How to Collect and Interpret Medical Pictures Captured in Highly Challenging Environments that Range from Nanoscale to Hyperspectral Imaging

被引：15
作者：
Laghari A.A. [1 ]
Estrela V.V. [2 ]
Yin S. [3 ]
机构：
[1] Department of Computer Science, Sindh Madressatul Islam University, Karachi
[2] Departamento de Engenharia de Telecomunica, Federal University of Rio de Janeiro, Rio de Janeiro
[3] Information and Communication Engineering, Harbin Institute of Technology, Harbin
来源：
Current Medical Imaging | 2024年 / 20卷
关键词：
Augmented reality (AR); Content-based image retrieval; Cyber-physical systems; Data imputation; Medical imaging; PACS; Public health; Virtual reality (VR); Visualization;
D O I：
10.2174/1573405619666221228094228
中图分类号：
学科分类号：
摘要：
Digital well-being records are multimodal and high-dimensional (HD). Better theradiagnostics stem from new computationally thorough and edgy technologies, i.e., hyperspectral (HSI) imaging, super-resolution, and nanoimaging, but advance mess data portrayal and retrieval. A patient's state involves multiple signals, medical imaging (MI) modalities, clinical variables, dialogs between clinicians and patients, metadata, genome sequencing, and signals from wearables. Patients' high volume, personalized data amassed over time have advanced artificial intelligence (AI) models for higher-precision inferences, prognosis, and tracking. AI promises are undeniable, but with slow spreading and adoption, given partly unstable AI model performance after real-world use. The HD data is a rate-limiting factor for AI algorithms generalizing real-world scenarios. This paper studies many health data challenges to robust AI models' growth, aka the dimensionality curse (DC). This paper overviews DC in the MIs' context, tackles the negative out-of-sample influence and stresses important worries for algorithm designers. It is tricky to choose an AI platform and analyze hardships. Automating complex tasks requires more examination. Not all MI problems need automation via DL. AI developers spend most time refining algorithms, and quality data are crucial. Noisy and incomplete data limits AI, requiring time to handle control, integration, and analyses. AI demands data mixing skills absent in regular systems, requiring hardware/software speed and flexible storage. A partner or service can fulfill anomaly detection, predictive analysis, and ensemble modeling. © 2024 The Author(s).
引用
收藏
相关论文
共 56 条
  • [1] Nguyen T, Nguyen N, Le T., Manufacturing PACS, online medical consultation system and designing security DICOM web viewer software, Proc Intl Symp El and Electr Eng (ISEE), pp. 37-42
  • [2] Estrela V, Saotome O, Loschi H, Et al., Emergency response cyber-physical framework for landslide avoidance with sustainable electronics, MDPI, Technologies (Basel), 6, 2, (2018)
  • [3] Neharkar M, Sudhansu SK, Sudhansu P., Multiresolution mosaic images by using Laplacian of Gaussian method: A review, Int J Eng Res Appl, 2, 2, pp. 20-25, (2012)
  • [4] Su MS, Hwang WL, Cheng KY., Analysis on multiresolution mosaic images, IEEE Trans Image Process, 13, 7, pp. 952-959, (2004)
  • [5] Rivera LA, Estrela VV, Carvalho PCP, Velho L., Oriented bounding boxes based on multiresolution contours, J WSCG (Plzen), 2004, (2004)
  • [6] Krishnamurthi R, Gopinathan D., Wavelet transformation and machine learning techniques for digital signal analysis in IoT systems, Machine Learning in Signal Processing, pp. 339-359, (2021)
  • [7] Afshar P, Mohammadi A, Plataniotis KN, Oikonomou A, Benali H., From handcrafted to deep-learning-based cancer radiomics: Challenges and opportunities, IEEE Signal Process Mag, 36, 4, pp. 132-160, (2019)
  • [8] Hemanth JD, Wang L, Tavares JM, Fuqian S.
  • [9] Shirly S, Ramesh K., Review on 2D and 3D MRI Image Segmentation Techniques, Curr Med Imaging Rev, 15, 2, pp. 150-160, (2019)
  • [10] Hashemi SMR, Hassanpour H, Kozegar E, Tan T., Cystoscopic image classification by unsupervised feature learning and fusion of classifiers
123456