Stroke Segmentation Research Articles

Stroke‐Seg: A deep learning‐based framework for chinese stroke segmentation

AbstractChinese stroke segmentation is a crucial and challenging task for various downstream applications such as font generation, aesthetic evaluation etc. Conventional semantic segmentation techniques typically face difficulties in accurately segmenting strokes, as intersection regions in Chinese characters can belong to multiple strokes simultaneously, and these approaches often lack a holistic understanding of character composition. This paper proposes a character stroke segmentation framework named Stroke‐Seg that integrates with various semantic segmentation architectures, demonstrating adaptability to different backbone networks to tackle the above tasks. A multi‐label output strategy is proposed to effectively classify strokes in intersection areas, overcoming the limitations of traditional semantic segmentation approaches. Additionally, a prior knowledge vector is incorporated into the input layer to provide character‐specific information on stroke composition, enhancing the ability of the framework to precisely identify and segment strokes. The effectiveness of the proposed framework is demonstrated through evaluations of a comprehensive dataset (brush calligraphy stroke segmentation dataset). Evaluations show that the proposed framework significantly improves the capability of semantic segmentation networks, achieving a remarkable improvement of up to 19.9% in the true stroke rate, compared to traditional stroke segmentation techniques. The Stroke‐Seg framework integrated with TransUNet demonstrates its high performance with an impressive 98.2% true stroke rate. Furthermore, the proposed framework combined with FCN still achieves good performance while consuming the least amount of computational resources and memory, demonstrating its potential for lightweight design.

Ischemic Stroke Segmentation by Transformer and Convolutional Neural Network Using Few-Shot Learning

Stroke is a major factor in causing disability and fatalities. Doctors use computerized tomography (CT) and magnetic resonance imaging (MRI) scans to assess the severity of a stroke. Automatic image segmentation can help doctors diagnose strokes more quickly and accurately, but it is challenging due to the variability of stroke lesions and the limited availability of labeled data. Deep learning is the cutting-edge technique of machine learning and artificial intelligence, which needs an extensive labeled dataset for effective training. Unfortunately, in the medical domain, the availability of labeled data is severely limited, posing a challenge for conventional deep learning approaches. In this paper, we introduce a system that utilizes deep learning in the form of fusing transformer-based and convolutional neural network (CNN)-based features and few-shot learning techniques to segment ischemic strokes in multimedia MRIs. To accomplish this, we employ two different methods. The first method involves parallel fusion, where we combine CNN-based and transformer-based features. The second method utilizes serial fusion, combining CNN-based and transformer models using few-shot learning. Through the integration of transformer and CNN models, we can extract both global and local features and enhance the system's performance. Moreover, we tackle the issue of limited labeled data by integrating few-shot learning techniques. Additionally, our system optimizes efficiency by selecting only the slices with lesions, disregarding unlesioned slices. The system under consideration is trained with the BraTS2020 dataset, evaluated on the ISLES 2015 dataset, and contrasted the performance with cutting-edge systems. The suggested system attains a dice coefficient score of 0.76, surpassing the scores of previous cutting-edge systems by a substantial margin.

Transformers-based architectures for stroke segmentation: a review

Stroke remains a significant global health concern, necessitating precise and efficient diagnostic tools for timely intervention and improved patient outcomes. The emergence of deep learning methodologies has transformed the landscape of medical image analysis. Recently, Transformers, initially designed for natural language processing, have exhibited remarkable capabilities in various computer vision applications, including medical image analysis. This comprehensive review aims to provide an in-depth exploration of the cutting-edge Transformer-based architectures applied in the context of stroke segmentation. It commences with an exploration of stroke pathology, imaging modalities, and the challenges associated with accurate diagnosis and segmentation. Subsequently, the review delves into the fundamental ideas of Transformers, offering detailed insights into their architectural intricacies and the underlying mechanisms that empower them to effectively capture complex spatial information within medical images. The existing literature is systematically categorized and analyzed, discussing various approaches that leverage Transformers for stroke segmentation. A critical assessment is provided, highlighting the strengths and limitations of these methods, including considerations of performance and computational efficiency. Additionally, this review explores potential avenues for future research and development.

