[{"data":1,"prerenderedAt":561},["ShallowReactive",2],{"content-query-RBIR6HWmTn":3},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":9,"date":10,"cover":11,"type":12,"body":13,"_type":555,"_id":556,"_source":557,"_file":558,"_stem":559,"_extension":560},"/news/zh/1851","zh",false,"","加入昇思MindSpore医疗影像AI SIG，共同提高医学诊疗服务水平","昇思MindSpore医疗影像AI专项兴趣小组（简称：医疗影像AI SIG）正式成立，并面向开源社区招募志同道合的伙伴。","2022-09-19","https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/09/29/f7085541abe046049865491134ce64b6.png","news",{"type":14,"children":15,"toc":552},"root",[16,24,33,38,43,59,64,69,82,87,98,103,114,119,130,135,146,151,162,167,178,183,197,205,210,218,223,231,236,250,258,265,275,282,292,300,312,324,336,347,358,370,384,389,396,401,409,414,422,429,434,441,446,451,456,461,468,475,483,493,511,521,537],{"type":17,"tag":18,"props":19,"children":21},"element","h1",{"id":20},"加入昇思mindspore医疗影像ai-sig共同提高医学诊疗服务水平",[22],{"type":23,"value":8},"text",{"type":17,"tag":25,"props":26,"children":27},"p",{},[28],{"type":17,"tag":29,"props":30,"children":32},"img",{"alt":7,"src":31},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/09/29/facf787817f34d8195739c08b429ea96.gif",[],{"type":17,"tag":25,"props":34,"children":35},{},[36],{"type":23,"value":37},"随着人们健康意识的逐渐增强，人们对医学诊疗服务的需求也与日俱增。目前，基于AI的医学图像辅助诊断模型日趋成熟，如在皮肤病、眼底视网膜病变等诊断任务中，基于人工智能的辅助诊断算法在精度方面已经能够接近、甚至超越了临床专家。将基于AI影像的辅助诊断模型部署到诊疗服务水平较低的城乡基层卫生单位，可有效降低误诊率，提高城乡医疗诊断质量，缓解我国各地医疗资源分配不均衡的问题。因此，研究基于AI影像的辅助诊断系统具有重要的社会价值。",{"type":17,"tag":25,"props":39,"children":40},{},[41],{"type":23,"value":42},"在此背景下，昇思MindSpore医疗影像AI专项兴趣小组（简称：医疗影像AI SIG）正式成立，并面向开源社区招募志同道合的伙伴。",{"type":17,"tag":25,"props":44,"children":45},{},[46,52,54],{"type":17,"tag":47,"props":48,"children":49},"strong",{},[50],{"type":23,"value":51},"1",{"type":23,"value":53}," ",{"type":17,"tag":47,"props":55,"children":56},{},[57],{"type":23,"value":58},"医疗影像AI SIG的使命",{"type":17,"tag":25,"props":60,"children":61},{},[62],{"type":23,"value":63},"对多数疾病诊断问题而言，受数据采集成本、医师临床经验水平和标注习惯差异等因素影响，可用的带标签医学图像通常只有几千张甚至更少。因此，医疗影像AI SIG成立的目的是针对医学小样本数据，在昇思MindSpore框架下开发高效精确的AI辅助诊断模型，构建高效的高维医学影像分割标注工具，提升疾病诊断的精确性。",{"type":17,"tag":25,"props":65,"children":66},{},[67],{"type":23,"value":68},"小组的重点工作包括一下几个方向：",{"type":17,"tag":70,"props":71,"children":72},"ul",{},[73],{"type":17,"tag":74,"props":75,"children":76},"li",{},[77],{"type":17,"tag":47,"props":78,"children":79},{},[80],{"type":23,"value":81},"轻量级深度学习模型构建",{"type":17,"tag":25,"props":83,"children":84},{},[85],{"type":23,"value":86},"针对二维医学小样本数据，构建轻量级深度学习模型（包括CNN，GAN及Transformer等模型），降低模型训练难度，提升模型在疾病诊断中的通用性。",{"type":17,"tag":70,"props":88,"children":89},{},[90],{"type":17,"tag":74,"props":91,"children":92},{},[93],{"type":17,"tag":47,"props":94,"children":95},{},[96],{"type":23,"value":97},"面向高维医学图像的新型深度学习模型设计",{"type":17,"tag":25,"props":99,"children":100},{},[101],{"type":23,"value":102},"研究高维深度学习模型，通过引入注意力机制等策略，在降低模型复杂度的同时，提升模型的性能。",{"type":17,"tag":70,"props":104,"children":105},{},[106],{"type":17,"tag":74,"props":107,"children":108},{},[109],{"type":17,"tag":47,"props":110,"children":111},{},[112],{"type":23,"value":113},"轻量级深度学习模型及高维深度学习模型的高效训练策略研究",{"type":17,"tag":25,"props":115,"children":116},{},[117],{"type":23,"value":118},"研究新的自监督训练策略（如知识蒸馏、元匹配），提升CNN及Transformer等模型在小样本医学数据上的性能。",{"type":17,"tag":70,"props":120,"children":121},{},[122],{"type":17,"tag":74,"props":123,"children":124},