摘要
机器人与机器学习每日新闻-脑血管疾病和状况的新研究-的新闻记者兼新闻编辑-中风是一篇报道的主题。根据NewsRx记者在中国大庆的新闻报道，研究人员指出：“本研究提出了一种基于全脑特征差异的预后预测方法，以提高缺血性卒中预后预测的准确性和有效性，而不使用患者的基本信息和病灶的IM年龄特征。”我们直接从动态敏感性对比灌注加权成像(DSCPWI)中提取动态放射组学特征(DRFs)，进一步从DSC-PWI图像的时间维度生成的最小强度投影(MinIP)图中提取静态放射组学特征(SRFs)和静态包裹特征(SEFs)。新闻记者引用了东北石油大学的一篇研究文章:“用LASO算法从DRFs、SRFs和SEFs的组合中选择全脑特征F后,利用各种机器和深度学习模型S来评价F在预测脑卒中预后中的作用,实验结果表明,由DRFs、SEFs生成的特征F在预测脑卒中预后中的作用。”SEFs(Resne T 18)在机器学习模型和深度学习模型上表现优于其他单一特征和组合特征，最佳MEAN得分为0.971，95%CI分别为(0.703，0.877)和(0.92,0.983)。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Cerebrovascular Diseas es and Conditions - Stroke is the subject of a report. According to news reporti ng originating in Daqing, People’s Republic of China, by NewsRx journalists, res earch stated, “This study proposed an outcome prediction method to improve the a ccuracy and efficacy of ischemic stroke outcome prediction based on the diversit y of whole brain features, without using basic information about patients and im age features in lesions. In this study, we directly extracted dynamic radiomics features (DRFs) from dynamic susceptibility contrast perfusion-weighted imaging (DSCPWI) and further extracted static radiomics features (SRFs) and static enco ding features (SEFs) from the minimum intensity projection (MinIP) map, which wa s generated from the time dimension of DSC-PWI images.” The news reporters obtained a quote from the research from Northeast Petroleum U niversity, “After selecting whole brain features F from the combinations of DRFs , SRFs, and SEFs by the Lasso algorithm, various machine and deep learning model s were used to evaluate the role of F in predicting stroke outcomes. The experim ental results show that the feature F generated from DRFs, SRFs, and SEFs (Resne t 18) outperformed other single and combination features and achieved the best m ean score of 0.971 both on machine learning models and deep learning models and the 95% CI were (0.703, 0.877) and (0.92, 0.983), respectively. Be sides, the deep learning models generally performed better than the machine lear ning models.”
NETL
NSTL