Hyperspectral Imaging of Whole‐Cell Region for Differentiating Cervical Squamous Intraepithelial Lesion Cytology

BACKGROUND: Cervical cytology offers a relatively safe and reliable method for cancer screening, but the tests contain vague grading criteria, such as atypical squamous cells, and cannot exclude high-grade squamous intraepithelial lesions (ASC-H) and atypical squamous cells of undetermined significance (ASC-US). METHODS: To explore distinct differentiation points among ASC-H, high-grade squamous intraepithelial lesions (HSIL), and non-keratinizing squamous cell carcinoma (SCC), and among ASC-US, low-grade squamous intraepithelial lesions (LSIL), and negative for intraepithelial lesion or malignancy, hyperspectral imaging analyses were performed in cells mounted on 150 Papanicolaou-stained specimens containing nine cervical cell types. Hyperspectral data were obtained from nuclei, cytoplasm, and whole-cell regions in 4841 cells without overlap at 15-nm increments in wavelength within the visible light spectrum (450-750 nm). RESULTS: = 0.8339, p < 0.001), indicating that intensity from the whole cell provided the most informative indicator of cervical cells. CONCLUSION: These results suggest that hyperspectral analysis of whole cells offers a valuable tool for differentiating atypical squamous cells from other cell types.

Authors

Institutions

Publication Details

Journal
Cancer Medicine
Published
2026-04-01
DOI
https://doi.org/10.1002/cam4.71746
Primary Topic
Optical Imaging and Spectroscopy Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Hyperspectral Imaging of Whole‐Cell Region for Differentiating Cervical Squamous Intraepithelial Lesion Cytology

Keiko Yugawa, Hironobu Naiki, Kumiko Kamada, Kazumi FURUICHI et al.
Cancer Medicine
Optical Imaging and Spectroscopy Techniques
article

Hyperspectral Imaging of Whole‐Cell Region for Differentiating Cervical Squamous Intraepithelial Lesion Cytology

Keiko Yugawa, Hironobu Naiki, Kumiko Kamada, Kazumi FURUICHI, Yoshiaki Imamura, K. Tanabe, Kunihiro Inai, Sakon Noriki, Chikai Hosokawa, Haruka Matsukawa
article en

Abstract

BACKGROUND: Cervical cytology offers a relatively safe and reliable method for cancer screening, but the tests contain vague grading criteria, such as atypical squamous cells, and cannot exclude high-grade squamous intraepithelial lesions (ASC-H) and atypical squamous cells of undetermined significance (ASC-US). METHODS: To explore distinct differentiation points among ASC-H, high-grade squamous intraepithelial lesions (HSIL), and non-keratinizing squamous cell carcinoma (SCC), and among ASC-US, low-grade squamous intraepithelial lesions (LSIL), and negative for intraepithelial lesion or malignancy, hyperspectral imaging analyses were performed in cells mounted on 150 Papanicolaou-stained specimens containing nine cervical cell types. Hyperspectral data were obtained from nuclei, cytoplasm, and whole-cell regions in 4841 cells without overlap at 15-nm increments in wavelength within the visible light spectrum (450-750 nm). RESULTS: = 0.8339, p < 0.001), indicating that intensity from the whole cell provided the most informative indicator of cervical cells. CONCLUSION: These results suggest that hyperspectral analysis of whole cells offers a valuable tool for differentiating atypical squamous cells from other cell types.

Cancer MedicineVol. 15(4)
University of Fukui (JP), Fukui University of Technology (JP), Panasonic (Japan) (JP), Nagoya Institute of Technology (JP), University of Fukui Hospital (JP), Fukui Prefectural University (JP)
Openalex Percentile: Top 27%
Optical Imaging and Spectroscopy Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.