Cargando…
The Utility of Applying Various Image Preprocessing Strategies to Reduce the Ambiguity in Deep Learning-based Clinical Image Diagnosis
PURPOSE: A general problem of machine-learning algorithms based on the convolutional neural network (CNN) technique is that the reason for the output judgement is unclear. The purpose of this study was to introduce a strategy that may facilitate better understanding of how and why a specific judgeme...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Japanese Society for Magnetic Resonance in Medicine
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7232029/ https://www.ncbi.nlm.nih.gov/pubmed/31080211 http://dx.doi.org/10.2463/mrms.mp.2019-0021 |
_version_ | 1783535294708973568 |
---|---|
author | Tachibana, Yasuhiko Obata, Takayuki Kershaw, Jeff Sakaki, Hironao Urushihata, Takuya Omatsu, Tokuhiko Kishimoto, Riwa Higashi, Tatsuya |
author_facet | Tachibana, Yasuhiko Obata, Takayuki Kershaw, Jeff Sakaki, Hironao Urushihata, Takuya Omatsu, Tokuhiko Kishimoto, Riwa Higashi, Tatsuya |
author_sort | Tachibana, Yasuhiko |
collection | PubMed |
description | PURPOSE: A general problem of machine-learning algorithms based on the convolutional neural network (CNN) technique is that the reason for the output judgement is unclear. The purpose of this study was to introduce a strategy that may facilitate better understanding of how and why a specific judgement was made by the algorithm. The strategy is to preprocess the input image data in different ways to highlight the most important aspects of the images for reaching the output judgement. MATERIALS AND METHODS: T(2)-weighted brain image series falling into two age-ranges were used. Classifying each series into one of the two age-ranges was the given task for the CNN model. The images from each series were preprocessed in five different ways to generate five different image sets: (1) subimages from the inner area of the brain, (2) subimages from the periphery of the brain, (3–5) subimages of brain parenchyma, gray matter area, and white matter area, respectively, extracted from the subimages of (2). The CNN model was trained and tested in five different ways using one of these image sets. The network architecture and all the parameters for training and testing remained unchanged. RESULTS: The judgement accuracy achieved by training was different when the image set used for training was different. Some of the differences was statistically significant. The judgement accuracy decreased significantly when either extra-parenchymal or gray matter area was removed from the periphery of the brain (P < 0.05). CONCLUSION: The proposed strategy may help visualize what features of the images were important for the algorithm to reach correct judgement, helping humans to understand how and why a particular judgement was made by a CNN. |
format | Online Article Text |
id | pubmed-7232029 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Japanese Society for Magnetic Resonance in Medicine |
record_format | MEDLINE/PubMed |
spelling | pubmed-72320292020-05-26 The Utility of Applying Various Image Preprocessing Strategies to Reduce the Ambiguity in Deep Learning-based Clinical Image Diagnosis Tachibana, Yasuhiko Obata, Takayuki Kershaw, Jeff Sakaki, Hironao Urushihata, Takuya Omatsu, Tokuhiko Kishimoto, Riwa Higashi, Tatsuya Magn Reson Med Sci Major Paper PURPOSE: A general problem of machine-learning algorithms based on the convolutional neural network (CNN) technique is that the reason for the output judgement is unclear. The purpose of this study was to introduce a strategy that may facilitate better understanding of how and why a specific judgement was made by the algorithm. The strategy is to preprocess the input image data in different ways to highlight the most important aspects of the images for reaching the output judgement. MATERIALS AND METHODS: T(2)-weighted brain image series falling into two age-ranges were used. Classifying each series into one of the two age-ranges was the given task for the CNN model. The images from each series were preprocessed in five different ways to generate five different image sets: (1) subimages from the inner area of the brain, (2) subimages from the periphery of the brain, (3–5) subimages of brain parenchyma, gray matter area, and white matter area, respectively, extracted from the subimages of (2). The CNN model was trained and tested in five different ways using one of these image sets. The network architecture and all the parameters for training and testing remained unchanged. RESULTS: The judgement accuracy achieved by training was different when the image set used for training was different. Some of the differences was statistically significant. The judgement accuracy decreased significantly when either extra-parenchymal or gray matter area was removed from the periphery of the brain (P < 0.05). CONCLUSION: The proposed strategy may help visualize what features of the images were important for the algorithm to reach correct judgement, helping humans to understand how and why a particular judgement was made by a CNN. Japanese Society for Magnetic Resonance in Medicine 2019-05-10 /pmc/articles/PMC7232029/ /pubmed/31080211 http://dx.doi.org/10.2463/mrms.mp.2019-0021 Text en © 2019 Japanese Society for Magnetic Resonance in Medicine This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc-nd/4.0/ |
spellingShingle | Major Paper Tachibana, Yasuhiko Obata, Takayuki Kershaw, Jeff Sakaki, Hironao Urushihata, Takuya Omatsu, Tokuhiko Kishimoto, Riwa Higashi, Tatsuya The Utility of Applying Various Image Preprocessing Strategies to Reduce the Ambiguity in Deep Learning-based Clinical Image Diagnosis |
title | The Utility of Applying Various Image Preprocessing Strategies to Reduce the Ambiguity in Deep Learning-based Clinical Image Diagnosis |
title_full | The Utility of Applying Various Image Preprocessing Strategies to Reduce the Ambiguity in Deep Learning-based Clinical Image Diagnosis |
title_fullStr | The Utility of Applying Various Image Preprocessing Strategies to Reduce the Ambiguity in Deep Learning-based Clinical Image Diagnosis |
title_full_unstemmed | The Utility of Applying Various Image Preprocessing Strategies to Reduce the Ambiguity in Deep Learning-based Clinical Image Diagnosis |
title_short | The Utility of Applying Various Image Preprocessing Strategies to Reduce the Ambiguity in Deep Learning-based Clinical Image Diagnosis |
title_sort | utility of applying various image preprocessing strategies to reduce the ambiguity in deep learning-based clinical image diagnosis |
topic | Major Paper |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7232029/ https://www.ncbi.nlm.nih.gov/pubmed/31080211 http://dx.doi.org/10.2463/mrms.mp.2019-0021 |
work_keys_str_mv | AT tachibanayasuhiko theutilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT obatatakayuki theutilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT kershawjeff theutilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT sakakihironao theutilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT urushihatatakuya theutilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT omatsutokuhiko theutilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT kishimotoriwa theutilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT higashitatsuya theutilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT tachibanayasuhiko utilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT obatatakayuki utilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT kershawjeff utilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT sakakihironao utilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT urushihatatakuya utilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT omatsutokuhiko utilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT kishimotoriwa utilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis AT higashitatsuya utilityofapplyingvariousimagepreprocessingstrategiestoreducetheambiguityindeeplearningbasedclinicalimagediagnosis |