Literature DB >> 31811427

A deep residual learning network for predicting lung adenocarcinoma manifesting as ground-glass nodule on CT images.

Jing Gong1,2, Jiyu Liu3, Wen Hao1, Shengdong Nie4, Bin Zheng5, Shengping Wang6,7, Weijun Peng8,9.   

Abstract

OBJECTIVE: To develop a deep learning-based artificial intelligence (AI) scheme for predicting the likelihood of the ground-glass nodule (GGN) detected on CT images being invasive adenocarcinoma (IA) and also compare the accuracy of this AI scheme with that of two radiologists.
METHODS: First, we retrospectively collected 828 histopathologically confirmed GGNs of 644 patients from two centers. Among them, 209 GGNs are confirmed IA and 619 are non-IA, including 409 adenocarcinomas in situ and 210 minimally invasive adenocarcinomas. Second, we applied a series of pre-preprocessing techniques, such as image resampling, rescaling and cropping, and data augmentation, to process original CT images and generate new training and testing images. Third, we built an AI scheme based on a deep convolutional neural network by using a residual learning architecture and batch normalization technique. Finally, we conducted an observer study and compared the prediction performance of the AI scheme with that of two radiologists using an independent dataset with 102 GGNs.
RESULTS: The new AI scheme yielded an area under the receiver operating characteristic curve (AUC) of 0.92 ± 0.03 in classifying between IA and non-IA GGNs, which is equivalent to the senior radiologist's performance (AUC 0.92 ± 0.03) and higher than the score of the junior radiologist (AUC 0.90 ± 0.03). The Kappa value of two sets of subjective prediction scores generated by two radiologists is 0.6.
CONCLUSIONS: The study result demonstrates using an AI scheme to improve the performance in predicting IA, which can help improve the development of a more effective personalized cancer treatment paradigm. KEY POINTS: • The feasibility of using a deep learning method to predict the likelihood of the ground-glass nodule being invasive adenocarcinoma. • Residual learning-based CNN model improves the performance in classifying between IA and non-IA nodules. • Artificial intelligence (AI) scheme yields higher performance than radiologists in predicting invasive adenocarcinoma.

Entities:  

Keywords:  Carcinoma; Computer-assisted image interpretation; Lung neoplasms; Multiple pulmonary nodules; X-Ray computed tomography scanners

Mesh:

Year:  2019        PMID: 31811427     DOI: 10.1007/s00330-019-06533-w

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  20 in total

1.  Computer-aided diagnosis of lung cancer: the effect of training data sets on classification accuracy of lung nodules.

Authors:  Jing Gong; Ji-Yu Liu; Xi-Wen Sun; Bin Zheng; Sheng-Dong Nie
Journal:  Phys Med Biol       Date:  2018-02-05       Impact factor: 3.609

Review 2.  Receiver operating characteristic analysis: a tool for the quantitative evaluation of observer performance and imaging systems.

Authors:  Charles E Metz
Journal:  J Am Coll Radiol       Date:  2006-06       Impact factor: 5.532

Review 3.  Non-small cell lung cancer: current treatment and future advances.

Authors:  Cecilia Zappa; Shaker A Mousa
Journal:  Transl Lung Cancer Res       Date:  2016-06

4.  Software performance in segmenting ground-glass and solid components of subsolid nodules in pulmonary adenocarcinomas.

Authors:  Julien G Cohen; Jin Mo Goo; Roh-Eul Yoo; Chang Min Park; Chang Hyun Lee; Bram van Ginneken; Doo Hyun Chung; Young Tae Kim
Journal:  Eur Radiol       Date:  2016-04-05       Impact factor: 5.315

5.  Changes in quantitative CT image features of ground-glass nodules in differentiating invasive pulmonary adenocarcinoma from benign and in situ lesions: histopathological comparisons.

Authors:  Y P Zhang; M A Heuvelmans; H Zhang; M Oudkerk; G X Zhang; X Q Xie
Journal:  Clin Radiol       Date:  2018-01-09       Impact factor: 2.350

6.  Lung Adenocarcinoma Invasiveness Risk in Pure Ground-Glass Opacity Lung Nodules Smaller than 2 cm.

Authors:  Geun Dong Lee; Chul Hwan Park; Heae Surng Park; Min Kwang Byun; Ik Jae Lee; Tae Hoon Kim; Sungsoo Lee
Journal:  Thorac Cardiovasc Surg       Date:  2018-01-22       Impact factor: 1.827

Review 7.  Deep Learning in Medical Image Analysis.

Authors:  Dinggang Shen; Guorong Wu; Heung-Il Suk
Journal:  Annu Rev Biomed Eng       Date:  2017-03-09       Impact factor: 9.590

8.  Computerized texture analysis of persistent part-solid ground-glass nodules: differentiation of preinvasive lesions from invasive pulmonary adenocarcinomas.

