Next Article in Journal
Retrospective Cohort Study of Frequency and Patterns of Orbital Injuries on Whole-Body CT with Maxillofacial Multi-Slice CT
Previous Article in Journal
Combination of Radiomics and Machine Learning with Diffusion-Weighted MR Imaging for Clinical Outcome Prognostication in Cervical Cancer
Article

Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning

1
Quantitative Imaging and Analysis Lab, Department of Radiology, Duke University Medical Center, Durham, NC 27710, USA
2
Department of Radiation Oncology, Duke University Medical Center, Durham, NC 27710, USA
3
Department of Head and Neck Surgery & Communication Sciences, Duke University Medical Center, Durham, NC 27710, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Kimberly A. Kelly
Tomography 2021, 7(3), 358-372; https://doi.org/10.3390/tomography7030032
Received: 1 June 2021 / Revised: 23 July 2021 / Accepted: 2 August 2021 / Published: 7 August 2021
We are developing imaging methods for a co-clinical trial investigating synergy between immunotherapy and radiotherapy. We perform longitudinal micro-computed tomography (micro-CT) of mice to detect lung metastasis after treatment. This work explores deep learning (DL) as a fast approach for automated lung nodule detection. We used data from control mice both with and without primary lung tumors. To augment the number of training sets, we have simulated data using real augmented tumors inserted into micro-CT scans. We employed a convolutional neural network (CNN), trained with four competing types of training data: (1) simulated only, (2) real only, (3) simulated and real, and (4) pretraining on simulated followed with real data. We evaluated our model performance using precision and recall curves, as well as receiver operating curves (ROC) and their area under the curve (AUC). The AUC appears to be almost identical (0.76–0.77) for all four cases. However, the combination of real and synthetic data was shown to improve precision by 8%. Smaller tumors have lower rates of detection than larger ones, with networks trained on real data showing better performance. Our work suggests that DL is a promising approach for fast and relatively accurate detection of lung tumors in mice. View Full-Text
Keywords: preclinical imaging; machine learning (ML); X-ray CT (CT) preclinical imaging; machine learning (ML); X-ray CT (CT)
Show Figures

Figure 1

MDPI and ACS Style

Holbrook, M.D.; Clark, D.P.; Patel, R.; Qi, Y.; Bassil, A.M.; Mowery, Y.M.; Badea, C.T. Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning. Tomography 2021, 7, 358-372. https://doi.org/10.3390/tomography7030032

AMA Style

Holbrook MD, Clark DP, Patel R, Qi Y, Bassil AM, Mowery YM, Badea CT. Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning. Tomography. 2021; 7(3):358-372. https://doi.org/10.3390/tomography7030032

Chicago/Turabian Style

Holbrook, Matthew D., Darin P. Clark, Rutulkumar Patel, Yi Qi, Alex M. Bassil, Yvonne M. Mowery, and Cristian T. Badea 2021. "Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning" Tomography 7, no. 3: 358-372. https://doi.org/10.3390/tomography7030032

Find Other Styles

Article Access Map by Country/Region

1
Back to TopTop