TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss Weighting
 
Options

Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss Weighting

Publikationstyp
Journal Article
Date Issued
2020-02
Sprache
English
Author(s)
Gessert, Nils Thorben  
Sentker, Thilo  
Madesta, Frederic  
Schmitz, Rüdiger  
Kniep, Helge  
Baltruschat, Ivo-Matteo  orcid-logo
Werner, René  
Schlaefer, Alexander  
Institut
Medizintechnische Systeme E-1  
TORE-URI
http://hdl.handle.net/11420/4295
Journal
IEEE transactions on biomedical engineering  
Volume
67
Issue
2
Start Page
495
End Page
503
Article Number
8710336
Citation
IEEE Transactions on Biomedical Engineering 67 (2): 8710336 (2020-02)
Publisher DOI
10.1109/TBME.2019.2915839
Scopus ID
2-s2.0-85078509539
OBJECTIVE: This work addresses two key problems of skin lesion classification. The first problem is the effective use of high-resolution images with pretrained standard architectures for image classification. The second problem is the high class imbalance encountered in real-world multi-class datasets.

METHODS: To use high-resolution images, we propose a novel patch-based attention architecture that provides global context between small, high-resolution patches. We modify three pretrained architectures and study the performance of patch-based attention. To counter class imbalance problems, we compare oversampling, balanced batch sampling, and class-specific loss weighting. Additionally, we propose a novel diagnosis-guided loss weighting method which takes the method used for ground-truth annotation into account.

RESULTS: Our patch-based attention mechanism outperforms previous methods and improves the mean sensitivity by 7%. Class balancing significantly improves the mean sensitivity and we show that our diagnosis-guided loss weighting method improves the mean sensitivity by 3% over normal loss balancing.

CONCLUSION: The novel patch-based attention mechanism can be integrated into pretrained architectures and provides global context between local patches while outperforming other patch-based methods. Hence, pretrained architectures can be readily used with high resolution images without downsampling. The new diagnosis-guided loss weighting method outperforms other methods and allows for effective training when facing class imbalance.

SIGNIFICANCE: The proposed methods improve automatic skin lesion classification. They can be extended to other clinical applications where high-resolution image data and class imbalance are relevant.
DDC Class
000: Allgemeines, Wissenschaft
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback