View in EDS HTML Full Text PDF Full Text

Benchmarking PathCLIP for Pathology Image Analysis.

Saved in:
Bibliographic Details
Title: Benchmarking PathCLIP for Pathology Image Analysis.
Authors: Zheng, Sunyi1,2, Cui, Xiaonan1, Sun, Yuxuan3, Li, Jingxiong3, Li, Honglin3, Zhang, Yunlong3, Chen, Pingyi3, Jing, Xueping4, Ye, Zhaoxiang1, Yang, Lin2 yanglin@westlake.edu.cn
Source: Journal of Imaging Informatics in Medicine. Feb2025, Vol. 38 Issue 1, p422-438. 17p.
Subjects: Fraud prevention, Osteosarcoma, Predictive tests, Databases, Medical information storage & retrieval systems, Image retrieval, Research funding, Data analysis, Benchmarking (Management), Evaluation of organizational effectiveness, Decision making, Clinical pathology, Experimental design, Lung tumors, Research methodology, Statistics, Mathematical models, Deep learning, Digital image processing, Data quality, Theory, Algorithms
Abstract: Accurate image classification and retrieval are of importance for clinical diagnosis and treatment decision-making. The recent contrastive language-image pre-training (CLIP) model has shown remarkable proficiency in understanding natural images. Drawing inspiration from CLIP, pathology-dedicated CLIP (PathCLIP) has been developed, utilizing over 200,000 image and text pairs in training. While the performance the PathCLIP is impressive, its robustness under a wide range of image corruptions remains unknown. Therefore, we conduct an extensive evaluation to analyze the performance of PathCLIP on various corrupted images from the datasets of osteosarcoma and WSSS4LUAD. In our experiments, we introduce eleven corruption types including brightness, contrast, defocus, resolution, saturation, hue, markup, deformation, incompleteness, rotation, and flipping at various settings. Through experiments, we find that PathCLIP surpasses OpenAI-CLIP and the pathology language-image pre-training (PLIP) model in zero-shot classification. It is relatively robust to image corruptions including contrast, saturation, incompleteness, and orientation factors. Among the eleven corruptions, hue, markup, deformation, defocus, and resolution can cause relatively severe performance fluctuation of the PathCLIP. This indicates that ensuring the quality of images is crucial before conducting a clinical test. Additionally, we assess the robustness of PathCLIP in the task of image-to-image retrieval, revealing that PathCLIP performs less effectively than PLIP on osteosarcoma but performs better on WSSS4LUAD under diverse corruptions. Overall, PathCLIP presents impressive zero-shot classification and retrieval performance for pathology images, but appropriate care needs to be taken when using it. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Imaging Informatics in Medicine 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: 184471456
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Benchmarking PathCLIP for Pathology Image Analysis.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zheng%2C+Sunyi%22">Zheng, Sunyi</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AR" term="%22Cui%2C+Xiaonan%22">Cui, Xiaonan</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Sun%2C+Yuxuan%22">Sun, Yuxuan</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Li%2C+Jingxiong%22">Li, Jingxiong</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Li%2C+Honglin%22">Li, Honglin</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Yunlong%22">Zhang, Yunlong</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Chen%2C+Pingyi%22">Chen, Pingyi</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Jing%2C+Xueping%22">Jing, Xueping</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Ye%2C+Zhaoxiang%22">Ye, Zhaoxiang</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Yang%2C+Lin%22">Yang, Lin</searchLink><relatesTo>2</relatesTo><i> yanglin@westlake.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Imaging+Informatics+in+Medicine%22">Journal of Imaging Informatics in Medicine</searchLink>. Feb2025, Vol. 38 Issue 1, p422-438. 17p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Fraud+prevention%22">Fraud prevention</searchLink><br /><searchLink fieldCode="DE" term="%22Osteosarcoma%22">Osteosarcoma</searchLink><br /><searchLink fieldCode="DE" term="%22Predictive+tests%22">Predictive tests</searchLink><br /><searchLink fieldCode="DE" term="%22Databases%22">Databases</searchLink><br /><searchLink fieldCode="DE" term="%22Medical+information+storage+%26+retrieval+systems%22">Medical information storage & retrieval systems</searchLink><br /><searchLink fieldCode="DE" term="%22Image+retrieval%22">Image retrieval</searchLink><br /><searchLink fieldCode="DE" term="%22Research+funding%22">Research funding</searchLink><br /><searchLink fieldCode="DE" term="%22Data+analysis%22">Data analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Benchmarking+%28Management%29%22">Benchmarking (Management)</searchLink><br /><searchLink fieldCode="DE" term="%22Evaluation+of+organizational+effectiveness%22">Evaluation of organizational effectiveness</searchLink><br /><searchLink fieldCode="DE" term="%22Decision+making%22">Decision making</searchLink><br /><searchLink fieldCode="DE" term="%22Clinical+pathology%22">Clinical pathology</searchLink><br /><searchLink fieldCode="DE" term="%22Experimental+design%22">Experimental design</searchLink><br /><searchLink fieldCode="DE" term="%22Lung+tumors%22">Lung tumors</searchLink><br /><searchLink fieldCode="DE" term="%22Research+methodology%22">Research methodology</searchLink><br /><searchLink fieldCode="DE" term="%22Statistics%22">Statistics</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+models%22">Mathematical models</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Digital+image+processing%22">Digital image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Data+quality%22">Data quality</searchLink><br /><searchLink fieldCode="DE" term="%22Theory%22">Theory</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Accurate image classification and retrieval are of importance for clinical diagnosis and treatment decision-making. The recent contrastive language-image pre-training (CLIP) model has shown remarkable proficiency in understanding natural images. Drawing inspiration from CLIP, pathology-dedicated CLIP (PathCLIP) has been developed, utilizing over 200,000 image and text pairs in training. While the performance the PathCLIP is impressive, its robustness under a wide range of image corruptions remains unknown. Therefore, we conduct an extensive evaluation to analyze the performance of PathCLIP on various corrupted images from the datasets of osteosarcoma and WSSS4LUAD. In our experiments, we introduce eleven corruption types including brightness, contrast, defocus, resolution, saturation, hue, markup, deformation, incompleteness, rotation, and flipping at various settings. Through experiments, we find that PathCLIP surpasses OpenAI-CLIP and the pathology language-image pre-training (PLIP) model in zero-shot classification. It is relatively robust to image corruptions including contrast, saturation, incompleteness, and orientation factors. Among the eleven corruptions, hue, markup, deformation, defocus, and resolution can cause relatively severe performance fluctuation of the PathCLIP. This indicates that ensuring the quality of images is crucial before conducting a clinical test. Additionally, we assess the robustness of PathCLIP in the task of image-to-image retrieval, revealing that PathCLIP performs less effectively than PLIP on osteosarcoma but performs better on WSSS4LUAD under diverse corruptions. Overall, PathCLIP presents impressive zero-shot classification and retrieval performance for pathology images, but appropriate care needs to be taken when using it. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Imaging Informatics in Medicine 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=184471456
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10278-024-01128-4
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
        StartPage: 422
    Subjects:
      – SubjectFull: Fraud prevention
        Type: general
      – SubjectFull: Osteosarcoma
        Type: general
      – SubjectFull: Predictive tests
        Type: general
      – SubjectFull: Databases
        Type: general
      – SubjectFull: Medical information storage & retrieval systems
        Type: general
      – SubjectFull: Image retrieval
        Type: general
      – SubjectFull: Research funding
        Type: general
      – SubjectFull: Data analysis
        Type: general
      – SubjectFull: Benchmarking (Management)
        Type: general
      – SubjectFull: Evaluation of organizational effectiveness
        Type: general
      – SubjectFull: Decision making
        Type: general
      – SubjectFull: Clinical pathology
        Type: general
      – SubjectFull: Experimental design
        Type: general
      – SubjectFull: Lung tumors
        Type: general
      – SubjectFull: Research methodology
        Type: general
      – SubjectFull: Statistics
        Type: general
      – SubjectFull: Mathematical models
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Digital image processing
        Type: general
      – SubjectFull: Data quality
        Type: general
      – SubjectFull: Theory
        Type: general
      – SubjectFull: Algorithms
        Type: general
    Titles:
      – TitleFull: Benchmarking PathCLIP for Pathology Image Analysis.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zheng, Sunyi
      – PersonEntity:
          Name:
            NameFull: Cui, Xiaonan
      – PersonEntity:
          Name:
            NameFull: Sun, Yuxuan
      – PersonEntity:
          Name:
            NameFull: Li, Jingxiong
      – PersonEntity:
          Name:
            NameFull: Li, Honglin
      – PersonEntity:
          Name:
            NameFull: Zhang, Yunlong
      – PersonEntity:
          Name:
            NameFull: Chen, Pingyi
      – PersonEntity:
          Name:
            NameFull: Jing, Xueping
      – PersonEntity:
          Name:
            NameFull: Ye, Zhaoxiang
      – PersonEntity:
          Name:
            NameFull: Yang, Lin
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: Feb2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 29482925
          Numbering:
            – Type: volume
              Value: 38
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Journal of Imaging Informatics in Medicine
              Type: main
ResultId 1