Yang Xu, Qiuyu Fu, Mengqi Qu, Junyao Chen, Jianqi Fan, Shike Hou, Lu Lu
{"title":"创伤性脑损伤患者血肿的自动检测和预后。","authors":"Yang Xu, Qiuyu Fu, Mengqi Qu, Junyao Chen, Jianqi Fan, Shike Hou, Lu Lu","doi":"10.1111/cns.70119","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Purpose</h3>\n \n <p>To develop a tool for automated subtype classification and segmentation of intracranial hemorrhages (ICH) on CT scans of patients with traumatic brain injury (TBI). Furthermore, outcome prediction for patients can effectively facilitate patient management.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>This study presents a cascade framework for two-stage segmentation and multi-label classification. The hematoma region of interest (ROI) is localized, and then the ROI is cropped and resized to the original pixel size before being input into the model again to obtain the segmentation results. In multilabel classification, the mask obtained from automatic segmentation is superimposed onto the corresponding ROI and CT slices, respectively, to constitute the input image. Subsequently, the ROI image is employed as the local network input to obtain local features. Third, the CT image is utilized to construct a feature extraction network to obtain global features. Ultimately, the local and global features are fused dimensions in the pooling layer, and calculated to generate the final retrieval results. For the prediction of 14-day in-hospital mortality, automatically extracted hematoma subtype and volume features were integrated to enhance the widely used CRASH model.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The proposed segmentation method achieves the best estimates on the Dice similarity coefficient and Jaccard Similarity Index. The proposed multilabel classification method achieved an average accuracy of 95.91%. For mortality prediction, the best model achieved an average area under the receiver operating characteristic curve (AUC) of 0.91 by 5-fold cross-validation.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>The proposed method enhances the precision of hematoma segmentation and subtype classification. In clinical settings, the method can streamline the evaluation of ICH for radiologists, and the automatically extracted features are anticipated to facilitate prognosis assessment.</p>\n </section>\n </div>","PeriodicalId":154,"journal":{"name":"CNS Neuroscience & Therapeutics","volume":"30 11","pages":""},"PeriodicalIF":4.8000,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11557439/pdf/","citationCount":"0","resultStr":"{\"title\":\"Automated Hematoma Detection and Outcome Prediction in Patients With Traumatic Brain Injury\",\"authors\":\"Yang Xu, Qiuyu Fu, Mengqi Qu, Junyao Chen, Jianqi Fan, Shike Hou, Lu Lu\",\"doi\":\"10.1111/cns.70119\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Purpose</h3>\\n \\n <p>To develop a tool for automated subtype classification and segmentation of intracranial hemorrhages (ICH) on CT scans of patients with traumatic brain injury (TBI). Furthermore, outcome prediction for patients can effectively facilitate patient management.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Methods</h3>\\n \\n <p>This study presents a cascade framework for two-stage segmentation and multi-label classification. The hematoma region of interest (ROI) is localized, and then the ROI is cropped and resized to the original pixel size before being input into the model again to obtain the segmentation results. In multilabel classification, the mask obtained from automatic segmentation is superimposed onto the corresponding ROI and CT slices, respectively, to constitute the input image. Subsequently, the ROI image is employed as the local network input to obtain local features. Third, the CT image is utilized to construct a feature extraction network to obtain global features. Ultimately, the local and global features are fused dimensions in the pooling layer, and calculated to generate the final retrieval results. For the prediction of 14-day in-hospital mortality, automatically extracted hematoma subtype and volume features were integrated to enhance the widely used CRASH model.