Machine learning approaches in medical image analysis: From detection to diagnosis

被引:206
作者
de Bruijne, Marleen [1 ,2 ,3 ,4 ]
机构
[1] Erasmus MC Univ Med Ctr Rotterdam, Dept Med Informat, Biomed Imaging Grp Rotterdam, Rotterdam, Netherlands
[2] Erasmus MC Univ Med Ctr Rotterdam, Dept Radiol, Biomed Imaging Grp Rotterdam, Rotterdam, Netherlands
[3] Erasmus MC Univ Med Ctr Rotterdam, Dept Nucl Med, Biomed Imaging Grp Rotterdam, Rotterdam, Netherlands
[4] Univ Copenhagen, Dept Comp Sci, Image Sect, DK-1168 Copenhagen, Denmark
关键词
Machine learning; Classification; Computer aided diagnosis; Transfer learning; SEGMENTATION;
D O I
10.1016/j.media.2016.06.032
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Machine learning approaches are increasingly successful in image-based diagnosis, disease prognosis, and risk assessment. This paper highlights new research directions and discusses three main challenges related to machine learning in medical imaging: coping with variation in imaging protocols, learning from weak labels, and interpretation and evaluation of results. (C) 2016 Elsevier B.V. All rights reserved.
引用
收藏
页码:94 / 97
页数:4
相关论文
共 11 条
[1]   Hippocampal shape is predictive for the development of dementia in a normal, elderly population [J].
Achterberg, Hakim C. ;
van der Lijn, Fedde ;
den Heijer, Tom ;
Vernooij, Meike W. ;
Ikram, M. Arfan ;
Niessen, Wiro J. ;
de Bruijne, Marleen .
HUMAN BRAIN MAPPING, 2014, 35 (05) :2359-2371
[2]   Anniversary Paper: History and status of CAD and quantitative image analysis: The role of Medical Physics and AAPM [J].
Giger, Maryellen L. ;
Chan, Heang-Ping ;
Boone, John .
MEDICAL PHYSICS, 2008, 35 (12) :5799-5820
[3]   Real-time ultrasound transducer localization in fluoroscopy images by transfer learning from synthetic training data [J].
Heimann, Tobias ;
Mountney, Peter ;
John, Matthias ;
Ionasec, Razvan .
MEDICAL IMAGE ANALYSIS, 2014, 18 (08) :1320-1328
[4]   Contrastive Pessimistic Likelihood Estimation for Semi-Supervised Classification [J].
Loog, Marco .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (03) :462-475
[5]   A Novel Multiple-Instance Learning-Based Approach to Computer-Aided Detection of Tuberculosis on Chest X-Rays [J].
Melendez, Jaime ;
van Ginneken, Bram ;
Maduskar, Pragnya ;
Philipsen, Rick H. H. M. ;
Reither, Klaus ;
Breuninger, Marianne ;
Adetifa, Ifedayo M. O. ;
Maane, Rahmatulai ;
Ayles, Helen ;
Sanchez, Clara I. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2015, 34 (01) :179-192
[6]  
Schlegl Thomas, 2015, Inf Process Med Imaging, V24, P437, DOI 10.1007/978-3-319-19992-4_34
[7]   Texture-Based Analysis of COPD: A Data-Driven Approach [J].
Sorensen, Lauge ;
Nielsen, Mads ;
Lo, Pechin ;
Ashraf, Haseem ;
Pedersen, Jesper H. ;
de Bruijne, Marleen .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2012, 31 (01) :70-78
[8]   Multi-Center MRI Carotid Plaque Component Segmentation Using Feature Normalization and Transfer Learning [J].
van Engelen, Arna ;
van Dijk, Anouk C. ;
Truijman, Martine T. B. ;
van't Klooster, Ronald ;
van Opbroek, Annegreet ;
van der Lugt, Aad ;
Niessen, Wiro J. ;
Kooi, M. Eline ;
de Bruijne, Marleen .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2015, 34 (06) :1294-1305
[9]   Three-Dimensional Carotid Ultrasound Plaque Texture Predicts Vascular Events [J].
van Engelen, Arna ;
Wannarong, Thapat ;
Parraga, Grace ;
Niessen, Wiro J. ;
Fenster, Aaron ;
Spence, J. David ;
de Bruijne, Marleen .
STROKE, 2014, 45 (09) :2695-+
[10]   Weighting training images by maximizing distribution similarity for supervised segmentation across scanners [J].
van Opbroek, Annegreet ;
Vernooij, Meike W. ;
Ikram, M. Arfan ;
de Bruijne, Marleen .
MEDICAL IMAGE ANALYSIS, 2015, 24 (01) :245-254