View in EDS HTML Full Text PDF Full Text

3D CNN-based Deep Learning Model-based Explanatory Prognostication in Patients  with Multiple Myeloma using Whole-body MRI.

Saved in:
Bibliographic Details
Title: 3D CNN-based Deep Learning Model-based Explanatory Prognostication in Patients  with Multiple Myeloma using Whole-body MRI.
Authors: Morita, Kento1, Karashima, Shigehiro2, Terao, Toshiki3,4, Yoshida, Kotaro5, Yamashita, Takeshi6, Yoroidaka, Takeshi7,8, Tanabe, Mikoto7, Imi, Tatsuya8, Zaimoku, Yoshitaka8, Yoshida, Akiyo8, Maruyama, Hiroyuki8, Iwaki, Noriko8, Aoki, Go8, Kotani, Takeharu7, Murata, Ryoichi6, Miyamoto, Toshihiro8, Machida, Youichi9, Matsue, Kosei3, Nambo, Hidetaka10 hide_nambo@staff.kanazawa-u.ac.jp, Takamatsu, Hiroyuki8,10 takamaz@staff.kanazawa-u.ac.jp
Source: Journal of Medical Systems. 3/8/2024, Vol. 48 Issue 1, p1-11. 11p.
Subjects: Multiple myeloma, Statistical models, Predictive tests, Three-dimensional imaging, Receiver operating characteristic curves, Research funding, Human beings, Magnetic resonance imaging, Retrospective studies, Descriptive statistics, Longitudinal method, Kaplan-Meier estimator, Log-rank test, Deep learning, Artificial neural networks, Medical records, Acquisition of data, Research methodology, Progression-free survival, Confidence intervals, Data analysis software, Sensitivity & specificity (Statistics), Proportional hazards models
Geographic Terms: Japan
Abstract: Although magnetic resonance imaging (MRI) data of patients with multiple myeloma (MM) are used to predict prognosis, few reports have applied artificial intelligence (AI) techniques for this purpose. We aimed to analyze whole-body diffusion-weighted MRI data using three-dimensional (3D) convolutional neural networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM), an explainable AI, to predict prognosis and explore the factors involved in prediction. We retrospectively analyzed the MRI data of a total of 142 patients with MM obtained from two medical centers. We defined the occurrence of progressive disease after MRI evaluation within 12 months as a poor prognosis and constructed a 3D CNN-based deep learning model to predict prognosis. Images from 111 cases were used as the training and internal validation data; images from 31 cases were used as the external validation data. Internal validation of the AI model with stratified 5-fold cross-validation resulted in a significant difference in progression-free survival (PFS) between good and poor prognostic cases (2-year PFS, 91.2% versus [vs.] 61.1%, P = 0.0002). The AI model clearly stratified good and poor prognostic cases in the external validation cohort (2-year PFS, 92.9% vs. 55.6%, P = 0.004), with an area under the receiver operating characteristic curve of 0.804. According to Grad-CAM, the MRI signals of the spleen and bones of the vertebrae and pelvis contributed to prognosis prediction. This study is the first to show that image analysis of whole-body MRI using a 3D CNN without any other clinical data is effective in predicting the prognosis of patients with MM. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Medical Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 176782301
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: 3D CNN-based Deep Learning Model-based Explanatory Prognostication in Patients  with Multiple Myeloma using Whole-body MRI.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Morita%2C+Kento%22">Morita, Kento</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Karashima%2C+Shigehiro%22">Karashima, Shigehiro</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Terao%2C+Toshiki%22">Terao, Toshiki</searchLink><relatesTo>3,4</relatesTo><br /><searchLink fieldCode="AR" term="%22Yoshida%2C+Kotaro%22">Yoshida, Kotaro</searchLink><relatesTo>5</relatesTo><br /><searchLink fieldCode="AR" term="%22Yamashita%2C+Takeshi%22">Yamashita, Takeshi</searchLink><relatesTo>6</relatesTo><br /><searchLink fieldCode="AR" term="%22Yoroidaka%2C+Takeshi%22">Yoroidaka, Takeshi</searchLink><relatesTo>7,8</relatesTo><br /><searchLink fieldCode="AR" term="%22Tanabe%2C+Mikoto%22">Tanabe, Mikoto</searchLink><relatesTo>7</relatesTo><br /><searchLink fieldCode="AR" term="%22Imi%2C+Tatsuya%22">Imi, Tatsuya</searchLink><relatesTo>8</relatesTo><br /><searchLink fieldCode="AR" term="%22Zaimoku%2C+Yoshitaka%22">Zaimoku, Yoshitaka</searchLink><relatesTo>8</relatesTo><br /><searchLink fieldCode="AR" term="%22Yoshida%2C+Akiyo%22">Yoshida, Akiyo</searchLink><relatesTo>8</relatesTo><br /><searchLink fieldCode="AR" term="%22Maruyama%2C+Hiroyuki%22">Maruyama, Hiroyuki</searchLink><relatesTo>8</relatesTo><br /><searchLink fieldCode="AR" term="%22Iwaki%2C+Noriko%22">Iwaki, Noriko</searchLink><relatesTo>8</relatesTo><br /><searchLink fieldCode="AR" term="%22Aoki%2C+Go%22">Aoki, Go</searchLink><relatesTo>8</relatesTo><br /><searchLink fieldCode="AR" term="%22Kotani%2C+Takeharu%22">Kotani, Takeharu</searchLink><relatesTo>7</relatesTo><br /><searchLink fieldCode="AR" term="%22Murata%2C+Ryoichi%22">Murata, Ryoichi</searchLink><relatesTo>6</relatesTo><br /><searchLink fieldCode="AR" term="%22Miyamoto%2C+Toshihiro%22">Miyamoto, Toshihiro</searchLink><relatesTo>8</relatesTo><br /><searchLink fieldCode="AR" term="%22Machida%2C+Youichi%22">Machida, Youichi</searchLink><relatesTo>9</relatesTo><br /><searchLink fieldCode="AR" term="%22Matsue%2C+Kosei%22">Matsue, Kosei</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Nambo%2C+Hidetaka%22">Nambo, Hidetaka</searchLink><relatesTo>10</relatesTo><i> hide_nambo@staff.kanazawa-u.ac.jp</i><br /><searchLink fieldCode="AR" term="%22Takamatsu%2C+Hiroyuki%22">Takamatsu, Hiroyuki</searchLink><relatesTo>8,10</relatesTo><i> takamaz@staff.kanazawa-u.ac.jp</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Medical+Systems%22">Journal of Medical Systems</searchLink>. 3/8/2024, Vol. 48 Issue 1, p1-11. 11p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Multiple+myeloma%22">Multiple myeloma</searchLink><br /><searchLink fieldCode="DE" term="%22Statistical+models%22">Statistical models</searchLink><br /><searchLink fieldCode="DE" term="%22Predictive+tests%22">Predictive tests</searchLink><br /><searchLink fieldCode="DE" term="%22Three-dimensional+imaging%22">Three-dimensional imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Receiver+operating+characteristic+curves%22">Receiver operating characteristic curves</searchLink><br /><searchLink fieldCode="DE" term="%22Research+funding%22">Research funding</searchLink><br /><searchLink fieldCode="DE" term="%22Human+beings%22">Human beings</searchLink><br /><searchLink fieldCode="DE" term="%22Magnetic+resonance+imaging%22">Magnetic resonance imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Retrospective+studies%22">Retrospective studies</searchLink><br /><searchLink fieldCode="DE" term="%22Descriptive+statistics%22">Descriptive statistics</searchLink><br /><searchLink fieldCode="DE" term="%22Longitudinal+method%22">Longitudinal method</searchLink><br /><searchLink fieldCode="DE" term="%22Kaplan-Meier+estimator%22">Kaplan-Meier estimator</searchLink><br /><searchLink fieldCode="DE" term="%22Log-rank+test%22">Log-rank test</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Medical+records%22">Medical records</searchLink><br /><searchLink fieldCode="DE" term="%22Acquisition+of+data%22">Acquisition of data</searchLink><br /><searchLink fieldCode="DE" term="%22Research+methodology%22">Research methodology</searchLink><br /><searchLink fieldCode="DE" term="%22Progression-free+survival%22">Progression-free survival</searchLink><br /><searchLink fieldCode="DE" term="%22Confidence+intervals%22">Confidence intervals</searchLink><br /><searchLink fieldCode="DE" term="%22Data+analysis+software%22">Data analysis software</searchLink><br /><searchLink fieldCode="DE" term="%22Sensitivity+%26+specificity+%28Statistics%29%22">Sensitivity & specificity (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Proportional+hazards+models%22">Proportional hazards models</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Japan%22">Japan</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Although magnetic resonance imaging (MRI) data of patients with multiple myeloma (MM) are used to predict prognosis, few reports have applied artificial intelligence (AI) techniques for this purpose. We aimed to analyze whole-body diffusion-weighted MRI data using three-dimensional (3D) convolutional neural networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM), an explainable AI, to predict prognosis and explore the factors involved in prediction. We retrospectively analyzed the MRI data of a total of 142 patients with MM obtained from two medical centers. We defined the occurrence of progressive disease after MRI evaluation within 12 months as a poor prognosis and constructed a 3D CNN-based deep learning model to predict prognosis. Images from 111 cases were used as the training and internal validation data; images from 31 cases were used as