Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Cluster activation mapping with application to computed tomography scans of the lung

Cluster activation mapping with application to computed tomography scans of the lung Abstract.Purpose: An open question in deep clustering is how to explain what in the image is driving the cluster assignments. This is especially important for applications in medical imaging when the derived cluster assignments may inform decision-making or create new disease subtypes. We develop cluster activation mapping (CLAM), which is methodology to create localization maps highlighting the image regions important for cluster assignment.Approach: Our approach uses a linear combination of the activation channels from the last layer of the encoder within a pretrained autoencoder. The activation channels are weighted by a channelwise confidence measure, which is a modification of score-CAM.Results: Our approach performs well under medical imaging-based simulation experiments, when the image clusters differ based on size, location, and intensity of abnormalities. Under simulation, the cluster assignments were predicted with 100% accuracy when the number of clusters was set at the true value. In addition, applied to computed tomography scans from a sarcoidosis population, CLAM identified two subtypes of sarcoidosis based purely on CT scan presentation, which were significantly associated with pulmonary function tests and visual assessment scores, such as ground-glass, fibrosis, and honeycombing.Conclusions: CLAM is a transparent methodology for identifying explainable groupings of medical imaging data. As deep learning networks are often criticized and not trusted due to their lack of interpretability, our contribution of CLAM to deep clustering architectures is critical to our understanding of cluster assignments, which can ultimately lead to new subtypes of diseases. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Medical Imaging SPIE

Cluster activation mapping with application to computed tomography scans of the lung

Download PDF
21 pages

Loading next page...
 
/lp/spie/cluster-activation-mapping-with-application-to-computed-tomography-ycq0K08gqu
Publisher
SPIE
Copyright
© 2022 Society of Photo-Optical Instrumentation Engineers (SPIE)
ISSN
2329-4302
eISSN
2329-4310
DOI
10.1117/1.jmi.9.2.026001
Publisher site
See Article on Publisher Site

Abstract

Abstract.Purpose: An open question in deep clustering is how to explain what in the image is driving the cluster assignments. This is especially important for applications in medical imaging when the derived cluster assignments may inform decision-making or create new disease subtypes. We develop cluster activation mapping (CLAM), which is methodology to create localization maps highlighting the image regions important for cluster assignment.Approach: Our approach uses a linear combination of the activation channels from the last layer of the encoder within a pretrained autoencoder. The activation channels are weighted by a channelwise confidence measure, which is a modification of score-CAM.Results: Our approach performs well under medical imaging-based simulation experiments, when the image clusters differ based on size, location, and intensity of abnormalities. Under simulation, the cluster assignments were predicted with 100% accuracy when the number of clusters was set at the true value. In addition, applied to computed tomography scans from a sarcoidosis population, CLAM identified two subtypes of sarcoidosis based purely on CT scan presentation, which were significantly associated with pulmonary function tests and visual assessment scores, such as ground-glass, fibrosis, and honeycombing.Conclusions: CLAM is a transparent methodology for identifying explainable groupings of medical imaging data. As deep learning networks are often criticized and not trusted due to their lack of interpretability, our contribution of CLAM to deep clustering architectures is critical to our understanding of cluster assignments, which can ultimately lead to new subtypes of diseases.

Journal

Journal of Medical Imaging – SPIE

Published: Mar 1, 2022

Keywords: deep clustering; explainable machine learning; convolutional autoencoder; medical imaging; sarcoidoisis

References

  • Unsupervised deep embedding for clustering analysis
    Xie, J.; Girshick, R.; Farhadi, A.
  • Deep clustering with convolutional autoencoders
    Guo, X.
  • Deep clustering with a Dynamic Autoencoder: From reconstruction towards centroids construction
    Mrabah, N.; Khan, N. M.; Ksantini, R.
  • Score-CAM: improved visual explanations via score-weighted class activation mapping
    Wang, H.
  • Radiomic measures from chest HRCT associated with lung function in sarcoidosis
    Ryan, S. M.
  • Cardiac computed tomography radiomics
    Kolossváry, M.
  • From hand-crafted to deep learning-based cancer radiomics: challenges and opportunities
    Afshar, P.
  • Learning deep features for discriminative localization
    Zhou, B.
  • Grad-CAM: visual explanations from deep networks via gradient-based localization
    Selvaraju, R. R.
  • Visualizing data using T-SNE
    Maaten, L. V. D.; Hinton, G.
  • Silhouettes: a graphical aid to the interpretation and validation of cluster analysis
    Rousseeuw, P. J.
  • Estimating the number of clusters in a data set via the gap statistic
    Tibshirani, R.; Walther, G.; Hastie, T.
  • Understanding of internal clustering validation measures
    Liu, Y.
  • Estimating the optimal number of clusters k in a dataset using data depth
    Patil, C.; Baidari, I.
  • Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks
    Chattopadhay, A.
  • Template creation for high-resolution computed tomography scans of the lung in R software
    Ryan, S. M.
  • Adam: a method for stochastic optimization
    Kingma, D. P.; Ba, J.
  • Rationale and design of the genomic research in Alpha-1 antitrypsin deficiency and sarcoidosis (GRADS) study. sarcoidosis protocol
    Moller, D. R.
  • Genetic epidemiology of COPD (COPDgene) study design
    Regan, E. A.
  • Quantitative CT of the lungs and airways in healthy non-smoking adults
    Zach, J. A.
  • The first step for neuroimaging data analysis: DICOM to NIfTI conversion
    Li, X.
  • A framework for feature selection in clustering
    Witten, D. M.; Tibshirani, R.
  • Significant CD4, CD8, and CD19 lymphopenia in peripheral blood of sarcoidosis patients correlates with severe disease manifestations
    Sweiss, N. J.