دورية أكاديمية
أعرض في EDS

Adaptive Tensor-Based Feature Extraction for Pupil Segmentation in Cataract Surgery.

التفاصيل البيبلوغرافية
العنوان: Adaptive Tensor-Based Feature Extraction for Pupil Segmentation in Cataract Surgery.
المؤلفون: Giap BD, Srinivasan K, Mahmoud O, Mian SI, Tannen BL, Nallasamy N
المصدر: IEEE journal of biomedical and health informatics [IEEE J Biomed Health Inform] 2024 Mar; Vol. 28 (3), pp. 1599-1610. Date of Electronic Publication: 2024 Mar 07.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Institute of Electrical and Electronics Engineers Country of Publication: United States NLM ID: 101604520 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2168-2208 (Electronic) Linking ISSN: 21682194 NLM ISO Abbreviation: IEEE J Biomed Health Inform Subsets: MEDLINE
أسماء مطبوعة: Original Publication: New York, NY : Institute of Electrical and Electronics Engineers, 2013-
مواضيع طبية MeSH: Cataract Extraction*/methods , Cataract*/diagnostic imaging, Humans ; Pupil ; Image Processing, Computer-Assisted
مستخلص: Cataract surgery remains the only definitive treatment for visually significant cataracts, which are a major cause of preventable blindness worldwide. Successful performance of cataract surgery relies on stable dilation of the pupil. Automated pupil segmentation from surgical videos can assist surgeons in detecting risk factors for pupillary instability prior to the development of surgical complications. However, surgical illumination variations, surgical instrument obstruction, and lens material hydration during cataract surgery can limit pupil segmentation accuracy. To address these problems, we propose a novel method named adaptive wavelet tensor feature extraction (AWTFE). AWTFE is designed to enhance the accuracy of deep learning-powered pupil recognition systems. First, we represent the correlations among spatial information, color channels, and wavelet subbands by constructing a third-order tensor. We then utilize higher-order singular value decomposition to eliminate redundant information adaptively and estimate pupil feature information. We evaluated the proposed method by conducting experiments with state-of-the-art deep learning segmentation models on our BigCat dataset consisting of 5,700 annotated intraoperative images from 190 cataract surgeries and a public CaDIS dataset. The experimental results reveal that the AWTFE method effectively identifies features relevant to the pupil region and improved the overall performance of segmentation models by up to 2.26% (BigCat) and 3.31% (CaDIS). Incorporation of the AWTFE method led to statistically significant improvements in segmentation performance (P < 1.29  ×  10 -10 for each model) and yielded the highest-performing model overall (Dice coefficients of 94.74% and 96.71% for the BigCat and CaDIS datasets, respectively). In performance comparisons, the AWTFE consistently outperformed other feature extraction methods in enhancing model performance. In addition, the proposed AWTFE method significantly improved pupil recognition performance by up to 2.87% in particularly challenging phases of cataract surgery.
References: J Cataract Refract Surg. 2014 Jul;40(7):1163-9. (PMID: 24957436)
IEEE Trans Med Imaging. 1997 Dec;16(6):953-61. (PMID: 9533597)
IEEE Trans Pattern Anal Mach Intell. 2021 Oct;43(10):3349-3364. (PMID: 32248092)
J Neuroophthalmol. 2003 Sep;23(3):213-24. (PMID: 14504595)
Indian J Ophthalmol. 2017 Dec;65(12):1323-1328. (PMID: 29208812)
IEEE Trans Pattern Anal Mach Intell. 2022 Dec;44(12):8704-8716. (PMID: 31135351)
Front Syst Neurosci. 2022 May 26;16:838822. (PMID: 35720439)
IEEE Trans Image Process. 1992;1(2):244-50. (PMID: 18296159)
Psychometrika. 1966 Sep;31(3):279-311. (PMID: 5221127)
IEEE Trans Image Process. 2011 May;20(5):1458-60. (PMID: 20959267)
Med Image Anal. 2021 Jul;71:102053. (PMID: 33864969)
CMAJ. 2011 Oct 4;183(14):1621. (PMID: 21825045)
IEEE Trans Syst Man Cybern B Cybern. 2012 Aug;42(4):1072-82. (PMID: 22389153)
J Cataract Refract Surg. 2000 Aug;26(8):1210-8. (PMID: 11008050)
Ann Transl Med. 2020 Nov;8(22):1540. (PMID: 33313285)
Surv Ophthalmol. 2003 Jul-Aug;48(4):452-8. (PMID: 12850233)
Clin Ophthalmol. 2014 Oct 24;8:2141-50. (PMID: 25368512)
Int J Intell Syst. 2022 Feb;37(2):1572-1598. (PMID: 38607823)
Front Cell Dev Biol. 2022 Jan 03;9:813996. (PMID: 35047515)
IEEE Trans Inf Technol Biomed. 1998 Sep;2(3):197-203. (PMID: 10719530)
IEEE Trans Pattern Anal Mach Intell. 2007 Oct;29(10):1700-15. (PMID: 17699917)
Annu Int Conf IEEE Eng Med Biol Soc. 2023 Jul;2023:1-4. (PMID: 38082579)
Eur J Ophthalmol. 1994 Jul-Sep;4(3):151-8. (PMID: 7819730)
Ophthalmology. 1987 May;94(5):461-6. (PMID: 3601359)
Bull N Y Acad Med. 1992 Jul;68(3):367-89. (PMID: 1498635)
IEEE Trans Image Process. 1996;5(1):4-15. (PMID: 18285085)
معلومات مُعتمدة: D43 TW012027 United States TW FIC NIH HHS; K12 EY022299 United States EY NEI NIH HHS
تواريخ الأحداث: Date Created: 20231221 Date Completed: 20240308 Latest Revision: 20240425
رمز التحديث: 20240425
مُعرف محوري في PubMed: PMC11018356
DOI: 10.1109/JBHI.2023.3345837
PMID: 38127596
قاعدة البيانات: MEDLINE
الوصف
تدمد:2168-2208
DOI:10.1109/JBHI.2023.3345837