Gabor-Enhanced EfficientNet for Automated Bone Cancer Classification in Pelvic Computed Tomography (CT) Images

Bone cancer classification from computed tomography (CT) images is challenging because abnormal changes in bone structure and texture can be subtle. This study proposes a Gabor-Enhanced EfficientNet model for automated classification of pelvic CT images into Normal and Cancerous categories. The proposed framework first preprocesses the CT images and applies Gabor filtering to enhance directional texture and structural patterns. The Gabor representation is then fused with the original CT image to preserve both anatomical and texture information. The fused images are classified using EfficientNet, which learns discriminative features for binary classification. The effectiveness of the proposed model is evaluated using a comprehensive set of performance indicators, namely accuracy, precision, sensitivity, specificity, F1-score, and Matthews correlation coefficient. The proposed method combines Gabor-based texture features with deep learning for bone cancer classification from CT images.

Authors

Publication Details

Journal
Cureus Journal of Computer Science.
Published
2026-11-17
DOI
https://doi.org/10.7759/s44389-026-00375-6
Primary Topic
Radiomics and Machine Learning in Medical Imaging
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Gabor-Enhanced EfficientNet for Automated Bone Cancer Classification in Pelvic Computed Tomography (CT) Images

Vibhakar Mansotra, Paramjit Kour
4 links
Cureus Journal of Computer Science.
Radiomics and Machine Learning in Medical Imaging
article

Gabor-Enhanced EfficientNet for Automated Bone Cancer Classification in Pelvic Computed Tomography (CT) Images

Vibhakar Mansotra, Paramjit Kour
article en

Abstract

Bone cancer classification from computed tomography (CT) images is challenging because abnormal changes in bone structure and texture can be subtle. This study proposes a Gabor-Enhanced EfficientNet model for automated classification of pelvic CT images into Normal and Cancerous categories. The proposed framework first preprocesses the CT images and applies Gabor filtering to enhance directional texture and structural patterns. The Gabor representation is then fused with the original CT image to preserve both anatomical and texture information. The fused images are classified using EfficientNet, which learns discriminative features for binary classification. The effectiveness of the proposed model is evaluated using a comprehensive set of performance indicators, namely accuracy, precision, sensitivity, specificity, F1-score, and Matthews correlation coefficient. The proposed method combines Gabor-based texture features with deep learning for bone cancer classification from CT images.

Cureus Journal of Computer Science.
Good health and well-being
Radiomics and Machine Learning in Medical Imaging
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon