DeepCattle: A Deep Learning Framework for Automated Detection and Severity Assessment of Ocular Squamous Cell Carcinoma in Cattle

Manikandan, D and Saranya, S and Divya Bairavi, S and Varadharajan, S (2025) DeepCattle: A Deep Learning Framework for Automated Detection and Severity Assessment of Ocular Squamous Cell Carcinoma in Cattle. DeepCattle: A Deep Learning Framework for Automated Detection and Severity Assessment of Ocular Squamous Cell Carcinoma in Cattle. ISSN 2352-538X

[thumbnail of 126017350 (2).pdf] Text
126017350 (2).pdf - Published Version

Download (667kB)

Abstract

In this artificial intelligence era, health care plays vigorous role in day today life. The disease caused to the cattle’s are pink eye, new forest disease are caused by infectious Bovine Keratoconjuctivitis (IBK) and cancer eye are caused by Ocular Squamous Cell Carcinoma (OSCC) disease which are often found in young calf where these bacterial diseases spread easily through the transmitter such as flies, etc., The cow suffers more through this disease such as tear straining on the eyes, pains and irritation are exposed due to sunlight. These diseases are not accurately identified through naked eyes where diagnosing at earlier stage will prevent the cattle from the loss of its life. Eyes of the cattle’s are major representation to classify whether the significant cow is infected or not through these disease.Ocular squamous cell carcinoma is a critical ocular disease affecting young calves, which can lead to severe health complications when it is left untreated. The deep learning-based approach for the early detection and classification of OSCC is to identify an early-stage OSCC lesions and assess disease severity. The model leverages a Convolutional Neural Network combined with a Bidirectional Long Short Term Memory to classify ocular images and to determine disease progression. Experimental results demonstrate that the proposed model achieves an accuracy of 93% when applied to high-resolution ocular images, significantly enhancing diagnostic efficiency and supporting timely clinical decision-making.

Item Type: Article
Subjects: Computer Science Engineering > Deep Learning
Domains: Computer Science Engineering
Depositing User: AA BB CC
Date Deposited: 13 Mar 2026 10:25
Last Modified: 13 Mar 2026 10:25
URI: https://ir.vistas.ac.in/id/eprint/13153

Actions (login required)

View Item
View Item