{},[125],{"type":17,"tag":47,"props":126,"children":127},{},[128],{"type":23,"value":129},"模型的推广",{"type":17,"tag":25,"props":131,"children":132},{},[133],{"type":23,"value":134},"基于全场景AI框架昇思MindSpore，实现模型的落地和推广。",{"type":17,"tag":70,"props":136,"children":137},{},[138],{"type":17,"tag":74,"props":139,"children":140},{},[141],{"type":17,"tag":47,"props":142,"children":143},{},[144],{"type":23,"value":145},"面向医学影像诊断可解释性的强化学习框架",{"type":17,"tag":25,"props":147,"children":148},{},[149],{"type":23,"value":150},"基于昇思MindSpore，在医学影像诊断的可解释性领域研发深度强化学习框架。",{"type":17,"tag":70,"props":152,"children":153},{},[154],{"type":17,"tag":74,"props":155,"children":156},{},[157],{"type":17,"tag":47,"props":158,"children":159},{},[160],{"type":23,"value":161},"稳健的医学影像深度学习分析模型构建",{"type":17,"tag":25,"props":163,"children":164},{},[165],{"type":23,"value":166},"探索深度学习模型在医学影像分割和诊断任务中对影像质量漂移的稳健性，尤其是探索推动昇思MindSpore对轻量、快速的在线学习的支持。",{"type":17,"tag":70,"props":168,"children":169},{},[170],{"type":17,"tag":74,"props":171,"children":172},{},[173],{"type":17,"tag":47,"props":174,"children":175},{},[176],{"type":23,"value":177},"高效的高维医学影像分割标注工具的构建",{"type":17,"tag":25,"props":179,"children":180},{},[181],{"type":23,"value":182},"基于昇思MindSpore，构建通用的、高效的高维医学影像（视频影像和三维影像）的分割标注工具模块，为医生提供简单易用、精确快速的标注支持，减少医生的耗时。",{"type":17,"tag":25,"props":184,"children":185},{},[186,191,192],{"type":17,"tag":47,"props":187,"children":188},{},[189],{"type":23,"value":190},"2",{"type":23,"value":53},{"type":17,"tag":47,"props":193,"children":194},{},[195],{"type":23,"value":196},"医疗影像AI SIG工作计划",{"type":17,"tag":25,"props":198,"children":199},{},[200],{"type":17,"tag":47,"props":201,"children":202},{},[203],{"type":23,"value":204},"初期",{"type":17,"tag":25,"props":206,"children":207},{},[208],{"type":23,"value":209},"以成员学术交流活动为主，每月组织线上交流活动，围绕医疗AI中涉及的图像分类、图像降噪、图像分割、图像配准、图像降噪及图像融合等问题，介绍研究工作进展，讨论研究工作中的难点。",{"type":17,"tag":25,"props":211,"children":212},{},[213],{"type":17,"tag":47,"props":214,"children":215},{},[216],{"type":23,"value":217},"中期",{"type":17,"tag":25,"props":219,"children":220},{},[221],{"type":23,"value":222},"通过合作开发等模式，在国内高校及企业间开展医疗AI问题的合作研究。",{"type":17,"tag":25,"props":224,"children":225},{},[226],{"type":17,"tag":47,"props":227,"children":228},{},[229],{"type":23,"value":230},"后期",{"type":17,"tag":25,"props":232,"children":233},{},[234],{"type":23,"value":235},"通过任务揭榜或比赛PK等模式，在全球范围内开展医疗AI问题的合作研究。",{"type":17,"tag":25,"props":237,"children":238},{},[239,244,245],{"type":17,"tag":47,"props":240,"children":241},{},[242],{"type":23,"value":243},"3",{"type":23,"value":53},{"type":17,"tag":47,"props":246,"children":247},{},[248],{"type":23,"value":249},"医疗影像AI SIG构成",{"type":17,"tag":25,"props":251,"children":252},{},[253],{"type":17,"tag":47,"props":254,"children":255},{},[256],{"type":23,"value":257},"领衔成员",{"type":17,"tag":25,"props":259,"children":260},{},[261],{"type":17,"tag":29,"props":262,"children":264},{"alt":7,"src":263},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/09/29/8c8576d7a6a549b8a76ef9b21452327e.png",[],{"type":17,"tag":25,"props":266,"children":267},{},[268,273],{"type":17,"tag":47,"props":269,"children":270},{},[271],{"type":23,"value":272},"张旭明",{"type":23,"value":274},"，华中科技大学生命科学与技术学院副教授，研究方向包括手术导航和手术机器人，博士毕业于上海交通大学。