Comparison of Image Normalization Methods for Multi-Site Deep Learning

被引:6
|
作者
Albert, Steffen [1 ]
Wichtmann, Barbara D. [2 ]
Zhao, Wenzhao [3 ,4 ]
Maurer, Angelika [2 ]
Hesser, Juergen [3 ,4 ,5 ,6 ]
Attenberger, Ulrike I. [2 ]
Schad, Lothar R. [1 ]
Zoellner, Frank G. [1 ]
机构
[1] Heidelberg Univ, Mannheim Inst Intelligent Syst Med MIISM, Med Fac Mannheim, Comp Assisted Clin Med, D-68167 Mannheim, Germany
[2] Univ Hosp Bonn, Dept Diagnost & Intervent Radiol, D-53127 Bonn, Germany
[3] Heidelberg Univ, Mannheim Inst Intelligent Syst Med MIISM, Med Fac Mannheim, Data Anal & Modeling Med, D-68167 Mannheim, Germany
[4] Heidelberg Univ, Cent Inst Sci Comp IWR, D-69120 Heidelberg, Germany
[5] Heidelberg Univ, Cent Inst Sci Comp IWR, CZS Heidelberg Ctr Model Based, D-69120 Heidelberg, Germany
[6] Heidelberg Univ, Cent Inst Comp Engn ZITI, D-69120 Heidelberg, Germany
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 15期
关键词
normalization; MRI; medical imaging; RECTAL-CANCER; HARMONIZATION;
D O I
10.3390/app13158923
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
In this study, we evaluate the influence of normalization on the performance of deep learning networks for tumor segmentation and the prediction of the pathological response of locally advanced rectal cancer to neoadjuvant chemoradiotherapy. The techniques were applied to a multicenter and multimodal magnet resonance imaging data set consisting of 201 patients recorded at six centers. We implemented and investigated six different normalization methods (setting the mean and standard deviation, histogram matching, percentiles, combining percentiles and histogram matching, fixed window and an auto-encoder with adversarial loss using the imaging parameters) and evaluated their impact on four deep learning tasks: tumor segmentation, prediction of treatment outcome, and prediction of sex and age. The latter two tasks were implemented as a reference test. We trained a modified U-Net with different normalization methods in multiple configurations: on all images, images from all centers except one, and images from a single center. Our results show that normalization only plays a minor role in segmentation, with a difference in Dice of less than 0.02 between the best and worst performing networks. For the prediction of sex and treatment outcomes, the percentile method combined with histogram matching works best for all scenarios. The biggest difference in performance, depending on the normalization method, occurs for classification. In conclusion, normalization is especially important for small data sets or for generalizing to different data distributions. The deep learning method was superior to the classical methods only in a minority of cases, probably due to the limited amount of training data.
引用
收藏
页数:13
相关论文
共 50 条
  • [41] Comparison of CCD astrolabe multi-site solar diameter observations
    Andrei, A.H.
    Boscardin, S.C.
    Chollet, F.
    Delmas, C.
    Golbasi, O.
    Jilinski, E.G.
    Kiliç, H.
    Laclare, F.
    Morand, F.
    Penna, J.L.
    Neto, E. Reis
    Astronomy and Astrophysics, 1600, 427 (02): : 717 - 723
  • [42] Control of interplot interference in grain maize: A multi-site comparison
    David, O
    Monod, H
    Lorgeou, J
    Philippeau, G
    CROP SCIENCE, 2001, 41 (02) : 406 - 414
  • [43] A multi-site comparison of environmental characteristics to support workplace walking
    Gilson, Nicholas D.
    Ainsworth, Barbara
    Biddle, Stuart
    Faulkner, Guy
    Murphy, Marie H.
    Niven, Ailsa
    Pringle, Andy
    Puig-Ribera, Anna
    Stathi, Afroditi
    Umstattd, M. Rene
    PREVENTIVE MEDICINE, 2009, 49 (01) : 21 - 23
  • [44] A comparison of three stochastic multi-site precipitation occurrence generators
    Mehrotra, R.
    Srikanthan, R.
    Sharma, Ashish
    JOURNAL OF HYDROLOGY, 2006, 331 (1-2) : 280 - 292
  • [45] A multi-site comparison of psychosocial approaches for the treatment of methamphetamine dependence
    Rawson, RA
    Marinelli-Casey, P
    Anglin, MD
    Dickow, A
    Frazier, Y
    Gallagher, C
    Galloway, GP
    Herrell, J
    Huber, A
    McCann, MJ
    Obert, J
    Pennell, S
    Reiber, C
    Vandersloot, D
    Zweben, J
    ADDICTION, 2004, 99 (06) : 708 - 717
  • [46] CONTRASTIVE LEARNING FOR REGRESSION IN MULTI-SITE BRAIN AGE PREDICTION
    Barbano, Carlo Alberto
    Dufumier, Benoit
    Duchesnay, Edouard
    Grangetto, Marco
    Gori, Pietro
    2023 IEEE 20TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI, 2023,
  • [47] Multi-site comparison of the effects of success for all on reading achievement
    Smith, LJ
    Ross, SM
    Casey, J
    JOURNAL OF LITERACY RESEARCH, 1996, 28 (03) : 329 - 353
  • [48] Comparison of CCD astrolabe multi-site solar diameter observations
    Andrei, AH
    Boscardin, SC
    Chollet, F
    Delmas, C
    Golbasi, O
    Jilinski, EG
    Kiliç, H
    Laclare, F
    Morand, F
    Penna, JL
    Neto, ER
    ASTRONOMY & ASTROPHYSICS, 2004, 427 (02): : 717 - 723
  • [49] Federated Bayesian network learning from multi-site data
    Liu, Shuai
    Yan, Xiao
    Guo, Xiao
    Qi, Shun
    Wang, Huaning
    Chang, Xiangyu
    JOURNAL OF BIOMEDICAL INFORMATICS, 2025, 163
  • [50] Factors associated with image guided radiation therapy image rejection in a multi-site institution
    Traube, B.
    Khan, M.
    Kumar, R.
    Walker, G.
    RADIOTHERAPY AND ONCOLOGY, 2020, 152 : S901 - S901