Computer Augmented Reality Model-Based Interactive Teaching System for Chinese Line Drawing CAD

To achieve automatic target region detection, an interactive image segmentation technique has been always used as preferences. However, when it comes to the implementation of computer aided design, there is a problem with the structured method. The technique of stroke contour extraction based on boundary detection is used in this investigation. The high-frequency lifting filter improves the original image, and the grey scale and spatial distribution of the pixels are used to determine how the pixels are distributed on the pen track. The segmentation of mural lines and strokes is achieved well in a limited space. To ascertain each pixel's grey value distribution, a non-realistic rendering technique is suggested. Draw in accordance with the boundary tangential flow and each pixel's category. In conclusion, the two approaches can cover more application scenarios and yield good results in the extraction of creative materials from Chinese classical mural painting while maintaining the entire shape of the original strokes in the painting.

DRRN: Differential rectification & refinement network for ischemic infarct segmentation

AbstractAccurate segmentation of infarct tissue in ischemic stroke is essential to determine the extent of injury and assess the risk and choose optimal treatment for this life‐threatening disease. With the prior knowledge that asymmetric analysis of anatomical structures can provide discriminative information, plenty of symmetry‐based approaches have emerged to detect abnormalities in brain images. However, the inevitable non‐pathological noise has not been fully alleviated and weakened, leading to unsatisfactory results. A novel differential rectification and refinement network (DRRN) for the automatic segmentation of ischemic strokes is proposed. Specifically, a differential feature perception encoder (DFPE) is developed to fully exploit and propagate the bilateral quasi‐symmetry of healthy brains. In DFPE, an erasure‐rectification (ER) module is devised to rectify pseudo‐lesion features caused by non‐pathological noise through utilising discriminant features within the symmetric neighbourhood of the original image. And a differential‐attention (DA) mechanism is also integrated to fully perceive the differences in cross‐axial features and estimate the similarity of long‐range spatial context information. In addition, a crisscross differential feature reinforce module embedded with multiple boundary enhancement attention modules is designed to effectively integrate multi‐scale features and refine textual details and margins of the infarct area. Experimental results on the public ATLAS and Kaggle dataset demonstrate the effectiveness of DRRN over state‐of‐the‐arts.

SrSNet: Accurate segmentation of stroke lesions by a two-stage segmentation framework with asymmetry information

Ischemic stroke is a common neurological disease with a high mortality rate. Accurate stroke segmentation is crucial to evaluating patients’ disease outcomes. Stroke segmentation suffers from variable lesion size and noise interference due to similar image contrast characteristics of tissue structures. In this work, we propose a novel two-stage framework named Segmentation–reSegmentation Net (SrSNet) that mainly considers the bilateral symmetric comparison of brain hemispheres to locate pathological abnormalities. The whole framework includes two stages, the coarse segmentation stage and the fine segmentation stage. In the coarse segmentation stage, the brain images are first divided into three patches according to their spatial information to learn the local-level feature and then fed into a 2D Triplet Multi-scale Symmetric Transformer (TMSFormer) with a feature fusion module. This module facilitates the TMSFormer to generate detailed coarse segmentation results. In the fine segmentation stage, we refine the coarse segmentations with a 2D ResUNet. Extensive experiments are conducted using the two ischemic stroke lesion segmentation datasets, and the results are compared with other advanced models. Experiment results on two datasets show that SrSNet achieves state-of-the-art (SOTA) performance. Moreover, on the Ischemic Stroke Lesion Segmentation 2022 (ISLES’22) dataset, the recall score for stroke lesions that the maximum cross-sectional diameter is larger than 5 cm is 83.80%, and the recall score for strokes that the number of lesions of more than five is 79.05%. Overall, our method provides a potentially successful tool for improving the diagnosis of ischemic stroke.

Fine Segmentation of Chinese Character Strokes Based on Coordinate Awareness and Enhanced BiFPN.

