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

Learn More →

Automated vascular analysis of breast thermograms with interpretable features

Automated vascular analysis of breast thermograms with interpretable features AbstractPurpose: Vascular changes are observed from initial stages of breast cancer, and monitoring of vessel structures helps in early detection of malignancies. In recent years, thermal imaging is being evaluated as a low-cost imaging modality to visualize and analyze early vascularity. However, visual inspection of thermal vascularity is challenging and subjective. Therefore, there is a need for automated techniques to assist physicians in visualization and interpretation of vascularity by marking the vessel structures and by providing quantified qualitative parameters that helps in malignancy classificationApproach: In the literature, there are very few approaches for vascular analysis and classification of breast thermal images using interpretable vascular features. One major challenge is the automated detection of breast vascularity due to diffused vessel boundaries. We first propose a deep learning-based semantic segmentation approach that generates heatmaps of vessel structures from two-dimensional breast thermal images for quantitative assessment of breast vascularity. Second, we extract interpretable vascular parameters and propose a classifier to predict likelihood of breast cancer purely from the extracted vascular parameters.Results: The results of the cancer classifier were validated using an independent clinical dataset consisting of 258 participants. The results were encouraging as the proposed approach segmented vessels well and gave a good classification performance with area under receiver operating characteristic curve of 0.85 with the proposed vascularity parameters.Conclusions: The detected vasculature and its associated high classification performance show the utility of the proposed approach in interpretation of breast vascularity. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Medical Imaging SPIE

Automated vascular analysis of breast thermograms with interpretable features

Download PDF
14 pages

Loading next page...
 
/lp/spie/automated-vascular-analysis-of-breast-thermograms-with-interpretable-3XaVOCUWJZ

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
SPIE
Copyright
© 2022 Society of Photo-Optical Instrumentation Engineers (SPIE)
ISSN
2329-4302
eISSN
2329-4310
DOI
10.1117/1.jmi.9.4.044502
Publisher site
See Article on Publisher Site

Abstract

AbstractPurpose: Vascular changes are observed from initial stages of breast cancer, and monitoring of vessel structures helps in early detection of malignancies. In recent years, thermal imaging is being evaluated as a low-cost imaging modality to visualize and analyze early vascularity. However, visual inspection of thermal vascularity is challenging and subjective. Therefore, there is a need for automated techniques to assist physicians in visualization and interpretation of vascularity by marking the vessel structures and by providing quantified qualitative parameters that helps in malignancy classificationApproach: In the literature, there are very few approaches for vascular analysis and classification of breast thermal images using interpretable vascular features. One major challenge is the automated detection of breast vascularity due to diffused vessel boundaries. We first propose a deep learning-based semantic segmentation approach that generates heatmaps of vessel structures from two-dimensional breast thermal images for quantitative assessment of breast vascularity. Second, we extract interpretable vascular parameters and propose a classifier to predict likelihood of breast cancer purely from the extracted vascular parameters.Results: The results of the cancer classifier were validated using an independent clinical dataset consisting of 258 participants. The results were encouraging as the proposed approach segmented vessels well and gave a good classification performance with area under receiver operating characteristic curve of 0.85 with the proposed vascularity parameters.Conclusions: The detected vasculature and its associated high classification performance show the utility of the proposed approach in interpretation of breast vascularity.

Journal

Journal of Medical Imaging – SPIE

Published: Jul 1, 2022

Keywords: vessel segmentation; breast cancer; deep learning; malignancy classification; vessel features; thermal imaging

References

  • Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries
    Sung, H.
  • Breast cancer in the 21st century: from early detection to new therapies
    Merino Bonilla, J. A.; Torres Tabanera, M.; Ros Mendoza, L. H.
  • Breast cancer in limited-resource countries: early detection and access to care
    Smith, R. A.
  • Early detection and screening for breast cancer
    Coleman, C.
  • What is the evidence that tumors are angiogenesis dependent?
    Folkman, J.
  • Functional infrared imaging of the breast
    Keyserlingk, J. R.
  • A comparative review of thermography as a breast cancer screening technique
    Kennedy, D. A.; Lee, T.; Seely, D.
  • Magnetic resonance imaging of breast vascularity in medial versus lateral breast cancer
    Grubstein, A.; Yepes, M.; Kiszonas, R.
  • Breast contrast enhanced MR imaging: semi-automatic detection of vascular map and predominant feeding vessel
    Petrillo, A.
  • Evaluation of ipsilateral increased vascularity in differentiating benign and malignant breast lesions
    Wang, H.
  • Thermopathology of breast cancer: measurement and analysis of in vivo temperature and blood flow
    Gautherie, M.
  • Advances in breast thermography
    Kakileti, S. T.; Malik, A. M.
  • Multicentric study to evaluate the effectiveness of Thermalytix as compared with standard screening modalities in subjects who show possible symptoms of suspected breast cancer
    Singh, A.
  • Observational study to evaluate the clinical efficacy of thermalytix for detecting breast cancer in symptomatic and asymptomatic women
    Kakileti, S. T.
  • Personalized risk prediction for breast cancer pre-screening using artificial intelligence and thermal radiomics
    Kakileti, S. T.
  • Automated blood vessel extraction in two-dimensional breast thermography
    Kakileti, S. T.; Venkataramani, K.
  • A novel method to infrared thermal images vessel extraction based on fractal dimension
    Navid, M.
  • Multiscale vessel enhancement filtering
    Frangi, A. F.
  • Mask R-CNN
    He, K.
  • Faster R-CNN: towards real-time object detection with region proposal networks
    Ren, S.
  • U-Net: convolutional networks for biomedical image segmentation
    Ronneberger, O.; Fischer, P.; Brox, T.
  • Exploring deep learning networks for tumour segmentation in infrared images
    Kakileti, S. T.; Dalmia, A.; Manjunath, G.
  • V-net: fully convolutional neural networks for volumetric medical image segmentation
    Milletari, F.; Navab, N.; Ahmadi, S.-A.
  • Deep residual learning for image recognition
    He, K.
  • Adam: a method for stochastic optimization
    Kingma, D. P.; Ba, J.
  • Extraction of medically interpretable features for classification of malignancy in breast thermography
    Madhu, H.
  • Support-vector networks
    Cortes, C.; Vapnik, V.
  • Estimation of the probability of an event as a function of several independent variables
    Walker, S. H.; Duncan, D. B.
  • Random decision forests
    Ho, T. K.
  • Technology, application and potential of dynamic breast thermography for the detection of breast cancer
    Gonzalez-Hernandez, J. L.
  • The importance of interpretability and visualization in machine learning for applications in medicine and health care
    Vellido, A.