Parameter-Efficient Methods for Metastases Detection from Clinical Notes
Memorial Sloan Kettering Cancer Center(纪念斯隆凯特琳癌症中心)
Maede Ashofteh Barabadi, Xiaodan Zhu, Wai Yip Chan, Amber L. Simpson, Richard K. G. Do
备注:
6 pages, 1 figure, The 36th Canadian Conference on Artificial Intelligence
发表信息:
Barabadi, M. A., Zhu, X., Chan, W. Y., Simpson, A. L., & Do, R. K. G. (2023). Parameter-Efficient Methods for Metastases Detection fromClinical Notes. Proceedings of the Canadian Conference on Artificial Intelligence
Understanding the progression of cancer is crucial for defining treatments for patients. The objective of this study is to automate the detection of metastatic liver disease from free-style computed tomography (CT) radiology reports. Our research demonstrates that transferring knowledge using three approaches can improve model performance. First, we utilize generic language models (LMs), pretrained in a self-supervised manner. Second, we use a semi-supervised approach to train our model by automatically annotating a large unlabeled dataset; this approach substantially enhances the model's performance. Finally, we transfer knowledge from related tasks by designing a multi-task transfer learning methodology. We leverage the recent advancement of parameter-efficient LM adaptation strategies to improve performance and training efficiency. Our dataset consists of CT reports collected at Memorial Sloan Kettering Cancer Center (MSKCC) over the course of 12 years. 2,641 reports were manually annotated by domain experts; among them, 841 reports have been annotated for the presence of liver metastases. Our best model achieved an F1-score of 73.8%, a precision of 84%, and a recall of 65.8%.
Stanford Center for Biomedical Informatics Research(斯坦福大学生物医学信息学研究中心);USC Information Sciences Institute, University of Southern California(南加州大学信息科学研究所)
Prediction of Local Failure after Stereotactic Radiotherapy in Melanoma Brain Metastases Using Ensemble Learning on Clinical, Dosimetric, and Radiomic Data
Medical Center University of Freiburg(弗莱堡大学医学中心);University Medical Center Schleswig-Holstein(石勒苏益格-荷尔斯泰因大学医学中心);Technical University of Munich (TUM)(慕尼黑工业大学);German Cancer Consortium (DKTK)(德国癌症联盟)
Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images
National Institute of Informatics(国立信息学研究所);National Center for Global Health and Medicine(国立国际医疗研究中心);University of Cambridge(剑桥大学);The University of Tokyo(东京大学)
准确的计算机辅助诊断,与适当的数据争论相关联,可以减轻在临床环境中忽视诊断的风险。为此,作为一种数据增强(DA)技术,生成对抗网络(GANs)可以合成额外的训练数据来处理从各种扫描仪收集的小/碎片医学成像数据集;这些图像是真实的,但与原始图像完全不同,填补了真实图像分布中的数据缺失。然而,考虑到专家医师昂贵的注释成本,我们不能轻易地使用它们来定位疾病区域。因此,本文提出了GANs的条件渐进生长(CPGGAN),将高度粗糙的边界框条件递增地并入PGGAN中,以将脑转移瘤放置在256 X 256磁共振(MR)图像上的期望位置/尺寸处,用于基于卷积神经网络的肿瘤检测;这是第一个使用自动限界框注释的基于GAN的医学DA,提高了训练鲁棒性。结果表明,基于CPGGAN的DA可以提高10%的诊断灵敏度,并具有临床上可接受的额外假阳性。令人惊讶的是,使用额外的正常脑MR图像进行CPGGAN训练所实现的进一步的肿瘤真实性对检测性能没有贡献,而即使是三位医生也无法在视觉图灵测试中准确地将它们与真实的肿瘤区分开来。
AI-driven software for automated quantification of skeletal metastases and treatment response evaluation using Whole-Body Diffusion-Weighted MRI (WB-DWI) in Advanced Prostate Cancer
The Institute of Cancer Research(癌症研究院);The Royal Marsden NHS Foundation Trust(皇家马斯登NHS基金会信托);IEO European Institute of Oncology IRCCS(欧洲肿瘤研究院);University Hospital Basel(巴塞尔大学医院)
Computing patient similarity based on unstructured clinical notes