Considering the complex structure of Chinese characters, particularly the connections and intersections between strokes, there are challenges in low accuracy of Chinese character stroke extraction and recognition, as well as unclear segmentation. This study builds upon the YOLOv8n-seg model to propose the YOLOv8n-seg-CAA-BiFPN Chinese character stroke fine segmentation model. The proposed Coordinate-Aware Attention mechanism (CAA) divides the backbone network input feature map into four parts, applying different weights for horizontal, vertical, and channel attention to compute and fuse key information, thus capturing the contextual regularity of closely arranged stroke positions. The network's neck integrates an enhanced weighted bi-directional feature pyramid network (BiFPN), enhancing the fusion effect for features of strokes of various sizes. The Shape-IoU loss function is adopted in place of the traditional CIoU loss function, focusing on the shape and scale of stroke bounding boxes to optimize the bounding box regression process. Finally, the Grad-CAM++ technique is used to generate heatmaps of segmentation predictions, facilitating the visualization of effective features and a deeper understanding of the model's focus areas. Trained and tested on the public Chinese character stroke datasets CCSE-Kai and CCSE-HW, the model achieves an average accuracy of 84.71%, an average recall rate of 83.65%, and a mean average precision of 80.11%. Compared to the original YOLOv8n-seg and existing mainstream segmentation models like SegFormer, BiSeNetV2, and Mask R-CNN, the average accuracy improved by 3.50%, 4.35%, 10.56%, and 22.05%, respectively; the average recall rates improved by 4.42%, 9.32%, 15.64%, and 24.92%, respectively; and the mean average precision improved by 3.11%, 4.15%, 8.02%, and 19.33%, respectively. The results demonstrate that the YOLOv8n-seg-CAA-BiFPN network can accurately achieve Chinese character stroke segmentation.

Enhanced Segmentation of Ischemic Stroke Lesion in MRI Images Using a Geometrically Customised Deep Convolution Model (GCDCM)

Ischemic stroke lesion often known as a stroke, is a significant health issue that requires accurate analysis and classification of brain magnetic resonance imaging (MRI) data. In this study, we propose a novel deep transfer learning approach, called geometrically customized deep convolution model, for the purpose of MRI analysis and classification of brain stroke. Neurostroke segmentation is a serious medical image processing challenge. Segmented regions aid disease identification and treatment. Anywhere can form thrombi. Segmentation facilitates automatic detection because they can be any size or shape. Popular image analysis tool MRI diagnoses well. This diagnostic method shows brain stroke architecture. MRI must replace manual detection. Online datasets recommended cerebral stroke detection and segmentation. Deep learning model MRI scans and detectron 2 with masked CNN Nets segment thrombus. This net architecture recognises dataset stroke boundaries. Classifying strokes with vgg16, resnet50, inceptionv3, and resnet5 transfer learning is possible. Mask the image, then binary predict by eliminating the skull, extracting features, and iterating to find stroke. The model and thrombus mask are predicted if the binary prediction matches the human forecast. Otherwise, data processing resumes. Binary prediction uses the segmentation region and pixels overlap between the ground truth and predicted segmentation to calculate parameters. Compared to reality, the categorization of medical images with weak signals seems tough, especially with a short "train" dataset. Mixing deep learning architectures avoids these drawbacks and extracts signals to accurately classify classes. Deep neural networks best recognise, find, and divide computer vision objects for clinical image analysis. Preprocessing MRI scans, skull stripping with deep CNN architecture combinational net, and brain stroke segmentation are our main tasks. Modern medical image processing is hard. Flexible and uneven borders make brain strokes hard to identify and segment. The transfer learning-based super pixel approach segments brainstrokes. Because we predict every visual pixel, dense prediction occurs. Early discovery of thrombus improves treatment and survival. These procedures have considerably improved our quality indexes.

Robust Ensemble of Two Different Multimodal Approaches to Segment 3D Ischemic Stroke Segmentation Using Brain Tumor Representation Among Multiple Center Datasets.

Ischemic stroke segmentation at an acute stage is vital in assessing the severity of patients' impairment and guiding therapeutic decision-making for reperfusion. Although many deep learning studies have shown attractive performance in medical segmentation, it is difficult to use these models trained on public data with private hospitals' datasets. Here, we demonstrate an ensemble model that employs two different multimodal approaches for generalization, a more effective way to perform on external datasets. First, after we jointly train a segmentation model on diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) MR modalities, the model is inferred on the DWI images. Second, a channel-wise segmentation model is trained by concatenating the DWI and ADC images as input, and then is inferred using both MR modalities. Before training with ischemic stroke data, we utilized BraTS 2021, a public brain tumor dataset, for transfer learning. An extensive ablation study evaluates which strategy learns better representations for ischemic stroke segmentation. In our study, nnU-Net well-known for robustness is selected as our baseline model. Our proposed method is evaluated on three different datasets: the Asan Medical Center (AMC) I and II, and the 2022 Ischemic Stroke Lesion Segmentation (ISLES). Our experiments are widely validated over a large, multi-center, and multi-scanner dataset with a huge amount of 846 scans. Not only stroke lesion models can benefit from transfer learning using brain tumor data, but combining the MR modalities using different training schemes also highly improves segmentation performance. The method achieved a top-1 ranking in the ongoing ISLES'22 challenge and performed particularly well on lesion-wise metrics of interest to neuroradiologists, achieving a Dice coefficient of 78.69% and a lesion-wise F1 score of 82.46%. Also, the method was relatively robust on the AMC I (Dice, 60.35%; lesion-wise F1, 68.30%) and II (Dice; 74.12%; lesion-wise F1, 67.53%) datasets in different settings. The high segmentation accuracy of our proposed method could improve radiologists' ability to detect ischemic stroke lesions in MRI images. Our model weights and inference code are available on https://github.com/MDOpx/ISLES22-model-inference .

Skeleton extraction of hard‐pen regular script based on stroke characterization and ambiguous zone detection

AbstractThe Intelligent Evaluation System for Calligraphy Characters (IESCC) is used for teaching calligraphy, and users can learn calligraphy through the modifications given by the system. Chinese character skeleton extraction is an important step in the intelligent evaluation algorithm of calligraphic characters. The skeletons of Chinese characters extracted by traditional refinement algorithms are prone to redundant branches and deformed skeletons, which can lead to skeleton extraction results that do not conform to the topology of the original character. In this study, the focus lies on hard‐pen regular script, and skeleton repair and extraction are performed for these characters. According to the writing characteristics of regular script, the redundant burs are removed and the deformation zone of the thinned skeleton is detected, and then the idea of first splitting is used, then restructuring, to propose a skeleton extraction algorithm based on stroke characterization and ambiguous zone detection for hard‐pen regular script, referred to as SCAD. First, a thinning algorithm is used to extract the skeleton of Chinese characters and remove redundant pixels. By analyzing the stroke characteristics of regular script, the burrs are classified and different conditions are set to detect and remove the burrs. Then the ambiguous zones are detected according to the different kinds of junction points. Then, curvature, stroke width and direction deviation are used to analyze the continuity of stroke segments, and the decision function is used to classify the stroke segments. Finally, the stroke segments with optimal pairings were compensated by interpolation according to the direction trend. This concludes the skeleton extraction. Skeleton extraction is performed on 1000 sample characters, and the SCAD algorithm can extract the skeleton of Chinese characters with an accuracy of up to 98.37%. It is proved that the SCAD method proposed here is a practical and effective method to extract the skeleton of hard‐pen regular script.

UNet based on dynamic convolution decomposition and triplet attention

The robustness and generalization of medical image segmentation models are being challenged by the differences between different disease types, different image types, and different cases.Deep learning based semantic segmentation methods have been providing state-of-the-art performance in the last few years. One deep learning technique, U-Net, has become the most popular architecture in the medical imaging segmentation. Despite outstanding overall performance in segmenting medical images, it still has the problems of limited feature expression ability and inaccurate segmentation. To this end, we propose a DTA-UNet based on Dynamic Convolution Decomposition (DCD) and Triple Attention (TA). Firstly, the model with Attention U-Net as the baseline network uses DCD to replace all the conventional convolution in the encoding-decoding process to enhance its feature extraction capability. Secondly, we combine TA with Attention Gate (AG) to be used for skip connection in order to highlight lesion regions by removing redundant information in both spatial and channel dimensions. The proposed model are tested on the two public datasets and actual clinical dataset such as the public COVID-SemiSeg dataset, the ISIC 2018 dataset, and the cooperative hospital stroke segmentation dataset. Ablation experiments on the clinical stroke segmentation dataset show the effectiveness of DCD and TA with only a 0.7628 M increase in the number of parameters compared to the baseline model. The proposed DTA-UNet is further evaluated on the three datasets of different types of images to verify its universality. Extensive experimental results show superior performance on different segmentation metrics compared to eight state-of-art methods.The GitHub URL of our code is https://github.com/shuaihou1234/DTA-UNet.

