Literature DB >> 31157258

Deep learning based classification of ultrasound images for thyroid nodules: a large scale of pilot study.

Qing Guan1,2, Yunjun Wang1,2, Jiajun Du3, Yu Qin3, Hongtao Lu3, Jun Xiang1,2, Fen Wang2,4.   

Abstract

BACKGROUND: To explore the ability of the deep learning network Inception-v3 to differentiate between papillary thyroid carcinomas (PTCs) and benign nodules in ultrasound images.
METHODS: A total of 2,836 thyroid ultrasound images from 2,235 patients were divided into a training dataset and a test dataset. Inception-v3 was trained and tested to crop the margin of the images of nodules and provide a differential diagnosis. The sizes and sonographic features of nodules were further analysed to identify the factors that may influence diagnostic efficiency. Statistical analyses included χ2 and Fisher's exact tests and univariate and multivariate analyses.
RESULTS: There were 1,275 PTCs and 1,162 benign nodules in the training group and 209 PTCs and 190 benign nodules in the test group. A margin size of 50 pixels and an input size of 384×384 showed the best outcome after training, and these parameters were selected for the test group. In the test group, the sensitivity and specificity for Inception-v3 were 93.3% (195/209) and 87.4% (166/190), respectively. Inception-v3 displayed the highest accuracy for 0.5-1.0 cm nodules. The accuracy differed according to the margin description (P=0.024). Taller nodules were more accurately diagnosed than were wider nodules (P=0.015). Microcalcification [odds ratio (OR) =0.254, 95% confidence interval (CI): 0.076-0.847, P=0.026] and taller shape (OR =0.243, 95% CI: 0.073-0.810, P=0.021) were negatively associated with misdiagnosis rate.
CONCLUSIONS: Inception-v3 can achieve an excellent diagnostic efficiency. Nodules that are 0.5-1.0 cm in size and have microcalcification and a taller shape can be more accurately diagnosed by Inception-v3.

Entities:  

Keywords:  Inception-v3; Ultrasound; deep learning; papillary thyroid cancer

Year:  2019        PMID: 31157258      PMCID: PMC6511554          DOI: 10.21037/atm.2019.04.34

Source DB:  PubMed          Journal:  Ann Transl Med        ISSN: 2305-5839


  15 in total

1.  A taller-than-wide shape in thyroid nodules in transverse and longitudinal ultrasonographic planes and the prediction of malignancy.

Authors:  Hee Jung Moon; Jin Young Kwak; Eun-Kyung Kim; Min Jung Kim
Journal:  Thyroid       Date:  2011-08-30       Impact factor: 6.568

2.  A Computer-Aided Diagnosis System Using Artificial Intelligence for the Diagnosis and Characterization of Thyroid Nodules on Ultrasound: Initial Clinical Assessment.

Authors:  Young Jun Choi; Jung Hwan Baek; Hye Sun Park; Woo Hyun Shim; Tae Yong Kim; Young Kee Shong; Jeong Hyun Lee
Journal:  Thyroid       Date:  2017-02-28       Impact factor: 6.568

3.  Taller-than-wide sign for predicting thyroid microcarcinoma: comparison and combination of two ultrasonographic planes.

Authors:  Shun-Ping Chen; Yuan-Ping Hu; Bin Chen
Journal:  Ultrasound Med Biol       Date:  2014-06-25       Impact factor: 2.998

Review 4.  2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: The American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer.

Authors:  Bryan R Haugen; Erik K Alexander; Keith C Bible; Gerard M Doherty; Susan J Mandel; Yuri E Nikiforov; Furio Pacini; Gregory W Randolph; Anna M Sawka; Martin Schlumberger; Kathryn G Schuff; Steven I Sherman; Julie Ann Sosa; David L Steward; R Michael Tuttle; Leonard Wartofsky
Journal:  Thyroid       Date:  2016-01       Impact factor: 6.568

5.  Predictors of Malignancy in Children with Thyroid Nodules.

Authors:  Alessandro Mussa; Maurilio De Andrea; Manuela Motta; Alberto Mormile; Nicola Palestini; Andrea Corrias
Journal:  J Pediatr       Date:  2015-07-08       Impact factor: 4.406

6.  Thyroid imaging reporting and data system for US features of nodules: a step in establishing better stratification of cancer risk.