Faculty of Informatics, Masaryk University(马萨里克大学信息学院);Department of Comprehensive Cancer Care, Masaryk Memorial Cancer Institute(马萨里克纪念癌症研究所综合癌症护理部门);Faculty of Medicine, Masaryk University(马萨里克大学医学院);Bioinformatics research group, Masaryk Memorial Cancer Institute(马萨里克纪念癌症研究所生物信息学研究组)
Harvard T.H. Chan School of Public Health(哈佛陈曾熙公共卫生学院);Massachusetts Institute of Technology(麻省理工学院);Harvard Medical School(哈佛医学院);Dana-Farber Cancer Institute(丹娜-法伯癌症研究所);Brigham and Women’s Hospital(布莱根妇女医院)
Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT
Institute of Neuroradiology, TUM University Hospital, School of Medicine and Health, Technical University of Munich (TUM)(慕尼黑工业大学大学医院神经放射学研究所,医学与健康学院,慕尼黑工业大学);Chair for AI in Healthcare and Medicine, TUM and TUM University Hospital(慕尼黑工业大学及大学医院医疗与医学人工智能教席);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Institute of Diagnostic and Interventional Radiology, TUM University Hospital, School of Medicine and Health, Technical University of Munich (TUM)(慕尼黑工业大学大学医院诊断与介入放射学研究所,医学与健康学院,慕尼黑工业大学);Department of Neuroradiology, University Hospital Munich (LMU)(慕尼黑大学医院神经放射学系);Department of Quantitative Biomedicine, University of Zurich(苏黎世大学定量生物医学系);Department of Computing, Imperial College London(伦敦帝国理工学院计算系);Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt(法兰克福大学医院诊断与介入放射学系);Department of Orthopedics and Sports Orthopedics, TUM University Hospital, School of Medicine and Health, Technical University of Munich (TUM)(慕尼黑工业大学大学医院骨科与运动骨科,医学与健康学院,慕尼黑工业大学)
HERMES: Contrast-Aware Knowledge Graph Reasoning from Clinical Notes for Patient Outcome Prediction
Business AI Lab, College of Technology, National Economics University(国民经济大学技术学院商业人工智能实验室);Hanoi University of Science and Technology(河内理工大学);A2I Lab, Phenikaa School of Computing, Phenikaa University(Phenikaa大学Phenikaa计算学院A2I实验室);Department of Head and Neck Surgery, Vietnam National Cancer Hospital & Hanoi Medical University(越南国家癌症医院头颈外科与河内医科大学);VNPT AI, VNPT Group(VNPT集团VNPT AI)
DENSE: Longitudinal Progress Note Generation with Temporal Modeling of Heterogeneous Clinical Notes Across Hospital Visits
Department of Computer Science and Information Systems, Birla Institute of Technology and Science, Pilani, Hyderabad Campus(计算机科学与信息系统系,比拉理工学院,比拉理工学院,海得拉巴校区)
Towards Adapting Open-Source Large Language Models for Expert-Level Clinical Note Generation
Mayo Clinic Health System(梅奥诊所健康系统);School of Computing and Data Science, UIUC(UIUC计算与数据科学学院);Mayo Clinic Rochester(梅奥诊所罗切斯特分部);Carle Illinois College of Medicine, UIUC(UIUC卡勒伊利诺伊医学院)
Adaptation of Autoencoder for Sparsity Reduction From Clinical Notes Representation Learning
École de Technologie Supérieure, University of Québec(魁北克大学高等技术学院);CHU Sainte-Justine Research Center(圣贾斯汀儿童医院研究中心);CHU Sainte-Justine Hospital(圣贾斯汀儿童医院);University of Montreal(蒙特利尔大学)
Towards Scalable SOAP Note Generation: A Weakly Supervised Multimodal Framework
Department of Computer Science, University of Maryland, Baltimore County(计算机科学系,马里兰大学巴尔的摩县分校);Department of Dermatology, Johns Hopkins University School of Medicine(皮肤科系,约翰霍普金斯大学医学院)
Skin-SOAP: A Weakly Supervised Framework for Generating Structured SOAP Notes
Department of Computer Science, University of Maryland, Baltimore County(计算机科学系,马里兰大学巴尔的摩县分校);Department of Dermatology, Johns Hopkins University School of Medicine(皮肤科系,约翰霍普金斯大学医学院)