Brain Diffusion in Brainstem Infarctions and Lesion Segmentation using Fluidattenuation Inversion Recovery: A Diagnostic Accuracy Study

Introduction: Diffusion can efficiently detect infratentorial and brainstem infarctions. Fluid-attenuation Inversion Recovery (FLAIR) is a widely used Magnetic Resonance Imaging (MRI) technique for the segmentation of brain lesions and strokes. Aim: To investigate the sensitivity of the Lesion Prediction Algorithm (LPA) within the Lesion Segmentation Tool (LST) in the automated segmentation of acute and subacute brainstem infarctions. Materials and Methods: This study was a retrospective diagnostic accuracy study where 24 patients with brainstem infarctions were referred from the Emergency Department to the Department of Radiodiagnosis at Kasr Alainy Hospital, Cairo University, Egypt. The study was conducted from September 2016 to June 2023. It included 24 patients (14 males and 10 females) with acute and subacute brainstem infarctions. MRI of the brain and diffusion were performed on all patients. Automated segmentation of brainstem infarctions using FLAIR was conducted in all cases. Manual and segmented volumes of brainstem infarctions were calculated. Sensitivity and accuracy of the LPA within the LST in automated segmentation of acute and subacute brainstem infarctions were evaluated. Pearson correlation was used to correlate volumes of White Matter Lesion (WML) burden in patients with brainstem infarctions and patients’ age. Results: The mean age of the participants was 51.75±11.95 years. The sensitivity of the LPA in automated segmentation of acute and subacute brainstem infarctions was 63.6% and 76.9%, respectively. An insignificant correlation (r=0.08; p-value=0.68) between the volumes of WML burden in patients with brainstem infarctions and patients’ age was noted. Conclusion: The sensitivity of the automated method in the segmentation of subacute brainstem infarctions was higher than that in acute brainstem infarctions.

A few-shot learning-based ischemic stroke segmentation system using weighted MRI fusion

Stroke, particularly ischemic stroke, is a major cause of disability and one of the leading causes of adult mortality worldwide. Early and prompt management of stroke patients can reduce the severity of the disease. Doctors usually determine the severity of a stroke by focusing on the region of interest (ROI) in the MRI or CT scan images. An accurate and effective automatic image segmentation system can assist medical professionals as well as automatic detection and classification systems. Deep learning is the current advanced approach for dealing with machine learning and artificial intelligence. However, conventional deep learning requires a large amount of data for training, and the amount of labeled data in the medical field is limited. In this paper, we propose a few-shot learning strategy and integrate it with a base convolutional neural network model, which utilizes a self-attention mechanism to segment MRI for ischemic stroke. By combining the base model with self-attention, we can focus more on the ROI and disregard less important features. Additionally, the proposed system only selects slices with lesions and ignores unlesioned slices. This helps to improve efficiency and reduce the computational load by eliminating the need to tune unnecessary parameters. To achieve even better results, the system also combines two weighted images, FLAIR and DWI, as an early fusion process. Experiments have shown that this approach leads to higher performance compared to using the same system without fusion. The proposed system is evaluated using a publicly available dataset, ISLES 2015 SSIS, and compared with other state-of-the-art (SOTA) systems. It achieves a dice coefficient score of 0.68, which is significantly better than that of other SOTA systems.

