Graph-based methods for cervical cancer segmentation: Advancements, limitations, and future directions
Cervical cancer remains a significant health concern worldwide, where precise segmentation of cervical lesions is integral for effective diagnosis and treatment planning. This systematic review critically evaluates the application of graph-based methodologies for cervical cancer segmentation, identi...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co. Ltd.
2023-01-01
|
Series: | AI Open |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666651023000086 |
_version_ | 1797378624543784960 |
---|---|
author | Nazar Zaki Wenjian Qin Anusuya Krishnan |
author_facet | Nazar Zaki Wenjian Qin Anusuya Krishnan |
author_sort | Nazar Zaki |
collection | DOAJ |
description | Cervical cancer remains a significant health concern worldwide, where precise segmentation of cervical lesions is integral for effective diagnosis and treatment planning. This systematic review critically evaluates the application of graph-based methodologies for cervical cancer segmentation, identifying their potential, drawbacks, and avenues for future development. An exhaustive literature search across Scopus and PubMed databases resulted in 20 pertinent studies. These studies were assessed focusing on their implementation of graph-based techniques for cervical cancer segmentation, the utilized datasets, evaluation metrics, and reported precision levels. The review highlights the progressive strides made in the field, especially regarding the segmentation of intricate, non-convex regions and facilitating the detection and grading of cervical cancer using graph-based methodologies. Nonetheless, several constraints were evident, including a dearth of comparative performance analysis, reliance on high-resolution images, difficulties in specific boundary delineation, and the imperative for additional validation and diversified datasets. The review suggests future work to integrate advanced deep learning strategies for heightened accuracy, formulate hybrid methodologies to counteract existing limitations, and explore multi-modal fusion to boost segmentation precision. Emphasizing the explainability and interpretability of outcomes also stands paramount. Lastly, addressing critical challenges such as scarcity of annotated data, the need for real-time and interactive segmentation, and the segmentation of multiple objects or regions of interest remains a crucial frontier for future endeavors. |
first_indexed | 2024-03-08T20:10:23Z |
format | Article |
id | doaj.art-b05d7eed44494ec4a2dcc1a80d88d4bd |
institution | Directory Open Access Journal |
issn | 2666-6510 |
language | English |
last_indexed | 2024-03-08T20:10:23Z |
publishDate | 2023-01-01 |
publisher | KeAi Communications Co. Ltd. |
record_format | Article |
series | AI Open |
spelling | doaj.art-b05d7eed44494ec4a2dcc1a80d88d4bd2023-12-23T05:22:53ZengKeAi Communications Co. Ltd.AI Open2666-65102023-01-0144255Graph-based methods for cervical cancer segmentation: Advancements, limitations, and future directionsNazar Zaki0Wenjian Qin1Anusuya Krishnan2Dept. of Computer Science and Software Eng., College of Info. Technology, United Arab Emirates University, Ai Ain, 15551, United Arab Emirates; Corresponding author.Shenzhen Institute of Advanced Technology, Chinese Academy of Science, 1068 Xueyuan Boulevard, University Town of Shenzhen, Xili Nanshan, Shenzhen, 518055, ChinaDept. of Computer Science and Software Eng., College of Info. Technology, United Arab Emirates University, Ai Ain, 15551, United Arab EmiratesCervical cancer remains a significant health concern worldwide, where precise segmentation of cervical lesions is integral for effective diagnosis and treatment planning. This systematic review critically evaluates the application of graph-based methodologies for cervical cancer segmentation, identifying their potential, drawbacks, and avenues for future development. An exhaustive literature search across Scopus and PubMed databases resulted in 20 pertinent studies. These studies were assessed focusing on their implementation of graph-based techniques for cervical cancer segmentation, the utilized datasets, evaluation metrics, and reported precision levels. The review highlights the progressive strides made in the field, especially regarding the segmentation of intricate, non-convex regions and facilitating the detection and grading of cervical cancer using graph-based methodologies. Nonetheless, several constraints were evident, including a dearth of comparative performance analysis, reliance on high-resolution images, difficulties in specific boundary delineation, and the imperative for additional validation and diversified datasets. The review suggests future work to integrate advanced deep learning strategies for heightened accuracy, formulate hybrid methodologies to counteract existing limitations, and explore multi-modal fusion to boost segmentation precision. Emphasizing the explainability and interpretability of outcomes also stands paramount. Lastly, addressing critical challenges such as scarcity of annotated data, the need for real-time and interactive segmentation, and the segmentation of multiple objects or regions of interest remains a crucial frontier for future endeavors.http://www.sciencedirect.com/science/article/pii/S2666651023000086Cervical cancerGraph-based methodsImage segmentationGeometric deep learningGraph attention networks |
spellingShingle | Nazar Zaki Wenjian Qin Anusuya Krishnan Graph-based methods for cervical cancer segmentation: Advancements, limitations, and future directions AI Open Cervical cancer Graph-based methods Image segmentation Geometric deep learning Graph attention networks |
title | Graph-based methods for cervical cancer segmentation: Advancements, limitations, and future directions |
title_full | Graph-based methods for cervical cancer segmentation: Advancements, limitations, and future directions |
title_fullStr | Graph-based methods for cervical cancer segmentation: Advancements, limitations, and future directions |
title_full_unstemmed | Graph-based methods for cervical cancer segmentation: Advancements, limitations, and future directions |
title_short | Graph-based methods for cervical cancer segmentation: Advancements, limitations, and future directions |
title_sort | graph based methods for cervical cancer segmentation advancements limitations and future directions |
topic | Cervical cancer Graph-based methods Image segmentation Geometric deep learning Graph attention networks |
url | http://www.sciencedirect.com/science/article/pii/S2666651023000086 |
work_keys_str_mv | AT nazarzaki graphbasedmethodsforcervicalcancersegmentationadvancementslimitationsandfuturedirections AT wenjianqin graphbasedmethodsforcervicalcancersegmentationadvancementslimitationsandfuturedirections AT anusuyakrishnan graphbasedmethodsforcervicalcancersegmentationadvancementslimitationsandfuturedirections |