Segmentation of organs and tumor within brain magnetic resonance images using K-nearest neighbor classification
Purpose: To fully exploit the benefits of magnetic resonance imaging (MRI) for radiotherapy, it is desirable to develop segmentation methods to delineate patients' MRI images fast and accurately. The purpose of this work is to develop a semi-automatic method to segment organs and tumor within t...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer Medknow Publications
2022-01-01
|
| Series: | Journal of Medical Physics |
| Subjects: | |
| Online Access: | http://www.jmp.org.in/article.asp?issn=0971-6203;year=2022;volume=47;issue=1;spage=40;epage=49;aulast=Yoganathan |
| _version_ | 1811279375295840256 |
|---|---|
| author | S A Yoganathan Rui Zhang |
| author_facet | S A Yoganathan Rui Zhang |
| author_sort | S A Yoganathan |
| collection | DOAJ |
| description | Purpose: To fully exploit the benefits of magnetic resonance imaging (MRI) for radiotherapy, it is desirable to develop segmentation methods to delineate patients' MRI images fast and accurately. The purpose of this work is to develop a semi-automatic method to segment organs and tumor within the brain on standard T1- and T2-weighted MRI images. Methods and Materials: Twelve brain cancer patients were retrospectively included in this study, and a simple rigid registration was used to align all the images to the same spatial coordinates. Regions of interest were created for organs and tumor segmentations. The K-nearest neighbor (KNN) classification algorithm was used to characterize the knowledge of previous segmentations using 15 image features (T1 and T2 image intensity, 4 Gabor filtered images, 6 image gradients, and 3 Cartesian coordinates), and the trained models were used to predict organ and tumor contours. Dice similarity coefficient (DSC), normalized surface dice, sensitivity, specificity, and Hausdorff distance were used to evaluate the performance of segmentations. Results: Our semi-automatic segmentations matched with the ground truths closely. The mean DSC value was between 0.49 (optical chiasm) and 0.89 (right eye) for organ segmentations and was 0.87 for tumor segmentation. Overall performance of our method is comparable or superior to the previous work, and the accuracy of our semi-automatic segmentation is generally better for large volume objects. Conclusion: The proposed KNN method can accurately segment organs and tumor using standard brain MRI images, provides fast and accurate image processing and planning tools, and paves the way for clinical implementation of MRI-guided radiotherapy and adaptive radiotherapy. |
| first_indexed | 2024-04-13T00:53:28Z |
| format | Article |
| id | doaj.art-bd1e003b53a142ffa61b2083cc2d10e2 |
| institution | Directory Open Access Journal |
| issn | 0971-6203 1998-3913 |
| language | English |
| last_indexed | 2024-04-13T00:53:28Z |
| publishDate | 2022-01-01 |
| publisher | Wolters Kluwer Medknow Publications |
| record_format | Article |
| series | Journal of Medical Physics |
| spelling | doaj.art-bd1e003b53a142ffa61b2083cc2d10e22022-12-22T03:09:48ZengWolters Kluwer Medknow PublicationsJournal of Medical Physics0971-62031998-39132022-01-01471404910.4103/jmp.jmp_87_21Segmentation of organs and tumor within brain magnetic resonance images using K-nearest neighbor classificationS A YoganathanRui ZhangPurpose: To fully exploit the benefits of magnetic resonance imaging (MRI) for radiotherapy, it is desirable to develop segmentation methods to delineate patients' MRI images fast and accurately. The purpose of this work is to develop a semi-automatic method to segment organs and tumor within the brain on standard T1- and T2-weighted MRI images. Methods and Materials: Twelve brain cancer patients were retrospectively included in this study, and a simple rigid registration was used to align all the images to the same spatial coordinates. Regions of interest were created for organs and tumor segmentations. The K-nearest neighbor (KNN) classification algorithm was used to characterize the knowledge of previous segmentations using 15 image features (T1 and T2 image intensity, 4 Gabor filtered images, 6 image gradients, and 3 Cartesian coordinates), and the trained models were used to predict organ and tumor contours. Dice similarity coefficient (DSC), normalized surface dice, sensitivity, specificity, and Hausdorff distance were used to evaluate the performance of segmentations. Results: Our semi-automatic segmentations matched with the ground truths closely. The mean DSC value was between 0.49 (optical chiasm) and 0.89 (right eye) for organ segmentations and was 0.87 for tumor segmentation. Overall performance of our method is comparable or superior to the previous work, and the accuracy of our semi-automatic segmentation is generally better for large volume objects. Conclusion: The proposed KNN method can accurately segment organs and tumor using standard brain MRI images, provides fast and accurate image processing and planning tools, and paves the way for clinical implementation of MRI-guided radiotherapy and adaptive radiotherapy.http://www.jmp.org.in/article.asp?issn=0971-6203;year=2022;volume=47;issue=1;spage=40;epage=49;aulast=Yoganathanbrain cancerk-nearest neighbormachine learningmagnetic resonance imagingradiotherapysegmentation |
| spellingShingle | S A Yoganathan Rui Zhang Segmentation of organs and tumor within brain magnetic resonance images using K-nearest neighbor classification Journal of Medical Physics brain cancer k-nearest neighbor machine learning magnetic resonance imaging radiotherapy segmentation |
| title | Segmentation of organs and tumor within brain magnetic resonance images using K-nearest neighbor classification |
| title_full | Segmentation of organs and tumor within brain magnetic resonance images using K-nearest neighbor classification |
| title_fullStr | Segmentation of organs and tumor within brain magnetic resonance images using K-nearest neighbor classification |
| title_full_unstemmed | Segmentation of organs and tumor within brain magnetic resonance images using K-nearest neighbor classification |
| title_short | Segmentation of organs and tumor within brain magnetic resonance images using K-nearest neighbor classification |
| title_sort | segmentation of organs and tumor within brain magnetic resonance images using k nearest neighbor classification |
| topic | brain cancer k-nearest neighbor machine learning magnetic resonance imaging radiotherapy segmentation |
| url | http://www.jmp.org.in/article.asp?issn=0971-6203;year=2022;volume=47;issue=1;spage=40;epage=49;aulast=Yoganathan |
| work_keys_str_mv | AT sayoganathan segmentationoforgansandtumorwithinbrainmagneticresonanceimagesusingknearestneighborclassification AT ruizhang segmentationoforgansandtumorwithinbrainmagneticresonanceimagesusingknearestneighborclassification |