An artificial intelligence approach for segmenting and classifying brain lesions caused by stroke

ABSTRACT Brain injuries caused by strokes are one of the leading causes of disability worldwide. Current procedures require a specialised physician to analyse MRI images before diagnosing and deciding on the specific treatment. However, the procedure can be costly and time-consuming. Artificial intelligence techniques are becoming a game-changer for analysing MRI images. This work proposes an end-to-end approach in three stages: Pre-processing techniques for normalising the images to the standard MNI space, as well as inhomogeneities and bias corrections; lesion segmentation using a CNN network, trained for cerebrovascular accidents and feature extraction; and, classification for determining the vascular territory within which the lesion occurred. A CLCI-Net was used for stroke segmentation. Four Deep Learning (DL) and four Shallow Machine Learning (ML) network architectures were evaluated to assess the strokes’ territory localisation. All models’ architectures were designed, analysed, and compared based on their performance scores, reaching an accuracy of 84% with the DL models and 95% with the Shallow ML models. The proposed methodology may be helpful for rapid and accurate stroke assessment for an acute treatment to minimise patient complications.

Non-inferiority of deep learning ischemic stroke segmentation on non-contrast CT within 16-hours compared to expert neuroradiologists

We determined if a convolutional neural network (CNN) deep learning model can accurately segment acute ischemic changes on non-contrast CT compared to neuroradiologists. Non-contrast CT (NCCT) examinations from 232 acute ischemic stroke patients who were enrolled in the DEFUSE 3 trial were included in this study. Three experienced neuroradiologists independently segmented hypodensity that reflected the ischemic core on each scan. The neuroradiologist with the most experience (expert A) served as the ground truth for deep learning model training. Two additional neuroradiologists’ (experts B and C) segmentations were used for data testing. The 232 studies were randomly split into training and test sets. The training set was further randomly divided into 5 folds with training and validation sets. A 3-dimensional CNN architecture was trained and optimized to predict the segmentations of expert A from NCCT. The performance of the model was assessed using a set of volume, overlap, and distance metrics using non-inferiority thresholds of 20%, 3 ml, and 3 mm, respectively. The optimized model trained on expert A was compared to test experts B and C. We used a one-sided Wilcoxon signed-rank test to test for the non-inferiority of the model-expert compared to the inter-expert agreement. The final model performance for the ischemic core segmentation task reached a performance of 0.46 ± 0.09 Surface Dice at Tolerance 5mm and 0.47 ± 0.13 Dice when trained on expert A. Compared to the two test neuroradiologists the model-expert agreement was non-inferior to the inter-expert agreement, p < 0.05. The before, CNN accurately delineates the hypodense ischemic core on NCCT in acute ischemic stroke patients with an accuracy comparable to neuroradiologists.

Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration

Stroke extraction of Chinese characters plays an important role in the field of character recognition and generation. The most existing character stroke extraction methods focus on image morphological features. These methods usually lead to errors of cross strokes extraction and stroke matching due to rarely using stroke semantics and prior information. In this paper, we propose a deep learning-based character stroke extraction method that takes semantic features and prior information of strokes into consideration. This method consists of three parts: image registration-based stroke registration that establishes the rough registration of the reference strokes and the target as prior information; image semantic segmentation-based stroke segmentation that preliminarily separates target strokes into seven categories; and high-precision extraction of single strokes. In the stroke registration, we propose a structure deformable image registration network to achieve structure-deformable transformation while maintaining the stable morphology of single strokes for character images with complex structures. In order to verify the effectiveness of the method, we construct two datasets respectively for calligraphy characters and regular handwriting characters. The experimental results show that our method strongly outperforms the baselines. Code is available at https://github.com/MengLi-l1/StrokeExtraction.

