Anomaly Detection in Skull scanning Images based on Multi-sensor Fusion
DOI:
https://doi.org/10.4108/eetpht.11.5828Keywords:
Skull scanning images, Bilateral filter, Double domain decomposition, High and low frequency fusion, Deep neural networksAbstract
INTRODUCTION: Skull bones typically possess complex structures and features. When scanned with ordinary sensors, they are easily affected by noise due to the small difference between abnormal areas and normal tissue.
OBJECTIVES: In order to solve the problem of small differences between abnormal areas and normal tissues, which make them susceptible to noise interference, this paper proposes a multi-sensor fusion based skull scan image anomaly detection method.
METHODS: Firstly, the frequency correction factor is utilized to modify the frequency domain characteristics of the sensor signal during the skull scanning image acquisition process, aiming to enhance signal quality and reduce noise impact during acquisition. Secondly, bilateral filters and discrete wavelet transform are employed to subject the skull scanning image to dual domain decomposition in spatial and transformation domains, aiding in distinguishing between normal and abnormal regions. Subsequently, the low-frequency fusion algorithm guided by filtering and the high-frequency fusion algorithm based on multi-scale morphological gradients are fused, and the fused dual frequency components are merged back into the original spatial domain to retain important details. The fused reconstructed image aids in improving the accuracy of anomaly detection. Finally, a backbone network with an auto encoder structure is established to learn the feature representation of fused images, and an unsupervised deep neural network is employed to establish a detection model for anomaly detection in skull scanning images.
RESULTS: Through experiments, it has been demonstrated that the F1 score approaches 1, the ROC curve closely approaches the upper left corner, and the AUC value approaches 1 after applying the proposed method for anomaly detection in skull scanning images.
CONCLUSION: This algorithm has high sensitivity and low specificity, achieving high detection accuracy and demonstrating good performance.
Downloads
References
[1] Wen C, Liu S, Liu S, et al. ACSN: Attention capsule sampling network for diagnosing COVID-19 based on chest CT scans[J]. Computers in Biology and Medicine, 2023, 153: 106338 DOI: https://doi.org/10.1016/j.compbiomed.2022.106338
[2] Sun L, Peng R. The value of integration of bone scan and targeted SPECT/CT in diagnosis of primary hyperparathyroidism with multiple bone brown tumor[J]. Skeletal radiology, 2023,52(12):2505-2511. DOI: https://doi.org/10.1007/s00256-023-04361-0
[3] Saidi B, Fallahi B, Haghighi F, et al. Three-phase 99mTc-MDP bone scan in a case of pigment villonodular synovitis[J]. Iranian Journal of Nuclear Medicine, 2021(156). https://readpaper.com/paper/3130285393.
[4] Zhang Y, Satapathy S C, Guttery D S, et al. Improved breast cancer classification through combining graph convolutional network and convolutional neural network[J], Information Processing and Management, 2021, 58(2), 102439 DOI: https://doi.org/10.1016/j.ipm.2020.102439
[5] Xiao Y, Xia K, Yin H, et al. AFSTGCN: prediction for multivariate time series using an adaptive fused spatial-temporal graph convolutional network[J]. Digital Communications and Networks, 2024, 10(2): 292-303, DOI: https://doi.org/10.1016/j.dcan.2022.06.019
[6] Feo M D, Frantellizzi V, Rocco A D, et al. Evaluation of Bone Scan Index as a Prognostic Tool in Breast Cancer Patients with Bone Metastasis[J]. Current radiopharmaceuticals, 2023,16(4):284-291. DOI: https://doi.org/10.2174/1874471016666230509113108
[7] Hiddema L, Muthusami A, Brookes P, et al. 41Diagnosing Bone Metastases in Breast Cancer – CT Vs Nuclear Medicine Bone Scan[J]. British Journal of Surgery, 2021, 108(Supplement_2), znab135.024. DOI: https://doi.org/10.1093/bjs/znab135.024
[8] Song L, Liu X, Chen S, et al. A deep fuzzy model for diagnosis of COVID-19 from CT images[J]. Applied Soft Computing, 2022, 122: 108883 DOI: https://doi.org/10.1016/j.asoc.2022.108883
[9] Meyers J L, Cardoso H F V. Reliability of wet versus dry bone CT scan-based quantification of cortical area measurements[J]. American Journal of Physical Anthropology, 2021, 174(Suppl.71): 71-71.
