Intraoperative thermal infrared imaging in neurosurgery: machine learning approaches for advanced segmentation of tumors.
Brain tumor segmentation
Classification
Machine learning
Neurosurgery
Thermal infrared imaging
Journal
Physical and engineering sciences in medicine
ISSN: 2662-4737
Titre abrégé: Phys Eng Sci Med
Pays: Switzerland
ID NLM: 101760671
Informations de publication
Date de publication:
Mar 2023
Mar 2023
Historique:
received:
20
09
2022
accepted:
17
01
2023
pubmed:
31
1
2023
medline:
24
3
2023
entrez:
30
1
2023
Statut:
ppublish
Résumé
Surgical resection is one of the most relevant practices in neurosurgery. Finding the correct surgical extent of the tumor is a key question and so far several techniques have been employed to assist the neurosurgeon in preserving the maximum amount of healthy tissue. Some of these methods are invasive for patients, not always allowing high precision in the detection of the tumor area. The aim of this study is to overcome these limitations, developing machine learning based models, relying on features obtained from a contactless and non-invasive technique, the thermal infrared (IR) imaging. The thermal IR videos of thirteen patients with heterogeneous tumors were recorded in the intraoperative context. Time (TD)- and frequency (FD)-domain features were extracted and fed different machine learning models. Models relying on FD features have proven to be the best solutions for the optimal detection of the tumor area (Average Accuracy = 90.45%; Average Sensitivity = 84.64%; Average Specificity = 93,74%). The obtained results highlight the possibility to accurately detect the tumor lesion boundary with a completely non-invasive, contactless, and portable technology, revealing thermal IR imaging as a very promising tool for the neurosurgeon.
Identifiants
pubmed: 36715852
doi: 10.1007/s13246-023-01222-x
pii: 10.1007/s13246-023-01222-x
pmc: PMC10030394
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
325-337Informations de copyright
© 2023. The Author(s).
Références
Hervey-Jumper SL, Berger MS (2016) Maximizing safe resection of low- and high-grade glioma. J Neurooncol 130:269–282. https://doi.org/10.1007/s11060-016-2110-4
doi: 10.1007/s11060-016-2110-4
pubmed: 27174197
Willems PW, Taphoorn MJ, Burger H, van Berkelbach der Sprenkel JW, Tulleken CAF (2006) Effectiveness of neuronavigation in resecting solitary intracerebral contrast-enhancing tumors: a randomized controlled trial. J Neurosurg 104:360–368. https://doi.org/10.3171/jns.2006.104.3.360
doi: 10.3171/jns.2006.104.3.360
pubmed: 16572647
Trevisi G, Barbone P, Treglia G, Mattoli MV, Mangiola A (2020) Reliability of intraoperative ultrasound in detecting tumor residual after brain diffuse glioma surgery: a systematic review and meta-analysis. Neurosurg Rev 43:1221–1233. https://doi.org/10.1007/s10143-019-01160-x
doi: 10.1007/s10143-019-01160-x
pubmed: 31410683
Eatz TA, Eichberg DG, Lu VM, Di L, Komotar RJ, Ivan ME (2022) Intraoperative 5-ALA fluorescence-guided resection of high-grade glioma leads to greater extent of resection with better outcomes: a systematic review. J Neurooncol 156:233–256. https://doi.org/10.1007/s11060-021-03901-9
doi: 10.1007/s11060-021-03901-9
pubmed: 34989964
Boschi A, Della Puppa A (2019) 5-ALA fluorescence on tumors different from malignant gliomas. review of the literature and our experience. J Neurosurg Sci 63:661–669. https://doi.org/10.23736/s0390-5616.19.04766-0
doi: 10.23736/s0390-5616.19.04766-0
pubmed: 31355622
Ricciardi L, Sturiale CL, Scerrati A, Stifano V, Somma T, Ius T, Trungu S, Acqui M, Raco A, Miscusi M et al (2022) 5-Aminolevulinic acid false-positive rates in newly diagnosed and recurrent glioblastoma: do pseudoprogression and radionecrosis play a role? A Meta-Analysis. Front Oncol 12:848036. https://doi.org/10.3389/fonc.2022.848036
doi: 10.3389/fonc.2022.848036
pubmed: 35252015
Rogers CM, Jones PS, Weinberg JS (2021) Intraoperative MRI for brain tumors. J Neurooncol 151:479–490. https://doi.org/10.1007/s11060-020-03667-6
doi: 10.1007/s11060-020-03667-6
pubmed: 33611714
Ahmad M, Ai D, Xie G, Qadri SF, Song H, Huang Y, Wang Y, Yang J (2019) Deep belief network modeling for automatic liver segmentation. IEEE Access 7:20585–20595. https://doi.org/10.1109/ACCESS.2019.2896961
doi: 10.1109/ACCESS.2019.2896961
