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

Learn More →

Lung nodule malignancy classification with weakly supervised explanation generation

Lung nodule malignancy classification with weakly supervised explanation generation Abstract.Purpose: Explainable AI aims to build systems that not only give high performance but also are able to provide insights that drive the decision making. However, deriving this explanation is often dependent on fully annotated (class label and local annotation) data, which are not readily available in the medical domain.Approach: This paper addresses the above-mentioned aspects and presents an innovative approach to classifying a lung nodule in a CT volume as malignant or benign, and generating a morphologically meaningful explanation for the decision in the form of attributes such as nodule margin, sphericity, and spiculation. A deep learning architecture that is trained using a multi-phase training regime is proposed. The nodule class label (benign/malignant) is learned with full supervision and is guided by semantic attributes that are learned in a weakly supervised manner.Results: Results of an extensive evaluation of the proposed system on the LIDC-IDRI dataset show good performance compared with state-of-the-art, fully supervised methods. The proposed model is able to label nodules (after full supervision) with an accuracy of 89.1% and an area under curve of 0.91 and to provide eight attributes scores as an explanation, which is learned from a much smaller training set. The proposed system’s potential to be integrated with a sub-optimal nodule detection system was also tested, and our system handled 95% of false positive or random regions in the input well by labeling them as benign, which underscores its robustness.Conclusions: The proposed approach offers a way to address computer-aided diagnosis system design under the constraint of sparse availability of fully annotated images. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Medical Imaging SPIE

Lung nodule malignancy classification with weakly supervised explanation generation

Download PDF
12 pages

Loading next page...
 
/lp/spie/lung-nodule-malignancy-classification-with-weakly-supervised-o3EoIKOUaZ
Publisher
SPIE
Copyright
© 2021 Society of Photo-Optical Instrumentation Engineers (SPIE)
ISSN
2329-4302
eISSN
2329-4310
DOI
10.1117/1.jmi.8.4.044502
Publisher site
See Article on Publisher Site

Abstract

Abstract.Purpose: Explainable AI aims to build systems that not only give high performance but also are able to provide insights that drive the decision making. However, deriving this explanation is often dependent on fully annotated (class label and local annotation) data, which are not readily available in the medical domain.Approach: This paper addresses the above-mentioned aspects and presents an innovative approach to classifying a lung nodule in a CT volume as malignant or benign, and generating a morphologically meaningful explanation for the decision in the form of attributes such as nodule margin, sphericity, and spiculation. A deep learning architecture that is trained using a multi-phase training regime is proposed. The nodule class label (benign/malignant) is learned with full supervision and is guided by semantic attributes that are learned in a weakly supervised manner.Results: Results of an extensive evaluation of the proposed system on the LIDC-IDRI dataset show good performance compared with state-of-the-art, fully supervised methods. The proposed model is able to label nodules (after full supervision) with an accuracy of 89.1% and an area under curve of 0.91 and to provide eight attributes scores as an explanation, which is learned from a much smaller training set. The proposed system’s potential to be integrated with a sub-optimal nodule detection system was also tested, and our system handled 95% of false positive or random regions in the input well by labeling them as benign, which underscores its robustness.Conclusions: The proposed approach offers a way to address computer-aided diagnosis system design under the constraint of sparse availability of fully annotated images.

Journal

Journal of Medical Imaging – SPIE

Published: Jul 1, 2021

Keywords: CAD; lung nodule; malignancy; explanability

References

  • Knowledge-based collaborative deep learning for benign-malignant lung nodule classification on chest CT
    Xie, Y.
  • Agile convolutional neural network for pulmonary nodule classification using CT images
    Zhao, X.
  • Highly accurate model for prediction of lung nodule malignancy with CT scans
    Causey, J.
  • Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification
    Shen, W.
  • Pulmonary nodule classification with deep convolutional neural networks on computed tomography images
    Li, W.
  • Evaluation of the solitary pulmonary nodule: size matters, but do not ignore the power of morphology
    Snoeckx, A.
  • Bridging computational features toward multiple semantic features with multi-task regression: a study of ct pulmonary nodules
    Chen, S.
  • Regularization and variable selection via the elastic net
    Zou, H.
  • Risk stratification of lung nodules using 3D CNN-based multi-task learning
    Hussein, S.
  • Automatic scoring of multiple semantic attributes with multi-task feature leverage: a study on pulmonary nodules in CT images
    Chen, S.
  • Joint learning for pulmonary nodule segmentation, attributes and malignancy prediction
    Botong, W.
  • Multi-task deep model with margin ranking loss for lung nodule analysis
    Liu, L.
  • Explainable hierarchical semantic convolutional neural network for lung cancer diagnosis
    Shen, S.
  • The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans
    Armato, S.
  • Classification of lung nodule malignancy risk on computed tomography images using convolutional neural network: a comparison between 2D and 3D strategies
    Yan, X.
  • Classification of lung nodules in CT scans using three-dimensional deep convolutional neural networks with a checkpoint ensemble method
    Jung, H.
  • Stage-wise training: an improved feature learning strategy for deep models
    Barshan, E.; Fieguth, P.
  • Update in the evaluation of the solitary pulmonary nodule
    Truong, M. T.
  • Management of incidental lung nodules <8 mm in diameter
    Sánchez, M.
  • You only look once: unified, real-time object detection
    Redmon, J.