Feature-Based vs. Deep-Learning Fusion Methods for the In Vivo Detection of Radiation Dermatitis Using Optical Coherence Tomography, a Feasibility Study.
Acute radiation dermatitis
Classification
Deep learning
Feature extraction
Machine learning
Optical Coherence Tomography
Journal
Journal of imaging informatics in medicine
ISSN: 2948-2933
Titre abrégé: J Imaging Inform Med
Pays: Switzerland
ID NLM: 9918663679206676
Informations de publication
Date de publication:
04 Sep 2024
04 Sep 2024
Historique:
received:
23
05
2024
accepted:
18
08
2024
revised:
07
08
2024
medline:
5
9
2024
pubmed:
5
9
2024
entrez:
4
9
2024
Statut:
aheadofprint
Résumé
Acute radiation dermatitis (ARD) is a common and distressing issue for cancer patients undergoing radiation therapy, leading to significant morbidity. Despite available treatments, ARD remains a distressing issue, necessitating further research to improve prevention and management strategies. Moreover, the lack of biomarkers for early quantitative assessment of ARD impedes progress in this area. This study aims to investigate the detection of ARD using intensity-based and novel features of Optical Coherence Tomography (OCT) images, combined with machine learning. Imaging sessions were conducted twice weekly on twenty-two patients at six neck locations throughout their radiation treatment, with ARD severity graded by an expert oncologist. We compared a traditional feature-based machine learning technique with a deep learning late-fusion approach to classify normal skin vs. ARD using a dataset of 1487 images. The dataset analysis demonstrates that the deep learning approach outperformed traditional machine learning, achieving an accuracy of 88%. These findings offer a promising foundation for future research aimed at developing a quantitative assessment tool to enhance the management of ARD.
Identifiants
pubmed: 39231883
doi: 10.1007/s10278-024-01241-4
pii: 10.1007/s10278-024-01241-4
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : European Commission
ID : 739551
Informations de copyright
© 2024. The Author(s).
Références
Singh M, Afsaneh A., Rebecca W., and Sadanori A (2016) Radiodermatitis: A Review of Our Current Understanding. Am J Clin Dermatol 17, 277–292. https://doi.org/10.1007/s40257-016-0186-4
doi: 10.1007/s40257-016-0186-4
pubmed: 27021652
Oguchi M, Komura J, Ofuji S. (1978) Ultrastructural studies of epidermis in acute radiation dermatitis. Arch Dermatol Res.; 262(1): 73–81. 1. https://doi.org/10.1007/BF00455575
Bontempo, Priscila de Souza Maggi, et al (2021) Acute radiodermatitis in cancer patients: incidence and severity estimates." Revista da Escola de Enfermagem da USP 55 (2021): e03676. https://doi.org/10.1590/S1980-220X2019021703676
doi: 10.1590/S1980-220X2019021703676
Allen C, Her S, Jaffray DA (2017) Radiotherapy for Cancer: Present and Future. Adv Drug Deliv Rev; 109: 1–2. https://doi.org/10.1016/j.addr.2017.01.004
doi: 10.1016/j.addr.2017.01.004
pubmed: 28189183
Lopez E, Isabel N, Rosario G, Rosario M, et al (2002) Breast Cancer Acute Radiotherapy Morbidity Evaluated by Different Scoring Systems. Breast Cancer Res Treat 73, 127–134. https://doi.org/10.1023/A:1015296607061
doi: 10.1023/A:1015296607061
pubmed: 12088115
Dahn, H. M., Boersma, L. J., De Ruysscher, et al (2021) The use of bolus in postmastectomy radiation therapy for breast cancer: A systematic review. Crit Rev Oncol Hematol 163:103391. https://doi.org/10.1016/j.critrevonc.2021.103391
doi: 10.1016/j.critrevonc.2021.103391
pubmed: 34102286
Chan RJ, Webster J, Chung B, et al (2014) Prevention and treatment of acute radiation-induced skin reactions: A systematic review and meta-analysis of randomized controlled trials. BMC Cancer. 14: 53. https://doi.org/10.1186/1471-2407-14-53
doi: 10.1186/1471-2407-14-53
pubmed: 24484999
pmcid: 3909507
Ryan JL (2012) Ionizing Radiation: The Good, the Bad, and the Ugly. J Invest Dermatol.; 132: 985–93. https://doi.org/10.1038/jid.2011.411
doi: 10.1038/jid.2011.411
pubmed: 22217743
pmcid: 3779131
