دورية أكاديمية
Ultrasound Radiomics for the Detection of Early-Stage Liver Fibrosis.
العنوان: | Ultrasound Radiomics for the Detection of Early-Stage Liver Fibrosis. |
---|---|
المؤلفون: | Al-Hasani M; Ultrasound Research Lab, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA., Sultan LR; Ultrasound Research Lab, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA., Sagreiya H; Ultrasound Research Lab, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA., Cary TW; Ultrasound Research Lab, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA., Karmacharya MB; Ultrasound Research Lab, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA., Sehgal CM; Ultrasound Research Lab, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA. |
المصدر: | Diagnostics (Basel, Switzerland) [Diagnostics (Basel)] 2022 Nov 09; Vol. 12 (11). Date of Electronic Publication: 2022 Nov 09. |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: MDPI AG Country of Publication: Switzerland NLM ID: 101658402 Publication Model: Electronic Cited Medium: Print ISSN: 2075-4418 (Print) Linking ISSN: 20754418 NLM ISO Abbreviation: Diagnostics (Basel) Subsets: PubMed not MEDLINE |
أسماء مطبوعة: | Original Publication: Basel, Switzerland : MDPI AG, [2011]- |
مستخلص: | Objective: The study evaluates quantitative ultrasound (QUS) texture features with machine learning (ML) to enhance the sensitivity of B-mode ultrasound (US) for the detection of fibrosis at an early stage and distinguish it from advanced fibrosis. Different ML methods were evaluated to determine the best diagnostic model. Methods: 233 B-mode images of liver lobes with early and advanced-stage fibrosis induced in a rat model were analyzed. Sixteen features describing liver texture were measured from regions of interest (ROIs) drawn on B-mode images. The texture features included a first-order statistics run length (RL) and gray-level co-occurrence matrix (GLCM). The features discriminating between early and advanced fibrosis were used to build diagnostic models with logistic regression (LR), naïve Bayes (nB), and multi-class perceptron (MLP). The diagnostic performances of the models were compared by ROC analysis using different train-test sampling approaches, including leave-one-out, 10-fold cross-validation, and varying percentage splits. METAVIR scoring was used for histological fibrosis staging of the liver. Results: 15 features showed a significant difference between the advanced and early liver fibrosis groups, p < 0.05. Among the individual features, first-order statics features led to the best classification with a sensitivity of 82.1−90.5% and a specificity of 87.1−89.8%. For the features combined, the diagnostic performances of nB and MLP were high, with the area under the ROC curve (AUC) approaching 0.95−0.96. LR also yielded high diagnostic performance (AUC = 0.91−0.92) but was lower than nB and MLP. The diagnostic variability between test-train trials, measured by the coefficient-of-variation (CV), was higher for LR (3−5%) than nB and MLP (1−2%). Conclusion: Quantitative ultrasound with machine learning differentiated early and advanced fibrosis. Ultrasound B-mode images contain a high level of information to enable accurate diagnosis with relatively straightforward machine learning methods like naïve Bayes and logistic regression. Implementing simple ML approaches with QUS features in clinical settings could reduce the user-dependent limitation of ultrasound in detecting early-stage liver fibrosis. |
