Ying Ren1, Min-Yu Tsai2,3,4, Liyuan Chen3,4, Jing Wang3,4, Shulong Li3, Yufei Liu5,6, Xun Jia7,8,9, Chenyang Shen10,11,12. 1. Department of Neurology, Heilongjiang Province Number III Hospital, Beian, 164000, Heilongjiang, China. 2. Innovative Technology Of Radiotherapy Computations and Hardware (iTORCH) Laboratory, University of Texas Southwestern Medical Center, Dallas, TX, 75235, USA. 3. Medical Artificial Intelligence and Automation (MAIA) Laboratory, University of Texas Southwestern Medical Center, Dallas, TX, 75235, USA. 4. Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, 75235, USA. 5. Key Laboratory of Optoelectronic Technology and Systems, Ministry of Education, Chongqing University, Chongqing, 400044, China. 6. Centre for Intelligent Sensing Technology, College of Optoelectronic Engineering, Chongqing University, Chongqing, 400044, China. 7. Innovative Technology Of Radiotherapy Computations and Hardware (iTORCH) Laboratory, University of Texas Southwestern Medical Center, Dallas, TX, 75235, USA. Xun.Jia@UTSouthwestern.edu. 8. Medical Artificial Intelligence and Automation (MAIA) Laboratory, University of Texas Southwestern Medical Center, Dallas, TX, 75235, USA. Xun.Jia@UTSouthwestern.edu. 9. Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, 75235, USA. Xun.Jia@UTSouthwestern.edu. 10. Innovative Technology Of Radiotherapy Computations and Hardware (iTORCH) Laboratory, University of Texas Southwestern Medical Center, Dallas, TX, 75235, USA. Chenyang.Shen@UTSouthwestern.edu. 11. Medical Artificial Intelligence and Automation (MAIA) Laboratory, University of Texas Southwestern Medical Center, Dallas, TX, 75235, USA. Chenyang.Shen@UTSouthwestern.edu. 12. Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, 75235, USA. Chenyang.Shen@UTSouthwestern.edu.
Abstract
PURPOSE: Diagnosis of lung cancer requires radiologists to review every lung nodule in CT images. Such a process can be very time-consuming, and the accuracy is affected by many factors, such as experience of radiologists and available diagnosis time. To address this problem, we proposed to develop a deep learning-based system to automatically classify benign and malignant lung nodules. METHODS: The proposed method automatically determines benignity or malignancy given the 3D CT image patch of a lung nodule to assist diagnosis process. Motivated by the fact that real structure among data is often embedded on a low-dimensional manifold, we developed a novel manifold regularized classification deep neural network (MRC-DNN) to perform classification directly based on the manifold representation of lung nodule images. The concise manifold representation revealing important data structure is expected to benefit the classification, while the manifold regularization enforces strong, but natural constraints on network training, preventing over-fitting. RESULTS: The proposed method achieves accurate manifold learning with reconstruction error of ~ 30 HU on real lung nodule CT image data. In addition, the classification accuracy on testing data is 0.90 with sensitivity of 0.81 and specificity of 0.95, which outperforms state-of-the-art deep learning methods. CONCLUSION: The proposed MRC-DNN facilitates an accurate manifold learning approach for lung nodule classification based on 3D CT images. More importantly, MRC-DNN suggests a new and effective idea of enforcing regularization for network training, possessing the potential impact to a board range of applications.
PURPOSE: Diagnosis of lung cancer requires radiologists to review every lung nodule in CT images. Such a process can be very time-consuming, and the accuracy is affected by many factors, such as experience of radiologists and available diagnosis time. To address this problem, we proposed to develop a deep learning-based system to automatically classify benign and malignant lung nodules. METHODS: The proposed method automatically determines benignity or malignancy given the 3D CT image patch of a lung nodule to assist diagnosis process. Motivated by the fact that real structure among data is often embedded on a low-dimensional manifold, we developed a novel manifold regularized classification deep neural network (MRC-DNN) to perform classification directly based on the manifold representation of lung nodule images. The concise manifold representation revealing important data structure is expected to benefit the classification, while the manifold regularization enforces strong, but natural constraints on network training, preventing over-fitting. RESULTS: The proposed method achieves accurate manifold learning with reconstruction error of ~ 30 HU on real lung nodule CT image data. In addition, the classification accuracy on testing data is 0.90 with sensitivity of 0.81 and specificity of 0.95, which outperforms state-of-the-art deep learning methods. CONCLUSION: The proposed MRC-DNN facilitates an accurate manifold learning approach for lung nodule classification based on 3D CT images. More importantly, MRC-DNN suggests a new and effective idea of enforcing regularization for network training, possessing the potential impact to a board range of applications.