[10] Malloy P, Newhouse A C, Alejandro A. Espinoza Orías,et al. MRI‐- and CT‐-based metrics for the quantification of arthroscopic bone resections in femoroacetabular impingement syndrome[J]. Journal of Orthopaedic Research, 2022, 40(5): 1174-1181. DOI: https://doi.org/10.1002/jor.25139
[11] Banday S A, Nahvi R, Mir A H, et al. Ground glass opacity detection and segmentation using CT images: an image statistics framework[J]. IET image processing, 2022, 16(9): 2432-2445. DOI: https://doi.org/10.1049/ipr2.12498
[12] Heidari A, Javaheri D, Toumaj S, et al. A new lung cancer detection method based on the chest CT images using Federated Learning and blockchain systems[J]. Artificial intelligence in medicine, 2023, 141(7): 1. DOI: https://doi.org/10.1016/j.artmed.2023.102572
[13] Li Z, Zhao Z, Lian S. YOLOv5x deep learning network model based on SPECT whole body bone scanning for diagnosing benign and malignant bone lesions[J]. Chinese Journal of Medical Imaging Technology, 2023, 39(12): 1867-1871.
[14] Chen J, Wee L, Dekker A, et al. Using 3D deep features from CT scans for cancer prognosis based on a video classification model: A multi‐dataset feasibility study[J]. Medical physics, 2023, 50(7): 4220-4233. DOI: https://doi.org/10.1002/mp.16430
[15] Cerci J J, Fanti S, Lobato E E et al. Diagnostic Performance and Clinical Impact of Ga-68-PSMA-11 PET/CT Imaging in Early Relapsed Prostate Cancer After Radical Therapy: A Prospective Multicenter Study (IAEA-PSMA Study)[J]. The Journal of Nuclear Medicine, 2022, 63(2): 240-247. DOI: https://doi.org/10.2967/jnumed.120.261886
[16] Rashid R, Zhang E, Abdi A. Some measured frequency domain characteristics of the underwater vector and scalar acoustic field components with applications to communication receivers[J]. The Journal of the Acoustical Society of America, 2021, 150(4): A155. DOI: https://doi.org/10.1121/10.0007968
[17] Liu X, Hou S, Liu S, et al. Attention-based Multimodal Glioma Segmentation with Multi-attention Layers for Small-intensity Dissimilarity[J]. Journal of King Saud University - Computer and Information Sciences, 2023, 35: 183-195 DOI: https://doi.org/10.1016/j.jksuci.2023.03.011
[18] Manikandan L C, Selvakumar R K, Nair S A H, et al. Hardware implementation of fast bilateral filter and canny edge detector using Raspberry Pi for telemedicine applications[J]. Journal of Ambient Intelligence and Humanized Computing, 2021, 12(5): 4689-4695. DOI: https://doi.org/10.1007/s12652-020-01871-w
[19] Geetha V, Anbumani V, Murugesan G, et al. Hybrid optimal algorithm-based 2D discrete wavelet transform for image compression using fractional KCA[J]. Multimedia Systems, 2020, 26(8): 1-16. DOI: https://doi.org/10.1007/s00530-020-00681-6
[20] Han H, Wang X. Fast Multi-Sensor Information Fusion Based on Deep Hybrid Convolution[J]. Computer Simulation, 2022, 39(05): 288-291+298.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Xiaochun Guo, Hashim Ali

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
Funding data
-
Education Department of Jiangxi Province
Grant numbers GJJ2202724