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
  • [31] Multi-site scheduling with multiple job reservations and forecasting methods
    Ioannidou, Maria A.
    Karatza, Helen D.
    PARALLEL AND DISTRIBUTED PROCESSING AND APPLICATIONS, 2006, 4330 : 894 - +
  • [32] Tools and methods for risk management in multi-site engineering projects
    Zhou, MW
    Nemes, L
    Reidsema, C
    Ahmed, A
    Kayis, B
    KNOWLEDGE AND SKILL CHAINS IN ENGINEERING AND MANUFACTURING: INFORMATION INFRASTRUCTURE IN THE ERA OF GLOBAL COMMUNICATIONS, 2005, 168 : 217 - 224
  • [33] Multi-site service
    Korts, S
    BWK, 2005, 57 (7-8): : 41 - 41
  • [34] MULTI-SITE DILEMMA
    ASHWORTH, W
    JOURNAL OF LIBRARIANSHIP, 1980, 12 (01): : 1 - 13
  • [35] Distributed deep learning for robust multi-site segmentation of CT imaging after traumatic brain injury
    Remedios, Samuel
    Roy, Snehashis
    Blaber, Justin
    Bermudez, Camilo
    Nath, Vishwesh
    Patel, Mayur B.
    Butman, John A.
    Landman, Bennett A.
    Pham, Dzung L.
    MEDICAL IMAGING 2019: IMAGE PROCESSING, 2019, 10949
  • [36] Comparison Multi Transfer Learning Models for Deep Fake Image Recognizer
    Rosli, Nur Aizah
    Abdullah, Siti Norul Huda Sheikh
    Zamani, Ahmad Nazri
    Ghazvini, Anahita
    Othman, Nor Sakinah Md
    Tajuddin, Nor Alia Athirah Abdul Muariff
    2021 3RD INTERNATIONAL CYBER RESILIENCE CONFERENCE (CRC), 2021, : 38 - 43
  • [37] Comparison of single-site, multi-site and multi-variable SWAT calibration strategies
    Lazzari Franco, Ana Clara
    de Oliveira, Debora Yumi
    Bonuma, Nadia Bernardi
    HYDROLOGICAL SCIENCES JOURNAL-JOURNAL DES SCIENCES HYDROLOGIQUES, 2020, 65 (14): : 2376 - 2389
  • [38] Comparison of single-site and multi-site stochastic models for streamflow generation
    Sanghamitra Medda
    Kalyan Kumar Bhar
    Applied Water Science, 2019, 9
  • [39] Comparison of single-site and multi-site stochastic models for streamflow generation
    Medda, Sanghamitra
    Bhar, Kalyan Kumar
    APPLIED WATER SCIENCE, 2019, 9 (03)
  • [40] COMPARISON OF COSTS BETWEEN A MULTI-SITE AND A SINGLE CAMPUS UNIVERSITY
    BOURLIAUD, G
    COULAIS, JM
    HIGHER EDUCATION REVIEW, 1978, 10 (02): : 7 - 16