STAR-YOLO: A High-Accuracy and Ultra-Lightweight Method for Brain Tumor Detection

Brain tumors are among the deadliest malignant neoplasms worldwide, and early detection is critical for improving treatment outcomes and patient prognosis. Magnetic resonance imaging (MRI) plays a central role in the clinical diagnosis of brain tumors due to its exceptional ability to visualize brai...

Full description

Saved in:
Bibliographic Details
Main Authors: Liyan Sun, Linxuan Zheng, Zhiguo Xiao, Yi Xin, Linqing Jiang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11044341/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849415873253605376
author Liyan Sun
Linxuan Zheng
Zhiguo Xiao
Yi Xin
Linqing Jiang
author_facet Liyan Sun
Linxuan Zheng
Zhiguo Xiao
Yi Xin
Linqing Jiang
author_sort Liyan Sun
collection DOAJ
description Brain tumors are among the deadliest malignant neoplasms worldwide, and early detection is critical for improving treatment outcomes and patient prognosis. Magnetic resonance imaging (MRI) plays a central role in the clinical diagnosis of brain tumors due to its exceptional ability to visualize brain structures and detect tumors. However, traditional MRI detection models for brain tumors often struggle to balance high accuracy with a lightweight design. To address this challenge, this study proposes a novel model—STAR-YOLO—based on the optimization of YOLOv8n. The model refines the backbone network and enhances the C2f module within the neck network. It also integrates SimAM, a parameter-free attention mechanism, and utilizes ShapeIoU as the localization loss function. These innovations enable STAR-YOLO to achieve both high accuracy and a lightweight design. Experimental results on the Br35H public dataset show that STAR-YOLO outperforms existing models, achieving outstanding scores of 0.937 in Precision, 0.852 in Recall, and 0.642 in mAP50–95. Additionally, the model contains only 2.01 million parameters and has a computational complexity of 6.1 GFLOPs, significantly lower than other models. STAR-YOLO accomplishes a lightweight design while guaranteeing high detection accuracy, prominently demonstrating its immense potential in the diagnosis of clinical brain tumors, particularly in circumstances with constrained computing resources.
format Article
id doaj-art-bb924f2c8f9e45a1a55d4c230215fc65
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-bb924f2c8f9e45a1a55d4c230215fc652025-08-20T03:33:21ZengIEEEIEEE Access2169-35362025-01-011310991410993010.1109/ACCESS.2025.358123411044341STAR-YOLO: A High-Accuracy and Ultra-Lightweight Method for Brain Tumor DetectionLiyan Sun0https://orcid.org/0000-0003-2145-6341Linxuan Zheng1https://orcid.org/0009-0007-2674-5704Zhiguo Xiao2Yi Xin3https://orcid.org/0009-0003-5450-9291Linqing Jiang4College of Computer Science and Technology, Changchun University, Changchun, ChinaCollege of Computer Science and Technology, Changchun University, Changchun, ChinaCollege of Computer Science and Technology, Changchun University, Changchun, ChinaCollege of Computer Science and Technology, Changchun University, Changchun, ChinaCollege of Computer Science and Technology, Changchun University, Changchun, ChinaBrain tumors are among the deadliest malignant neoplasms worldwide, and early detection is critical for improving treatment outcomes and patient prognosis. Magnetic resonance imaging (MRI) plays a central role in the clinical diagnosis of brain tumors due to its exceptional ability to visualize brain structures and detect tumors. However, traditional MRI detection models for brain tumors often struggle to balance high accuracy with a lightweight design. To address this challenge, this study proposes a novel model—STAR-YOLO—based on the optimization of YOLOv8n. The model refines the backbone network and enhances the C2f module within the neck network. It also integrates SimAM, a parameter-free attention mechanism, and utilizes ShapeIoU as the localization loss function. These innovations enable STAR-YOLO to achieve both high accuracy and a lightweight design. Experimental results on the Br35H public dataset show that STAR-YOLO outperforms existing models, achieving outstanding scores of 0.937 in Precision, 0.852 in Recall, and 0.642 in mAP50–95. Additionally, the model contains only 2.01 million parameters and has a computational complexity of 6.1 GFLOPs, significantly lower than other models. STAR-YOLO accomplishes a lightweight design while guaranteeing high detection accuracy, prominently demonstrating its immense potential in the diagnosis of clinical brain tumors, particularly in circumstances with constrained computing resources.https://ieeexplore.ieee.org/document/11044341/Accuracybrain tumor detectionlightweightMRISTAR-YOLO
spellingShingle Liyan Sun
Linxuan Zheng
Zhiguo Xiao
Yi Xin
Linqing Jiang
STAR-YOLO: A High-Accuracy and Ultra-Lightweight Method for Brain Tumor Detection
IEEE Access
Accuracy
brain tumor detection
lightweight
MRI
STAR-YOLO
title STAR-YOLO: A High-Accuracy and Ultra-Lightweight Method for Brain Tumor Detection
title_full STAR-YOLO: A High-Accuracy and Ultra-Lightweight Method for Brain Tumor Detection
title_fullStr STAR-YOLO: A High-Accuracy and Ultra-Lightweight Method for Brain Tumor Detection
title_full_unstemmed STAR-YOLO: A High-Accuracy and Ultra-Lightweight Method for Brain Tumor Detection
title_short STAR-YOLO: A High-Accuracy and Ultra-Lightweight Method for Brain Tumor Detection
title_sort star yolo a high accuracy and ultra lightweight method for brain tumor detection
topic Accuracy
brain tumor detection
lightweight
MRI
STAR-YOLO
url https://ieeexplore.ieee.org/document/11044341/
work_keys_str_mv AT liyansun staryoloahighaccuracyandultralightweightmethodforbraintumordetection
AT linxuanzheng staryoloahighaccuracyandultralightweightmethodforbraintumordetection
AT zhiguoxiao staryoloahighaccuracyandultralightweightmethodforbraintumordetection
AT yixin staryoloahighaccuracyandultralightweightmethodforbraintumordetection
AT linqingjiang staryoloahighaccuracyandultralightweightmethodforbraintumordetection