TechRxiv
UNET__MobileNetV2_Segmentation_Model_for_an_Early_Breast_Cancer_Detection _IkramBA.pdf (1.27 MB)
Download file

Hybrid UNET Model Segmentation for an Early Breast Cancer Detection using Ulrasound Images

Download (1.27 MB)
preprint
posted on 10.05.2022, 08:54 by Ikram BEN AHMEDIkram BEN AHMED
. In this paper, we present a deep learning framework built on the U-Net architecture. We used a MobileNetV2 and a VGG16 model encoder to handle the semantic segmentation of a biomedical image effectively. This approach is based on the integration of these pre-trained models with the UNet and having an efficient network architecture. By transfer learning, these CNNs are fine-tuned to segment Breast Ultrasound images in normal and tumoral pixels. An extensive experiment of our proposed architecture has been done using Breast Ultrasound Dataset B. Quantitative metrics for evalu?ation of segmentation results including Dice coefficient, Precision, Recall, and , all reached over 80% , which indicates that the method proposed has the capacity to distinguish functional tissues in breast ultrasound images. Thus, our proposed method might have the potential to pro?vide the segmentations necessary to assist the clinical diagnosis of breast cancer and improve imaging in other modes in medical ultrasound.

History

Email Address of Submitting Author

benahmedikram@gmail.com

Submitting Author's Institution

Higher Institute of Computer Science and Communication Technology (IsitCom)

Submitting Author's Country

Tunisia