AI-FLEET:一期多模组深度学习模型,用于细胞瘤瘤分类
Logan Holt1, Victoria Chamberlain1, Tyler Shern1
1Breast Section, Division of Gastrointestinal and Oncologic Surgery, MGH Center for Breast Cancer, Massachusetts General Hospital, Boston, MA, USA.
整合超声波和临床数据的人工智能 (AI) 模型准确地区分良性与恶性纤维皮质乳腺病变. 这种人工智能辅助的方法提高了植物瘤 (PTs) 的诊断准确性,减少了错误分类的风险.
科学领域:
- 放射学和医学成像学 医学成像学
- 人工智能在医学中的应用
- 在瘤学瘤学.
背景情况:
- 纤维皮质乳腺病变,包括纤维腺瘤和乳腺瘤 (PTs),在针活检中构成诊断挑战.
- 错误分类可能导致对良性病变进行不必要的手术或延迟对恶性PT的治疗.
- 该AI-FLEET计划旨在通过整合各种数据类型来提高诊断准确性.
研究的目的:
- 开发和评估人工智能模型,使用超声波和临床数据来区分良性和边缘性/恶性PT.
- 评估不同深度学习架构在分类纤维皮质病变方面的表现.
主要方法:
- 对81名经组织学确认的PT患者 (65名良性,16名边缘/恶性) 的回顾性分析.
- 使用超声波图像和临床变量 (年龄,BMI,种族,更年期状态,回声性,瘤大小) 训练多式深度学习模型 (ConvNeXt,ResNet18).
- 通过对象分层的五重交叉验证进行评估.
主要成果:
- 多式联网 ConvNeXt 和 ResNet18 模型实现了高精度 (0.91-0.92) 和 AUC (0.94).
- 仅超声波和仅临床模型的性能较低 (AUC分别为0.89和0.78).
- 通过突出性分析,内异质性被确定为一个关键的预测特征.
结论:
- 多模式深度学习模型有效地区分良性与边缘性/恶性PT.
- 人工智能辅助的纤维皮质病变评估是可行的,显示出高的诊断准确性.
- 未来的工作 (第二阶段) 将纳入组织病理学和良性纤维腺瘤病例,以加强整合.
更多相关视频
09:34A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
Published on: September 25, 2021
12:55Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties
Published on: September 27, 2020
相关概念视频
Phase Diagrams
Phase Transitions
Force Classification
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Classification of Neurotransmitters
Classification of Leukocytes
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
