Academic Journal
Machine-learning-enhanced image reconstruction in optical tomography using the Monte Carlo method for light transport.
| Τίτλος: | Machine-learning-enhanced image reconstruction in optical tomography using the Monte Carlo method for light transport. |
|---|---|
| Συγγραφείς: | Kangasniemi J; University of Eastern Finland, Department of Technical Physics, Kuopio, Finland., Mozumder M; University of Eastern Finland, Department of Technical Physics, Kuopio, Finland., Hauptmann A; University of Oulu, Research Unit of Mathematical Sciences, Oulu, Finland.; University College London, Department of Computer Science, London, United Kingdom., Tarvainen T; University of Eastern Finland, Department of Technical Physics, Kuopio, Finland. |
| Πηγή: | Journal of biomedical optics [J Biomed Opt] 2026 Sep; Vol. 31 (9), pp. 096001. Date of Electronic Publication: 2026 Sep 01. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Published by SPIE--the International Society for Optical Engineering in cooperation with International Biomedical Optics Society Country of Publication: United States NLM ID: 9605853 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1560-2281 (Electronic) Linking ISSN: 10833668 NLM ISO Abbreviation: J Biomed Opt Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Bellingham, WA : Published by SPIE--the International Society for Optical Engineering in cooperation with International Biomedical Optics Society, c1996- |
| Ιατρικοί όροι (MeSH): | Tomography, Optical*/methods , Image Processing, Computer-Assisted*/methods , Machine Learning*, Monte Carlo Method ; Algorithms ; Scattering, Radiation ; Phantoms, Imaging ; Stochastic Processes ; Computer Simulation ; Light ; Convolutional Neural Networks ; Soft Computing |
| Περίληψη: | Significance: The Monte Carlo method for light transport is widely accepted as an accurate method for simulating light propagation in a scattering medium. Its use in optical tomography, however, suffers from inherent stochastic noise. This noise is present in both evaluations of the forward model, as well as in the search direction of the minimization algorithm used for image reconstruction. Aim: We aim to utilize machine learning to compensate for the stochastic Monte Carlo noise in the reconstruction of absorption and scattering in optical tomography. Approach: An iterative image reconstruction algorithm is proposed. The algorithm uses convolutional neural networks in a stochastic Gauss-Newton update when estimating absorption and scattering coefficients. Results: The methodology is evaluated using numerical simulations and compared against the conventional stochastic Gauss-Newton algorithm in optical tomography. It is demonstrated that the methodology can be used to compensate for image reconstruction artifacts caused by the stochastic noise. Conclusions: The proposed machine learning approach can be used to compensate for stochastic noise in Gauss-Newton iterations, and it enables reconstruction of absorption and scattering with a significantly lower number of photons than a conventional stochastic Gauss-Newton algorithm. (© 2026 The Authors.) |
| Competing Interests: | The authors declare that there are no financial interests, commercial affiliations, or other potential conflicts of interest that could have influenced the objectivity of this research or the writing of this paper. |
| References: | Phys Med Biol. 2005 Feb 21;50(4):R1-43. (PMID: 15773619) Biomed Opt Express. 2018 Sep 04;9(10):4588-4603. (PMID: 30319888) IEEE Trans Med Imaging. 2011 Oct;30(10):1725-36. (PMID: 21964730) J Biomed Opt. 2013 Jul;18(7):076002. (PMID: 23856916) J Biomed Opt. 2022 May;27(8):. (PMID: 35614533) Phys Med Biol. 2023 Jul 03;68(13):. (PMID: 37167982) Appl Opt. 2020 Feb 10;59(5):1461-1470. (PMID: 32225405) J Biomed Opt. 2020 Aug;25(8):. (PMID: 32798354) IEEE Trans Med Imaging. 2022 Mar;41(3):515-530. (PMID: 34606449) Biomed Opt Express. 2024 Jul 30;15(8):4925-4942. (PMID: 39347007) Opt Express. 2024 Jan 1;32(1):125-150. (PMID: 38175044) J Biomed Opt. 2016 Sep;21(9):091311. (PMID: 27403837) Appl Opt. 1998 Nov 1;37(31):7392-400. (PMID: 18301573) J Biomed Opt. 2023 Jun;28(6):066002. (PMID: 37347003) Phys Med Biol. 1996 Oct;41(10):2221-7. (PMID: 8912392) Opt Lett. 2025 May 1;50(9):3122-3125. (PMID: 40310851) J Biomed Opt. 2023 Mar;28(3):036002. (PMID: 36908760) IEEE Trans Med Imaging. 2020 Apr;39(4):877-887. (PMID: 31442973) Phys Med Biol. 2013 Jun 7;58(11):R37-61. (PMID: 23666068) J Opt Soc Am A Opt Image Sci Vis. 2012 Oct 1;29(10):2110-7. (PMID: 23201658) IEEE Trans Comput Imaging. 2023;9:459-474. (PMID: 37456517) J Biomed Opt. 2018 Dec;24(5):1-12. (PMID: 30569669) Neuroimage. 2021 Jan 15;225:117490. (PMID: 33157266) IEEE Trans Med Imaging. 2020 Oct;39(10):2985-2995. (PMID: 32217473) Rep Prog Phys. 2010 Jul;73(7):. (PMID: 26120204) IEEE Trans Med Imaging. 2018 Jun;37(6):1382-1393. (PMID: 29870367) IEEE Trans Med Imaging. 2022 May;41(5):1289-1299. (PMID: 34914584) Biomed Opt Express. 2024 Feb 27;15(3):1910-1925. (PMID: 38495688) J Biomed Opt. 2016 Sep;21(9):091312. (PMID: 27420810) Neuroimage. 2014 Jan 15;85 Pt 1:117-26. (PMID: 23578579) Phys Med Biol. 2005 May 21;50(10):2365-86. (PMID: 15876673) Opt Express. 2009 Oct 26;17(22):20178-90. (PMID: 19997242) J Biomed Opt. 2024 Aug;29(8):086001. (PMID: 39070721) Comput Methods Programs Biomed. 1995 Jul;47(2):131-46. (PMID: 7587160) J Biomed Opt. 2013 Jul;18(7):076001. (PMID: 23856915) Biomed Opt Express. 2024 Jul 05;15(8):4470-4485. (PMID: 39347006) J Biomed Opt. 2004 Sep-Oct;9(5):1002-12. (PMID: 15447022) J Biomed Opt. 2013 May;18(5):50902. (PMID: 23698318) IEEE Trans Comput Imaging. 2021;7:1341-1353. (PMID: 35873096) SIAM J Imaging Sci. 2021 Jan;14(1):92-127. (PMID: 39741577) J Biomed Opt. 2022 Apr;27(8):. (PMID: 35396833) Phys Med Biol. 2014 Jan 6;59(1):R1-64. (PMID: 24334634) J Biomed Opt. 2024 Jul;29(7):076004. (PMID: 39035576) Opt Express. 2009 Oct 26;17(22):19566-79. (PMID: 19997176) Phys Med Biol. 2005 Oct 21;50(20):4913-30. (PMID: 16204880) |
| Contributed Indexing: | Keywords: Monte Carlo method for light transport; machine learning; optical tomography; radiative transfer equation; stochastic optimization |
| Entry Date(s): | Date Created: 20260902 Date Completed: 20260902 Latest Revision: 20260903 |
| Update Code: | 20260903 |
| PubMed Central ID: | PMC13533593 |
| DOI: | 10.1117/1.JBO.31.9.096001 |
| PMID: | 42683500 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!