Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Classification of Bones

Classification of Bones

The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...

Vertebral Column: Regions and Curvature

Vertebral Column: Regions and Curvature

The vertebral column or spine is a flexible column that supports the head, neck, and body and allows for their movements. It also protects the spinal cord.
Regions of the Vertebral Column
In an adult, the spine is subdivided into five regions: the cervical, the thoracic, the lumbar, the sacral, and the coccygeal region. The spine initially develops as a series of 33 vertebrae; after 20 years of age, the nine bones in the sacral region, five sacral, and four coccygeal bones fuse to form...

You might also read

Related Articles

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

Sort by

Same author

A lightweight deep learning model with channel attention for kidney cell classification from microscopy images.

Scientific reports·2026

Same author

An Improved Deep Learning Algorithm for Breast Cancer Survival Prediction Based on Multi-Omics Data.

F1000Research·2026

Same author

TSM-NIDS: A time-series mixer-based intrusion detection system for IoT networks.

MethodsX·2026

Same author

Contrast enhancement for brain MRI images via genetic algorithm-based dual cut histogram equalization.

Scientific reports·2026

Same author

Assistive Robotics for Healthy Aging: A Foundational Phenomenological Co-Design Exercise.

Journal of medical Internet research·2026

Same author

Reinforcement learning for medical image analysis: a systematic review of algorithms, engineering challenges, and clinical deployment.

Computer assisted surgery (Abingdon, England)·2025

Same journal

Multiphysics Investigation on Thermal Characteristics of Internal Bio-Inspired V-Ribbed Cooling Channels for Outer Rotor PMSM.

Biomimetics (Basel, Switzerland)·2026

Same journal

Smart Logistics Model for Supply Chain Management via Brain-Inspired Geometric Deep Networks.

Biomimetics (Basel, Switzerland)·2026

Same journal

A Systematic Taxonomy of the Sunflower Optimization Algorithm: Variants, Hybridization Strategies, Applications, and Research Directions.

Biomimetics (Basel, Switzerland)·2026

Same journal

Toward a Compositional Theory of Trust in Embodied Intelligence: A QNLP Framework for Modeling Context, Interaction, and Trustworthiness.

Biomimetics (Basel, Switzerland)·2026

Same journal

Empirical Logic for Bio-Inspired Soft Computing: Illustrative Applications in Control Engineering and Cluster Analysis.

Biomimetics (Basel, Switzerland)·2026

Same journal

A Modified Multi-Strategy Dhole Optimization Algorithm and Its Engineering Applications.

Biomimetics (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Mar 29, 2026

Imaging Dendritic Spines of Rat Primary Hippocampal Neurons using Structured Illumination Microscopy

Imaging Dendritic Spines of Rat Primary Hippocampal Neurons using Structured Illumination Microscopy

Published on: May 4, 2014

A Trustable Spine Abnormalities Classification System Using ResNet50 and VGG16 Supported by Explainable Artificial

Muhammad Shahrul Zaim Ahmad¹, Nor Azlina Ab Aziz^1,2, Heng Siong Lim¹

¹Faculty of Engineering & Technology, Multimedia University, Melaka 75450, Malaysia.

Biomimetics (Basel, Switzerland)

|March 27, 2026

Summary

This summary is machine-generated.

Deep learning models for spinal abnormality classification can be trusted when explainable methods like Grad-CAM are used. Fine-tuned ResNet50 and VGG16 models showed high accuracy and focused on clinically relevant regions in X-ray images.

Keywords:

explainable artificial intelligence heatmaps spine spondylolisthesis and scoliosis

More Related Videos

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites

Published on: September 27, 2024

Related Experiment Videos

Last Updated: Mar 29, 2026

Imaging Dendritic Spines of Rat Primary Hippocampal Neurons using Structured Illumination Microscopy

Imaging Dendritic Spines of Rat Primary Hippocampal Neurons using Structured Illumination Microscopy

Published on: May 4, 2014

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites

Author Spotlight: Optimizing Dendritic Spine Analysis for Balanced Manual and Automated Assessment in the Hippocampus CA1 Apical Dendrites

Published on: September 27, 2024

Area of Science:

Artificial Intelligence
Medical Imaging Analysis
Computer Vision

Background:

Deep learning models are often black boxes, limiting trust in critical applications like medical diagnostics.
Explainable AI (XAI) methods, such as Grad-CAM, are crucial for understanding model decisions and aligning them with clinical practices.
Interpreting deep learning classifications is vital for medical practitioners to trust AI-driven diagnostic tools.

Purpose of the Study:

To evaluate the explainability and clinical relevance of deep learning models for spinal abnormality classification using X-ray images.
To compare the performance of VGG16 and ResNet50 models trained with different methods (random initialization, feature extraction, fine-tuning).
To assess the alignment of model focus with clinically relevant regions using Grad-CAM heatmaps.

Main Methods:

Trained VGG16 and ResNet50 models using random initialization, feature extraction, and fine-tuning on spinal X-ray images.
Employed Grad-CAM to visualize and interpret the decision-making process of the deep learning models.
Utilized stratified five-fold cross-validation to evaluate model performance and clinical relevance.

Main Results:

Randomly initialized VGG16 achieved 93.79% accuracy but focused on irrelevant regions.
Fine-tuned ResNet50 (98.22% accuracy) and VGG16 (99.12% accuracy) demonstrated high performance and focused on clinically relevant areas.
Grad-CAM heatmaps indicated that fine-tuned ResNet50's focus was more aligned with clinical interpretation than fine-tuned VGG16.

Conclusions:

Explainable AI methods like Grad-CAM enhance the trustworthiness of deep learning models in medical diagnostics.
Fine-tuning deep learning models significantly improves both accuracy and clinical relevance for spinal abnormality classification.
ResNet50, when fine-tuned, shows superior alignment with clinical perspectives compared to VGG16 in this specific application.