دورية أكاديمية
Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning.
| العنوان: | Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning. |
|---|---|
| المؤلفون: | Holbrook MD; Quantitative Imaging and Analysis Lab, Department of Radiology, Duke University Medical Center, Durham, NC 27710, USA., Clark DP; Quantitative Imaging and Analysis Lab, Department of Radiology, Duke University Medical Center, Durham, NC 27710, USA., Patel R; Department of Radiation Oncology, Duke University Medical Center, Durham, NC 27710, USA., Qi Y; Quantitative Imaging and Analysis Lab, Department of Radiology, Duke University Medical Center, Durham, NC 27710, USA., Bassil AM; Department of Radiation Oncology, Duke University Medical Center, Durham, NC 27710, USA., Mowery YM; Department of Radiation Oncology, Duke University Medical Center, Durham, NC 27710, USA.; Department of Head and Neck Surgery & Communication Sciences, Duke University Medical Center, Durham, NC 27710, USA., Badea CT; Quantitative Imaging and Analysis Lab, Department of Radiology, Duke University Medical Center, Durham, NC 27710, USA. |
| المصدر: | Tomography (Ann Arbor, Mich.) [Tomography] 2021 Aug 07; Vol. 7 (3), pp. 358-372. Date of Electronic Publication: 2021 Aug 07. |
| نوع المنشور: | Journal Article; Research Support, N.I.H., Extramural |
| اللغة: | English |
| بيانات الدورية: | Publisher: MDPI Country of Publication: Switzerland NLM ID: 101671170 Publication Model: Electronic Cited Medium: Internet ISSN: 2379-139X (Electronic) Linking ISSN: 23791381 NLM ISO Abbreviation: Tomography Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: 2021- : Basel, Switzerland : MDPI Original Publication: Ann Arbor, Michigan : Grapho Publications LLC, [2015]- |
| مواضيع طبية MeSH: | Deep Learning* , Lung Neoplasms*/diagnostic imaging, Animals ; Lung ; Mice ; Neural Networks, Computer ; X-Ray Microtomography |
| مستخلص: | 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. |
| References: | Front Oncol. 2013 Apr 02;3:72. (PMID: 23565506) Med Phys. 2010 Sep;37(9):4793-805. (PMID: 20964199) Comput Methods Programs Biomed. 2021 Mar;200:105866. (PMID: 33309304) Eur Radiol. 2016 Jul;26(7):2139-47. (PMID: 26443601) Comput Biol Med. 2018 Dec 1;103:287-300. (PMID: 30415174) PLoS One. 2020 Feb 25;15(2):e0225019. (PMID: 32097413) Sci Rep. 2019 Feb 4;9(1):1325. (PMID: 30718557) Neoplasia. 2004 Jul-Aug;6(4):374-9. (PMID: 15256059) Eur J Radiol. 2017 Mar;88:15-20. (PMID: 28189201) PLoS One. 2019 Apr 8;14(4):e0207555. (PMID: 30958825) Neuroimage. 2006 Jul 1;31(3):1116-28. (PMID: 16545965) Mol Imaging. 2004 Jan;3(1):55-62. (PMID: 15142412) J Am Med Inform Assoc. 2018 Oct 1;25(10):1301-1310. (PMID: 30137371) Phys Med Biol. 2013 Mar 21;58(6):1683-704. (PMID: 23422321) Med Image Anal. 2017 Dec;42:1-13. (PMID: 28732268) Diagnostics (Basel). 2019 Mar 07;9(1):. (PMID: 30866425) Nat Protoc. 2009;4(7):1064-72. (PMID: 19561589) Nature. 2012 Mar 18;483(7391):613-7. (PMID: 22425996) Cancer Prev Res (Phila). 2020 Dec;13(12):989-996. (PMID: 32816806) Med Phys. 2017 Jul;44(7):3615-3629. (PMID: 28409834) Phys Med Biol. 2017 Aug 22;62(18):7280-7299. (PMID: 28786399) Med Phys. 2011 Feb;38(2):915-31. (PMID: 21452728) AJR Am J Roentgenol. 2006 Feb;186(2):300-7. (PMID: 16423931) Biochem Pharmacol. 2014 Jan 1;87(1):150-61. (PMID: 23817077) |
| معلومات مُعتمدة: | R01 CA196667 United States CA NCI NIH HHS; U24 CA220245 United States CA NCI NIH HHS; RF1AG070149 United States CA NCI NIH HHS |
| فهرسة مساهمة: | Keywords: X-ray CT (CT); machine learning (ML); preclinical imaging |
| تواريخ الأحداث: | Date Created: 20210827 Date Completed: 20210924 Latest Revision: 20210924 |
| رمز التحديث: | 20231215 |
| مُعرف محوري في PubMed: | PMC8396172 |
| DOI: | 10.3390/tomography7030032 |
| PMID: | 34449750 |
| قاعدة البيانات: | MEDLINE |
Full Text Finder | تدمد: | 2379-139X |
|---|---|
| DOI: | 10.3390/tomography7030032 |