Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Feb 22, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.6K

Enhanced medical image segmentation using optimized bidirectional LSTM and dolphin partner optimizer.

Afnan M Alhassan1, Nouf I Altmami1

  • 1Department of Computer Science, College of Computing and Information Technology, Shaqra University, Shaqra, Saudi Arabia.

Plos One
|February 20, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Quadra Sense: A Fusion of Deep Learning Classifiers for Mitosis Detection in Breast Cancer Histopathology.

Diagnostics (Basel, Switzerland)·2026
Same author

DL-PCMNet: Distributed Learning Enabled Parallel Convolutional Memory Network for Skin Cancer Classification with Dermatoscopic Images.

Diagnostics (Basel, Switzerland)·2026
Same author

Intrusion detection using search-based learning optimized ensemble tree classifier model.

PloS one·2025
Same author

IV3TM: Inception V3 enabled bidirectional long short-term memory network for brain tumor classification.

PloS one·2025
Same author

Mitosis detection in histopathological images using customized deep learning and hybrid optimization algorithms.

PloS one·2025
Same author

Fuzzy Optimized Attention Network with Multi-Instance Deep Learning (FOAN-MIDL) for Alzheimer's Disease Diagnosis with Structural Magnetic Resonance Imaging (sMRI).

Diagnostics (Basel, Switzerland)·2025

This study introduces an Optimized Bidirectional Long-Short Term Memory (OBi-LSTM) model for enhanced medical image segmentation. The OBi-LSTM approach, optimized with Dolphin Partner Optimizer (DPO), significantly improves classification accuracy and feature extraction in medical scans.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Medical imaging is crucial for diagnosis and treatment, with machine learning and deep learning increasingly vital for image analysis.
  • Accurate segmentation of medical images is essential for effective clinical diagnosis and understanding tissue and organ function.
  • Deep learning techniques have garnered significant attention for advancing medical image segmentation capabilities.

Purpose of the Study:

  • To introduce an Optimized Bidirectional Long-Short Term Memory (OBi-LSTM) technique for medical image classification and segmentation.
  • To enhance the accuracy and efficiency of medical image segmentation using a novel deep learning approach.
  • To evaluate the performance of the proposed OBi-LSTM model against existing state-of-the-art methods.

Related Experiment Videos

Last Updated: Feb 22, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.6K

Main Methods:

  • Developed an Optimized Bidirectional Long-Short Term Memory (OBi-LSTM) classifier that processes sequential data in both forward and backward directions.
  • Employed the Dolphin Partner Optimizer (DPO) to tune weight and bias parameters within the Bi-LSTM classifier for optimized cell performance.
  • Implemented a deep learning model designed to simultaneously consider spatial placements, channels, and scales for improved segmentation.

Main Results:

  • The OBi-LSTM model achieved a Dice similarity coefficient of 94.05%, a Jaccard index of 88.77%, and an accuracy of 93.05% on MRI segmented tests.
  • The proposed OBi-LSTM + DPO model demonstrated superior performance compared to existing techniques in medical image segmentation.
  • The model showed significant improvements in boundary delineation and feature extraction, highlighting its effectiveness.

Conclusions:

  • The Optimized Bidirectional Long-Short Term Memory (OBi-LSTM) model, optimized with Dolphin Partner Optimizer (DPO), offers a powerful and efficient solution for medical image segmentation.
  • The proposed method significantly enhances segmentation performance, particularly in precise boundary delineation and detailed feature extraction.
  • OBi-LSTM demonstrates strong explanatory power and outperforms current state-of-the-art techniques, validating its clinical utility.