Segmentation, Detection and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou

Matias, André Victória; Cerentini, Allan; Macarini, Luiz Antonio Buschetto; Amorim, João Gustavo Atkinson; Daltoé, Felipe Perozzo; Wangenheim, Aldo von

doi:10.1109/cbms49503.2020.00018

Cited by 3 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From this point of view, a simple, computer-assisted and semi-automated quantitative cytology-based diagnostic method for oral cancer, which employs the traditional Papanicolaou staining method, has the potential to simplify and improve the oral cancer diagnosis process, while employing a traditional, well-known and widespread staining technique. In an earlier proof-of-concept study, we demonstrated that DL is a promising approach for the diagnosis support of oral cytology [37].…”

Section: Introductionmentioning

confidence: 92%

Segmentation, Detection, and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou

et al. 2021

Self Cite

View full text Add to dashboard Cite

Although oral cancer is considered a global health issue with 350,000 people diagnosed over a year, it can successfully be treated if diagnosed at early stages. Papanicolaou is an inexpensive and non-invasive method, generally applied to detect cervical cancer, but it can also be useful to detect cancer on oral cavities. The manual process of analyzing cells to detect abnormalities is a time-consuming cell analysis and is subject to variations in perceptions from different professionals. This paper compares three different deep learning (DL) approaches: segmentation, object detection, and image classification. Our results show that the binary object detection with Faster R-CNN is the best approach for nuclei detection and localization (0.76 IoU). Since ResNet 34 had a good performance on abnormal nuclei classification (0.86 F 1 score), we concluded that these two models can be used in combination to perform a reliable localization and classification pipeline. This work reinforces that the automated analysis of oral cytology to build a pipeline for nuclei classification and localization using DL can contribute to minimize the subjectivity of the human analysis and also support the detection of cancer at early stages.

show abstract

Section: Introductionmentioning

confidence: 92%

Segmentation, Detection, and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

What is the state of the art of computer vision-assisted cytology? A Systematic Literature Review

Matias

Amorim

Macarini

et al. 2021

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

Cytomorphometric Analysis of Buccal Exfoliated Cells in Geriatric and Pediatric Age Groups - A Cross-Sectional Study

Ramani,

Ramalingam

2023

Cureus

View full text Add to dashboard Cite

Background We have to establish variations in cellular dimensions in buccal smears with respect to age. It can be used as a reference standard while dealing with age-related pathological abnormalities. Aim The study aims to compare the nuclear area (NA), cellular area (CA), and nucleus-to-cytoplasm ratio (N:C) of pediatric and geriatric age groups in smears obtained from clinically normal buccal mucosa. Materials and methods Buccal smears were collected from 60 subjects with age groups of <10 and >60 years. Cytological smears were prepared and fixed using alcohol. H&E and Papanicolaou's staining was performed as per manufacturer instructions. Cytomorphometric analysis was carried out using Image J software v.1.52 for CA, NA, and N:C. Statistical analysis using Student's t-test was performed using SPSS version 23.0 (IBM Inc, Armonk, New York). Results A significant difference (p<0.001) in NA and CA between the pediatric and geriatric age groups was noted. There was no significant difference in N:C among the study groups. Conclusion The present study provides baseline data of two different age groups that can be used for comparison of abnormal cells in suspicious clinical lesions.

show abstract

Segmentation, Detection and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou

Cited by 3 publications

References 18 publications

Segmentation, Detection, and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou

Segmentation, Detection, and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou

What is the state of the art of computer vision-assisted cytology? A Systematic Literature Review

Cytomorphometric Analysis of Buccal Exfoliated Cells in Geriatric and Pediatric Age Groups - A Cross-Sectional Study

Contact Info

Product

Resources

About