近年来，承担国家重点研发计划课题2项，国家自然基金面上项目1项，863子课题1项，中国人工智能学会-华为MindSpore学术奖励基金1项，发表SCI论文60余篇，获得国家授权专利26项，获2021年湖北省科技部进步奖一等奖1项，在华为MindSpore平台支持下，指导本科生获全国生医电子创新大赛二等奖2项。",{"type":17,"tag":25,"props":276,"children":277},{},[278],{"type":17,"tag":29,"props":279,"children":281},{"alt":7,"src":280},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/09/29/570da5e3211a48c19537b5e401eafaaa.png",[],{"type":17,"tag":25,"props":283,"children":284},{},[285,290],{"type":17,"tag":47,"props":286,"children":287},{},[288],{"type":23,"value":289},"杨鑫",{"type":23,"value":291},"，深圳大学医学部助理教授。香港中文大学博士，北卡罗莱纳大学教堂山分校和哈佛大学医学院访问学者，深圳市海外高层次人才。主要从事智能化医学超声影像研究。在顶级期刊和会议发表论文60余篇，三次获得MICCAI大会演讲，学术引用4170余次。带领研发了首款一站式医学影像标注软件Pair，填补领域空白。推动了华为全场景深度学习框架MindSpore在医学影像标注领域的多个智能应用。主持国家自然科学基金1项、深圳市稳定支持A类项目1项，参与国家重点研发计划1项。",{"type":17,"tag":25,"props":293,"children":294},{},[295],{"type":17,"tag":47,"props":296,"children":297},{},[298],{"type":23,"value":299},"小组成员",{"type":17,"tag":25,"props":301,"children":302},{},[303,305,310],{"type":23,"value":304},"01：",{"type":17,"tag":47,"props":306,"children":307},{},[308],{"type":23,"value":309},"苑玉杰",{"type":23,"value":311},"，昇思MindSpore布道师",{"type":17,"tag":25,"props":313,"children":314},{},[315,317,322],{"type":23,"value":316},"02：",{"type":17,"tag":47,"props":318,"children":319},{},[320],{"type":23,"value":321},"朱星星",{"type":23,"value":323},"，华中科技大学生命科学与技术学院，博士后",{"type":17,"tag":25,"props":325,"children":326},{},[327,329,334],{"type":23,"value":328},"03：",{"type":17,"tag":47,"props":330,"children":331},{},[332],{"type":23,"value":333},"王一博",{"type":23,"value":335},"，华中科技大学生命科学与技术学院，硕士生",{"type":17,"tag":25,"props":337,"children":338},{},[339,341,346],{"type":23,"value":340},"04：",{"type":17,"tag":47,"props":342,"children":343},{},[344],{"type":23,"value":345},"闻明伟",{"type":23,"value":335},{"type":17,"tag":25,"props":348,"children":349},{},[350,352,357],{"type":23,"value":351},"05：",{"type":17,"tag":47,"props":353,"children":354},{},[355],{"type":23,"value":356},"余斌",{"type":23,"value":335},{"type":17,"tag":25,"props":359,"children":360},{},[361,363,368],{"type":23,"value":362},"06：",{"type":17,"tag":47,"props":364,"children":365},{},[366],{"type":23,"value":367},"叶胤妤",{"type":23,"value":369},"，深圳大学医学部生物医学工程学院，硕士生",{"type":17,"tag":25,"props":371,"children":372},{},[373,378,379],{"type":17,"tag":47,"props":374,"children":375},{},[376],{"type":23,"value":377},"4",{"type":23,"value":53},{"type":17,"tag":47,"props":380,"children":381},{},[382],{"type":23,"value":383},"医疗影像AI SIG召唤你",{"type":17,"tag":25,"props":385,"children":386},{},[387],{"type":23,"value":388},"扫码加入医疗影像AI SIG交流群",{"type":17,"tag":25,"props":390,"children":391},{},[392],{"type":17,"tag":29,"props":393,"children":395},{"alt":7,"src":394},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/09/29/a979e661f18f4b72a937db24c609c617.png",[],{"type":17,"tag":25,"props":397,"children":398},{},[399],{"type":23,"value":400},"医疗影像AI SIG联合2022CCF大数据与计算智能大赛发起昇思MindSpore赛道：基于昇思MindSpore AI框架的肾脏肿瘤分割。医疗影像AI SIG还会提供系统性的培训和参赛指导，帮助大家取得更好的成绩。",{"type":17,"tag":25,"props":402,"children":403},{},[404],{"type":17,"tag":47,"props":405,"children":406},{},[407],{"type":23,"value":408},"赛题任务",{"type":17,"tag":25,"props":410,"children":411},{},[412],{"type":23,"value":413},"这一挑战的目标是开发快速可靠的肾脏和肾脏肿瘤语义分割方法，形态上的异质性以及模糊的组织边界可能是需要解决的难题。