Effectiveness of encoder-decoder deep learning approach for colorectal polyp segmentation in colonoscopy images

被引:0
作者
Hamza, Ameer [1 ]
Bilal, Muhammad [2 ,3 ]
Ramzan, Muhammad [4 ]
Malik, Nadia [4 ,5 ]
机构
[1] Univ Sargodha, Fac Comp & IT, Dept Comp Sci, Sargodha 40100, Pakistan
[2] Univ Florida, Dept Pharmaceut Outcomes & Policy, Gainesville, FL 32610 USA
[3] Natl Univ Comp & Emerging Sci, Dept Software Engn, Islamabad 44000, Pakistan
[4] Univ Sargodha, Fac Comp & Informat Technol, Dept Software Engn, Sargodha 40100, Pakistan
[5] COMSATS Univ Islamabad, Dept Management Sci, Islamabad 45550, Pakistan
关键词
Medical Image Segmentation; Semantic Segmentation; Polyp Segmentation; Deep Learning; Kvasir-SEG; CVC-ClinicDB; MISS RATE; NETWORK;
D O I
10.1007/s10489-024-06167-6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Colorectal cancer is considered one of the deadliest diseases, contributing to an alarming increase in annual deaths worldwide, with colorectal polyps recognized as precursors to this malignancy. Early and accurate detection of these polyps is crucial for reducing the mortality rate of colorectal cancer. However, the manual detection of polyps is a time-consuming process and requires the expertise of trained medical professionals. Moreover, it often misses polyps due to their varied size, color, and texture. Computer-aided diagnosis systems offer potential improvements, but they often struggle with precision in complex visual environments. This study presents an enhanced deep learning approach using encoder-decoder architecture for colorectal polyp segmentation to capture and utilize complex feature representations. Our approach introduces an enhanced dual attention mechanism, combining spatial and channel-wise attention to focus precisely on critical features. Channel-wise attention, implemented via an optimized Squeeze-and-Excitation (S&E) block, allows the network to capture comprehensive contextual information and interrelationships among different channels, ensuring a more refined feature selection process. The experimental results showed that the proposed model achieved a mean Intersection over Union (IoU) of 0.9054 and 0.9277, a dice coefficient of 0.9006 and 0.9128, a precision of 0.8985 and 0.9517, a recall of 0.9190 and 0.9094, and an accuracy of 0.9806 and 0.9907 on the Kvasir-SEG and CVC-ClinicDB datasets, respectively. Moreover, the proposed model outperforms the existing state-of-the-art resulting in improved patient outcomes with the potential to enhance the early detection of colorectal polyps.
引用
收藏
页数:24
相关论文
共 50 条
[21]   A Deep Convolutional Encoder-Decoder Architecture for Retinal Blood Vessels Segmentation [J].
Adeyinka, Adegun Adekanmi ;
Adebiyi, Marion Olubunmi ;
Akande, Noah Oluwatobi ;
Ogundokun, Roseline Oluwaseun ;
Kayode, Anthonia Aderonke ;
Oladele, Tinuke Omolewa .
COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2019, PT V: 19TH INTERNATIONAL CONFERENCE, SAINT PETERSBURG, RUSSIA, JULY 14, 2019, PROCEEDINGS, PART V, 2019, 11623 :180-189
[22]   Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network [J].
Shahzad, Muhammad ;
Umar, Arif Iqbal ;
Shirazi, Syed Hamad ;
Shaikh, Israr Ahmed .
IEEE ACCESS, 2021, 9 :161326-161341
[23]   A multimodal deep learning approach for hurricane tack forecast based on encoder-decoder framework [J].
Wang, Wennan ;
Lu, Jiadong ;
Zhu, Linkai ;
Dai, Shugeng ;
Song, Shiyang .
PATTERN ANALYSIS AND APPLICATIONS, 2024, 27 (04)
[24]   An encoder-decoder deep learning method for multi-class object segmentation from 3D tunnel point clouds [J].
Ji, Ankang ;
Chew, Alvin Wei Ze ;
Xue, Xiaolong ;
Zhang, Limao .
AUTOMATION IN CONSTRUCTION, 2022, 137
[25]   SAS-UNet: Modified encoder-decoder network for the segmentation of obscenity in images [J].
Samal, Sonali ;
Gadekellu, Thippa Reddy ;
Rajput, Pankaj ;
Zhang, Yu-Dong ;
Balabantaray, Bunil Kumar .
2023 IEEE/ACM 23RD INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND INTERNET COMPUTING WORKSHOPS, CCGRIDW, 2023, :45-51
[26]   Encoder-Decoder With Cascaded CRFs for Semantic Segmentation [J].
Ji, Jian ;
Shi, Rui ;
Li, Sitong ;
Chen, Peng ;
Miao, Qiguang .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2021, 31 (05) :1926-1938
[27]   Automatic delamination segmentation for bridge deck based on encoder-decoder deep learning through UAV-based thermography [J].
Cheng, Chongsheng ;
Shang, Zhexiong ;
Shen, Zhigang .
NDT & E INTERNATIONAL, 2020, 116
[28]   HeteroNet: a heterogeneous encoder-decoder network for sea-land segmentation of remote sensing images [J].
Ji, Xun ;
Tang, Longbin ;
Liu, Tianhe ;
Guo, Hui .
JOURNAL OF ELECTRONIC IMAGING, 2023, 32 (05)
[29]   Boundary Refinement Network for Colorectal Polyp Segmentation in Colonoscopy Images [J].
Yue, Guanghui ;
Li, Yuanyan ;
Jiang, Wenchao ;
Zhou, Wei ;
Zhou, Tianwei .
IEEE SIGNAL PROCESSING LETTERS, 2024, 31 :954-958
[30]   Polyp Segmentation of Colonoscopy Images by Exploring the Uncertain Areas [J].
Guo, Qingqing ;
Fang, Xianyong ;
Wang, Linbo ;
Zhang, Enming .
IEEE ACCESS, 2022, 10 :52971-52981