TY - JOUR
T1 - DCT-MIL
T2 - Deep CNN transferred multiple instance learning for COPD identification using CT images
AU - Xu, Caiwen
AU - Qi, Shouliang
AU - Feng, Jie
AU - Xia, Shuyue
AU - Kang, Yan
AU - Yao, Yudong
AU - Qian, Wei
N1 - Publisher Copyright:
© 2020 Institute of Physics and Engineering in Medicine.
PY - 2020/7/21
Y1 - 2020/7/21
N2 - While many pre-defined computed tomographic (CT) measures have been utilized to characterize chronic obstructive pulmonary disease (COPD), it is still challenging to represent pathological alternations of multiple dimensions and highly spatial heterogeneity. Deep CNN transferred multiple instance learning (DCT-MIL) is proposed to identify COPD via CT images. After the lung is divided into eight sections along the axial direction, one random axial CT image is taken out from each section as one instance. With one instance as the input, the activations of neural layers of AlexNet trained by natural images are extracted as features. After dimension reduction through principle component analysis, features of all instances are input into three MIL methods: Citation k-Nearest-Neighbor (Citation-KNN), multiple instance support vector machine, and expectation-maximization diverse density. Moreover, the performance dependence of the resulted models on the depth of the neural layer where activations are extracted and the number of features is investigated. The proposed DCT-MIL achieves an exceptional performance with an accuracy of 99.29% and area under curve of 0.9826 while using 100 principle components of features extracted from the fourth convolutional layer and Citation-KNN. It outperforms not only DCT-MIL models using other settings and the pre-trained AlexNet with fine-tuning by montages of eight lung CT images, but also other state-of-art methods. Deep CNN transferred multiple instance learning is suited for identification of COPD using CT images. It can help finding subgroups with high risk of COPD from large populations through CT scans ordered doing lung cancer screening.
AB - While many pre-defined computed tomographic (CT) measures have been utilized to characterize chronic obstructive pulmonary disease (COPD), it is still challenging to represent pathological alternations of multiple dimensions and highly spatial heterogeneity. Deep CNN transferred multiple instance learning (DCT-MIL) is proposed to identify COPD via CT images. After the lung is divided into eight sections along the axial direction, one random axial CT image is taken out from each section as one instance. With one instance as the input, the activations of neural layers of AlexNet trained by natural images are extracted as features. After dimension reduction through principle component analysis, features of all instances are input into three MIL methods: Citation k-Nearest-Neighbor (Citation-KNN), multiple instance support vector machine, and expectation-maximization diverse density. Moreover, the performance dependence of the resulted models on the depth of the neural layer where activations are extracted and the number of features is investigated. The proposed DCT-MIL achieves an exceptional performance with an accuracy of 99.29% and area under curve of 0.9826 while using 100 principle components of features extracted from the fourth convolutional layer and Citation-KNN. It outperforms not only DCT-MIL models using other settings and the pre-trained AlexNet with fine-tuning by montages of eight lung CT images, but also other state-of-art methods. Deep CNN transferred multiple instance learning is suited for identification of COPD using CT images. It can help finding subgroups with high risk of COPD from large populations through CT scans ordered doing lung cancer screening.
KW - COPD
KW - CT
KW - convolutional neural networks
KW - multiple instance learning
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85090027238&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090027238&partnerID=8YFLogxK
U2 - 10.1088/1361-6560/ab857d
DO - 10.1088/1361-6560/ab857d
M3 - Article
C2 - 32235077
AN - SCOPUS:85090027238
SN - 0031-9155
VL - 65
JO - Physics in Medicine and Biology
JF - Physics in Medicine and Biology
IS - 14
M1 - 145011
ER -