比赛提供接受部分或根治性肾切除术的210例肾癌患者的动脉期腹部CT扫描数据，并标记了真实的语义分割结果。",{"type":17,"tag":25,"props":415,"children":416},{},[417],{"type":17,"tag":47,"props":418,"children":419},{},[420],{"type":23,"value":421},"赛题奖金",{"type":17,"tag":25,"props":423,"children":424},{},[425],{"type":17,"tag":29,"props":426,"children":428},{"alt":7,"src":427},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/09/29/7d298f7e4a3d4fd4b4727b7e43876522.png",[],{"type":17,"tag":25,"props":430,"children":431},{},[432],{"type":23,"value":433},"扫码了解更多赛题详情",{"type":17,"tag":25,"props":435,"children":436},{},[437],{"type":17,"tag":29,"props":438,"children":440},{"alt":7,"src":439},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/09/29/4b2e88ef82f44aa9a9aaee3e3a8cde62.png",[],{"type":17,"tag":25,"props":442,"children":443},{},[444],{"type":23,"value":445},"关于MindSpore SIG",{"type":17,"tag":25,"props":447,"children":448},{},[449],{"type":23,"value":450},"昇思MindSpore社区欢迎业界专家、学术伙伴在社区成立特别兴趣小组（SIG），作为社区领域技术代言人，打造领域技术品牌，共建昇思MindSpore开源生态。",{"type":17,"tag":25,"props":452,"children":453},{},[454],{"type":23,"value":455},"MindSpore SIG即MindSpore Special Interest Groups，即“昇思特别兴趣小组”，MindSpore社区成立个技术SIG的初衷是为该领域的专家、教授和学生提供一个开放交流的平台，通过会议分享、项目开发等活动促进技术交流、合作共赢，并使得SIG成员的影响力和技术能力得到提升，截止目前，MindSpore SIG共计成立20+。",{"type":17,"tag":25,"props":457,"children":458},{},[459],{"type":23,"value":460},"如果你也想成立一个SIG",{"type":17,"tag":25,"props":462,"children":463},{},[464],{"type":17,"tag":29,"props":465,"children":467},{"alt":7,"src":466},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/09/29/4b02bd88c7134d1a997d20300256f43e.png",[],{"type":17,"tag":25,"props":469,"children":470},{},[471],{"type":17,"tag":29,"props":472,"children":474},{"alt":7,"src":473},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/09/29/24695f96c23c474cb008d860fbb1fd6a.jpg",[],{"type":17,"tag":25,"props":476,"children":477},{},[478],{"type":17,"tag":47,"props":479,"children":480},{},[481],{"type":23,"value":482},"MindSpore官方资料",{"type":17,"tag":25,"props":484,"children":485},{},[486,491],{"type":17,"tag":47,"props":487,"children":488},{},[489],{"type":23,"value":490},"官方QQ群",{"type":23,"value":492}," : 486831414",{"type":17,"tag":25,"props":494,"children":495},{},[496,501,503],{"type":17,"tag":47,"props":497,"children":498},{},[499],{"type":23,"value":500},"官网",{"type":23,"value":502},"：",{"type":17,"tag":504,"props":505,"children":509},"a",{"href":506,"rel":507},"https://www.mindspore.cn/",[508],"nofollow",[510],{"type":23,"value":506},{"type":17,"tag":25,"props":512,"children":513},{},[514,519],{"type":17,"tag":47,"props":515,"children":516},{},[517],{"type":23,"value":518},"Gitee",{"type":23,"value":520}," : https : //gitee.com/mindspore/mindspore",{"type":17,"tag":25,"props":522,"children":523},{},[524,529,531],{"type":17,"tag":47,"props":525,"children":526},{},[527],{"type":23,"value":528},"GitHub",{"type":23,"value":530}," : ",{"type":17,"tag":504,"props":532,"children":535},{"href":533,"rel":534},"https://github.com/mindspore-ai/mindspore",[508],[536],{"type":23,"value":533},{"type":17,"tag":25,"props":538,"children":539},{},[540,545,546],{"type":17,"tag":47,"props":541,"children":542},{},[543],{"type":23,"value":544},"论坛",{"type":23,"value":502},{"type":17,"tag":504,"props":547,"children":550},{"href":548,"rel":549},"https://bbs.huaweicloud.com/forum/forum-1076-1.html",[508],[551],{"type":23,"value":548},{"title":7,"searchDepth":553,"depth":553,"links":554},4,[],"markdown","content:news:zh:1851.md","content","news/zh/1851.md","news/zh/1851","md",1776506054977]