Current Volume 8
Abstract
Deep learning is a type of artificial intelligence that helps computers analyze medical images, such as brain scans, to detect tumors. This is because brain tumors can look very similar to normal tissue, making them hard to spot. In this study, we use a powerful AI model called YOLOv12, which is known for its speed and accuracy in detecting objects in images. To improve its performance, we introduce two special techniques: RGNet and GDB. RGNet helps the model recognize tumors of different sizes and textures more effectively, while GDB helps combine important details from different parts of the image to avoid missing information. For training and testing, we use the Ultralytics Brain Tumor Dataset, which contains many labeled brain scans with different types of tumors. This dataset is challenging because it includes images with complex backgrounds and variations in brightness, making it a great test for our model. Our goal is to make tumor detection faster and more reliable, which can help doctors in diagnosing patients more efficiently. By using advanced deep learning techniques, our model provides a strong step forward in automated medical image analysis. The YOLOv12 framework is a promising tool that can improve medical imaging and potentially be used in other healthcare applications as well.
Keywords
Deep Learning, Brain Tumor Detection, YOLOv12, Ultralytics Brain Tumor Dataset, Feature Extraction
Citations
IRE Journals:
Vemula Keerthi , Netha Keerthideva , Sandhi Anusha , Chalamani Bhavana
"Brain Tumor Detection from Medical Images Using YOLOv12 Algorithm" Iconic Research And Engineering Journals Volume 8 Issue 11 2025 Page 981-986
IEEE:
Vemula Keerthi , Netha Keerthideva , Sandhi Anusha , Chalamani Bhavana
"Brain Tumor Detection from Medical Images Using YOLOv12 Algorithm" Iconic Research And Engineering Journals, 8(11)
About IRE Journals
IRE Journals is an open access online journals established with an aim to publish high quality of research work in various diciplines. We have more than 6 years in publications. Over 2500+ papers already published.
Important Links
For Authors
Volume 7:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 6:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 5:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 4:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 3:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12