Journal Home > Volume 27 , Issue 1
Tsinghua Science and Technology 2022, 27(1): 103-113 https://doi.org/10.26599/TST.2021.9010028
Open Access | Issue | Published: 17 August 2021

Two-Stage Lesion Detection Approach Based on Dimension-Decomposition and 3D Context

Show Author's Information Jiacheng Jiao,  Haiwei Pan( ),  Chunling Chen,  Tao Jin,  Yang Dong,  Jingyi Chen
College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China
School of Software, Tsinghua University, Beijng 100084, China
Keywords:
lesion detection, Computed Tomography (CT), dimension-decomposition, 3D context, computer-aided diagnosis
Cite this article:
Jiao J, Pan H, Chen C, et al. Two-Stage Lesion Detection Approach Based on Dimension-Decomposition and 3D Context. Tsinghua Science and Technology, 2022, 27(1): 103-113. https://doi.org/10.26599/TST.2021.9010028
Download citation
EndNote(RIS)
BibTeX

649

Views

71

Downloads

Citations

3

Crossref

3

WoS

3

Scopus

0

CSCD

Abstract Full text About this article

Lesion detection in Computed Tomography (CT) images is a challenging task in the field of computer-aided diagnosis. An important issue is to locate the area of lesion accurately. As a branch of Convolutional Neural Networks (CNNs), 3D Context-Enhanced (3DCE) frameworks are designed to detect lesions on CT scans. The False Positives (FPs) detected in 3DCE frameworks are usually caused by inaccurate region proposals, which slow down the inference time. To solve the above problems, a new method is proposed, a dimension-decomposition region proposal network is integrated into 3DCE framework to improve the location accuracy in lesion detection. Without the restriction of "anchors" on ratios and scales, anchors are decomposed to independent "anchor strings" . Anchor segments are dynamically combined in accordance with probability, and anchor strings with different lengths dynamically compose bounding boxes. Experiments show that the accurate region proposals generated by our model promote the sensitivity of FPs and spend less inference time compared with the current methods.


menu
Abstract
Full text
Outline
About this article

Two-Stage Lesion Detection Approach Based on Dimension-Decomposition and 3D Context

Show Author's information Jiacheng Jiao, Haiwei Pan( ), Chunling Chen, Tao Jin, Yang Dong, Jingyi Chen
College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China
School of Software, Tsinghua University, Beijng 100084, China

Abstract

Lesion detection in Computed Tomography (CT) images is a challenging task in the field of computer-aided diagnosis. An important issue is to locate the area of lesion accurately. As a branch of Convolutional Neural Networks (CNNs), 3D Context-Enhanced (3DCE) frameworks are designed to detect lesions on CT scans. The False Positives (FPs) detected in 3DCE frameworks are usually caused by inaccurate region proposals, which slow down the inference time. To solve the above problems, a new method is proposed, a dimension-decomposition region proposal network is integrated into 3DCE framework to improve the location accuracy in lesion detection. Without the restriction of "anchors" on ratios and scales, anchors are decomposed to independent "anchor strings" . Anchor segments are dynamically combined in accordance with probability, and anchor strings with different lengths dynamically compose bounding boxes. Experiments show that the accurate region proposals generated by our model promote the sensitivity of FPs and spend less inference time compared with the current methods.

Keywords: lesion detection, Computed Tomography (CT), dimension-decomposition, 3D context, computer-aided diagnosis

References(31)

[1]
A. Krizhevsky, I. Sutskever, and G. E. Hinton, Imagenet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems, Lake Jahoe, NV, USA, 2012, pp. 1097-1105.
[2]
C. Lam, C. Yu, L. Huang, and D. Rubin, Retinal lesion detection with deep learning using image patches, Investigative Ophthalmology & Visual Science, vol. 59, no. 1, pp. 590-596, 2018.
DOI Google Scholar
[3]
Z. Li, C. Wang, M. Han, Y. Xue, W. Wei, L. Li, and F.-F. Li, Thoracic disease identification and localization with limited supervision, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 8290-8299.
DOI
[4]
Q. Dou, H. Chen, L. Yu, J. Qin, and P. A. Heng, Multilevel contextual 3-D CNNs for false positive reduction in pulmonary nodule detection, IEEE Transactions on Biomedical Engineering, vol. 64, no. 7, pp. 1558-1567, 2016.
DOI Google Scholar
[5]
J. Wang, J. H. Noble, and B. M. Dawant, Metal artifact reduction for the segmentation of the intra cochlear anatomy in CT images of the ear with 3D-conditional GANs, Medical Image Analysis, vol. 58, p. 101553, 2019.
DOI Google Scholar
[6]
J. Park, J. Yun, N. Kim, B. Park, Y. Cho, H. J. Park, M. Song, M. Lee, and J. B. Seo, Fully automated lung lobe segmentation in volumetric chest CT with 3D U-net: Validation with intra-and extra-datasets, Journal of Digital Imaging, vol. 33, no. 1, pp. 221-230, 2020.
DOI Google Scholar
[7]
F. Liao, M. Liang, Z. Li, X. Hu, and S. Song, Evaluate the malignancy of pulmonar nodules using the 3D deep leaky noisy-or network, IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11, pp. 3484-3495, 2019.
DOI Google Scholar
[8]
K. Yan, M. Bagheri, and R. M. Summers, 3D context enhanced region-based convolutional neural network for end-to-end lesion detection, in International Conference on Medical Image Computing and Computer-Assisted Intervention, Granada, Spain, 2018, pp. 511-519.
DOI
[9]
Q. Tao, Z. Ge, J. Cai, J. Yin, and S. See, Improving deep lesion detection using 3D contextual and spatial attention, in International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China, 2019, pp. 185-193.
DOI
[10]
J. R. R. Uijlings, K. E. A. van de Sande, T. Gevers, and A. W. M. Smeulders, Selective search for object recognition, International Journal of Computer Vision, vol. 104, no. 2, pp. 154-171, 2013.
DOI Google Scholar
[11]
R. Girshick, J. Donahue, T. Darrell, and J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 580-587.
DOI
[12]
S. Ren, K. He, R. B. Girshick, and J. Sun, Faster R-CNN: Towards real-time object detection with region proposal networks, in Advances in Neural Information Processing Systems, Montreal, Canada, 2015, pp. 91-99.
[13]
J. Dai, Y. Li, K. He, and J. Sun, R-FCN: Object detection via region-based fully convolutional networks, in Advances in Neural Information Processing Systems, Barcelona, Spain, 2016, pp. 379-387.
[14]
J. Pang, K. Chen, J. Shi, H. Feng, W. Ouyang, and D. Lin, Libra R-CNN: Towards balanced learning for object detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 2019, pp. 821-830.
DOI
[15]
S. Bae, Object detection based on region decomposition and assembly, in Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA, 2019, pp. 8094-8101.
DOI
[16]
X. Zhang, F. Wan, C. Liu, R. Ji, and Q. Ye, Free anchor: Learning to match anchors for visual object detection, in Advances in Neural Information Processing Systems, Vancouver, Canada, 2019, pp. 147-155.
[17]
J. Redmon, S. K. Divvala, R. B. Girshick, and A. Farhadi, You only look once: Unified, real-time object detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 779-788.
DOI
[18]
J. Redmon and A. Farhadi, YOLO9000: Better, faster, stronger, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, pp. 7263-7271.
DOI
[19]
Z. Tian, C. Shen, H. Chen, and T. He, FCOS: Fully convolutional one-stage object detection, in Proceedings of the IEEE International Conference on Computer Vision, Seoul, South Korea, 2019, pp. 9627-9636.
DOI
[20]
C. L. Zitnick, and P. Dollár, Edge boxes: Locating object proposals from edges, in Proc. of European Conference on Computer Vision, Zurich, Switzerland, 2014, pp. 391-405.
DOI
[21]
Y. Li, Detecting lesion bounding ellipses with Gaussian proposal networks, in Proc. of International Workshop on Machine Learning in Medical Imaging, Shenzhen, China, 2019, pp. 337-344.
DOI
[22]
J. Ribera, D. Guera, Y. Chen, and E. J. Delp, Locating objects without bounding boxes, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 2019, pp. 6479-6489.
DOI
[23]
K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, and Q. Tian, Centernet: Keypoint triplets for object detection, in Proceedings of the IEEE International Conference on Computer Vision, Seoul, South Korea, 2019, pp. 6568-6577.
DOI
[24]
S. Liu, D. Huang, and Y. Wang, Adaptive NMS: Refining pedestrian detection in a crowd, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 2019, pp. 6459-6468.
DOI
[25]
L. Cai, B. Zhao, Z. Wang, J. Lin, C. S. Foo, M. S. Aly, and V. Chandrasekhar, Maxpool NMS: Getting rid of NMS bottlenecks in two-stage object detectors, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 2019, pp. 9356-9364.
DOI
[26]
Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, and D. Ren, Distance-IoU Loss: Faster and better learning for bounding box regression, in Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA, 2020, pp. 12 993-13 000.
[27]
K. Simonyan and Z. Andrew, Very deep convolutional networks for large-scale image recognition, https://arxiv.org/pdf/1409.1556, 2014.
[28]
L. Xie, Y. Liu, L. Jin, and Z. Xie, DeRPN: Taking a further step toward more general object detection, in Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA, 2019, pp. 9046-9053.
DOI
[29]
K. Yan, X. Wang, L. Lu, and R. M. Summers, Deeplesion: Automated deep mining, categorization and detection of significant radiology image findings using large-scale clinical lesion annotations, https://arxiv.org/abs/1710.01766, 2017.
[30]
J. Deng, W. Dong, R. Socher, L. Li, Kai Li, and F.-F. Li, ImageNet: A large-scale hierarchical image database, in Proc. of 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami Beach, FL, USA, 2009, pp. 248-255.
DOI
[31]
S. Suut, A. Zeid, A. Carolyn, and R. Prabhakar, Pictorial essay of radiological features of benign intrathoracic masses, Annals of Thoracic Medicine, vol. 10, no. 4, pp. 231-242, 2015.
Google Scholar
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 12 June 2020
Revised: 13 August 2020
Accepted: 31 August 2020
Published: 17 August 2021
Issue date: February 2022

Copyright

© The author(s) 2022

Acknowledgements

The paper was supported by the National Natural Science Foundation of China (Nos. 62072135, 61672181).

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return