Application of object detection algorithm in pathology diagnosis of lung cancer

doi:10.3969/j.issn.1000-1565.2023.05.014

Abstract

Abstract: Object detection based on deep learning has been widely studied in many fields such as transportation and military, and has achieved remarkable results. In order to further study its usability in medical image diagnosis, two classical models of object detection algorithms, SSD and Faster RCNN, are proposed to appliy to the lesion detection of lung cancer pathological images. The experimental comparison shows that the average processing time of Faster RCNN is about 4.6 times longer than that of SSD, but the recognition accuracy and precision are higher than that of SSD, and the model performance of Faster RCNN is much better. The research results show that the object detection algorithm can realize the intelligent diagnosis of lung cancer pathological images and improve the diagnosis rate of lung cancer.

Key words: deep learning, object detection, lung cancer, pathological image, intelligent diagnosis

CLC Number:

TP399

WU Jianguo,YANG Xiaoru,WANG Pan,WU Junfang,LI Ruikai. Application of object detection algorithm in pathology diagnosis of lung cancer[J]. Journal of Hebei University(Natural Science Edition), 2023, 43(5): 546-552.

References

[1] SIEGEL R L, MILLER K D, JEMAL A. Cancer statistics[J]. CA Cancer J Clin, 2020, 70(1): 7-30. DOI: 10.3322/caac.21590.
[2] HE Y F, WEI J, CHE S L, et al. Computer-aided pathological annotation framework: a deep learning-based diagnostic algorithm of lung cancer[C] //2019 International Conference on Information Technology and Computer Application(ITCA), 2019, Guangzhou, China, IEEE, 2020: 110-113. DOI: 10.1109/ITCA49981.2019.00032.
[3] ESTEVA A, KUPREL B, NOVOA R A, et al. Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 542(7639): 115-118. DOI: 10.1038/nature21056.
[4] SIRINUKUNWATTANA K, RAZA S E A, TSANG Y W, et al. Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images[J]. IEEE T Med Imaging, 2016, 35(5): 1196-1206. DOI: 10.1109/TMI.2016.2525803.
[5] SHARMA H, ZERBE N, KLEMPERT I, et al. Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology[J]. Comput Med Imaging Graph, 2017, 61: 2-13. DOI: 10.1016/j.compmedimag.2017.06.001.
[6] WAHAB N, KHAN A, LEE Y S. Two-phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detection[J]. Comput Biol Med, 2017, 85: 86-97. DOI: 10.1016/j.compbiomed.2017.04.012.
[7] WAN T, CAO J J, CHEN J H, et al. Automated grading of breast cancer histopathology using cascaded ensemble with combination of multi-level image features[J]. Neurocomputing, 2017, 229: 34-44. DOI: 10.1016/j.neucom.2016.05.084.
[8] XU X W, HOU R P, ZHAO W Y, et al. A weak supervision-based framework for automatic lung cancer classification on whole slide image[C] //2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society(EMBC), 2020, Montreal, QC, Canada, IEEE, 2020: 1372-1375. DOI: 10.1109/EMBC44109.2020.9176620.
[9] DENIZ N A, SERKAN O. Lung cancer classification and detection using convolutional neural networks[C] //Proceedings of the 6th International Conference on Engineering & MIS 2020, 2020, Almaty, Kazakhstan, New York: ACM, 2020: 1-8. DOI: 10.1145/3410352.3410822.
[10] ABUBAKIR AHMED H, ABDULLA MAHMOOD S. A deep learning technique for lung nodule classification based on false positive reduction[J]. J Zankoy Sulaimani A, 2019, 21(1): 107-116. DOI: 10.17656/jzs.10749.
[11] PANG S C, MENG F, WANG X, et al. VGG16-T: a novel deep convolutional neural network with boosting to identify pathological type of lung cancer in early stage by CT images[J]. Int J Comput Int Sys, 2020, 13(1): 771. DOI: 10.2991/ijcis.d.200608.001.
[12] JAKIMOVSKI G, DAVCEV D. Using double convolution neural network for lung cancer stage detection[J]. Appl Sci, 2019, 9(3): 427. DOI: 10.3390/app9030427.
[13] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C] //2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Las Vegas, NV, USA, IEEE, 2016: 779-788. DOI: 10.1109/CVPR.2016.91.
[14] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[M] //Computer Vision – ECCV 2016. Cham: Springer International Publishing, 2016: 21-37. DOI: 10.1007/978-3-319-46448-0_2.
[15] GIRSHICK R. Fast R-CNN[C] //2015 IEEE International Conference on Computer Vision(ICCV), 2015, Santiago, Chile, IEEE, 2016: 1440-1448. DOI: 10.1109/ICCV.2015.169.
[16] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C] //IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE, 2016: 1137-1149. DOI: 10.1109/TPAMI.2016.2577031.
[17] LAW H, DENG J. CornerNet: detecting objects as paired keypoints[J]. Int J Comput Vision, 2020, 128(3): 642-656. DOI: 10.1007/s11263-019-01204-1.
[18] HE K M, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C] //2017 IEEE International Conference on Computer Vision(ICCV), Venice, Italy. IEEE, 2017: 2980-2988. DOI: 10.1109/ICCV.2017.322.
[19] EVERINGHAM M, VAN GOOL L, WILLIAMS C K I, et al. The pascal visual object classes(VOC)challenge[J]. Int J Comput Vision, 2010, 88(2): 303-338. DOI: 10.1007/s11263-009-0275-4.
[20] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. [2022-02-26]. https://arxiv.org/abs/1409.1556.
[21] JANOWCZYK A, MADABHUSHI A. Deep learning for digital pathology image analysis: a comprehensive tutorial with selected use cases[J]. J Pathol Inform, 2016, 7(1): 29. DOI: 10.4103/2153-3539.186902. (