View in EDS HTML Full Text PDF Full Text

Multimodal deep learning: tumor and visceral fat impact on colorectal cancer occult peritoneal metastasis.

Saved in:
Bibliographic Details
Title: Multimodal deep learning: tumor and visceral fat impact on colorectal cancer occult peritoneal metastasis.
Authors: Miao, Shidi1 (AUTHOR), Sun, Mengzhuo1 (AUTHOR), Zhang, Beibei2 (AUTHOR), Jiang, Yuyang1 (AUTHOR), Xuan, Qifan1 (AUTHOR), Wang, Guopeng1 (AUTHOR), Wang, Mingxuan1 (AUTHOR), Jiang, Yuxin1 (AUTHOR), Wang, Qiujun3 (AUTHOR), Liu, Zengyao4 (AUTHOR), Ding, Xuemei5 (AUTHOR), Wang, Ruitao2 (AUTHOR) ruitaowang@126.com
Source: European Radiology. Aug2025, Vol. 35 Issue 8, p4522-4532. 11p.
Subjects: Colorectal cancer, Abdominal adipose tissue, Computed tomography, Peritoneal cancer, Tumor classification, Prognosis, Deep learning
Abstract: Objectives: This study proposes a multimodal deep learning (DL) approach to investigate the impact of tumors and visceral fat on occult peritoneal metastasis in colorectal cancer (CRC) patients. Methods: We developed a DL model named Multi-scale Feature Fusion Network (MSFF-Net) based on ResNet18, which extracted features of tumors and visceral fat from the longest diameter tumor section and the third lumbar vertebra level (L3) in preoperative CT scans of CRC patients. Logistic regression analysis was applied to patients' clinical data that integrated with DL features. A random forest (RF) classifier was established to evaluate the MSFF-Net's performance on internal and external test sets and compare it with radiologists' performance. Results: The model incorporating fat features outperformed the single tumor modality in the internal test set. Combining clinical information with DL provided the best diagnostic performance for predicting peritoneal metastasis in CRC patients. The AUCs were 0.941 (95% CI: [0.891, 0.986], p = 0.03) for the internal test set and 0.911 (95% CI: [0.857, 0.971], p = 0.013) for the external test set. CRC patients with peritoneal metastasis had a higher visceral adipose tissue index (VATI) compared to those without. Maximum tumor diameter and VATI were identified as independent prognostic factors for peritoneal metastasis. Grad-CAM decision regions corresponded with the independent prognostic factors identified by logistic regression analysis. Conclusion: The study confirms the network features of tumors and visceral fat significantly enhance predictive performance for peritoneal metastasis in CRC. Visceral fat is a meaningful imaging biomarker for peritoneal metastasis's early detection in CRC patients. Key Points: QuestionCurrent research on predicting colorectal cancer with peritoneal metastasis mainly focuses on single-modality analysis, while studies based on multimodal imaging information are relatively scarce. FindingsThe Multi-scale Feature Fusion Network, constructed based on ResNet18, can utilize CT images of tumors and visceral fat to detect occult peritoneal metastasis in colorectal cancer. Clinical relevanceThis study identified independent prognostic factors for colorectal cancer peritoneal metastasis and combines them with tumor and visceral fat network features, aiding early diagnosis and accurate prognostic assessment. [ABSTRACT FROM AUTHOR]
Copyright of European Radiology 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: 186373278
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Multimodal deep learning: tumor and visceral fat impact on colorectal cancer occult peritoneal metastasis.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Miao%2C+Shidi%22">Miao, Shidi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+Mengzhuo%22">Sun, Mengzhuo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Beibei%22">Zhang, Beibei</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Jiang%2C+Yuyang%22">Jiang, Yuyang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xuan%2C+Qifan%22">Xuan, Qifan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Guopeng%22">Wang, Guopeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Mingxuan%22">Wang, Mingxuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Jiang%2C+Yuxin%22">Jiang, Yuxin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Qiujun%22">Wang, Qiujun</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Zengyao%22">Liu, Zengyao</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ding%2C+Xuemei%22">Ding, Xuemei</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Ruitao%22">Wang, Ruitao</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> ruitaowang@126.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22European+Radiology%22">European Radiology</searchLink>. Aug2025, Vol. 35 Issue 8, p4522-4532. 