Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning Approaches

Osteosarcoma is an aggressive and highly malignant bone cancer primarily affecting adolescents and young adults, with males being more commonly affected. Although deep learning models such as YOLO (95.73% accuracy) and VGG19 (95.25% accuracy), have demonstrated effectiveness in osteosarcoma detectio...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Ainul Fikri, Ajie Kusuma Wardhana, Yudha Riwanto, Inggrid Yanuar Risca Partiwi, Fauzia Sekar Anis Sekar Ningrum, Iqbal Kurniawan Asmar Putra
Format: Article
Language:English
Published: State Islamic University Sunan Kalijaga 2025-02-01
Series:IJID (International Journal on Informatics for Development)
Subjects:
Online Access:https://ejournal.uin-suka.ac.id/saintek/ijid/article/view/4890
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849700976946053120
author Muhammad Ainul Fikri
Ajie Kusuma Wardhana
Yudha Riwanto
Inggrid Yanuar Risca Partiwi
Fauzia Sekar Anis Sekar Ningrum
Iqbal Kurniawan Asmar Putra
author_facet Muhammad Ainul Fikri
Ajie Kusuma Wardhana
Yudha Riwanto
Inggrid Yanuar Risca Partiwi
Fauzia Sekar Anis Sekar Ningrum
Iqbal Kurniawan Asmar Putra
author_sort Muhammad Ainul Fikri
collection DOAJ
description Osteosarcoma is an aggressive and highly malignant bone cancer primarily affecting adolescents and young adults, with males being more commonly affected. Although deep learning models such as YOLO (95.73% accuracy) and VGG19 (95.25% accuracy), have demonstrated effectiveness in osteosarcoma detection, their large model sizes and extensive computational requirements limit their feasibility in resource-constrained environments. This study proposes a lightweight AI approach that optimizes osteosarcoma detection while maintaining high diagnostic accuracy, leveraging machine learning models under 5MB, manually or semi-automatically extracted features, and SMOTE for data balancing. Experimental results show that Random Forest, SVM, and XGBoost achieve accuracies of 94.70%, 94.23%, and 94.39%, respectively, closely matching the performance of YOLO and VGG19 while maintaining computational efficiency. Furthermore, the inference time for SVM is under one second (0.97s), demonstrating the speed advantage of lightweight models. These findings highlight the potential of small-size (lightweight) machine learning models to deliver high diagnostic accuracy with minimal computational requirements, providing a scalable and practical solution for early osteosarcoma detection in resource-limited settings. By balancing simplicity, efficiency, and high performance, this study establishes a new benchmark for achieving state-of-the-art results with lightweight models and paving the way for improved healthcare accessibility in underserved regions.
format Article
id doaj-art-c92d372e04774d2f926152bf7516993c
institution DOAJ
issn 2252-7834
2549-7448
language English
publishDate 2025-02-01
publisher State Islamic University Sunan Kalijaga
record_format Article
series IJID (International Journal on Informatics for Development)
spelling doaj-art-c92d372e04774d2f926152bf7516993c2025-08-20T03:18:05ZengState Islamic University Sunan KalijagaIJID (International Journal on Informatics for Development)2252-78342549-74482025-02-0113251752910.14421/ijid.2024.48904515Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning ApproachesMuhammad Ainul FikriAjie Kusuma WardhanaYudha RiwantoInggrid Yanuar Risca PartiwiFauzia Sekar Anis Sekar NingrumIqbal Kurniawan Asmar PutraOsteosarcoma is an aggressive and highly malignant bone cancer primarily affecting adolescents and young adults, with males being more commonly affected. Although deep learning models such as YOLO (95.73% accuracy) and VGG19 (95.25% accuracy), have demonstrated effectiveness in osteosarcoma detection, their large model sizes and extensive computational requirements limit their feasibility in resource-constrained environments. This study proposes a lightweight AI approach that optimizes osteosarcoma detection while maintaining high diagnostic accuracy, leveraging machine learning models under 5MB, manually or semi-automatically extracted features, and SMOTE for data balancing. Experimental results show that Random Forest, SVM, and XGBoost achieve accuracies of 94.70%, 94.23%, and 94.39%, respectively, closely matching the performance of YOLO and VGG19 while maintaining computational efficiency. Furthermore, the inference time for SVM is under one second (0.97s), demonstrating the speed advantage of lightweight models. These findings highlight the potential of small-size (lightweight) machine learning models to deliver high diagnostic accuracy with minimal computational requirements, providing a scalable and practical solution for early osteosarcoma detection in resource-limited settings. By balancing simplicity, efficiency, and high performance, this study establishes a new benchmark for achieving state-of-the-art results with lightweight models and paving the way for improved healthcare accessibility in underserved regions.https://ejournal.uin-suka.ac.id/saintek/ijid/article/view/4890lightweight machine learningmedical diagnostic osteosarcoma detectionrandom forestsmote
spellingShingle Muhammad Ainul Fikri
Ajie Kusuma Wardhana
Yudha Riwanto
Inggrid Yanuar Risca Partiwi
Fauzia Sekar Anis Sekar Ningrum
Iqbal Kurniawan Asmar Putra
Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning Approaches
IJID (International Journal on Informatics for Development)
lightweight machine learning
medical diagnostic
osteosarcoma detection
random forest
smote
title Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning Approaches
title_full Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning Approaches
title_fullStr Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning Approaches
title_full_unstemmed Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning Approaches
title_short Improving Osteosarcoma Detection through SMOTE-Driven Machine Learning Approaches
title_sort improving osteosarcoma detection through smote driven machine learning approaches
topic lightweight machine learning
medical diagnostic
osteosarcoma detection
random forest
smote
url https://ejournal.uin-suka.ac.id/saintek/ijid/article/view/4890
work_keys_str_mv AT muhammadainulfikri improvingosteosarcomadetectionthroughsmotedrivenmachinelearningapproaches
AT ajiekusumawardhana improvingosteosarcomadetectionthroughsmotedrivenmachinelearningapproaches
AT yudhariwanto improvingosteosarcomadetectionthroughsmotedrivenmachinelearningapproaches
AT inggridyanuarriscapartiwi improvingosteosarcomadetectionthroughsmotedrivenmachinelearningapproaches
AT fauziasekaranissekarningrum improvingosteosarcomadetectionthroughsmotedrivenmachinelearningapproaches
AT iqbalkurniawanasmarputra improvingosteosarcomadetectionthroughsmotedrivenmachinelearningapproaches