Automated identification of keratinization and keratin pearl area from in situ oral histological images

Das, Dev Kumar; Chakraborty, Chandan; Sawaimoon, Satyakam; Maiti, Ananda; Chatterjee, Sanjoy

doi:10.1016/j.tice.2015.04.009

Cited by 34 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Keratinocytes follow a unique program of terminal differentiation and apoptotic cell death, ultimately leading to the formation of the keratin layer17. For these reasons, keratinization within tumors is considered a marker of well-differentiated SCC of the head and neck, as well as of the lungs1819.…”

Section: Discussionmentioning

confidence: 99%

Keratinization of Lung Squamous Cell Carcinoma Is Associated with Poor Clinical Outcome

et al. 2017

View full text Add to dashboard Cite

BackgroundAlthough the World Health Organization (WHO) classification of lung squamous cell carcinoma (SCC) was revised in 2015, its clinical implications for lung SCC subsets remain unclear. We investigated whether the morphologic characteristics of lung SCC, including keratinization, were associated with clinical parameters and clinical outcome of patients.MethodsA total of 81 patients who underwent curative surgical resection of diagnosed lung SCC, were enrolled in this study. Attributes such as keratinization, tumor budding, single cell invasion, and nuclear size within the tumor, as well as immunohistochemistry of Bcl-xL and pS6 expressions, were evaluated.ResultsThe keratinizing and nonkeratinizing subtypes did not differ with respect to age, sex, TNM stage, and morphologic parameters such as nuclear diameter, tumor budding, and single cell invasion at the tumor edge. Most patients with the keratinizing subtype (98.0%) had a history of smoking, whereas the nonkeratinizing group had a relatively higher proportion of never-smokers relative to the keratinizing group (24.0% vs. 2.0%; p=0.008, chi-square test). Expression of pS6 (a surrogate marker of mammalian target of rapamycin complex 1 [mTORC1] signaling that regulates keratinocyte differentiation), and Bcl-xL (a key anti-apoptotic molecule that may inhibit keratinization), did not correlate significantly with the presence of keratinization. Patients with the keratinizing subtype had a significantly shorter overall survival (85.2 months vs. 135.7 months, p=0.010, log-rank test), and a multivariate analysis showed that keratinization was an independent, poor prognostic factor (hazard ratio, 2.389; 95% confidence interval, 1.090–5.233; p=0.030).ConclusionIn lung SCC, keratinization is associated with a poor prognosis, and might be associated with smoking.

show abstract

Section: Discussionmentioning

confidence: 99%

Keratinization of Lung Squamous Cell Carcinoma Is Associated with Poor Clinical Outcome

et al. 2017

View full text Add to dashboard Cite

show abstract

“… 16 The average performance of this segmentation method was evaluated by the Jaccard coefficient (77.76%), yielding a first-rate correlation value (0.85) and segmentation accuracy (95.08%). 17 Another study by Das et al described a convolutional neural network (CNN) used to distinguish epithelial, subepithelial, and keratinizing regions as well as detect keratin pearls in OSCC. CNN is an artificial neural network that contains many layers to perform operations through numerous hyperparameters, that can be useful to build a classification model.…”

Section: Resultsmentioning

confidence: 99%

Artificial intelligence in head and neck cancer diagnosis

Bassani

Nicola

Eccher³

et al. 2022

Journal of Pathology Informatics

View full text Add to dashboard Cite

“…Dev Kumar et al (2015) [74] developed a model to detect the keratinization and keratin pearl areas from which the keratinization index was calculated. This Keratinization scoring index can be used as a quantitative measure for OSCC for even very low (4x) magnification.…”

Section: Literature Reviewmentioning

confidence: 99%

Machine Learning Techniques used for the Histopathological Image Analysis of Oral Cancer-A Review

Panigrahi¹,

Swarnkar²

2020

TOBIOIJ

View full text Add to dashboard Cite

Oral diseases are the 6th most revealed malignancy happening in head and neck regions found mainly in south Asian countries. It is the most common cancer with fourteen deaths in an hour on a yearly basis, as per the WHO oral cancer incidence in India. Due to the cost of tests, mistakes in the recognition procedure, and the enormous remaining task at hand of the cytopathologist, oral growths cannot be diagnosed promptly. This area is open to be looked into by biomedical analysts to identify it at an early stage. At present, with the advent of entire slide computerized scanners and tissue histopathology, there is a gigantic aggregation of advanced digital histopathological images, which has prompted the necessity for their analysis. A lot of computer aided analysis techniques have been developed by utilizing machine learning strategies for prediction and prognosis of cancer. In this review paper, first various steps of obtaining histopathological images, followed by the visualization and classification done by the doctors are discussed. As machine learning techniques are well known, in the second part of this review, the works done for histopathological image analysis as well as other oral datasets using these strategies for growth prognosis and anticipation are discussed. Comparing the pitfalls of machine learning and how it has overcome by deep learning mostly for image recognition tasks are also discussed subsequently. The third part of the manuscript describes how deep learning is beneficial and widely used in different cancer domains. Due to the remarkable growth of deep learning and wide applicability, it is best suited for the prognosis of oral disease. The aim of this review is to provide insight to the researchers opting to work for oral cancer by implementing deep learning and artificial neural networks.

show abstract

Automated identification of keratinization and keratin pearl area from in situ oral histological images

Cited by 34 publications

References 20 publications

Keratinization of Lung Squamous Cell Carcinoma Is Associated with Poor Clinical Outcome

Keratinization of Lung Squamous Cell Carcinoma Is Associated with Poor Clinical Outcome

Artificial intelligence in head and neck cancer diagnosis

Machine Learning Techniques used for the Histopathological Image Analysis of Oral Cancer-A Review

Contact Info

Product

Resources

About