Adaptive Refinement of Segmented Object Contour Based on the Brightness of Neighboring Pixels Using the Ensemble Method
Improving the accuracy of computer vision algorithms plays a significant role in the tasks of medical image segmentation. After all, determining the boundaries of objects is a difficult task when using medical images, and especially X-ray images. The use of X-ray images in segmentation tasks is a co...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
NAS of Ukraine, A. Pidhornyi Institute of Mechanical Engineering Problems
2024-12-01
|
| Series: | Journal of Mechanical Engineering |
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832086657367539712 |
|---|---|
| author | Vladyslav D. Koniukhov |
| author_facet | Vladyslav D. Koniukhov |
| author_sort | Vladyslav D. Koniukhov |
| collection | DOAJ |
| description | Improving the accuracy of computer vision algorithms plays a significant role in the tasks of medical image segmentation. After all, determining the boundaries of objects is a difficult task when using medical images, and especially X-ray images. The use of X-ray images in segmentation tasks is a complex process, since these images themselves can have a sufficient amount of noise and artifacts. Classical segmentation methods face significant challenges when segmenting X-ray images where there are objects with fuzzy boundaries. To solve such tasks, it is suggested to use segmentation with the help of machine learning, and to increase the accuracy of determining the boundaries of objects, it is necessary to use adaptive approaches. This paper proposes a new method to improve the accuracy of X-ray image segmentation, which analyzes the neighboring pixels of each contour element and adaptively reshapes it if necessary, and then combines all predictions using an ensemble method, which improves the previous version of the contour. The method was able to demonstrate an improvement in the quality of image segmentation on three datasets with different complexity of structures. Improvements in object boundary accuracy were obtained for all three sets. |
| format | Article |
| id | doaj-art-731a86e575314f5687530aff7720fd1d |
| institution | Kabale University |
| issn | 2709-2984 2709-2992 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | NAS of Ukraine, A. Pidhornyi Institute of Mechanical Engineering Problems |
| record_format | Article |
| series | Journal of Mechanical Engineering |
| spelling | doaj-art-731a86e575314f5687530aff7720fd1d2025-02-06T09:59:11ZengNAS of Ukraine, A. Pidhornyi Institute of Mechanical Engineering ProblemsJournal of Mechanical Engineering2709-29842709-29922024-12-01274737810.15407/pmach2024.04.073Adaptive Refinement of Segmented Object Contour Based on the Brightness of Neighboring Pixels Using the Ensemble MethodVladyslav D. Koniukhov0https://orcid.org/0009-0007-0256-1388Anatolii Pidhornyi Institute of Power Machines and Systems of NAS of UkraineImproving the accuracy of computer vision algorithms plays a significant role in the tasks of medical image segmentation. After all, determining the boundaries of objects is a difficult task when using medical images, and especially X-ray images. The use of X-ray images in segmentation tasks is a complex process, since these images themselves can have a sufficient amount of noise and artifacts. Classical segmentation methods face significant challenges when segmenting X-ray images where there are objects with fuzzy boundaries. To solve such tasks, it is suggested to use segmentation with the help of machine learning, and to increase the accuracy of determining the boundaries of objects, it is necessary to use adaptive approaches. This paper proposes a new method to improve the accuracy of X-ray image segmentation, which analyzes the neighboring pixels of each contour element and adaptively reshapes it if necessary, and then combines all predictions using an ensemble method, which improves the previous version of the contour. The method was able to demonstrate an improvement in the quality of image segmentation on three datasets with different complexity of structures. Improvements in object boundary accuracy were obtained for all three sets.machine learningneural networksdeep learningimage segmentationmedical image analysis |
| spellingShingle | Vladyslav D. Koniukhov Adaptive Refinement of Segmented Object Contour Based on the Brightness of Neighboring Pixels Using the Ensemble Method Journal of Mechanical Engineering machine learning neural networks deep learning image segmentation medical image analysis |
| title | Adaptive Refinement of Segmented Object Contour Based on the Brightness of Neighboring Pixels Using the Ensemble Method |
| title_full | Adaptive Refinement of Segmented Object Contour Based on the Brightness of Neighboring Pixels Using the Ensemble Method |
| title_fullStr | Adaptive Refinement of Segmented Object Contour Based on the Brightness of Neighboring Pixels Using the Ensemble Method |
| title_full_unstemmed | Adaptive Refinement of Segmented Object Contour Based on the Brightness of Neighboring Pixels Using the Ensemble Method |
| title_short | Adaptive Refinement of Segmented Object Contour Based on the Brightness of Neighboring Pixels Using the Ensemble Method |
| title_sort | adaptive refinement of segmented object contour based on the brightness of neighboring pixels using the ensemble method |
| topic | machine learning neural networks deep learning image segmentation medical image analysis |
| work_keys_str_mv | AT vladyslavdkoniukhov adaptiverefinementofsegmentedobjectcontourbasedonthebrightnessofneighboringpixelsusingtheensemblemethod |