Abstract
At present, the judgment of the burn depth is mainly based on the experience of doctors, so the accuracy of judgment is low, which will affect the follow-up treatment and nursing. In order to improve the diagnostic effect of clinical burns, based on incremental reinforcement learning algorithms, this paper constructs a classification model of clinical burn thermal images based on machine learning algorithms. Moreover, this paper proposes an adaptive network algorithm and uses the structure of the network to implement a reinforcement learning algorithm. In this algorithm, in order to reduce the computational complexity under the premise of ensuring sample utilization, the parameters are updated in the form of increments. In addition, this paper uses the value function approximator to linearly approximate the value function and TD error. Finally, this paper constructs the basic structure of the model based on the functional requirements and constructs experiments to verify the performance of the model. The research results show that the algorithm has good convergence and the image classification effect is very obvious, so it has certain practical significance.
Similar content being viewed by others
Change history
16 May 2021
A Correction to this paper has been published: https://doi.org/10.1007/s00521-021-06052-0
References
Baco E, Ukimura O, Rud E et al (2015) Magnetic resonance imaging–transectal ultrasound image-fusion biopsies accurately characterize the index tumor: correlation with step-sectioned radical prostatectomy specimens in 135 patients[J]. Eur Urol 67(4):787–794
Banerjee A, Maji P (2015) Rough sets and stomped normal distribution for simultaneous segmentation and bias field correction in brain MR images[J]. IEEE Trans Image Process 24(12):5764–5776
Bao S, Chung ACS (2018) Multi-scale structured CNN with label consistency for brain MR image segmentation[J]. Comput Methods Biomech Biomed Eng Imaging Vis 6(1):113–117
Chuang YH, Ou HY, Lazo MZ et al (2018) Predicting post-hepatectomy liver failure by combined volumetric, functional MR image and laboratory analysis[J]. Liver Int 38(5):868–874
Gao Z, Li Y, Sun Y et al (2017) Motion tracking of the carotid artery wall from ultrasound image sequences: a nonlinear state-space approach[J]. IEEE Trans Med Imaging 37(1):273–283
Gatter M, Kimport K, Foster DG et al (2014) Relationship between ultrasound viewing and proceeding to abortion[J]. Obstet Gynecol 123(1):81–87
Hansen N, Patruno G, Wadhwa K et al (2016) Magnetic resonance and ultrasound image fusion supported transperineal prostate biopsy using the Ginsburg protocol: technique, learning points, and biopsy results[J]. Eur Urol 70(2):332–340
Harward S, Farber SH, Malinzak M et al (2018) T2-weighted images are superior to other MR image types for the determination of diffuse intrinsic pontine glioma intratumoral heterogeneity[J]. Child’s Nervous Syst 34(3):449–455
Hu Y, Gibson E, Ahmed HU et al (2015) Population-based prediction of subject-specific prostate deformation for MR-to-ultrasound image registration[J]. Med Image Anal 26(1):332–344
Janaki SD, Geetha K (2017) Automatic segmentation of lesion from breast DCE-MR image using artificial fish swarm optimization algorithm[J]. Pol J Med Phys Eng 23(2):29–36
Ji Z, Liu J, Cao G et al (2014) Robust spatially constrained fuzzy c-means algorithm for brain MR image segmentation[J]. Pattern Recogn 47(7):2454–2466
Kim Y (2015) Advances in MR image-guided high-intensity focused ultrasound therapy[J]. Int J Hyperth 31(3):225–232
Knoll F, Holler M, Koesters T et al (2016) Joint MR-PET reconstruction using a multi-channel image regularizer[J]. IEEE Trans Med Imaging 36(1):1–16
Kuo CC, Chuang HC, Teng KT et al (2016) An autotuning respiration compensation system based on ultrasound image tracking[J]. J X-ray Sci Technol 24(6):875–892
Madhukumar S, Santhiyakumari N (2015) Evaluation of k-Means and fuzzy C-means segmentation on MR images of brain[J]. Egypt J Radiol Nuclear Med 46(2):475–479
Mitsouras D, Lee TC, Liacouras P et al (2017) Three-dimensional printing of MRI-visible phantoms and MR image-guided therapy simulation[J]. Magn Reson Med 77(2):613–622
Moeskops P, Viergever MA, Mendrik AM et al (2016) Automatic segmentation of MR brain images with a convolutional neural network[J]. IEEE Trans Med Imaging 35(5):1252–1261
Portela NM, Cavalcanti GDC, Ren TI (2014) Semi-supervised clustering for MR brain image segmentation[J]. Expert Syst Appl 41(4):1492–1497
Qin C, Schlemper J, Caballero J et al (2018) Convolutional recurrent neural networks for dynamic MR image reconstruction[J]. IEEE Trans Med Imaging 38(1):280–290
Qiu W, Yuan J, Ukwatta E et al (2014) Dual optimization based prostate zonal segmentation in 3D MR images[J]. Med Image Anal 18(4):660–673
Rivaz H, Chen SJS, Collins DL (2014) Automatic deformable MR-ultrasound registration for image-guided neurosurgery[J]. IEEE Trans Med Imaging 34(2):366–380
Schlemper J, Caballero J, Hajnal JV et al (2017) A deep cascade of convolutional neural networks for dynamic MR image reconstruction[J]. IEEE Trans Med Imaging 37(2):491–503
Siddiqui MM, Rais-Bahrami S, Turkbey B et al (2015) Comparison of MR/ultrasound fusion–guided biopsy with ultrasound-guided biopsy for the diagnosis of prostate cancer[J]. JAMA 313(4):390–397
Song YT, Ji ZX, Sun QS (2014) Brain MR image segmentation algorithm based on Markov random field with image patch[J]. Acta Autom Sin 40(8):1754–1763
Tian Z, Liu L, Zhang Z et al (2015) Superpixel-based segmentation for 3D prostate MR images[J]. IEEE Trans Med Imaging 35(3):791–801
Acknowledgements
This work is supported by High-level Hospital Construction Research Project of Maoming People’s Hospital.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interests, and Xianjun Wu and Wendong Huang are co-first authors of the article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wu, X., Huang, W., Wu, X. et al. Classification of thermal image of clinical burn based on incremental reinforcement learning. Neural Comput & Applic 34, 3457–3470 (2022). https://doi.org/10.1007/s00521-021-05772-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-05772-7