Authors:  Hee-Dong Chae; Chang Min Park; Sang Joon Park; Sang Min Lee; Kwang Gi Kim; Jin Mo Goo
Journal:  Radiology       Date:  2014-08-01       Impact factor: 11.105

9.  Radiomics signature: a biomarker for the preoperative discrimination of lung invasive adenocarcinoma manifesting as a ground-glass nodule.

Authors:  Li Fan; MengJie Fang; ZhaoBin Li; WenTing Tu; ShengPing Wang; WuFei Chen; Jie Tian; Di Dong; ShiYuan Liu
Journal:  Eur Radiol       Date:  2018-07-02       Impact factor: 5.315

10.  Solid component proportion is an important predictor of tumor invasiveness in clinical stage T1N0M0 (cT1N0M0) lung adenocarcinoma.

Authors:  Meng Li; Ning Wu; Li Zhang; Wei Sun; Ying Liu; Lv Lv; Jiansong Ren; Dongmei Lin
Journal:  Cancer Imaging       Date:  2018-05-04       Impact factor: 3.909

View more
  21 in total

1.  A semi-supervised learning framework for micropapillary adenocarcinoma detection.

Authors:  Yuan Gao; Yanhui Ding; Wei Xiao; Zhigang Yao; Xiaoming Zhou; Xiaodan Sui; Yanna Zhao; Yuanjie Zheng
Journal:  Int J Comput Assist Radiol Surg       Date:  2022-02-12       Impact factor: 2.924

Review 2.  A narrative review on current imaging applications of artificial intelligence and radiomics in oncology: focus on the three most common cancers.

Authors:  Simone Vicini; Chandra Bortolotto; Marco Rengo; Daniela Ballerini; Davide Bellini; Iacopo Carbone; Lorenzo Preda; Andrea Laghi; Francesca Coppola; Lorenzo Faggioni
Journal:  Radiol Med       Date:  2022-06-30       Impact factor: 6.313

3.  Development and Validation of a Risk Stratification Model of Pulmonary Ground-Glass Nodules Based on Complementary Lung-RADS 1.1 and Deep Learning Scores.

Authors:  Qingcheng Meng; Bing Li; Pengrui Gao; Wentao Liu; Peijin Zhou; Jia Ding; Jiaqi Zhang; Hong Ge
Journal:  Front Public Health       Date:  2022-05-23

4.  Natural history of pathologically confirmed pulmonary subsolid nodules with deep learning-assisted nodule segmentation.

Authors:  Lin-Lin Qi; Jian-Wei Wang; Lin Yang; Yao Huang; Shi-Jun Zhao; Wei Tang; Yu-Jing Jin; Ze-Wei Zhang; Zhen Zhou; Yi-Zhou Yu; Yi-Zhou Wang; Ning Wu
Journal:  Eur Radiol       Date:  2020-11-21       Impact factor: 5.315

5.  Investigating the association between ground-glass nodules glucose metabolism and the invasive growth pattern of early lung adenocarcinoma.

Authors:  Xiaoliang Shao; Xiaonan Shao; Rong Niu; Zhenxing Jiang; Mei Xu; Yuetao Wang
Journal:  Quant Imaging Med Surg       Date:  2021-08

6.  3D deep learning based classification of pulmonary ground glass opacity nodules with automatic segmentation.

Authors:  Duo Wang; Tao Zhang; Ming Li; Raphael Bueno; Jagadeesan Jayender
Journal:  Comput Med Imaging Graph       Date:  2020-12-11       Impact factor: 4.790

7.  [Research Progress in Distinguishing Methods of Simultaneous Multiple Primary Lung Cancer and Intrapulmonary Metastasis].

Authors:  Jifan Wang; Te Zhang; Hanlin Ding; Gaochao Dong; Lin Xu; Feng Jiang
Journal:  Zhongguo Fei Ai Za Zhi       Date:  2021-05-20

8.  Computer tomographic differential diagnosis of ameloblastoma and odontogenic keratocyst: classification using a convolutional neural network.

Authors:  Mayara Simões Bispo; Mário Lúcio Gomes de Queiroz Pierre Júnior; Antônio Lopes Apolinário; Jean Nunes Dos Santos; Braulio Carneiro Junior; Frederico Sampaio Neves; Iêda Crusoé-Rebello
Journal:  Dentomaxillofac Radiol       Date:  2021-04-29       Impact factor: 3.525

9.  COVIDiag: a clinical CAD system to diagnose COVID-19 pneumonia based on CT findings.

Authors:  Ali Abbasian Ardakani; U Rajendra Acharya; Sina Habibollahi; Afshin Mohammadi
Journal:  Eur Radiol       Date:  2020-08-01       Impact factor: 5.315

10.  Comparison and Fusion of Deep Learning and Radiomics Features of Ground-Glass Nodules to Predict the Invasiveness Risk of Stage-I Lung Adenocarcinomas in CT Scan.

Authors:  Xianwu Xia; Jing Gong; Wen Hao; Ting Yang; Yeqing Lin; Shengping Wang; Weijun Peng
Journal:  Front Oncol       Date:  2020-03-31       Impact factor: 6.244

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.