Next Article in Journal
Evaluation of Integrated HPV DNA as Individualized Biomarkers for the Detection of Recurrent CIN2/3 during Post-Treatment Surveillance
Next Article in Special Issue
Artificial Intelligence Compared to Radiologists for the Initial Diagnosis of Prostate Cancer on Magnetic Resonance Imaging: A Systematic Review and Recommendations for Future Studies
Previous Article in Journal
Current Advances in Basic and Translational Research of Cholangiocarcinoma
Article

DeepRePath: Identifying the Prognostic Features of Early-Stage Lung Adenocarcinoma Using Multi-Scale Pathology Images and Deep Convolutional Neural Networks

1
Deargen Inc., Daejeon 34051, Korea
2
Department of Hospital Pathology, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea
3
Department of Pathology, College of Medicine, Chung-Ang University, Seoul 06974, Korea
4
Division of Oncology, Department of Internal Medicine, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea
5
Department of Radiology, Uijeongbu St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea
6
Department of Thoracic and Cardiovascular Surgery, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea
7
Cancer Research Institute, College of Medicine, The Catholic University of Korea, Seoul 06591, Korea
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editors: Reza Forghani, Rajiv Gupta and Farhad Maleki
Cancers 2021, 13(13), 3308; https://doi.org/10.3390/cancers13133308
Received: 17 May 2021 / Revised: 10 June 2021 / Accepted: 28 June 2021 / Published: 1 July 2021
Pathology images are vital for understanding solid cancers. In this study, we created DeepRePath using multi-scale pathology images with two-channel deep learning to predict the prognosis of patients with early-stage lung adenocarcinoma (LUAD). DeepRePath demonstrated that it could predict the recurrence of early-stage LUAD with average area under the curve scores of 0.77 and 0.76 in cohort I and cohort II (external validation set), respectively. Pathological features found to be associated with a high probability of recurrence included tumor necrosis, discohesive tumor cells, and atypical nuclei. In conclusion, DeepRePath can improve the treatment modality for patients with early-stage LUAD through recurrence prediction.
The prognosis of patients with lung adenocarcinoma (LUAD), especially early-stage LUAD, is dependent on clinicopathological features. However, its predictive utility is limited. In this study, we developed and trained a DeepRePath model based on a deep convolutional neural network (CNN) using multi-scale pathology images to predict the prognosis of patients with early-stage LUAD. DeepRePath was pre-trained with 1067 hematoxylin and eosin-stained whole-slide images of LUAD from the Cancer Genome Atlas. DeepRePath was further trained and validated using two separate CNNs and multi-scale pathology images of 393 resected lung cancer specimens from patients with stage I and II LUAD. Of the 393 patients, 95 patients developed recurrence after surgical resection. The DeepRePath model showed average area under the curve (AUC) scores of 0.77 and 0.76 in cohort I and cohort II (external validation set), respectively. Owing to low performance, DeepRePath cannot be used as an automated tool in a clinical setting. When gradient-weighted class activation mapping was used, DeepRePath indicated the association between atypical nuclei, discohesive tumor cells, and tumor necrosis in pathology images showing recurrence. Despite the limitations associated with a relatively small number of patients, the DeepRePath model based on CNNs with transfer learning could predict recurrence after the curative resection of early-stage LUAD using multi-scale pathology images. View Full-Text
Keywords: deep learning; lung adenocarcinoma; pathology image; prognosis deep learning; lung adenocarcinoma; pathology image; prognosis
Show Figures

Figure 1

MDPI and ACS Style

Shim, W.S.; Yim, K.; Kim, T.-J.; Sung, Y.E.; Lee, G.; Hong, J.H.; Chun, S.H.; Kim, S.; An, H.J.; Na, S.J.; Kim, J.J.; Moon, M.H.; Moon, S.W.; Park, S.; Hong, S.A.; Ko, Y.H. DeepRePath: Identifying the Prognostic Features of Early-Stage Lung Adenocarcinoma Using Multi-Scale Pathology Images and Deep Convolutional Neural Networks. Cancers 2021, 13, 3308. https://doi.org/10.3390/cancers13133308

AMA Style

Shim WS, Yim K, Kim T-J, Sung YE, Lee G, Hong JH, Chun SH, Kim S, An HJ, Na SJ, Kim JJ, Moon MH, Moon SW, Park S, Hong SA, Ko YH. DeepRePath: Identifying the Prognostic Features of Early-Stage Lung Adenocarcinoma Using Multi-Scale Pathology Images and Deep Convolutional Neural Networks. Cancers. 2021; 13(13):3308. https://doi.org/10.3390/cancers13133308

Chicago/Turabian Style

Shim, Won S., Kwangil Yim, Tae-Jung Kim, Yeoun E. Sung, Gyeongyun Lee, Ji H. Hong, Sang H. Chun, Seoree Kim, Ho J. An, Sae J. Na, Jae J. Kim, Mi H. Moon, Seok W. Moon, Sungsoo Park, Soon A. Hong, and Yoon H. Ko. 2021. "DeepRePath: Identifying the Prognostic Features of Early-Stage Lung Adenocarcinoma Using Multi-Scale Pathology Images and Deep Convolutional Neural Networks" Cancers 13, no. 13: 3308. https://doi.org/10.3390/cancers13133308

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop