TY - JOUR
T1 - A manifold learning regularization approach to enhance 3D CT image-based lung nodule classification
AU - Ren, Ying
AU - Tsai, Min Yu
AU - Chen, Liyuan
AU - Wang, Jing
AU - Li, Shulong
AU - Liu, Yufei
AU - Jia, Xun
AU - Shen, Chenyang
N1 - Funding Information:
This work was supported by the China National Key Research and Development Program of China (Grant Nos. 2016YFE0125200 and 2016YFC0101100) and the China Fundamental Research Funds for the Central Universities (Grant No. 2019CDQYGD020).
Funding Information:
This work was supported by the China National Key Research and Development Program of China (Grant Nos. 2016YFE0125200 and 2016YFC0101100) and the China Fundamental Research Funds for the Central Universities (Grant No. 2019CDQYGD020).
Publisher Copyright:
© 2019, CARS.
PY - 2020/2/1
Y1 - 2020/2/1
N2 - Purpose: Diagnosis of lung cancer requires radiologists to review every lung nodule in CT images. Such a process can be very time-consuming, and the accuracy is affected by many factors, such as experience of radiologists and available diagnosis time. To address this problem, we proposed to develop a deep learning-based system to automatically classify benign and malignant lung nodules. Methods: The proposed method automatically determines benignity or malignancy given the 3D CT image patch of a lung nodule to assist diagnosis process. Motivated by the fact that real structure among data is often embedded on a low-dimensional manifold, we developed a novel manifold regularized classification deep neural network (MRC-DNN) to perform classification directly based on the manifold representation of lung nodule images. The concise manifold representation revealing important data structure is expected to benefit the classification, while the manifold regularization enforces strong, but natural constraints on network training, preventing over-fitting. Results: The proposed method achieves accurate manifold learning with reconstruction error of ~ 30 HU on real lung nodule CT image data. In addition, the classification accuracy on testing data is 0.90 with sensitivity of 0.81 and specificity of 0.95, which outperforms state-of-the-art deep learning methods. Conclusion: The proposed MRC-DNN facilitates an accurate manifold learning approach for lung nodule classification based on 3D CT images. More importantly, MRC-DNN suggests a new and effective idea of enforcing regularization for network training, possessing the potential impact to a board range of applications.
AB - Purpose: Diagnosis of lung cancer requires radiologists to review every lung nodule in CT images. Such a process can be very time-consuming, and the accuracy is affected by many factors, such as experience of radiologists and available diagnosis time. To address this problem, we proposed to develop a deep learning-based system to automatically classify benign and malignant lung nodules. Methods: The proposed method automatically determines benignity or malignancy given the 3D CT image patch of a lung nodule to assist diagnosis process. Motivated by the fact that real structure among data is often embedded on a low-dimensional manifold, we developed a novel manifold regularized classification deep neural network (MRC-DNN) to perform classification directly based on the manifold representation of lung nodule images. The concise manifold representation revealing important data structure is expected to benefit the classification, while the manifold regularization enforces strong, but natural constraints on network training, preventing over-fitting. Results: The proposed method achieves accurate manifold learning with reconstruction error of ~ 30 HU on real lung nodule CT image data. In addition, the classification accuracy on testing data is 0.90 with sensitivity of 0.81 and specificity of 0.95, which outperforms state-of-the-art deep learning methods. Conclusion: The proposed MRC-DNN facilitates an accurate manifold learning approach for lung nodule classification based on 3D CT images. More importantly, MRC-DNN suggests a new and effective idea of enforcing regularization for network training, possessing the potential impact to a board range of applications.
KW - Deep learning
KW - Diagnosis
KW - Lung nodule classification
KW - Manifold learning
KW - Regularization
UR - http://www.scopus.com/inward/record.url?scp=85076109657&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076109657&partnerID=8YFLogxK
U2 - 10.1007/s11548-019-02097-8
DO - 10.1007/s11548-019-02097-8
M3 - Article
C2 - 31768885
AN - SCOPUS:85076109657
VL - 15
SP - 287
EP - 295
JO - Computer-Assisted Radiology and Surgery
JF - Computer-Assisted Radiology and Surgery
SN - 1861-6410
IS - 2
ER -