Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models
The lumbar spine plays a very important role in our load transfer and mobility. Vertebrae localization and segmentation are useful in detecting spinal deformities and fractures. Understanding of automated medical imagery is of main importance to help doctors in handling the time-consuming manual or...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/4/1547 |
| _version_ | 1827652834048344064 |
|---|---|
| author | Malaika Mushtaq Muhammad Usman Akram Norah Saleh Alghamdi Joddat Fatima Rao Farhat Masood |
| author_facet | Malaika Mushtaq Muhammad Usman Akram Norah Saleh Alghamdi Joddat Fatima Rao Farhat Masood |
| author_sort | Malaika Mushtaq |
| collection | DOAJ |
| description | The lumbar spine plays a very important role in our load transfer and mobility. Vertebrae localization and segmentation are useful in detecting spinal deformities and fractures. Understanding of automated medical imagery is of main importance to help doctors in handling the time-consuming manual or semi-manual diagnosis. Our paper presents the methods that will help clinicians to grade the severity of the disease with confidence, as the current manual diagnosis by different doctors has dissimilarity and variations in the analysis of diseases. In this paper we discuss the lumbar spine localization and segmentation which help for the analysis of lumbar spine deformities. The lumber spine is localized using YOLOv5 which is the fifth variant of the YOLO family. It is the fastest and the lightest object detector. Mean average precision (mAP) of 0.975 is achieved by YOLOv5. To diagnose the lumbar lordosis, we correlated the angles with region area that is computed from the YOLOv5 centroids and obtained 74.5% accuracy. Cropped images from YOLOv5 bounding boxes are passed through HED U-Net, which is a combination of segmentation and edge detection frameworks, to obtain the segmented vertebrae and its edges. Lumbar lordortic angles (LLAs) and lumbosacral angles (LSAs) are found after detecting the corners of vertebrae using a Harris corner detector with very small mean errors of 0.29° and 0.38°, respectively. This paper compares the different object detectors used to localize the vertebrae, the results of two methods used to diagnose the lumbar deformity, and the results with other researchers. |
| first_indexed | 2024-03-09T21:06:42Z |
| format | Article |
| id | doaj.art-f6b169f1971e48cc9f40a90f2fd6524a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T21:06:42Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f6b169f1971e48cc9f40a90f2fd6524a2023-11-23T22:01:18ZengMDPI AGSensors1424-82202022-02-01224154710.3390/s22041547Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning ModelsMalaika Mushtaq0Muhammad Usman Akram1Norah Saleh Alghamdi2Joddat Fatima3Rao Farhat Masood4Department of Computer and Software Engineering, National University of Sciences and Technology, Islamabad 44000, PakistanDepartment of Computer and Software Engineering, National University of Sciences and Technology, Islamabad 44000, PakistanDepartment of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaDepartment of Computer Science, Bahria University, Islamabad 44000, PakistanDepartment of Electrical Engineering, Capital University of Science and Technology, Islamabad 44000, PakistanThe lumbar spine plays a very important role in our load transfer and mobility. Vertebrae localization and segmentation are useful in detecting spinal deformities and fractures. Understanding of automated medical imagery is of main importance to help doctors in handling the time-consuming manual or semi-manual diagnosis. Our paper presents the methods that will help clinicians to grade the severity of the disease with confidence, as the current manual diagnosis by different doctors has dissimilarity and variations in the analysis of diseases. In this paper we discuss the lumbar spine localization and segmentation which help for the analysis of lumbar spine deformities. The lumber spine is localized using YOLOv5 which is the fifth variant of the YOLO family. It is the fastest and the lightest object detector. Mean average precision (mAP) of 0.975 is achieved by YOLOv5. To diagnose the lumbar lordosis, we correlated the angles with region area that is computed from the YOLOv5 centroids and obtained 74.5% accuracy. Cropped images from YOLOv5 bounding boxes are passed through HED U-Net, which is a combination of segmentation and edge detection frameworks, to obtain the segmented vertebrae and its edges. Lumbar lordortic angles (LLAs) and lumbosacral angles (LSAs) are found after detecting the corners of vertebrae using a Harris corner detector with very small mean errors of 0.29° and 0.38°, respectively. This paper compares the different object detectors used to localize the vertebrae, the results of two methods used to diagnose the lumbar deformity, and the results with other researchers.https://www.mdpi.com/1424-8220/22/4/1547deep learninglocalizationlumbar lordortic anglelumbosacral anglelumbar spineedge-based segmentation |
| spellingShingle | Malaika Mushtaq Muhammad Usman Akram Norah Saleh Alghamdi Joddat Fatima Rao Farhat Masood Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models Sensors deep learning localization lumbar lordortic angle lumbosacral angle lumbar spine edge-based segmentation |
| title | Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models |
| title_full | Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models |
| title_fullStr | Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models |
| title_full_unstemmed | Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models |
| title_short | Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models |
| title_sort | localization and edge based segmentation of lumbar spine vertebrae to identify the deformities using deep learning models |
| topic | deep learning localization lumbar lordortic angle lumbosacral angle lumbar spine edge-based segmentation |
| url | https://www.mdpi.com/1424-8220/22/4/1547 |
| work_keys_str_mv | AT malaikamushtaq localizationandedgebasedsegmentationoflumbarspinevertebraetoidentifythedeformitiesusingdeeplearningmodels AT muhammadusmanakram localizationandedgebasedsegmentationoflumbarspinevertebraetoidentifythedeformitiesusingdeeplearningmodels AT norahsalehalghamdi localizationandedgebasedsegmentationoflumbarspinevertebraetoidentifythedeformitiesusingdeeplearningmodels AT joddatfatima localizationandedgebasedsegmentationoflumbarspinevertebraetoidentifythedeformitiesusingdeeplearningmodels AT raofarhatmasood localizationandedgebasedsegmentationoflumbarspinevertebraetoidentifythedeformitiesusingdeeplearningmodels |