the external validation data. Internal validation of the AI model with stratified 5-fold cross-validation resulted in a significant difference in progression-free survival (PFS) between good and poor prognostic cases (2-year PFS, 91.2% versus [vs.] 61.1%, P = 0.0002). The AI model clearly stratified good and poor prognostic cases in the external validation cohort (2-year PFS, 92.9% vs. 55.6%, P = 0.004), with an area under the receiver operating characteristic curve of 0.804. According to Grad-CAM, the MRI signals of the spleen and bones of the vertebrae and pelvis contributed to prognosis prediction. This study is the first to show that image analysis of whole-body MRI using a 3D CNN without any other clinical data is effective in predicting the prognosis of patients with MM. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Medical Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=176782301
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10916-024-02040-8
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 1
    Subjects:
      – SubjectFull: Multiple myeloma
        Type: general
      – SubjectFull: Statistical models
        Type: general
      – SubjectFull: Predictive tests
        Type: general
      – SubjectFull: Three-dimensional imaging
        Type: general
      – SubjectFull: Receiver operating characteristic curves
        Type: general
      – SubjectFull: Research funding
        Type: general
      – SubjectFull: Human beings
        Type: general
      – SubjectFull: Magnetic resonance imaging
        Type: general
      – SubjectFull: Retrospective studies
        Type: general
      – SubjectFull: Descriptive statistics
        Type: general
      – SubjectFull: Longitudinal method
        Type: general
      – SubjectFull: Kaplan-Meier estimator
        Type: general
      – SubjectFull: Log-rank test
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Medical records
        Type: general
      – SubjectFull: Acquisition of data
        Type: general
      – SubjectFull: Research methodology
        Type: general
      – SubjectFull: Progression-free survival
        Type: general
      – SubjectFull: Confidence intervals
        Type: general
      – SubjectFull: Data analysis software
        Type: general
      – SubjectFull: Sensitivity & specificity (Statistics)
        Type: general
      – SubjectFull: Proportional hazards models
        Type: general
      – SubjectFull: Japan
        Type: general
    Titles:
      – TitleFull: 3D CNN-based Deep Learning Model-based Explanatory Prognostication in Patients  with Multiple Myeloma using Whole-body MRI.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Morita, Kento
      – PersonEntity:
          Name:
            NameFull: Karashima, Shigehiro
      – PersonEntity:
          Name:
            NameFull: Terao, Toshiki
      – PersonEntity:
          Name:
            NameFull: Yoshida, Kotaro
      – PersonEntity:
          Name:
            NameFull: Yamashita, Takeshi
      – PersonEntity:
          Name:
            NameFull: Yoroidaka, Takeshi
      – PersonEntity:
          Name:
            NameFull: Tanabe, Mikoto
      – PersonEntity:
          Name:
            NameFull: Imi, Tatsuya
      – PersonEntity:
          Name:
            NameFull: Zaimoku, Yoshitaka
      – PersonEntity:
          Name:
            NameFull: Yoshida, Akiyo
      – PersonEntity:
          Name:
            NameFull: Maruyama, Hiroyuki
      – PersonEntity:
          Name:
            NameFull: Iwaki, Noriko
      – PersonEntity:
          Name:
            NameFull: Aoki, Go
      – PersonEntity:
          Name:
            NameFull: Kotani, Takeharu
      – PersonEntity:
          Name:
            NameFull: Murata, Ryoichi
      – PersonEntity:
          Name:
            NameFull: Miyamoto, Toshihiro
      – PersonEntity:
          Name:
            NameFull: Machida, Youichi
      – PersonEntity:
          Name:
            NameFull: Matsue, Kosei
      – PersonEntity:
          Name:
            NameFull: Nambo, Hidetaka
      – PersonEntity:
          Name:
            NameFull: Takamatsu, Hiroyuki
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 08
              M: 03
              Text: 3/8/2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 01485598
          Numbering:
            – Type: volume
              Value: 48
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Journal of Medical Systems
              Type: main
ResultId 1