Scholarlink

In the pursuit of enhancing clinical diagnoses, the field of optometry seeks to leverage technological advancements in the eye diseases classification. Tomography based Optical coherence imaging is pivotal in identifying age-related ocular conditions such as Choroidal Neovascularization, Diabetic Macular Edema, and Drusen. However, due to the nuanced and similar presentation of these conditions, accurate diagnosis demands extensive expertise and can be time-consuming. On focusing this challenge, this research explores the capability of Deep Learning Convolutional Neural Networks to effectively differentiate and classify these eye diseases. The use of a systematic and straightforward requirement structure for illness classification is emphasized for consistency in evaluation. By harnessing the power of a deep learning-based Ensemble model with multi-transfer learning architecture, this research achieves an impressive classification accuracy exceeding 83% in distinguishing among several algorithms handling optical images. This research focuses on the proposed Ensemble model’s proficiency in identifying eye disease with increased accuracy and comparative study has been made on several deep learning techniques with improved efficiency and neural model provides added support in several medical applications.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Ensemble Learning for Accurate Prediction of Ophthalmic Diseases in Medical Imaging

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • V. Manimekalai,
  • K. Vijayalakshmi

摘要

In the pursuit of enhancing clinical diagnoses, the field of optometry seeks to leverage technological advancements in the eye diseases classification. Tomography based Optical coherence imaging is pivotal in identifying age-related ocular conditions such as Choroidal Neovascularization, Diabetic Macular Edema, and Drusen. However, due to the nuanced and similar presentation of these conditions, accurate diagnosis demands extensive expertise and can be time-consuming. On focusing this challenge, this research explores the capability of Deep Learning Convolutional Neural Networks to effectively differentiate and classify these eye diseases. The use of a systematic and straightforward requirement structure for illness classification is emphasized for consistency in evaluation. By harnessing the power of a deep learning-based Ensemble model with multi-transfer learning architecture, this research achieves an impressive classification accuracy exceeding 83% in distinguishing among several algorithms handling optical images. This research focuses on the proposed Ensemble model’s proficiency in identifying eye disease with increased accuracy and comparative study has been made on several deep learning techniques with improved efficiency and neural model provides added support in several medical applications.