电子学报 ›› 2019, Vol. 47 ›› Issue (1): 220-226.DOI: 10.3969/j.issn.0372-2112.2019.01.029

所属专题: 机器学习与智慧医疗

• 综述评论 • 上一篇    下一篇

跨模态医学图像预测综述

周沛1, 陈后金1, 于泽宽2, 彭亚辉1, 李艳凤1, 杨帆1   

  1. 1. 北京交通大学, 北京 100044;
    2. 北京大学, 北京 100871
  • 收稿日期:2017-11-10 修回日期:2018-03-19 出版日期:2019-01-25 发布日期:2019-01-25
  • 作者简介:周沛 女,1995年出生,硕博连读研究生在读,主要研究方向为医学图像处理.E-mail:630005818@qq.com
  • 基金资助:
    国家自然科学基金(No.61571036,No.61502025,No.61771039);创新研究群体科学基金(No.81421004)

Review of Cross-Modality Medical Image Prediction

ZHOU Pei1, CHEN Hou-Jin1, YU Ze-kuan2, PENG Ya-hui1, LI Yan-feng1, YANG Fan1   

  1. 1. Beijing Jiaotong University, Beijing 100044, China;
    2. Peking University, Beijing 100871, China
  • Received:2017-11-10 Revised:2018-03-19 Online:2019-01-25 Published:2019-01-25

摘要: 医学影像技术与设备的进步在生物医学领域的各项研究中发挥着重要作用.跨模态医学图像预测旨在由一种模态图像预测另一种模态图像.本文详细综述了由MRI预测CT图像、7T-Like图像重构、PET预测及其他医学模态预测研究,阐述了各类模态预测的必要性及存在的挑战,说明各类预测方法的特点并进行性能比较,最终得出结论:基于深度学习的跨模态预测在预测精度和预测时间两方面更具优势.

关键词: 深度学习, CT预测, 7T-Like图像重构, PET预测

Abstract: Advances in medical imaging technologies and equipment play an important role in the biomedical researches.Cross-modality image-prediction technology predicts one modal image from that of another modal.This paper presents an overview of the literatures on medical imaging prediction technology and its applications,such as predicting Computed Tomography images from Magnetic Resonance (MR) images,7T-like MR image reconstruction,and predicting positron emission tomography images.The aim is twofold:the necessity and challenge for different modality medical image prediction technology;the overview and comparison of various methods in the field.We conclude that the cross-modality image prediction based on the deep learning technology has superiority in both predicting time and precision.

Key words: deep learning, computed tomography (CT) image prediction, 7T-like image reconstruction, positron emission tomography (PET) image prediction

中图分类号: