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

Search research articles

Related Experiment Video

Updated: Feb 28, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Bone-CNN: A Lightweight Deep Learning Architecture for Multi-Class Classification of Primary Bone Tumours in

Behnam Kiani Kalejahi¹, Sajid Khan¹, Rakhim Zakirov²

¹Computer Science Department, School of Engineering, Central Asian University, Tashkent 111221, Uzbekistan.

|February 27, 2026

Summary

This summary is machine-generated.

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...

You might also read

Related Articles

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

Sort by

Same author

Galeal scoring for salvage scalp closure following cranioplasty failure: a case report.

BMC neurology·2026

Same author

The Combination of a BCL-xL PROTAC and an mTOR Inhibitor Sensitizes Pancreatic Ductal Adenocarcinoma to KRAS<sup>G12D</sup> Inhibitor Treatment.

Cancers·2026

Same author

GAN-Based Cross-Modality Brain MRI Synthesis: Paired Versus Unpaired Training and Comparison with Diffusion and Transformer Models.

Biomimetics (Basel, Switzerland)·2026

Same author

Editorial: The ubiquitin-proteasome system and cellular signaling: mechanisms and regulatory roles in cancer and infectious diseases.

Frontiers in cell and developmental biology·2026

Same author

Stem Cells and their Key Derivatives in Degenerative Musculoskeletal Diseases.

Stem cell reviews and reports·2026

Same author

The combination of BCL-xL PROTAC and mTOR inhibitor sensitizes pancreatic ductal adenocarcinoma to KRAS<sup>G12D</sup> inhibitor treatment by enhancing apoptosis induction.

bioRxiv : the preprint server for biology·2026

A new lightweight deep learning model, Bone-CNN, accurately classifies primary bone tumors from radiographs with 96.52% accuracy. This efficient model is suitable for clinical deployment, improving bone tumor diagnosis.

Area of Science:

Medical imaging analysis
Artificial intelligence in oncology

Background:

Accurate classification of primary bone tumors from radiographs is crucial for patient management.
Deep convolutional neural networks (CNNs) show promise but often face computational challenges in clinical settings.

Purpose of the Study:

To develop a computationally efficient yet highly accurate deep learning model for multi-class primary bone tumor classification from radiographs.
To address the limitations of complex models in real-world clinical applications.

Main Methods:

Proposed Bone-CNN, a lightweight CNN architecture tailored for bone tumor classification.
Evaluated the model on the Figshare Radiograph Dataset of Primary Bone Tumors (nine classes).
Compared Bone-CNN performance against DenseNet121, EfficientNet-B0, and MobileNetV2.

Keywords:

bone-CNN deep learning lightweight CNN architecture primary bone tumours radiograph classification

Related Experiment Videos

Last Updated: Feb 28, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Main Results:

Bone-CNN achieved a test accuracy of 96.52% and a macro-AUC of 0.9989.
Outperformed established baseline models in classification accuracy.
Demonstrated robust discrimination between tumor subtypes through quantitative and qualitative analyses.

Conclusions:

Bone-CNN provides a strong balance between diagnostic accuracy and computational efficiency.
The lightweight design makes Bone-CNN suitable for clinical deployment.
Supports scalable and effective radiograph-based assessment of primary bone tumors.