Detection and Classification of Lung Cancer in Histopathology Images Using Deep Learning

Document Type : Research Article

Authors

1 Computer Engineering Department, Razi University, Kermanshah, Iran.

2 Department of Computer Engineering, Razi University, Kermanshah, Iran.

10.22108/jcs.2024.140356.1139

Abstract

In recent years, artificial intelligence has been used to diagnose and classify cancers using different deep learning-based models. Although they have good overall accuracy, they need high computation resources and execution time, and also have low accuracy, precision, and sensitivity. To this end, we try to employ a new model named the "EfficientNetB0" model with appropriate preprocessing to obtain high precision and sensitivity at a relatively low computation time for diagnosing lung cancer. The EfficientNetB0 model consists of 7 blocks, and each block includes one layer of mobile convolution (MB-Conv) and squeeze-excitation (SE) blocks. EfficientNetB0 has a higher accuracy compared to other common deep learning models due to incorporating a compound coefficient approach. The proposed model is evaluated on the histopathology images dataset and the obtained accuracy of the model is 0.9258. Also, its precision and sensitivity are 0.942 and 0.967, respectively, and these show the superiority of this model compared to existing methods.

Keywords

Main Subjects

References

[1] Ciresan Dan C and Giusti Alessandro and Gambardella Luca M and Schmidhuber Jurgen. Mitosis detection in breast cancer histology images with deep neural networks. Medical Image Computing and Computer-Assisted Intervention--MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part II 16. 411--418, 2013. [DOI ]
[2] Xu Jun and Xiang Lei and Liu Qingshan and Gilmore Hannah and Wu Jianzhong and Tang Jinghai and Madabhushi Anant. Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images. IEEE transactions on medical imaging. 35(1): 119--130, IEEE. 2015. [DOI ]
[3] Paul Angshuman and Mukherjee Dipti Prasad. Mitosis detection for invasive breast cancer grading in histopathological images. IEEE transactions on image processing. 24(11): 4041--4054, IEEE. 2015. [DOI ]
[4] Deniz Erkan and cengur Abdulkadir and Kadiroglu Zehra and Guo Yanhui and Bajaj Varun and Budak Umit. Transfer learning based histopathologic image classification for breast cancer detection. Health information science and systems. 6: 1--7, Springer. 2018. [DOI ]
[5] Fan Kun and Wen Shibo and Deng Zhuofu. Deep learning for detecting breast cancer metastases on WSI. Innovation in Medicine and Healthcare Systems, and Multimedia: Proceedings of KES-InMed-19 and KES-IIMSS-19 Conferences. 137--145, 2019. [DOI ]
[6] Gecer Baris and Aksoy Selim and Mercan Ezgi and Shapiro Linda G and Weaver Donald L and Elmore Joann G. Detection and classification of cancer in whole slide breast histopathology images using deep convolutional networks. Pattern recognition. 84: 345--356, Elsevier. 2018. [DOI ]
[7] Gori Fabio. Metagenomic data analysis: computational methods and applications. 2013.
[8] Howard Andrew G and Zhu Menglong and Chen Bo and Kalenichenko Dmitry and Wang Weijun and Weyand Tobias and Andreetto Marco and Adam Hartwig. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861. 2017. [DOI ]
[9] Janowczyk Andrew and Madabhushi Anant. Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases. Journal of pathology informatics. 7(1): 29, Elsevier. 2016. [DOI ]
[10] Khan Adnan Mujahid and Rajpoot Nasir and Treanor Darren and Magee Derek. A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution. IEEE transactions on Biomedical Engineering. 61(6): 1729--1738, IEEE. 2014. [DOI ]
[11] Koyun Onur Can and Bilgin Gokhan. Nuclei Detection in Histopathological Images with Deep Learning and Heuristic Optimization. 2017 21st National Biomedical Engineering Meeting (BIYOMUT). i--iv, 2017. [DOI ]
[12] Lee Byungjae and Paeng Kyunghyun. A robust and effective approach towards accurate metastasis detection and pn-stage classification in breast cancer. Medical Image Computing and Computer Assisted Intervention--MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part II 11. 841--850, 2018. [DOI ]
[13] Li Weizhe and Chen Weijie. Reproducibility in deep learning algorithms for digital pathology applications: a case study using the CAMELYON16 datasets. Medical Imaging 2021: Digital Pathology. 11603: 323--332, 2021. [DOI ]
[14] Liu Wei and Wang Yaohua and Chen Yu. A HIERARCHICAL AND ENSEMBLE FRAMEWORK FOR PATIENCE’S PN-STAGE PREDICTION. Camelyon Challenge, September. 26: 2017.
[15] Macenko Marc and Niethammer Marc and Marron James S and Borland David and Woosley John T and Guan Xiaojun and Schmitt Charles and Thomas Nancy E. A method for normalizing histology slides for quantitative analysis. 2009 IEEE international symposium on biomedical imaging: from nano to macro. 1107--1110, 2009. [DOI ]
[16] Penzien Donald B and Irby Megan B and Smitherman Todd A and Rains Jeanetta C and Houle Timothy T. Well-established and empirically supported behavioral treatments for migraine. Current pain and headache reports. 19: 1--7, Springer. 2015. [DOI ]
[17] Refaeilzadeh Payam and Tang Lei and Liu Huan. Cross-validation. Encyclopedia of database systems. 532--538, Springer US. 2009. [DOI ]
[18] Reinhard Erik and Adhikhmin Michael and Gooch Bruce and Shirley Peter. Color transfer between images. IEEE Computer graphics and applications. 21(5): 34--41, IEEE. 2001. [DOI ]
[19] Salvi Massimo and Molinari Filippo and Acharya U Rajendra and Molinaro Luca and Meiburger Kristen M. Impact of stain normalization and patch selection on the performance of convolutional neural networks in histological breast and prostate cancer classification. Computer Methods and Programs in Biomedicine Update. 1: 100004, Elsevier. 2021. [DOI ]
[20] Sandler Mark and Howard Andrew and Zhu Menglong and Zhmoginov Andrey and Chen Liang-Chieh. Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE conference on computer vision and pattern recognition. 4510--4520, 2018. [DOI ]
[21] Saric Matko and Russo Mladen and Stella Maja and Sikora Marjan. CNN-based method for lung cancer detection in whole slide histopathology images. 2019 4th International Conference on Smart and Sustainable Technologies (SpliTech). 1--4, 2019. [DOI ]
[22] Tabibu Sairam and Vinod PK and Jawahar CV. Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images using deep learning. Scientific reports. 9(1): 10509, Nature Publishing Group UK London. 2019. [DOI ]
[23] Talo Muhammed. Automated classification of histopathology images using transfer learning. Artificial intelligence in medicine. 101: 101743, Elsevier. 2019. [DOI ]
[24] Tan Mingxing and Le Quoc. Efficientnet: Rethinking model scaling for convolutional neural networks. International conference on machine learning. 6105--6114, 2019.
[25] Teramoto Atsushi and Tsukamoto Tetsuya and Kiriyama Yuka and Fujita Hiroshi and others. Automated classification of lung cancer types from cytological images using deep convolutional neural networks. BioMed research international. 2017: Hindawi. 2017. [DOI ]
[26] Thomas J St and Lamb D and Ashcroft T and Corrin B and Edwards CW and Gibbs AR and Kenyon WE and Stephens RJ and Whimster WF. How reliable is the diagnosis of lung cancer using small biopsy specimens? Report of a UKCCCR Lung Cancer Working Party.. Thorax. 48(11): 1135--1139, BMJ Publishing Group Ltd. 1993. [DOI ]
[27] Vahadane Abhishek and Peng Tingying and Sethi Amit and Albarqouni Shadi and Wang Lichao and Baust Maximilian and Steiger Katja and Schlitter Anna Melissa and Esposito Irene and Navab Nassir. Structure-preserving color normalization and sparse stain separation for histological images. IEEE transactions on medical imaging. 35(8): 1962--1971, IEEE. 2016. [DOI ]
[28] Veta Mitko and Van Diest Paul J and Willems Stefan M and Wang Haibo and Madabhushi Anant and Cruz-Roa Angel and Gonzalez Fabio and Larsen Anders BL and Vestergaard Jacob S and Dahl Anders B and others. Assessment of algorithms for mitosis detection in breast cancer histopathology images. Medical image analysis. 20(1): 237--248, Elsevier. 2015. [DOI ]
[29] Wei Jason W and Tafe Laura J and Linnik Yevgeniy A and Vaickus Louis J and Tomita Naofumi and Hassanpour Saeed. Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks. Scientific reports. 9(1): 3358, Nature Publishing Group UK London. 2019. [DOI ]
[30] Xia Tian and Kumar Ashnil and Feng Dagan and Kim Jinman. Patch-level tumor classification in digital histopathology images with domain adapted deep learning. 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC). 644--647, 2018. [DOI ]
[31] Yousefi Jamileh. Image binarization using Otsu thresholding algorithm. Ontario, Canada: University of Guelph. 10: 2011. [DOI ]
[32] Li Zhang and Zhang Jiehua and Tan Tao and Teng Xichao and Sun Xiaoliang and Zhao Hong and Liu Lihong and Xiao Yang and Lee Byungjae and Li Yilong and others. Deep learning methods for lung cancer segmentation in whole-slide histopathology images—the acdc@ lunghp challenge 2019. IEEE Journal of Biomedical and Health Informatics. 25(2): 429--440, IEEE. 2020. [DOI ]

Files

History

  • Receive Date: 06 January 2024
  • Revise Date: 24 March 2024
  • Accept Date: 07 April 2024

Share

How to cite

Statistics