayer spacing (4 mm) (The time interval between two examinations: less than 4 h). Setting MR-DWI as gold standard of infarct core and using deep learning ResNet combined with a maximum a posteriori probability (MAP) model and a post-processing method to detect the infarct core on non-contrast CT images. After that, we use decision curve analysis (DCA) establishing models to analyze the value of this new method in clinical practice.

RESULTS

116 ischemic stroke patients and 26 normal people were enrolled. 58 patients were allocated into training dataset and 58 were divided into testing dataset along with 26 normal samples. The identification accuracy of our ResNet based approach in detecting the infarct core on non-contrast CT is 75.9%. The DCA shows that this deep learning method is capable of improving the net benefit of ischemic stroke patients.

CONCLUSIONS

Our deep learning residual network assisted with optimization methods is able to detect early infarct core on non-contrast CT images and has the potential to help physicians improve diagnostic accuracy in acute ischemic stroke patients.

EIS-Net: Segmenting early infarct and scoring ASPECTS simultaneously on non-contrast CT of patients with acute ischemic stroke

Detecting early infarct (EI) plays an essential role in patient selection for reperfusion therapy in the management of acute ischemic stroke (AIS). EI volume at acute or hyper-acute stage can be measured using advanced pre-treatment imaging, such as MRI and CT perfusion. In this study, a novel multi-task learning approach, EIS-Net, is proposed to segment EI and score Alberta Stroke Program Early CT Score (ASPECTS) simultaneously on baseline non-contrast CT (NCCT) scans of AIS patients. The EIS-Net comprises of a 3D triplet convolutional neural network (T-CNN) for EI segmentation and a multi-region classification network for ASPECTS scoring. T-CNN has triple encoders with original NCCT, mirrored NCCT, and atlas as inputs, as well as one decoder. A comparison disparity block (CDB) is designed to extract and enhance image contexts. In the decoder, a multi-level attention gate module (MAGM) is developed to recalibrate the features of the decoder for both segmentation and classification tasks. Evaluations using a high-quality dataset comprising of baseline NCCT and concomitant diffusion weighted MRI (DWI) as reference standard of 260 patients with AIS show that the proposed EIS-Net can accurately segment EI. The EIS-Net segmented EI volume strongly correlates with EI volume on DWI (r=0.919), and the mean difference between the two volumes is 8.5 mL. For ASPECTS scoring, the proposed EIS-Net achieves an intraclass correlation coefficient of 0.78 for total 10-point ASPECTS and a kappa of 0.75 for dichotomized ASPECTS (≤ 4 vs. >4). Both EI segmentation and ASPECTS scoring tasks achieve state-of-the-art performances.

Identification of invisible ischemic stroke in noncontrast CT based on novel two-stage convolutional neural network model

PURPOSE

Early identification of ischemic stroke lesion regions plays a vital role in its treatments like thrombolytic therapy and patients' recovery. Noncontrast computed tomography (ncCT) is the most widespread imaging modality in emergency departments. Unfortunately, it is extremely hard to distinguish the lesion from healthy tissue during the hyper-acute phase of stroke. In this paper, a two-stage convolutional neural network-based method was proposed to identify the invisible ischemic stroke from ncCT.

METHODS

In order to combine the global and local information of images effectively, a cascaded structure with two coordinated networks was used to detect the suspicious stroke regions on the whole and optimize the detailed localization. In the first stage, an end-to-end U-net with adaptive threshold was proposed to integrate global position, symmetry and gray texture information to detect the suspicious regions. After reducing the interference from most normal regions, a ResNet-based patch classification network was used to eliminate some false positive samples on suspicious regions by mining deeper image features, contributing to a more precise localization of stroke. Finally, a MAP model was used to optimize the result by combining the classification results of each patch with their spatial constraint information.

RESULTS

Three independent experiments, that is, training and testing on dataset from one hospital, on the combination of two, and on the two respectively, were performed on a total of 277 cases from two hospitals to validate the proposed model, The proposed method achieved identification accuracy of 91.89%, 87.21%, and 85.71% in the three experiments, and the final localization accuracy in terms of precise localization of stroke were 82.35%, 83.02%, and 81.40%, respectively, which indicated the robustness and clinical values of the method.

CONCLUSIONS

There are some deep image feature differences between stroke region and normal region on ncCT images. The proposed two-stage convolutional neural network model can well seize these features and use them to effectively identify and locate stroke.