Comparison of Image Normalization Methods for Multi-Site Deep Learning

被引:4
|
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
  • [1] GENERALIZABLE MULTI-SITE TRAINING AND TESTING OF DEEP NEURAL NETWORKS USING IMAGE NORMALIZATION
    Onofrey, John A.
    Casetti-Dinescu, Dana I.
    Lauritzen, Andreas D.
    Sarkar, Saradwata
    Venkataraman, Rajesh
    Fan, Richard E.
    Sonn, Geoffrey A.
    Sprenkle, Preston C.
    Staib, Lawrence H.
    Papademetris, Xenophon
    [J]. 2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019), 2019, : 348 - 351
  • [2] Relay learning: a physically secure framework for clinical multi-site deep learning
    Bo, Zi-Hao
    Guo, Yuchen
    Lyu, Jinhao
    Liang, Hengrui
    He, Jianxing
    Deng, Shijie
    Xu, Feng
    Lou, Xin
    Dai, Qionghai
    [J]. NPJ DIGITAL MEDICINE, 2023, 6 (01)
  • [3] Relay learning: a physically secure framework for clinical multi-site deep learning
    Zi-Hao Bo
    Yuchen Guo
    Jinhao Lyu
    Hengrui Liang
    Jianxing He
    Shijie Deng
    Feng Xu
    Xin Lou
    Qionghai Dai
    [J]. npj Digital Medicine, 6
  • [4] Field of View Normalization in Multi-Site Brain MRI
    Yangming Ou
    Lilla Zöllei
    Xiao Da
    Kallirroi Retzepi
    Shawn N. Murphy
    Elizabeth R. Gerstner
    Bruce R. Rosen
    P. Ellen Grant
    Jayashree Kalpathy-Cramer
    Randy L. Gollub
    [J]. Neuroinformatics, 2018, 16 : 431 - 444
  • [5] Field of View Normalization in Multi-Site Brain MRI
    Ou, Yangming
    Zollei, Lilla
    Da, Xiao
    Retzepi, Kallirroi
    Murphy, Shawn N.
    Gerstner, Elizabeth R.
    Rosen, Bruce R.
    Grant, P. Ellen
    Kalpathy-Cramer, Jayashree
    Gollub, Randy L.
    [J]. NEUROINFORMATICS, 2018, 16 (3-4) : 431 - 444
  • [6] Multi-Site Assessment of Pediatric Bone Age Using Deep Learning
    Valliani, Aly A.
    Schwartz, John T.
    Arvind, Varun
    Taree, Amir
    Kim, Jun S.
    Cho, Samuel K.
    [J]. ACM-BCB 2020 - 11TH ACM CONFERENCE ON BIOINFORMATICS, COMPUTATIONAL BIOLOGY, AND HEALTH INFORMATICS, 2020,
  • [7] Multi-site validation of image analysis methods - Assessing intra and inter-site variability
    Styner, MA
    Charles, HC
    Park, J
    Gerig, G
    [J]. MEDICAL IMAGING 2002: IMAGE PROCESSING, VOL 1-3, 2002, 4684 : 278 - 286
  • [8] Deep learning classification of systemic sclerosis from multi-site photoplethysmography signals
    Iqbal, Sadaf
    Bacardit, Jaume
    Griffiths, Bridget
    Allen, John
    [J]. FRONTIERS IN PHYSIOLOGY, 2023, 14
  • [9] Solar Irradiance Forecasting Based on Deep Learning Methodologies and Multi-Site Data
    Brahma, Banalaxmi
    Wadhvani, Rajesh
    [J]. SYMMETRY-BASEL, 2020, 12 (11): : 1 - 20
  • [10] Multi-site household waste generation forecasting using a deep learning approach
    Cubillos, Maximiliano
    [J]. WASTE MANAGEMENT, 2020, 115 : 8 - 14