CMYK Systems

Westland, Stephen; Cheung, Vien

doi:10.1007/978-3-540-79567-4_13

Cited by 2 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A modest performance was reported when compared with the TSB readings (linear correlation of 0.84 with a mean error of 2.0 mg/dl), and the authors had discussed several limitations in their study, such as the difficulty in image segmentation and the neglect of the confounding effect of skin tone. Furthermore, the use of a cyan-magenta-yellow(-key) (CMY(K)) colour calibration card has a limited representation of the wide range of natural colours 23 . Such colour calibration cards require proper usage, storage, and cleaning to prevent the folding, dusting, and greasing of the card, which can lead to potentially inaccurate prediction of the bilirubin level 23 .…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, the use of a cyan-magenta-yellow(-key) (CMY(K)) colour calibration card has a limited representation of the wide range of natural colours 23 . Such colour calibration cards require proper usage, storage, and cleaning to prevent the folding, dusting, and greasing of the card, which can lead to potentially inaccurate prediction of the bilirubin level 23 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Machine Learning Algorithms for Accurate Determination of Bilirubin Level on Medically Relevant Tissue Phantom Images

Yuan,

Huang,

et al. 2023

Preprint

View full text Add to dashboard Cite

Neonatal Jaundice is a common occurrence in neonates. High excess bilirubin would lead to hyperbilirubinemia, leading to irreversible adverse damage such as kernicterus. Therefore, it is necessary and important to monitor neonates’ bilirubin levels in real-time for immediate intervention. However, current screening protocols have their inherent limitations, necessitating more convenient measurements. In this proof-of-concept study, we evaluated the feasibility of using machine learning for the screening of hyperbilirubinemia in neonates from smartphone-acquired photographs. Different machine learning models were compared and evaluated to gain a better understanding of feature selection and model performance in bilirubin determination. An in vitro study was conducted with a bilirubin-containing tissue phantom to identify potential biological and environmental confounding factors. The findings of this study present a systematic characterization of the confounding effect of various factors through separate parametric tests. These tests uncover potential techniques in image pre-processing highlighting important biological features (light scattering property and skin thickness) and external features (ISO, lighting conditions and white balance), which together contribute to robust model approaches for accurately determining bilirubin concentrations. By obtaining an accuracy of 0.848 in classification and 0.812 in regression, these findings indicate strong potential in aiding in the design of clinical studies using patient-derived images.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning Algorithms for Accurate Determination of Bilirubin Level on Medically Relevant Tissue Phantom Images

Yuan,

Huang,

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Application of machine learning algorithms for accurate determination of bilirubin level on in vitro engineered tissue phantom images

Yuan,

Huang,

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Neonatal Jaundice is a common occurrence in neonates. High excess bilirubin would lead to hyperbilirubinemia, leading to irreversible adverse damage such as kernicterus. Therefore, it is necessary and important to monitor neonates’ bilirubin levels in real-time for immediate intervention. However, current screening protocols have their inherent limitations, necessitating more convenient measurements. In this proof-of-concept study, we evaluated the feasibility of using machine learning for the screening of hyperbilirubinemia in neonates from smartphone-acquired photographs. Different machine learning models were compared and evaluated to gain a better understanding of feature selection and model performance in bilirubin determination. An in vitro study was conducted with a bilirubin-containing tissue phantom to identify potential biological and environmental confounding factors. The findings of this study present a systematic characterization of the confounding effect of various factors through separate parametric tests. These tests uncover potential techniques in image pre-processing, highlighting important biological features (light scattering property and skin thickness) and external features (ISO, lighting conditions and white balance), which together contribute to robust model approaches for accurately determining bilirubin concentrations. By obtaining an accuracy of 0.848 in classification and 0.812 in regression, these findings indicate strong potential in aiding in the design of clinical studies using patient-derived images.

show abstract

CMYK Systems

Cited by 2 publications

References 3 publications

Application of Machine Learning Algorithms for Accurate Determination of Bilirubin Level on Medically Relevant Tissue Phantom Images

Application of Machine Learning Algorithms for Accurate Determination of Bilirubin Level on Medically Relevant Tissue Phantom Images

Application of machine learning algorithms for accurate determination of bilirubin level on in vitro engineered tissue phantom images

Contact Info

Product

Resources

About