Ahmad M, Qadri SF, Qadri S, Saeed IA, Zareen SS, Iqbal Z, Alabrah A, Alaghbari HM, Mizanur Rahman SM (2022) A lightweight convolutional neural network model for liver segmentation in medical diagnosis. Comput Intell Neurosci. https://doi.org/10.1155/2022/7954333
doi: 10.1155/2022/7954333
pubmed: 36268150
pmcid: 9578842
Hirra I, Ahmad M, Hussain A, Ashraf MU, Saeed IA, Qadri SF, Alghamdi AM, Alfakeeh AS (2021) Breast cancer classification from histopathological images using patch-based deep learning modeling. IEEE Access 9:24273–24287. https://doi.org/10.1109/ACCESS.2021.3056516
doi: 10.1109/ACCESS.2021.3056516
Furqan Qadri S, Ai D, Hu G, Ahmad M, Huang Y, Wang Y, Yang J (2019) Automatic deep feature learning via patch-based deep belief network for vertebrae segmentation in CT images. Appl Sci 9:69. https://doi.org/10.3390/app9010069
doi: 10.3390/app9010069
Hakim A, Awale RN (2020) Thermal imaging—an emerging modality for breast cancer detection: a comprehensive review. J Med Syst 44:136. https://doi.org/10.1007/s10916-020-01581-y
doi: 10.1007/s10916-020-01581-y
pubmed: 32613403
Mambou SJ, Maresova P, Krejcar O, Selamat A, Kuca K (2018) Breast cancer detection using infrared thermal imaging and a deep learning model. Sensors 18:2799. https://doi.org/10.3390/s18092799
doi: 10.3390/s18092799
pubmed: 30149621
pmcid: 6164870
Schaefer G, Závišek M, Nakashima T (2009) Thermography based breast cancer analysis using statistical features and fuzzy classification. Pattern Recogn 42:1133–1137. https://doi.org/10.1016/j.patcog.2008.08.007
doi: 10.1016/j.patcog.2008.08.007
Wishart GC, Campisi M, Boswell M, Chapman D, Shackleton V, Iddles S, Hallett A, Britton PD (2010) The accuracy of digital infrared imaging for breast cancer detection in women undergoing breast biopsy. Eur J Surg Oncol (EJSO) 36:535–540. https://doi.org/10.1016/j.ejso.2010.04.003
doi: 10.1016/j.ejso.2010.04.003
pubmed: 20452740
Magalhaes C, Vardasca R, Rebelo M, Valenca-Filipe R, Ribeiro M, Mendes J (2019) Distinguishing melanocytic nevi from melanomas using static and dynamic infrared thermal imaging. J Eur Acad Dermatol Venereol 33:1700–1705. https://doi.org/10.1111/jdv.15611
doi: 10.1111/jdv.15611
pubmed: 30974494
Herman C (2013) The role of dynamic infrared imaging in melanoma diagnosis. Expert Rev Dermatol 8:177–184. https://doi.org/10.1586/edm.13.15
doi: 10.1586/edm.13.15
pubmed: 23745131
pmcid: 3670775
Buzug, T.M.; Schumann, S.; Pfaffmann, L.; Reinhold, U.; Ruhlmann, J. Functional Infrared Imaging for Skin-Cancer Screening. In Proceedings of the 2006 International Conference of the IEEE Engineering in Medicine and Biology Society; August 2006; pp. 2766–2769.
Namdari F, Dadpay M, Hamidi M, Ghayoumi zadeh H (2017) Evaluation of thermal imaging in the diagnosis and classification of varicocele. Iran J Med Phys 14:114–121
Ismail E, Orlando G, Pompa P, Gabrielli D, Di Donato L, Cardone D, Merla A (2014) Time-domain analysis of scrotal thermoregulatory impairment in varicocele. Front Physiol. https://doi.org/10.3389/fphys.2014.00342
doi: 10.3389/fphys.2014.00342
pubmed: 25278903
pmcid: 4165266
Filippini C, Cardone D, Perpetuini D, Chiarelli AM, Gualdi G, Amerio P, Merla A (2021) Convolutional neural networks for differential diagnosis of Raynaud’s phenomenon based on hands thermal patterns. Appl Sci 11:3614. https://doi.org/10.3390/app11083614
doi: 10.3390/app11083614
Horikoshi M, Inokuma S, Kijima Y, Kobuna M, Miura Y, Okada R, Kobayashi S (2016) Thermal disparity between fingers after cold-water immersion of hands: a useful indicator of disturbed peripheral circulation in Raynaud phenomenon patients. Intern Med 55:461–466. https://doi.org/10.2169/internalmedicine.55.5218
doi: 10.2169/internalmedicine.55.5218
pubmed: 26935364
Vasefi F, MacKinnon N, Farkas DL, Kateb B (2016) Review of the potential of optical technologies for cancer diagnosis in neurosurgery: a step toward intraoperative neurophotonics. Neurophotonics 4:011010
doi: 10.1117/1.NPh.4.1.011010
pubmed: 28042588
pmcid: 5184765
Gorbach AM, Heiss JD, Kopylev L, Oldfield EH (2004) Intraoperative infrared imaging of brain tumors. J Neurosurg 101:960–969. https://doi.org/10.3171/jns.2004.101.6.0960
doi: 10.3171/jns.2004.101.6.0960
pubmed: 15599965
pmcid: 4294194
Papaioannou, T.; Thompson, R.C.; Kateb, B.; M.d, O.S.; M.d, W.S.G.; Black, K.L. Thermal Imaging of Brain Tumors in a Rat Glioma Model. In Proceedings of the Biomedical Diagnostic, Guidance, and Surgical-Assist Systems IV; SPIE, May 13 2002; Vol. 4615, pp. 32–35.