Authors:  Jin Young Kwak; Kyung Hwa Han; Jung Hyun Yoon; Hee Jung Moon; Eun Ju Son; So Hee Park; Hyun Kyung Jung; Ji Soo Choi; Bo Mi Kim; Eun-Kyung Kim
Journal:  Radiology       Date:  2011-07-19       Impact factor: 11.105

7.  Benign and malignant thyroid nodules: US differentiation--multicenter retrospective study.

Authors:  Won-Jin Moon; So Lyung Jung; Jeong Hyun Lee; Dong Gyu Na; Jung-Hwan Baek; Young Hen Lee; Jinna Kim; Hyun Sook Kim; Jun Soo Byun; Dong Hoon Lee
Journal:  Radiology       Date:  2008-04-10       Impact factor: 11.105

8.  Thyroid cancer mortality and incidence: a global overview.

Authors:  Carlo La Vecchia; Matteo Malvezzi; Cristina Bosetti; Werner Garavello; Paola Bertuccio; Fabio Levi; Eva Negri
Journal:  Int J Cancer       Date:  2014-10-13       Impact factor: 7.396

9.  Risk of thyroid cancer based on thyroid ultrasound imaging characteristics: results of a population-based study.

Authors:  Rebecca Smith-Bindman; Paulette Lebda; Vickie A Feldstein; Dorra Sellami; Ruth B Goldstein; Natasha Brasic; Chengshi Jin; John Kornak
Journal:  JAMA Intern Med       Date:  2013-10-28       Impact factor: 21.873

10.  Worldwide increasing incidence of thyroid cancer: update on epidemiology and risk factors.

Authors:  Gabriella Pellegriti; Francesco Frasca; Concetto Regalbuto; Sebastiano Squatrito; Riccardo Vigneri
Journal:  J Cancer Epidemiol       Date:  2013-05-07
View more
  13 in total

1.  Boundary Restored Network for Subpleural Pulmonary Lesion Segmentation on Ultrasound Images at Local and Global Scales.

Authors:  Yupeng Xu; Yi Zhang; Ke Bi; Zhiyu Ning; Lisha Xu; Mengjun Shen; Guoying Deng; Yin Wang
Journal:  J Digit Imaging       Date:  2020-10       Impact factor: 4.056

2.  Using deep convolutional neural networks for multi-classification of thyroid tumor by histopathology: a large-scale pilot study.

Authors:  Yunjun Wang; Qing Guan; Iweng Lao; Li Wang; Yi Wu; Duanshu Li; Qinghai Ji; Yu Wang; Yongxue Zhu; Hongtao Lu; Jun Xiang
Journal:  Ann Transl Med       Date:  2019-09

Review 3.  Computer-Aided Diagnosis Systems in Diagnosing Malignant Thyroid Nodules on Ultrasonography: A Systematic Review and Meta-Analysis.

Authors:  Lei Xu; Junling Gao; Quan Wang; Jichao Yin; Pengfei Yu; Bin Bai; Ruixia Pei; Dingzhang Chen; Guochun Yang; Shiqi Wang; Mingxi Wan
Journal:  Eur Thyroid J       Date:  2019-12-04

Review 4.  Artificial Intelligence for Personalized Medicine in Thyroid Cancer: Current Status and Future Perspectives.

Authors:  Ling-Rui Li; Bo Du; Han-Qing Liu; Chuang Chen
Journal:  Front Oncol       Date:  2021-02-09       Impact factor: 6.244

Review 5.  A Systematic Review of Artificial Intelligence Techniques in Cancer Prediction and Diagnosis.

Authors:  Yogesh Kumar; Surbhi Gupta; Ruchi Singla; Yu-Chen Hu
Journal:  Arch Comput Methods Eng       Date:  2021-09-27       Impact factor: 8.171

6.  Recognition of Thyroid Ultrasound Standard Plane Images Based on Residual Network.

Authors:  Minghui Guo; Kangjian Wang; Shunlan Liu; Yongzhao Du; Peizhong Liu; Qichen Su; Guorong Lv
Journal:  Comput Intell Neurosci       Date:  2021-06-02

7.  Application of neural network model in assisting device fitting for low vision patients.

Authors:  Bingfa Dai; Yang Yu; Lijuan Huang; Zhiyong Meng; Liang Chen; Hongxia Luo; Ting Chen; Xuelan Chen; Wenwen Ye; Yuyuan Yan; Chi Cai; Jianqing Zheng; Jun Zhao; Liquan Dong; Jianmin Hu
Journal:  Ann Transl Med       Date:  2020-06

8.  Multi-channel convolutional neural network architectures for thyroid cancer detection.

Authors:  Xinyu Zhang; Vincent C S Lee; Jia Rong; Feng Liu; Haoyu Kong
Journal:  PLoS One       Date:  2022-01-21       Impact factor: 3.240

Review 9.  Towards Clinical Application of Artificial Intelligence in Ultrasound Imaging.

Authors:  Masaaki Komatsu; Akira Sakai; Ai Dozen; Kanto Shozu; Suguru Yasutomi; Hidenori Machino; Ken Asada; Syuzo Kaneko; Ryuji Hamamoto
Journal:  Biomedicines       Date:  2021-06-23

10.  Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer.

Authors:  Wai-Kin Chan; Jui-Hung Sun; Miaw-Jene Liou; Yan-Rong Li; Wei-Yu Chou; Feng-Hsuan Liu; Szu-Tah Chen; Syu-Jyun Peng
Journal:  Biomedicines       Date:  2021-11-26
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.