References: | Scand J Gastroenterol. 2014 May;49(5):611-6. (PMID: 24611771) Hepatology. 1992 Jun;15(6):1054-9. (PMID: 1592343) J Clin Ultrasound. 2016 Nov 12;44(9):580-586. (PMID: 27447717) Lancet. 1997 Mar 22;349(9055):825-32. (PMID: 9121257) Hepatology. 2000 Sep;32(3):477-81. (PMID: 10960438) Am J Gastroenterol. 2002 Oct;97(10):2614-8. (PMID: 12385448) J Nucl Med. 2018 May;59(5):740-746. (PMID: 29496981) Sci Rep. 2021 Jul 14;11(1):14490. (PMID: 34262098) Gastroenterology. 2018 Aug;155(2):443-457.e17. (PMID: 29733831) Insights Imaging. 2014 Aug;5(4):441-55. (PMID: 24859758) Hum Pathol. 2014 Jan;45(1):160-5. (PMID: 24321525) Liver Int. 2006 Sep;26(7):864-71. (PMID: 16911470) J Clin Imaging Sci. 2012;2:58. (PMID: 23230540) Ultrasound Med Biol. 2021 Apr;47(4):880-895. (PMID: 33451817) J Clin Med. 2022 Aug 05;11(15):. (PMID: 35956196) J Hepatol. 2017 Dec;67(6):1265-1273. (PMID: 28803953) Ultrasound. 2017 May;25(2):98-106. (PMID: 28567104) Singapore Med J. 2003 Jun;44(6):293-5. (PMID: 14560860) J Ultrasound Med. 2022 Jan;41(1):175-184. (PMID: 33749862) Int J Comput Assist Radiol Surg. 2018 Dec;13(12):1895-1903. (PMID: 30094778) Hepatology. 2017 May;65(5):1557-1565. (PMID: 28130788) Ultrasound Med Biol. 2012 Dec;38(12):2238-48. (PMID: 23062376) Clin Chim Acta. 2007 Jun;381(2):107-13. (PMID: 17399697) Dis Markers. 2011;31(3):129-38. (PMID: 22045398) Comput Methods Programs Biomed. 2009 Apr;94(1):66-76. (PMID: 18922598) J Hepatol. 1999 Mar;30(3):472-8. (PMID: 10190731) Biology (Basel). 2021 Jan 22;10(2):. (PMID: 33499069) AI (Basel). 2022 Sep;3(3):739-750. (PMID: 36168560) J Med Syst. 2017 Aug 23;41(10):152. (PMID: 28836045) BMJ. 2018 Jul 18;362:k2817. (PMID: 30021785) Radiology. 2020 May;295(2):342-350. (PMID: 32096706) Ann Intern Med. 2013 Sep 3;159(5):372. (PMID: 24026329) Ultrasonography. 2021 Oct;40(4):565-574. (PMID: 33966363) Ultrason Imaging. 2022 Nov;44(5-6):229-241. (PMID: 36017590) Sci Rep. 2019 Jun 18;9(1):8708. (PMID: 31213661) Eur J Radiol Open. 2015 May 26;2:90-100. (PMID: 26937441) Taehan Yongsang Uihakhoe Chi. 2021 Jan;82(1):116-127. (PMID: 36237456) J Am Coll Emerg Physicians Open. 2021 Apr 02;2(2):e12418. (PMID: 33842925) PLoS One. 2022 Jan 27;17(1):e0262291. (PMID: 35085294) J Natl Med Assoc. 1951 Nov;43(6):359-64. (PMID: 14889279) Comput Methods Programs Biomed. 2018 Mar;155:165-177. (PMID: 29512496) BMC Med. 2014 Sep 18;12:145. (PMID: 25242656) J Chin Med Assoc. 2021 Sep 1;84(9):842-850. (PMID: 34282076) J Biomed Phys Eng. 2021 Feb 01;11(1):73-84. (PMID: 33564642) J Clin Gastroenterol. 2015 Sep;49(8):690-6. (PMID: 25291348) Radiology. 1992 Oct;185(1):21-3; discussion 23-4. (PMID: 1523310) Dig Liver Dis. 2002 Jul;34(7):516-22. (PMID: 12236486) |
معلومات مُعتمدة: | R01 CA204446 United States CA NCI NIH HHS; S10 OD016310 United States OD NIH HHS; CA204446-01 United States NH NIH HHS; EB022612-01 United States GF NIH HHS |
فهرسة مساهمة: | Keywords: deep learning; liver fibrosis; machine learning; quantitative ultrasound; radiomics |
تواريخ الأحداث: | Date Created: 20221111 Latest Revision: 20230413 |
رمز التحديث: | 20231215 |
مُعرف محوري في PubMed: | PMC9689042 |
DOI: | 10.3390/diagnostics12112737 |
PMID: | 36359580 |
قاعدة البيانات: | MEDLINE |
تدمد: | 2075-4418 |
---|---|
DOI: | 10.3390/diagnostics12112737 |