Segmentation of ovarian cyst using improved U-NET and hybrid deep learning model

被引:0
|
作者
Kamala C
Joshi Manisha Shivaram
机构
[1] Dr. Ambedkar Institute of Technology,Department of Medical Electronics
[2] B.M.S College of Engineering,Department of Medical Electronics
来源
关键词
Ovarian cancer; Ultrasound detection; Deep learning model; Image enhancement; Cystic ovary; Segmentation; U-Net model; Seagull optimization algorithm; Bilateral filter;
D O I
暂无
中图分类号
学科分类号
摘要
The female reproductive system relies on the ovaries to produce eggs, but ovarian cysts can lead to complications such as torsion, infertility, and cancer, making it essential to diagnose them quickly. Ultrasound images are commonly used to detect ovarian cysts, but segmenting cyst regions from the surrounding tissue poses a challenge due to complex patterns and similar intensities. Few methods use the background's texture information to facilitate foreground segmentation. Ultrasound images include characters like speckle noise, low contrast appearance, and blurry boundaries that further complicate the task. Lesion shape and position variations exacerbate these challenges. This study proposes an improved deep learning-based segmentation technique using a database of ovarian ultrasound cyst images to overcome these issues. At the outset, the input has undergone pre-processing using non-sub-sampled contourlet domain-based cross-guided bilateral filtering (CGBF) and improved U-Net (IU-NET) for image segmentation. The presented architecture involved reducing the intricacy of U-Net through the alleviation of certain parameters. This resulted in a substantial acceleration of the learning process, by a factor of 100. To optimize the improved U-Net model, the Seagull Optimization Algorithm (SOA) was used. The algorithm helped to fine-tune the hyper-parameters of the U-Net architecture, including the batch size, learning rate, and epoch count, to achieve optimal performance. The optimization was performed by solving an objective function, which involved determining the dice loss coefficient (DLC) and weight cross-entropy (WCE). A numerical analysis was conducted, which demonstrated that the proposed methodology outperforms existing methods in terms of segmentation accuracy. The proposed model achieved a pixel accuracy of 99.36%, which was significantly higher than that achieved by existing methods.
引用
收藏
页码:42645 / 42679
页数:34
相关论文
共 50 条
  • [1] Segmentation of ovarian cyst using improved U-NET and hybrid deep learning model
    Kamala, C.
    Shivaram, Joshi Manisha
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (14) : 42645 - 42679
  • [2] Segmentation and Classification of Glaucoma Using U-Net with Deep Learning Model
    Sudhan, M. B.
    Sinthuja, M.
    Raja, S. Pravinth
    Amutharaj, J.
    Latha, G. Charlyn Pushpa
    Rachel, S. Sheeba
    Anitha, T.
    Rajendran, T.
    Waji, Yosef Asrat
    [J]. JOURNAL OF HEALTHCARE ENGINEERING, 2022, 2022
  • [3] Image Segmentation of Rectal Tumor Based on Improved U-Net Model with Deep Learning
    Faguo Zhou
    Yuansheng Ye
    Yanan Song
    [J]. Journal of Signal Processing Systems, 2022, 94 : 1145 - 1157
  • [4] Image Segmentation of Rectal Tumor Based on Improved U-Net Model with Deep Learning
    Zhou, Faguo
    Ye, Yuansheng
    Song, Yanan
    [J]. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2022, 94 (11): : 1145 - 1157
  • [5] Glaucoma Detection and Classification Using Improved U-Net Deep Learning Model
    Kashyap, Ramgopal
    Nair, Rajit
    Gangadharan, Syam Machinathu Parambil
    Botto-Tobar, Miguel
    Farooq, Saadia
    Rizwan, Ali
    [J]. HEALTHCARE, 2022, 10 (12)
  • [6] A Fundus Retinal Vessels Segmentation Scheme Based on the Improved Deep Learning U-Net Model
    Pan, Xiuqin
    Zhang, Qinrui
    Zhang, Hong
    Li, Sumin
    [J]. IEEE ACCESS, 2019, 7 : 122634 - 122643
  • [7] Improved U-Net Model for Nerve Segmentation
    Zhao, Houlong
    Sun, Nongliang
    [J]. IMAGE AND GRAPHICS (ICIG 2017), PT II, 2017, 10667 : 496 - 504
  • [8] Semantic segmentation and detection of satellite objects using U-Net model of deep learning
    Yadavendra
    Chand, Satish
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (30) : 44291 - 44310
  • [9] Semantic segmentation and detection of satellite objects using U-Net model of deep learning
    Satish Yadavendra
    [J]. Multimedia Tools and Applications, 2022, 81 : 44291 - 44310
  • [10] Cyst segmentation on kidney tubules by means of U-Net deep-learning models
    Monaco, Simone
    Bussola, Nicole
    Butto, Sara
    Sona, Diego
    Apiletti, Daniele
    Jurman, Giuseppe
    Viola, Elisa
    Chierici, Marco
    Xinaris, Christodoulos
    Viola, Vincenzo
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2021, : 3923 - 3926