Vol. 9, Issue 6, Part I (2024)

Author(s): Nripendra Singh, Srinivas Sathapathy, Ritun Patra, Mukesh Kumar, Surya Pratap Gond, Deepak Kumar Chaurasia, Shashi Tekam, Diksha Lade and Shveta Singh

Abstract: This review study was conducted at the Department of Veterinary Anatomy & Histology, College of Veterinary Science and Animal Husbandry, OUAT, Bhubaneswar, India, from August to September 2024. The study focuses on the development of AI-based image analysis techniques for the identification of visceral organs in veterolegal cases, aiming to improve the accuracy and efficiency of post-mortem examinations. Traditional methods of visceral organ identification often involve subjective assessment by veterinarians, which can lead to inconsistencies and errors. AI-based systems, leveraging deep learning algorithms and computer vision, offer a novel approach by providing objective, reproducible, and rapid identification of organs. In this study, convolutional neural networks (CNNs) were trained on a large dataset of veterinary post-mortem images to recognize and differentiate visceral organs such as the liver, lungs, heart, kidneys, and spleen. The AI model achieved high accuracy in organ identification, even in cases where organs were partially damaged or visually obscured. These findings demonstrate the potential of AI in assisting veterinarians in forensic investigations by reducing human error, expediting analyses, and enhancing the reliability of findings in veterolegal contexts. Future research will focus on expanding the dataset to include a wider variety of species and conditions, integrating 3D imaging for better spatial resolution, and developing user-friendly software interfaces for field applications in veterinary forensics.