Construction Models for Image Sketching and Retrieval: A Systematic Review

Introduction: Image searching is a continual challenge even with the many image retrieval models that have sprung up. Sketch-Based Image Retrieval (SBIR) models attempt to solve this challenge by searching using sketching. The existing SBIR algorithms have limited performance because of ambiguities and variations in hand-drawn sketches. Aims: The aim of this work was to review and identify the strengths and weaknesses of the existing SBIR models. Materials and Methods: Articles were selected from Google Scholar assessing strictly sketch construction models. Search terms include sketch construction, sketch-based image retrieval, hypermedia, multimedia, design strategies, and algorithms. Results: The search returned 455 articles of which only 134 studies met the inclusion criteria. 30 papers were on Convolutional Neural Network (CNN) and hybrids. 6 on Contour and Stroke Segments. 4 on Generative Adversarial Network while 3 papers were on Deep Hashing. 6 papers reported use of 3D-CNN-based methods while 85 papers used other methods like sparse coding and bag of regions. Accuracy, recall and precision ranged from 59.47% to 99.4%, 20.10% to 47.70% and 33.40% to 51.00% respectively. Conclusion: There are some promising SBIR models but lots of effort is required if computational SBIRs are to be adopted. Most studies did not include any performance metric which makes it difficult to assess the performances of the algorithms proposed. Researchers are advised to always report the performance algorithms. The future plan is to develop a robust SBIR algorithm which will accommodate handwriting ambiguity variations

Study on the influence of high and low temperature environment on the energy consumption of battery electric vehicles

In order to study the influence of high and low temperature environments on the energy consumption of battery electric vehicles, this paper takes Tianjin as an example to collect the actual road data of 8 battery electric passenger cars for eight months. It determines the correlation between each characteristic parameter and energy consumption based on the maximum mutual information coefficient of short stroke segments, of which the average driving speed correlation is the highest, which is 0.785. Given the two factors that have a greater impact on energy consumption in high and low temperature environments: driving resistance and air conditioning on motion and idle energy consumption analysis, the study shows that in terms of driving resistance, high temperature and low temperature energy consumption are reduced and increased by 5.4% and 13.3% respectively relative to normal temperature; The energy consumption of high temperature and low temperature air conditioner switching on increased by 17.12% and 47.48% respectively compared with the air conditioner off.

A deep supervised cross-attention strategy for ischemic stroke segmentation in MRI studies

The key component of stroke diagnosis is the localization and delineation of brain lesions, especially from MRI studies. Nonetheless, this manual delineation is time-consuming and biased by expert opinion. The main purpose of this study is to introduce an autoencoder architecture that effectively integrates cross-attention mechanisms, together with hierarchical deep supervision to delineate lesions under scenarios of remarked unbalance tissue classes, challenging geometry of the shape, and a variable textural representation. This work introduces a cross-attention deep autoencoder that focuses on the lesion shape through a set of convolutional saliency maps, forcing skip connections to preserve the morphology of affected tissue. Moreover, a deep supervision training scheme was herein adapted to induce the learning of hierarchical lesion details. Besides, a special weighted loss function remarks lesion tissue, alleviating the negative impact of class imbalance. The proposed approach was validated on the public ISLES2017 dataset outperforming state-of-the-art results, achieving a dice score of 0.36 and a precision of 0.42. Deeply supervised cross-attention autoencoders, trained to pay more attention to lesion tissue, are better at estimating ischemic lesions in MRI studies. The best architectural configuration was achieved by integrating ADC, TTP and Tmax sequences. The contribution of deeply supervised cross-attention autoencoders allows better support the discrimination between healthy and lesion regions, which in consequence results in favorable prognosis and follow-up of patients.

TSRL-Net: Target-aware supervision residual learning for stroke segmentation

Accurate stroke segmentation is a crucial task in establishing a computer-aided diagnostic system for brain diseases. However, reducing false negatives and accurately segmenting strokes in MRI images is often challenging because of the class imbalance and intraclass ambiguities problems. To address these issues, we propose a novel target-aware supervision residual learning framework for stroke segmentation. Considering the problem of imbalance of positive and negative samples, a creatively target-aware loss function is designed to dilate strong attention regions, pay high attention to the positive sample losses, and compensate for the loss of negative samples around the target. Then, a coarse-grained residual learning module is developed to gradually fix the lost residual features during the decoding phase to alleviate the problem of high number of false negatives caused by intraclass ambiguities. Here, our reverse/positive attention unit suppresses redundant target/background noise and allows relatively more focused highlighting of important features in the target residual region. Extensive experiments were performed on the Anatomical Tracings of Lesions After Stroke and Ischemic Stroke Lesion Segmentation public datasets, with results suggesting the effectiveness of our proposed method compared to several state-of-the-art methods.