Hymes SR, Strom EA, Fife C. (2006) Radiation dermatitis: Clinical presentation, pathophysiology, and treatment. J Am Acad Dermatol. 54(1): 28–46. https://doi.org/10.1016/j.jaad.2005.08.05
doi: 10.1016/j.jaad.2005.08.05
pubmed: 16384753
Kawamura M, Yoshimura M, Asada H et al (2019) A scoring system predicting acute radiation dermatitis in patients with head and neck cancer treated with intensity-modulated radiotherapy. Radiat Oncol.; 14(1): 14. https://doi.org/10.1186/s13014-019-1215-2
doi: 10.1186/s13014-019-1215-2
pubmed: 30665451
pmcid: 6341605
Brook I. (2021) Early side effects of radiation treatment for head and neck cancer. Cancer Radiotherapy; 25 (5): 507–5130. https://doi.org/10.1016/j.canrad.2021.02.001
doi: 10.1016/j.canrad.2021.02.001
Wong, R.K.S., Bensadoun, RJ., Boers-Doets, C.B. et al (2013) Clinical practice guidelines for the prevention and treatment of acute and late radiation reactions from the MASCC Skin Toxicity Study Group. Support Care Cancer 21, 2933–2948. https://doi.org/10.1007/s00520-013-1896-2
doi: 10.1007/s00520-013-1896-2
pubmed: 23942595
Rosenthal, Amanda, et al (2019) Management of acute radiation dermatitis: a review of the literature and proposal for treatment algorithm. Journal of the American Academy of Dermatology 81.2, 558-567. https://doi.org/10.1016/j.jaad.2019.02.047
doi: 10.1016/j.jaad.2019.02.047
pubmed: 30802561
Trotti, Andy, et al (2003) CTCAE v3. 0: development of a comprehensive grading system for the adverse effects of cancer treatment. Seminars in radiation oncology. Vol. 13. No. 3. WB Saunders. https://doi.org/10.1016/S1053-4296(03)00031-6
Miroshnichenko L., et al (2023) Infared thermal imaging control of radiation dermatitis dynamics. Experimental. Oncology. 45(4) (2023): 493–503. https://doi.org/10.15407/exp-oncology.2023.04.493
Ni, Ruiyan, et al (2022) Deep learning-based automatic assessment of radiation dermatitis in patients with nasopharyngeal carcinoma. International Journal of Radiation Oncology* Biology* Physics 113.3, 685–694. https://doi.org/10.1016/j.ijrobp.2022.03.011
Alexopoulou Eleftheria, et al (2018) An exploratory study of radiation dermatitis in breast cancer patients. Anticancer research 38.3, 1615–1622. https://doi.org/10.21873/anticanres.12392
Ibarra-Castanedo, Clemente, et al (2004) Infrared image processing and data analysis. Infrared physics & technology 46.1-2 75-83. https://doi.org/10.1016/j.infrared.2004.03.011
doi: 10.1016/j.infrared.2004.03.011
Saednia, Khadijeh, et al. (2020) Quantitative thermal imaging biomarkers to detect acute skin toxicity from breast radiation therapy using supervised machine learning. International Journal of Radiation Oncology* Biology* Physics 106.5: 1071–1083. https://doi.org/10.1016/j.ijrobp.2019.12.032
Park, Y. I., et al. (2023) A new approach to quantify and grade radiation dermatitis using deep-learning segmentation in skin photographs. Clinical Oncology 35.1: e10-e19. https://doi.org/10.1016/j.clon.2022.07.001
doi: 10.1016/j.clon.2022.07.001
pubmed: 35918275
Ranjan, Rahul, et al. (2021) The mathematics of erythema: Development of machine learning models for AI assisted measurement and severity scoring of radiation induced dermatitis. Computers in Biology and Medicine 139: 104952. https://doi.org/10.1016/j.compbiomed.2021.104952
doi: 10.1016/j.compbiomed.2021.104952
pubmed: 34739967
Gil-Lianes, J., et al (2024) Computational Model Based on Optical Coherence Tomography (OCT) Skin Scanning to Identify and Quantify Acute Radiation Dermatitis (ARD): A Prospective Diagnostic Study. Actas Dermo-Sifiliográficas. https://doi.org/10.1016/j.ad.2024.03.017
doi: 10.1016/j.ad.2024.03.017
pubmed: 39032772
Hussain, A.A., Themstrup, L. & Jemec, GBE (2015) Optical coherence tomography in the diagnosis of basal cell carcinoma. Arch Dermatol Res 307, 1–10. https://doi.org/10.1007/s00403-014-1498-y
doi: 10.1007/s00403-014-1498-y
pubmed: 25223745
Morsy, H., Kamp, S., Thrane, L., et al (2010) Optical coherence tomography (OCT) imaging of psoriasis vulgaris: correlation with histology and disease severity. Arch Dermatol Res 302, 105–111. https://doi.org/10.1007/s00403-009--4
doi: 10.1007/s00403-009-4
pubmed: 19894055
