Pattern identification of biomedical images with time series: Contrasting THz pulse imaging with DCE-MRIs

Abstract

We provide a survey of recent advances in biomedical image analysis and classification from emergent imaging modalities such as terahertz (THz) pulse imaging (TPI) and dynamic contrast-enhanced magnetic resonance images (DCE-MRIs) and identification of their underlining commonalities. Methods: Both time and frequency domain signal pre-processing techniques are considered: noise removal, spectral analysis, principal component analysis (PCA) and wavelet transforms. Feature extraction and classification methods based on feature vectors using the above processing techniques are reviewed. A tensorial signal processing de-noising framework suitable for spatiotemporal association between features in MRI is also discussed. Validation: Examples where the proposed methodologies have been successful in classifying TPIs and DCE-MRIs are discussed. Results: Identifying commonalities in the structure of such heterogeneous datasets potentially leads to a unified multi-channel signal processing framework for biomedical image analysis. Conclusion: The proposed complex valued classification methodology enables fusion of entire datasets from a sequence of spatial images taken at different time stamps; this is of interest from the viewpoint of inferring disease proliferation. The approach is also of interest for other emergent multi-channel biomedical imaging modalities and of relevance across the biomedical signal processing community.

Medical Big Data: Neurological Diseases Diagnosis Through Medical Data Analysis

“…Such tests are mainly used for swelling and lesions in certain areas, broken bones, heart disease and internal bleeding. In finding brain and spinal cord abnormalities, MRI tests are valuable to investigate detailed images of body structures including tissues, organs, bones and nerves [9][10][11]. MRI tests help physicians to diagnose torn ligaments, tumours, circulation (blood flow) problems, eye disease, inflammation (e.g.…”

An Effective Confidence-Based Early Classification of Time Series

“…2) For each confidence threshold candidate θ i ∈ : a) For each training time series X i ∈ X and each timestamp t ∈ L, if the confidence of the prediction result C t (H t (X i )) is greater than or equal to the confidence threshold θ i , the prediction result H t (X i ), the timestamp t and the confidence C t (H t (X i )) are returned; otherwise, the confidence at the next timestamp is selected to check. b) Calculate the cost CF(θ i ) by Equations ( 1), (2) and ( 8). 3) Choose the candidate confidence threshold that minimizes the cost as the confidence threshold θ .…”

“…Time series classification (TSC) has attracted a significant interest within many fields, due to the fact that time series data are present in a wide range of real-life domains including, but not limited to, biology [1], medicine [2], traffic [3], and engineering [4]. Generally, time series data are collected over time.…”

Artificial intelligence algorithm for optimal time series data model

“…Time series prediction is to predict the future data or trends from historical and current data by analyzing the rules or trends of time series over time. Time series prediction methods include classical time series analysis [20][21][22][23], neural networks [24][25][26], and expert systems [27][28][29][30]. Time series prediction can be performed by mining time series, discovering sequence rules, and using rule knowledge to predict.…”