Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-Means
Ganglion cysts are common soft tissue masses of the hand and wrist, and small size cysts are often hypoechoic. Thus, identifying them from ultrasonography is not an easy problem. In this paper, we propose an automatic segmentation method using two artificial intelligence algorithms in sequence. A de...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/12/2329 |
| _version_ | 1797505445390188544 |
|---|---|
| author | Kwang Baek Kim Doo Heon Song Hyun Jun Park |
| author_facet | Kwang Baek Kim Doo Heon Song Hyun Jun Park |
| author_sort | Kwang Baek Kim |
| collection | DOAJ |
| description | Ganglion cysts are common soft tissue masses of the hand and wrist, and small size cysts are often hypoechoic. Thus, identifying them from ultrasonography is not an easy problem. In this paper, we propose an automatic segmentation method using two artificial intelligence algorithms in sequence. A density based unsupervised learning algorithm called DBSCAN is performed as a front-end and its result determines the number of clusters used in the Fuzzy C-Means (FCM) clustering algorithm for quantification of ganglion cyst object. In an experiment using 120 images, the proposed method shows a higher extraction rate (89.2%) and lower false positive rate compared with FCM when the ground truth is set as the human expert’s decision. Such human-like behavior is more apparent when the size of the ganglion cyst is small that the quality of ultrasonography is often not very high. With this fully automatic segmentation method, the operator subjectivity that is highly dependent on the experience of the ultrasound examiner can be mitigated with high reliability. |
| first_indexed | 2024-03-10T04:18:41Z |
| format | Article |
| id | doaj.art-1f93609277174554ba3087555c18ee04 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T04:18:41Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-1f93609277174554ba3087555c18ee042023-11-23T07:54:32ZengMDPI AGDiagnostics2075-44182021-12-011112232910.3390/diagnostics11122329Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-MeansKwang Baek Kim0Doo Heon Song1Hyun Jun Park2Department of Artificial Intelligence, Silla University, Busan 46958, KoreaDepartment of Computer Games, Yong-In Art and Science University, Yongin 17145, KoreaDivision of Software Convergence, Cheongju University, Cheongju 28503, KoreaGanglion cysts are common soft tissue masses of the hand and wrist, and small size cysts are often hypoechoic. Thus, identifying them from ultrasonography is not an easy problem. In this paper, we propose an automatic segmentation method using two artificial intelligence algorithms in sequence. A density based unsupervised learning algorithm called DBSCAN is performed as a front-end and its result determines the number of clusters used in the Fuzzy C-Means (FCM) clustering algorithm for quantification of ganglion cyst object. In an experiment using 120 images, the proposed method shows a higher extraction rate (89.2%) and lower false positive rate compared with FCM when the ground truth is set as the human expert’s decision. Such human-like behavior is more apparent when the size of the ganglion cyst is small that the quality of ultrasonography is often not very high. With this fully automatic segmentation method, the operator subjectivity that is highly dependent on the experience of the ultrasound examiner can be mitigated with high reliability.https://www.mdpi.com/2075-4418/11/12/2329ganglion cystfuzzy C-meansDBSCANmachine learningpixel clustering |
| spellingShingle | Kwang Baek Kim Doo Heon Song Hyun Jun Park Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-Means Diagnostics ganglion cyst fuzzy C-means DBSCAN machine learning pixel clustering |
| title | Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-Means |
| title_full | Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-Means |
| title_fullStr | Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-Means |
| title_full_unstemmed | Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-Means |
| title_short | Intelligent Automatic Segmentation of Wrist Ganglion Cysts Using DBSCAN and Fuzzy C-Means |
| title_sort | intelligent automatic segmentation of wrist ganglion cysts using dbscan and fuzzy c means |
| topic | ganglion cyst fuzzy C-means DBSCAN machine learning pixel clustering |
| url | https://www.mdpi.com/2075-4418/11/12/2329 |
| work_keys_str_mv | AT kwangbaekkim intelligentautomaticsegmentationofwristganglioncystsusingdbscanandfuzzycmeans AT dooheonsong intelligentautomaticsegmentationofwristganglioncystsusingdbscanandfuzzycmeans AT hyunjunpark intelligentautomaticsegmentationofwristganglioncystsusingdbscanandfuzzycmeans |