Spectral-spatial feature-based neural network method for acute lymphoblastic leukemia cell identification via microscopic hyperspectral imaging technology

Wang, Qian; Wang, Jianbiao; Zhou, Mei; Li, Qingli; Wang, Yiting

doi:10.1364/boe.8.003017

Cited by 63 publications

(22 citation statements)

References 22 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 can be appreciated. It is also remarkable that the scattering at 620 nm is already used to identify protein-membrane lipid assembly, such as lipid rafts in RBC after density gradient centrifugation 24 . On the other hand, we cannot exclude that spectral bands from RBC molecular components not considered so far are superimposed with those here described.…”

Section: Discussionmentioning

confidence: 99%

High predictive values of RBC membrane-based diagnostics by biophotonics in an integrated approach for Autism Spectrum Disorders

Giacometti

Ferreri

Sansone

et al. 2017

Sci Rep

View full text Add to dashboard Cite

Membranes attract attention in medicine, concerning lipidome composition and fatty acid correlation with neurological diseases. Hyperspectral dark field microscopy (HDFM), a biophotonic imaging using reflectance spectra, provides accurate characterization of healthy adult RBC identifying a library of 8 spectral end-members. Here we report hyperspectral RBC imaging in children affected by Autism Spectrum Disorder (ASD) (n = 21) compared to healthy age-matched subjects (n = 20), investigating if statistically significant differences in their HDFM spectra exist, that can comprehensively map a membrane impairment involved in disease. A significant difference concerning one end-member (spectrum 4) was found (P value = 0.0021). A thorough statistical treatment evidenced: i) diagnostic performance by the receiving operators curve (ROC) analysis, with cut-offs and very high predictive values (P value = 0.0008) of spectrum 4 for identifying disease; ii) significant correlations of spectrum 4 with clinical parameters and with the RBC membrane deficit of the omega-3 docosahexaenoic acid (DHA) in ASD patients; iii) by principal component analysis, very high affinity values of spectrum 4 to the factor that combines behavioural parameters and the variable “cc” discriminating cases and controls. These results foresee the use of biophotonic methodologies in ASD diagnostic panels combining with molecular elements for a correct neuronal growth.

show abstract

Section: Discussionmentioning

confidence: 99%

High predictive values of RBC membrane-based diagnostics by biophotonics in an integrated approach for Autism Spectrum Disorders

Giacometti

Ferreri

Sansone

et al. 2017

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Wang etc. [13] proposed a marker-based learning vector quantization neural network to detect and classify ALL cells.…”

Section: Introductionmentioning

confidence: 99%

Acute lymphoblastic leukemia cells image analysis with deep bagging ensemble learning

Liu¹,

Long²

2019

Preprint

View full text Add to dashboard Cite

Acute lymphoblastic leukemia (ALL) is a blood cancer which leads 111,000 depth globally in 2015. Recently, diagnosing ALL often involves the microscopic image analysis with the help of deep learning (DL) techniques. However, as most medical related problems, deficiency training samples and minor visual difference between ALL and normal cells make the image analysis task quite challenging. Herein, an augmented image enhanced bagging ensemble learning with elaborately designed training subsets were proposed to tackle above challenges. The weighted F1-scores of preliminary test set and final test are 0.84 and 0.88 respectively employing our ensemble model predictions and ranked within top 10% in ISBI-2019 Classification of Normal vs. Malignant White Blood Cancer Cells contest. Our results preliminarily show the efficacy and accuracy of employing DL based techniques in ALL cells image analysis.

show abstract

“…In leukemia detection in blood smear slides, Wang et al evaluated the usage of three types of inputs for a supervised classifier: spatial features, spectral features, and spatial-spectral features. The results of this study suggest that the exploitation of both the spatial and the spectral features significantly improves the quality of the classification [66]. Similarly, Li et al evaluated the feasibility of utilizing HSI for Red Blood Cell (RBC) counting.…”

Section: Spatial-spectral Informationmentioning

confidence: 74%

“…Leukemia detection in blood smear [66] Red blood cell counting [67] Superpixel segmentation and supervised classification Brain tumor detection in histological slides [68] Supervised classification and K-NN spatial filtering…”

Section: Spatial and Spectral Features In Supervised Classificationmentioning

confidence: 99%

Information Extraction Techniques in Hyperspectral Imaging Biomedical Applications

Ortega¹,

Halicek²,

Fabelo³

et al. 2021

Multimedia Information Retrieval

View full text Add to dashboard Cite

Hyperspectral imaging (HSI) is a technology able to measure information about the spectral reflectance or transmission of light from the surface. The spectral data, usually within the ultraviolet and infrared regions of the electromagnetic spectrum, provide information about the interaction between light and different materials within the image. This fact enables the identification of different materials based on such spectral information. In recent years, this technology is being actively explored for clinical applications. One of the most relevant challenges in medical HSI is the information extraction, where image processing methods are used to extract useful information for disease detection and diagnosis. In this chapter, we provide an overview of the information extraction techniques for HSI. First, we introduce the background of HSI, and the main motivations of its usage for medical applications. Second, we present information extraction techniques based on both light propagation models within tissue and machine learning approaches. Then, we survey the usage of such information extraction techniques in HSI biomedical research applications. Finally, we discuss the main advantages and disadvantages of the most commonly used image processing approaches and the current challenges in HSI information extraction techniques in clinical applications.

show abstract

Spectral-spatial feature-based neural network method for acute lymphoblastic leukemia cell identification via microscopic hyperspectral imaging technology

Cited by 63 publications

References 22 publications

High predictive values of RBC membrane-based diagnostics by biophotonics in an integrated approach for Autism Spectrum Disorders

High predictive values of RBC membrane-based diagnostics by biophotonics in an integrated approach for Autism Spectrum Disorders

Acute lymphoblastic leukemia cells image analysis with deep bagging ensemble learning

Information Extraction Techniques in Hyperspectral Imaging Biomedical Applications

Contact Info

Product

Resources

About