Boone, M.A.L.M., Jemec, et al (2015) Differentiating allergic and irritant contact dermatitis by high-definition optical coherence tomography: a pilot study. Arch Dermatol Res 307, 11–22. https://doi.org/10.1007/s00403-014-1492-4
doi: 10.1007/s00403-014-1492-4
pubmed: 25186162
Jungbin Lee, et al (2020) Characterization of early-stage cutaneous radiation injury by using OCT angiography, Biomed. Optics Express 11, 2652-2664. https://doi.org/10.1364/BOE.387400
doi: 10.1364/BOE.387400
Holmes JV, von Braunmühl T, Berking C, et al (2018) OCT of BCC: influence of location and subtype on diagnostic performance. Brit J Dermatol, 178:1102-10. https://doi.org/10.1111/bjd.16154
doi: 10.1111/bjd.16154
Gao, W., et.al (2016) Medical images classification for skin cancer using quantitative image features with OCT. Journal of Innovative Optical Health Sciences, 9(02), 1650003, https://doi.org/10.1142/S1793545816500036
doi: 10.1142/S1793545816500036
Falconer, Kenneth (2004) Fractal geometry: mathematical foundations and applications. John Wiley & Sons
Photiou Christos, and Costas Pitris (2019) Comparison of tissue dispersion measurement techniques based on optical coherence tomography. Journal of Biomedical Optics: 046003. https://doi.org/10.1117/1.JBO.24.4.046003
Photiou C., et.al (2017) Using speckle to measure tissue dispersion in optical coherence tomography. Biomedical optics express, 8(5), 2528-2535. https://doi.org/10.1364/BOE.8.002528
doi: 10.1364/BOE.8.002528
pubmed: 28663889
pmcid: 5480496
Kassinopoulos, M., Bousi, E., Zouvani, I., & Pitris, C (2017) Correlation of the derivative as a robust estimator of scatterer size in optical coherence tomography (OCT). Biomedical optics express, 8(3), 1598-1606. https://doi.org/10.1364/BOE.8.001598
doi: 10.1364/BOE.8.001598
pubmed: 28663852
pmcid: 5480567
Photiou Christos, and Costas Pitris (2019) Dual-angle optical coherence tomography for index of refraction estimation using rigid registration and cross-correlation. Journal of biomedical optics 24.10: 106001-106001. https://doi.org/10.1117/1.JBO.24.10.106001
doi: 10.1117/1.JBO.24.10.106001
Photiou C, Kassinopoulos M, Pitris C (2023) Extracting Morphological and Sub-Resolution Features from Optical Coherence Tomography Images, a Review with Applications in Cancer Diagnosis. Photonics.; 10(1):51. https://doi.org/10.3390/photonics10010051
doi: 10.3390/photonics10010051
Demidov V, Demidova N, Pires L et al (2021) Volumetric tumor delineation and assessment of its early response to radiotherapy with optical coherence tomography. Biomed Optics Express.; 12(5): 2952–67. https://doi.org/10.1364/BOE.424045
doi: 10.1364/BOE.424045
Majumdar A, Allam N, Zabel WJ, et al (2022) Binary dose level classification of tumour microvascular response to radiotherapy using artificial intelligence analysis of OCT images. Sci Rep. 12(1): 13995. https://doi.org/10.1038/s41598-022-18393-4
doi: 10.1038/s41598-022-18393-4
pubmed: 35978040
pmcid: 9385745
Allam N, Jeffrey Zabel W, Demidov V, et al (2022) Longitudinal in-vivo quantification of tumour microvascular heterogeneity by optical coherence angiography in pre-clinical radiation therapy. Sci Rep. 12(1): 6140. https://doi.org/10.1038/s41598-022-09625-8
doi: 10.1038/s41598-022-09625-8
pubmed: 35414078
pmcid: 9005734
Sharma P., et al (2017) Noninvasive assessment of cutaneous alterations in mice exposed to whole body gamma irradiation using optical imaging techniques. Lasers Med Sci. 32(7): 1535–1544. https://doi.org/10.1007/s10103-017-2276-9
doi: 10.1007/s10103-017-2276-9
pubmed: 28699043
Hawass, NE (1997) Comparing the sensitivities and specificities of two diagnostic procedures performed on the same group of patients. The British journal of radiology 70.832, 360-366. https://doi.org/10.1259/bjr.70.832.9166071
doi: 10.1259/bjr.70.832.9166071
pubmed: 9166071
Ferreira, Elaine Barros, et al (2017) Topical interventions to prevent acute radiation dermatitis in head and neck cancer patients: a systematic review. Supportive Care in Cancer 25, 1001-1011. https://doi.org/10.1007/s00520-016-3521-7
doi: 10.1007/s00520-016-3521-7
pubmed: 27957620