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>The proposed segmentation method achieves the best estimates on the Dice similarity coefficient and Jaccard Similarity Index. The proposed multilabel classification method achieved an average accuracy of 95.91%. For mortality prediction, the best model achieved an average area under the receiver operating characteristic curve (AUC) of 0.91 by 5-fold cross-validation.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Conclusions</h3>\\n \\n <p>The proposed method enhances the precision of hematoma segmentation and subtype classification. In clinical settings, the method can streamline the evaluation of ICH for radiologists, and the automatically extracted features are anticipated to facilitate prognosis assessment.</p>\\n </section>\\n </div>\",\"PeriodicalId\":154,\"journal\":{\"name\":\"CNS Neuroscience & Therapeutics\",\"volume\":\"30 11\",\"pages\":\"\"},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2024-11-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11557439/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"CNS Neuroscience & Therapeutics\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/cns.70119\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"NEUROSCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"CNS Neuroscience & Therapeutics","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/cns.70119","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
引用次数: 0
摘要
目的:开发一种工具,用于对创伤性脑损伤(TBI)患者 CT 扫描中的颅内出血(ICH)进行自动亚型分类和分割。此外,对患者的预后预测可有效促进患者管理:本研究提出了一种用于两阶段分割和多标签分类的级联框架。首先对血肿感兴趣区域(ROI)进行定位,然后将 ROI 裁剪并调整为原始像素大小,最后再次输入模型以获得分割结果。在多标签分类中,自动分割得到的掩膜分别叠加到相应的 ROI 和 CT 切片上,构成输入图像。然后,将 ROI 图像作为局部网络输入,以获得局部特征。第三,利用 CT 图像构建特征提取网络,以获得全局特征。最后,局部特征和全局特征在池化层中进行维度融合,并通过计算得出最终检索结果。在预测 14 天院内死亡率时,自动提取的血肿亚型和体积特征被整合到广泛使用的 CRASH 模型中:结果:提出的分割方法实现了对 Dice 相似系数和 Jaccard 相似指数的最佳估计。所提出的多标签分类方法的平均准确率达到 95.91%。在死亡率预测方面,通过 5 倍交叉验证,最佳模型的接收者工作特征曲线下的平均面积(AUC)达到了 0.91:结论:所提出的方法提高了血肿分割和亚型分类的精确度。结论:所提出的方法提高了血肿分割和亚型分类的精确度,在临床环境中,该方法可简化放射科医生对 ICH 的评估,自动提取的特征有望促进预后评估。
Automated Hematoma Detection and Outcome Prediction in Patients With Traumatic Brain Injury
Purpose
To develop a tool for automated subtype classification and segmentation of intracranial hemorrhages (ICH) on CT scans of patients with traumatic brain injury (TBI). Furthermore, outcome prediction for patients can effectively facilitate patient management.
Methods
This study presents a cascade framework for two-stage segmentation and multi-label classification. The hematoma region of interest (ROI) is localized, and then the ROI is cropped and resized to the original pixel size before being input into the model again to obtain the segmentation results. In multilabel classification, the mask obtained from automatic segmentation is superimposed onto the corresponding ROI and CT slices, respectively, to constitute the input image. Subsequently, the ROI image is employed as the local network input to obtain local features. Third, the CT image is utilized to construct a feature extraction network to obtain global features. Ultimately, the local and global features are fused dimensions in the pooling layer, and calculated to generate the final retrieval results. For the prediction of 14-day in-hospital mortality, automatically extracted hematoma subtype and volume features were integrated to enhance the widely used CRASH model.
Results
The proposed segmentation method achieves the best estimates on the Dice similarity coefficient and Jaccard Similarity Index. The proposed multilabel classification method achieved an average accuracy of 95.91%. For mortality prediction, the best model achieved an average area under the receiver operating characteristic curve (AUC) of 0.91 by 5-fold cross-validation.
Conclusions
The proposed method enhances the precision of hematoma segmentation and subtype classification. In clinical settings, the method can streamline the evaluation of ICH for radiologists, and the automatically extracted features are anticipated to facilitate prognosis assessment.
期刊介绍:
CNS Neuroscience & Therapeutics provides a medium for rapid publication of original clinical, experimental, and translational research papers, timely reviews and reports of novel findings of therapeutic relevance to the central nervous system, as well as papers related to clinical pharmacology, drug development and novel methodologies for drug evaluation. The journal focuses on neurological and psychiatric diseases such as stroke, Parkinson’s disease, Alzheimer’s disease, depression, schizophrenia, epilepsy, and drug abuse.