Ecker RD, Goerss SJ, Meyer FB, Cohen-Gadol AA, Britton JW, Levine JA (2002) Vision of the future: initial experience with intraoperative real-time high-resolution dynamic infrared imaging: technical note. J Neurosurg 97:1460–1471. https://doi.org/10.3171/jns.2002.97.6.1460
doi: 10.3171/jns.2002.97.6.1460
pubmed: 12507150
Kateb B, Yamamoto V, Yu C, Grundfest W, Gruen JP (2009) Infrared thermal imaging: a review of the literature and case report. Neuroimage 47:T154–T162. https://doi.org/10.1016/j.neuroimage.2009.03.043
doi: 10.1016/j.neuroimage.2009.03.043
pubmed: 19332140
Kastek, M.; Piatkowski, T.; Polakowski, H.; Kaczmarska, K.; Czernicki, Z.; Bogucki, J.; Zębala, M. Intraoperative Application of Thermal Camera for the Assessment of during Surgical Resection or Biopsy of Human’s Brain Tumors. In Proceedings of the Thermosense: Thermal Infrared Applications XXXVI; SPIE, 2014; Vol. 9105, pp. 35–43.
Sadeghi-Goughari M, Mojra A, Sadeghi S (2016) Parameter estimation of brain tumors using intraoperative thermal imaging based on artificial tactile sensing in conjunction with artificial neural network. J Phys D Appl Phys. https://doi.org/10.1088/0022-3727/49/7/075404
doi: 10.1088/0022-3727/49/7/075404
Perpetuini D, Chiarelli AM, Filippini C, Cardone D, Croce P, Rotunno L, Anzoletti N, Zito M, Zappasodi F, Merla A (2020) Working memory decline in alzheimer’s disease is detected by complexity analysis of multimodal EEG-FNIRS. Entropy 22:1380. https://doi.org/10.3390/e22121380
doi: 10.3390/e22121380
pubmed: 33279924
pmcid: 7762102
Richman JS, Moorman JR (2000) Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol Heart Circ Physiol 278:H2039–H2049. https://doi.org/10.1152/ajpheart.2000.278.6.H2039
doi: 10.1152/ajpheart.2000.278.6.H2039
pubmed: 10843903
Chang, Y.-W.; Hsieh, C.-J.; Chang, K.-W.; Ringgaard, M.; Lin, C.-J. Training and Testing Low-Degree Polynomial Data Mappings via Linear SVM. Journal of Machine Learning Research 2010, 11.
Anguita, D.; Ghelardoni, L.; Ghio, A.; Oneto, L.; Ridella, S. The ‘K’in K-Fold Cross Validation. In Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN); i6doc. com publ, 2012; pp. 441–446.
Cardone D, Merla A (2017) New Frontiers for applications of thermal infrared imaging devices: computational psychopshysiology in the neurosciences. Sensors 17:1042. https://doi.org/10.3390/s17051042
doi: 10.3390/s17051042
pubmed: 28475155
pmcid: 5469647
Liu W-M, Meyer J, Scully CG, Elster E, Gorbach AM (2011) Observing temperature fluctuations in humans using infrared imaging. Quant Infrared Thermogr J 8:21–36. https://doi.org/10.3166/qirt.8.21-36
doi: 10.3166/qirt.8.21-36
pubmed: 23538682
Okur Güney ZE, Cardone D, Sattel H, Ariens S, Witthöft M, Merla A, Kuppens P, Henningsen P (2022) Interpersonal emotion dynamics in couples with somatic symptom disorder: dyadic coherence in facial temperature during emotional interactions. Psychosom Med 84:188–198. https://doi.org/10.1097/PSY.0000000000001032
doi: 10.1097/PSY.0000000000001032
pubmed: 34654022
Zhan, B.; Wu, Y. Infrared Image Enhancement Based on Wavelet Transformation and Retinex. In Proceedings of the 2010 Second International Conference on Intelligent Human-Machine Systems and Cybernetics; August 2010; Vol. 1, pp. 313–316.
Cho, J.; Lee, K.; Shin, E.; Choy, G.; Do, S. How Much Data Is Needed to Train a Medical Image Deep Learning System to Achieve Necessary High Accuracy? 2016.
Beleites C, Neugebauer U, Bocklitz T, Krafft C, Popp J (2013) Sample size planning for classification models. Anal Chim Acta 760:25–33. https://doi.org/10.1016/j.aca.2012.11.007
doi: 10.1016/j.aca.2012.11.007
pubmed: 23265730