Semantic segmentation guided detector for segmentation, classification, and lesion mapping of acute ischemic stroke in MRI images.

BACKGROUND AND PURPOSE: MRI images timely and accurately reflect ischemic injuries to the brain tissues and, therefore, can support clinical decision-making of acute ischemic stroke (AIS). To maximize the information provided by the MRI images, we leverage deep learning models to segment, classify, and map lesion distributions of AIS. METHODS: We evaluated brain MRI images of AIS patients from 2017 to 2020 at a tertiary teaching hospital and developed the Semantic Segmentation Guided Detector Network (SGD-Net), composed of the first U-shaped model for segmentation in diffusion-weighted imaging (DWI) and the second model for binary classification of lesion size (lacune vs. non-lacune) and circulatory territory of lesion location (anterior vs. posterior circulation). Next, we modified the two-stage deep learning model into SGD-Net Plus by automatically segmenting AIS lesions in DWI images and registering the lesion in T1-weighted images and the brain atlases. RESULTS: The final enrollment (216 patients with 4606 slices) was divided into 80% for model development and 20% for testing. S1 model segmented AIS lesions in DWI images accurately with a pixel accuracy > 99% (Dice 0.806-0.828 and IoU 0.675-707). In comprehensive evaluation of classification performance, the two-stage SGD-Net outperformed the traditional one-stage models in classifying AIS lesion size (accuracy 0.867-0.956 vs. 0.511-0.867, AUROC 0.962-0.992 vs. 0.528-0.937, AUPRC 0.964-0.994 vs. 0.549-0.938) and location (accuracy 0.860-0.930 vs. 0.326-0.721, AUROC 0.936-0.988 vs. 0.493-0.833, AUPRC 0.883-0.978 vs. 0.365-0.695). The precise lesion segmentation at the first stage of the deep learning model was the basis for further application. After that, the modified two-stage model SGD-Net Plus accurately reported the volume, region percentage, and lesion percentage of each region on the selected brain atlas. Its reports provided clear descriptions and quantifications of the AIS-related brain injuries on white matter tracts, Brodmann areas, and cytoarchitectonic areas. CONCLUSION: Domain knowledge-oriented design of artificial intelligence applications can deepen our understanding of patients' conditions and strengthen the use of MRI for patient care. SGD-Net precisely segments AIS lesions on DWI and accurately classifies the lesions. In addition, SGD-Net Plus maps the AIS lesions and quantifies their occupancy in each brain region. They are practical tools to meet the clinical needs and enrich educational resources of neuroimage.

Machine Learning Models for Predicting Influential Factors of Early Outcomes in Acute Ischemic Stroke: Registry-Based Study.

BACKGROUND: Timely and accurate outcome prediction plays a vital role in guiding clinical decisions on acute ischemic stroke. Early condition deterioration and severity after the acute stage are determinants for long-term outcomes. Therefore, predicting early outcomes is crucial in acute stroke management. However, interpreting the predictions and transforming them into clinically explainable concepts are as important as the predictions themselves. OBJECTIVE: This work focused on machine learning model analysis in predicting the early outcomes of ischemic stroke and used model explanation skills in interpreting the results. METHODS: Acute ischemic stroke patients registered on the Stroke Registry of the Chang Gung Healthcare System (SRICHS) in 2009 were enrolled for machine learning predictions of the two primary outcomes: modified Rankin Scale (mRS) at hospital discharge and in-hospital deterioration. We compared 4 machine learning models, namely support vector machine (SVM), random forest (RF), light gradient boosting machine (LGBM), and deep neural network (DNN), with the area under the curve (AUC) of the receiver operating characteristic curve. Further, 3 resampling methods, random under sampling (RUS), random over sampling, and the synthetic minority over-sampling technique, dealt with the imbalanced data. The models were explained based on the ranking of feature importance and the SHapley Additive exPlanations (SHAP). RESULTS: RF performed well in both outcomes (discharge mRS: mean AUC 0.829, SD 0.018; in-hospital deterioration: mean AUC 0.710, SD 0.023 on original data and 0.728, SD 0.036 on resampled data with RUS for imbalanced data). In addition, DNN outperformed other models in predicting in-hospital deterioration on data without resampling (mean AUC 0.732, SD 0.064). In general, resampling contributed to the limited improvement of model performance in predicting in-hospital deterioration using imbalanced data. The features obtained from the National Institutes of Health Stroke Scale (NIHSS), white blood cell differential counts, and age were the key features for predicting discharge mRS. In contrast, the NIHSS total score, initial blood pressure, having diabetes mellitus, and features from hemograms were the most important features in predicting in-hospital deterioration. The SHAP summary described the impacts of the feature values on each outcome prediction. CONCLUSIONS: Machine learning models are feasible in predicting early stroke outcomes. An enriched feature bank could improve model performance. Initial neurological levels and age determined the activity independence at hospital discharge. In addition, physiological and laboratory surveillance aided in predicting in-hospital deterioration. The use of the SHAP explanatory method successfully transformed machine learning predictions into clinically meaningful results.

rGO/SWCNT composites as novel electrode materials for electrochemical biosensing.

In this study we performed electrochemical sensing using conductive carbon composite films containing reduced graphene oxide (rGO) and single-walled carbon nanotubes (SWCNTs) as electrode modifiers on glassy carbon electrodes (GCEs). Raman spectroscopy, transmission electron microscopy, atomic force microscopy, and scanning electron microscopy all suggested that the rGO acted as a surfactant, covering and smoothing out the surface, and that the SWCNTs acted as a conducting bridge to connect the isolated rGO sheets, thereby (i) minimizing the barrier for charge transfer between the rGO sheets and (ii) increasing the conductivity of the film. We used the rGO/SWCNT-modified GCE as a sensor to analyze hydrogen peroxide (H2O2) and ß-nicotinamide adenine dinucleotide (NADH), obtaining substantial improvements in electrochemical reactivity and detection limits relative to those obtained from rGO- and SWCNT-modified electrodes, presumably because of the higher conductivity and greater coverage on the GCE, due to π-π interactions originating from the graphitic structures of the rGO and SWCNTs. The electrocatalysis response was measured by cyclic voltammetry and amperometric current-time (i-t) curve techniques. The linear concentration range of H2O2 and NADH detection at rGO/SWCNT-modified electrode is 0.5-5M and 20-400µM. The sensitivity for H2O2 and NADH detection is 2732.4 and 204µAmM(-1)cm(-2), and the limit of detection is 1.3 and 0.078µM respectively. Furthermore, interference tests indicated that the carbon composite film exhibited high selectivity toward H2O2 and NADH. Using GO as a solubilizing agent for SWCNTs establishes a new class of carbon electrodes for electrochemical sensors.

A strategic buffer layer of polythiophene enhances the efficiency of bulk heterojunction solar cells.

We have developed polymer solar cells featuring a buffer layer of polythiophene (PT) sandwiched between the active layer and the poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate) (PEDOT:PSS) layer. We attribute the improvement in power conversion efficiency of these polymer solar cells, relative to that of those based on poly(3-hexylthiophene):[6,6]-phenyl-C(61)-butyric acid methyl ester (P3HT:PCBM), to a reduction in the degree of carrier recombination at the junction interface. Because the conductivity and the energy level of PT can be tuned simply by applying a bias to it in an electrolytic solution, we also investigated the effect of the energy level on the devices' performances. The power conversion efficiency of a solar cell containing a PT buffer layer reached 4.18% under AM 1.5 G irradiation (100 mW/cm(2)).