11p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Colorectal+cancer%22">Colorectal cancer</searchLink><br /><searchLink fieldCode="DE" term="%22Abdominal+adipose+tissue%22">Abdominal adipose tissue</searchLink><br /><searchLink fieldCode="DE" term="%22Computed+tomography%22">Computed tomography</searchLink><br /><searchLink fieldCode="DE" term="%22Peritoneal+cancer%22">Peritoneal cancer</searchLink><br /><searchLink fieldCode="DE" term="%22Tumor+classification%22">Tumor classification</searchLink><br /><searchLink fieldCode="DE" term="%22Prognosis%22">Prognosis</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Objectives: This study proposes a multimodal deep learning (DL) approach to investigate the impact of tumors and visceral fat on occult peritoneal metastasis in colorectal cancer (CRC) patients. Methods: We developed a DL model named Multi-scale Feature Fusion Network (MSFF-Net) based on ResNet18, which extracted features of tumors and visceral fat from the longest diameter tumor section and the third lumbar vertebra level (L3) in preoperative CT scans of CRC patients. Logistic regression analysis was applied to patients' clinical data that integrated with DL features. A random forest (RF) classifier was established to evaluate the MSFF-Net's performance on internal and external test sets and compare it with radiologists' performance. Results: The model incorporating fat features outperformed the single tumor modality in the internal test set. Combining clinical information with DL provided the best diagnostic performance for predicting peritoneal metastasis in CRC patients. The AUCs were 0.941 (95% CI: [0.891, 0.986], p = 0.03) for the internal test set and 0.911 (95% CI: [0.857, 0.971], p = 0.013) for the external test set. CRC patients with peritoneal metastasis had a higher visceral adipose tissue index (VATI) compared to those without. Maximum tumor diameter and VATI were identified as independent prognostic factors for peritoneal metastasis. Grad-CAM decision regions corresponded with the independent prognostic factors identified by logistic regression analysis. Conclusion: The study confirms the network features of tumors and visceral fat significantly enhance predictive performance for peritoneal metastasis in CRC. Visceral fat is a meaningful imaging biomarker for peritoneal metastasis's early detection in CRC patients. Key Points: QuestionCurrent research on predicting colorectal cancer with peritoneal metastasis mainly focuses on single-modality analysis, while studies based on multimodal imaging information are relatively scarce. FindingsThe Multi-scale Feature Fusion Network, constructed based on ResNet18, can utilize CT images of tumors and visceral fat to detect occult peritoneal metastasis in colorectal cancer. Clinical relevanceThis study identified independent prognostic factors for colorectal cancer peritoneal metastasis and combines them with tumor and visceral fat network features, aiding early diagnosis and accurate prognostic assessment. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of European Radiology 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=186373278
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00330-025-11450-2
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 4522
    Subjects:
      – SubjectFull: Colorectal cancer
        Type: general
      – SubjectFull: Abdominal adipose tissue
        Type: general
      – SubjectFull: Computed tomography
        Type: general
      – SubjectFull: Peritoneal cancer
        Type: general
      – SubjectFull: Tumor classification
        Type: general
      – SubjectFull: Prognosis
        Type: general
      – SubjectFull: Deep learning
        Type: general
    Titles:
      – TitleFull: Multimodal deep learning: tumor and visceral fat impact on colorectal cancer occult peritoneal metastasis.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Miao, Shidi
      – PersonEntity:
          Name:
            NameFull: Sun, Mengzhuo
      – PersonEntity:
          Name:
            NameFull: Zhang, Beibei
      – PersonEntity:
          Name:
            NameFull: Jiang, Yuyang
      – PersonEntity:
          Name:
            NameFull: Xuan, Qifan
      – PersonEntity:
          Name:
            NameFull: Wang, Guopeng
      – PersonEntity:
          Name:
            NameFull: Wang, Mingxuan
      – PersonEntity:
          Name:
            NameFull: Jiang, Yuxin
      – PersonEntity:
          Name:
            NameFull: Wang, Qiujun
      – PersonEntity:
          Name:
            NameFull: Liu, Zengyao
      – PersonEntity:
          Name:
            NameFull: Ding, Xuemei
      – PersonEntity:
          Name:
            NameFull: Wang, Ruitao
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 09387994
          Numbering:
            – Type: volume
              Value: 35
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: European Radiology
              Type: main
ResultId 1