دورية أكاديمية
The impact of the combat method on radiomics feature compensation and analysis of scanners from different manufacturers.
| العنوان: | The impact of the combat method on radiomics feature compensation and analysis of scanners from different manufacturers. |
|---|---|
| المؤلفون: | Zhang X; Faculty of Engineering, Universiti Putra Malaysia, Serdang, Malaysia. zhangxiaolei_yx@163.com.; Hebei International Research Center of Medical Engineering, Chengde Medical University, Chengde City, Hebei Province, China. zhangxiaolei_yx@163.com.; Department of Biomedical Engineering, Chengde Medical University, Chengde City, Hebei Province, China. zhangxiaolei_yx@163.com., Iqbal Bin Saripan M; Faculty of Engineering, Universiti Putra Malaysia, Serdang, Malaysia., Wu Y; Hebei International Research Center of Medical Engineering, Chengde Medical University, Chengde City, Hebei Province, China., Wang Z; Hebei International Research Center of Medical Engineering, Chengde Medical University, Chengde City, Hebei Province, China., Wen D; Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China., Cao Z; Department of Radiology, the Affiliated Hospital of Chengde Medical University, Chengde, Hebei, China., Wang B; Faculty of Engineering, Universiti Putra Malaysia, Serdang, Malaysia.; Hebei International Research Center of Medical Engineering, Chengde Medical University, Chengde City, Hebei Province, China., Xu S; Hebei International Research Center of Medical Engineering, Chengde Medical University, Chengde City, Hebei Province, China., Liu Y; Hebei International Research Center of Medical Engineering, Chengde Medical University, Chengde City, Hebei Province, China., Marhaban MH; Faculty of Engineering, Universiti Putra Malaysia, Serdang, Malaysia., Dong X; Hebei International Research Center of Medical Engineering, Chengde Medical University, Chengde City, Hebei Province, China. dongxl@cdmc.edu.cn.; Hebei Provincial Key Laboratory of Nerve Injury and Repair, Chengde Medical University, Chengde City, Hebei Province, China. dongxl@cdmc.edu.cn. |
| المصدر: | BMC medical imaging [BMC Med Imaging] 2024 Jun 06; Vol. 24 (1), pp. 137. Date of Electronic Publication: 2024 Jun 06. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: BioMed Central Country of Publication: England NLM ID: 100968553 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2342 (Electronic) Linking ISSN: 14712342 NLM ISO Abbreviation: BMC Med Imaging Subsets: MEDLINE |
| أسماء مطبوعة: | Original Publication: London : BioMed Central, [2001- |
| مواضيع طبية MeSH: | Machine Learning* , Phantoms, Imaging*, Humans ; Tomography, X-Ray Computed ; Tomography Scanners, X-Ray Computed ; Principal Component Analysis ; Neural Networks, Computer ; Algorithms ; Radiomics |
| مستخلص: | Background: This study investigated whether the Combat compensation method can remove the variability of radiomic features extracted from different scanners, while also examining its impact on the subsequent predictive performance of machine learning models. Materials and Methods: 135 CT images of Credence Cartridge Radiomic phantoms were collected and screened from three scanners manufactured by Siemens, Philips, and GE. 100 radiomic features were extracted and 20 radiomic features were screened according to the Lasso regression method. The radiomic features extracted from the rubber and resin-filled regions in the cartridges were labeled into different categories for evaluating the performance of the machine learning model. Radiomics features were divided into three groups based on the different scanner manufacturers. The radiomic features were randomly divided into training and test sets with a ratio of 8:2. Five machine learning models (lasso, logistic regression, random forest, support vector machine, neural network) were employed to evaluate the impact of Combat on radiomic features. The variability among radiomic features were assessed using analysis of variance (ANOVA) and principal component analysis (PCA). Accuracy, precision, recall, and area under the receiver curve (AUC) were used as evaluation metrics for model classification. Results: The principal component and ANOVA analysis results show that the variability of different scanner manufacturers in radiomic features was removed (P˃0.05). After harmonization with the Combat algorithm, the distributions of radiomic features were aligned in terms of location and scale. The performance of machine learning models for classification improved, with the Random Forest model showing the most significant enhancement. The AUC value increased from 0.88 to 0.92. Conclusions: The Combat algorithm has reduced variability in radiomic features from different scanners. In the phantom CT dataset, it appears that the machine learning model's classification performance may have improved after Combat harmonization. However, further investigation and validation are required to fully comprehend Combat's impact on radiomic features in medical imaging. (© 2024. The Author(s).) |
| References: | MAGMA. 2021 Jun;34(3):355-366. (PMID: 33180226) Biostatistics. 2007 Jan;8(1):118-27. (PMID: 16632515) J Pers Med. 2021 Aug 27;11(9):. (PMID: 34575619) Neuroimage. 2017 Nov 1;161:149-170. (PMID: 28826946) Med Phys. 2017 Mar;44(3):1050-1062. (PMID: 28112418) Med Phys. 2021 Mar;48(3):1239-1249. (PMID: 33370474) Eur Radiol. 2021 Mar;31(3):1460-1470. (PMID: 32909055) Cancer Res. 2017 Nov 1;77(21):e104-e107. (PMID: 29092951) Eur J Cancer. 2012 Mar;48(4):441-6. (PMID: 22257792) Cancer Radiother. 2020 Aug;24(5):403-410. (PMID: 32265157) Eur Radiol. 2017 Nov;27(11):4498-4509. (PMID: 28567548) Sci Rep. 2020 Jun 24;10(1):10248. (PMID: 32581221) Invest Radiol. 2015 Nov;50(11):757-65. (PMID: 26115366) Front Oncol. 2021 Mar 29;11:633176. (PMID: 33854969) Magn Reson Imaging. 2012 Nov;30(9):1323-41. (PMID: 22770690) Neuroimage. 2018 Feb 15;167:104-120. (PMID: 29155184) PLoS One. 2021 May 7;16(5):e0251147. (PMID: 33961646) Radiology. 2019 Apr;291(1):53-59. (PMID: 30694160) Eur Radiol. 2022 Mar;32(3):1959-1970. (PMID: 34542695) PLoS One. 2021 Jul 1;16(7):e0253653. (PMID: 34197503) PLoS One. 2018 Jan 17;13(1):e0191597. (PMID: 29342209) Phys Med Biol. 2016 Jul 7;61(13):R150-66. (PMID: 27269645) Comput Biol Med. 2021 Jun;133:104400. (PMID: 33930766) Eur Radiol. 2022 Mar;32(3):1517-1527. (PMID: 34549324) |
| معلومات مُعتمدة: | 202423 United Kingdom WT_ Wellcome Trust; 202423 United Kingdom WT_ Wellcome Trust; C20220107 Hebei Province Introduced Returned Overseas Chinese Scholars Funding Project; 202205B086 Chengde Biomedicine Industry Research Institute Funding project |
| فهرسة مساهمة: | Keywords: CT images; Combat; Machine learning; Phantom; Radiomics |
| تواريخ الأحداث: | Date Created: 20240606 Date Completed: 20240606 Latest Revision: 20240609 |
| رمز التحديث: | 20240609 |
| مُعرف محوري في PubMed: | PMC11157873 |
| DOI: | 10.1186/s12880-024-01306-4 |
| PMID: | 38844854 |
| قاعدة البيانات: | MEDLINE |
Find this article in full text from Springer Verlag. 
Full Text Finder | تدمد: | 1471-2342 |
|---|---|
| DOI: | 10.1186/s12880-024-01306-4 |