Entities:
Keywords:
Deep learning; Diagnosis; Lung nodule classification; Manifold learning; Regularization
Authors: Samuel G Armato; Michael B Altman; Joel Wilkie; Shusuke Sone; Feng Li; Kunio Doi; Arunabha S Roy Journal: Med Phys Date: 2003-06 Impact factor: 4.071
Authors: Yutong Xie; Yong Xia; Jianpeng Zhang; Yang Song; Dagan Feng; Michael Fulham; Weidong Cai Journal: IEEE Trans Med Imaging Date: 2018-10-17 Impact factor: 10.048
Authors: Kenneth Clark; Bruce Vendt; Kirk Smith; John Freymann; Justin Kirby; Paul Koppel; Stephen Moore; Stanley Phillips; David Maffitt; Michael Pringle; Lawrence Tarbox; Fred Prior Journal: J Digit Imaging Date: 2013-12 Impact factor: 4.056
Authors: Samuel G Armato; Geoffrey McLennan; Luc Bidaut; Michael F McNitt-Gray; Charles R Meyer; Anthony P Reeves; Binsheng Zhao; Denise R Aberle; Claudia I Henschke; Eric A Hoffman; Ella A Kazerooni; Heber MacMahon; Edwin J R Van Beeke; David Yankelevitz; Alberto M Biancardi; Peyton H Bland; Matthew S Brown; Roger M Engelmann; Gary E Laderach; Daniel Max; Richard C Pais; David P Y Qing; Rachael Y Roberts; Amanda R Smith; Adam Starkey; Poonam Batrah; Philip Caligiuri; Ali Farooqi; Gregory W Gladish; C Matilda Jude; Reginald F Munden; Iva Petkovska; Leslie E Quint; Lawrence H Schwartz; Baskaran Sundaram; Lori E Dodd; Charles Fenimore; David Gur; Nicholas Petrick; John Freymann; Justin Kirby; Brian Hughes; Alessi Vande Casteele; Sangeeta Gupte; Maha Sallamm; Michael D Heath; Michael H Kuhn; Ekta Dharaiya; Richard Burns; David S Fryd; Marcos Salganicoff; Vikram Anand; Uri Shreter; Stephen Vastagh; Barbara Y Croft Journal: Med Phys Date: 2011-02 Impact factor: 4.071
Authors: Jayashree Kalpathy-Cramer; Artem Mamomov; Binsheng Zhao; Lin Lu; Dmitry Cherezov; Sandy Napel; Sebastian Echegaray; Daniel Rubin; Michael McNitt-Gray; Pechin Lo; Jessica C Sieren; Johanna Uthoff; Samantha K N Dilger; Brandan Driscoll; Ivan Yeung; Lubomir Hadjiiski; Kenny Cha; Yoganand Balagurunathan; Robert Gillies; Dmitry Goldgof Journal: Tomography Date: 2016-12
Authors: Lise Wei; Dawn Owen; Benjamin Rosen; Xinzhou Guo; Kyle Cuneo; Theodore S Lawrence; Randall Ten Haken; Issam El Naqa Journal: Phys Med Date: 2021-03-10 Impact factor: 2.685
Authors: Madison R Kocher; Jordan Chamberlin; Jeffrey Waltz; Madalyn Snoddy; Natalie Stringer; Joseph Stephenson; Jacob Kahn; Megan Mercer; Dhiraj Baruah; Gilberto Aquino; Ismail Kabakus; Philipp Hoelzer; Pooyan Sahbaee; U Joseph Schoepf; Jeremy R Burt Journal: Heliyon Date: 2022-02-15