Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray
Purpose: This study investigated the segmentation metrics of different segmentation networks trained on 730 manually annotated lateral lumbar spine X-rays to test the generalization ability and robustness which are the basis of clinical decision support algorithms. Methods: Instance segmentation net...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer Medknow Publications
2021-01-01
|
| Series: | Journal of Craniovertebral Junction and Spine |
| Subjects: | |
| Online Access: | http://www.jcvjs.com/article.asp?issn=0974-8237;year=2021;volume=12;issue=2;spage=136;epage=143;aulast=Konya |
| _version_ | 1818441756153217024 |
|---|---|
| author | Sandor Konya T R Sai Natarajan Hassan Allouch Kais Abu Nahleh Omneya Yakout Dogheim Heinrich Boehm |
| author_facet | Sandor Konya T R Sai Natarajan Hassan Allouch Kais Abu Nahleh Omneya Yakout Dogheim Heinrich Boehm |
| author_sort | Sandor Konya |
| collection | DOAJ |
| description | Purpose: This study investigated the segmentation metrics of different segmentation networks trained on 730 manually annotated lateral lumbar spine X-rays to test the generalization ability and robustness which are the basis of clinical decision support algorithms.
Methods: Instance segmentation networks were compared to semantic segmentation networks based on different metrics. The study cohort comprised diseased spines and postoperative images with metallic implants.
Results: However, the pixel accuracies and intersection over union are similarly high for the best performing instance and semantic segmentation models; the observed vertebral recognition rates of the instance segmentation models statistically significantly outperform the semantic models' recognition rates.
Conclusion: The results of the instance segmentation models on lumbar spine X-ray perform superior to semantic segmentation models in the recognition rates even by images of severe diseased spines by allowing the segmentation of overlapping vertebrae, in contrary to the semantic models where such differentiation cannot be performed due to the fused binary mask of the overlapping instances. These models can be incorporated into further clinical decision support pipelines. |
| first_indexed | 2024-12-14T18:33:18Z |
| format | Article |
| id | doaj.art-8a9cbd4358e647f3a9606958cafdeac4 |
| institution | Directory Open Access Journal |
| issn | 0974-8237 |
| language | English |
| last_indexed | 2024-12-14T18:33:18Z |
| publishDate | 2021-01-01 |
| publisher | Wolters Kluwer Medknow Publications |
| record_format | Article |
| series | Journal of Craniovertebral Junction and Spine |
| spelling | doaj.art-8a9cbd4358e647f3a9606958cafdeac42022-12-21T22:51:43ZengWolters Kluwer Medknow PublicationsJournal of Craniovertebral Junction and Spine0974-82372021-01-0112213614310.4103/jcvjs.jcvjs_186_20Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-raySandor KonyaT R Sai NatarajanHassan AllouchKais Abu NahlehOmneya Yakout DogheimHeinrich BoehmPurpose: This study investigated the segmentation metrics of different segmentation networks trained on 730 manually annotated lateral lumbar spine X-rays to test the generalization ability and robustness which are the basis of clinical decision support algorithms. Methods: Instance segmentation networks were compared to semantic segmentation networks based on different metrics. The study cohort comprised diseased spines and postoperative images with metallic implants. Results: However, the pixel accuracies and intersection over union are similarly high for the best performing instance and semantic segmentation models; the observed vertebral recognition rates of the instance segmentation models statistically significantly outperform the semantic models' recognition rates. Conclusion: The results of the instance segmentation models on lumbar spine X-ray perform superior to semantic segmentation models in the recognition rates even by images of severe diseased spines by allowing the segmentation of overlapping vertebrae, in contrary to the semantic models where such differentiation cannot be performed due to the fused binary mask of the overlapping instances. These models can be incorporated into further clinical decision support pipelines.http://www.jcvjs.com/article.asp?issn=0974-8237;year=2021;volume=12;issue=2;spage=136;epage=143;aulast=Konyaconvolutional neural networksdeep neural networksinstance segmentationlumbar vertebraemachine learningpostoperative image analysissemantic segmentationx-ray |
| spellingShingle | Sandor Konya T R Sai Natarajan Hassan Allouch Kais Abu Nahleh Omneya Yakout Dogheim Heinrich Boehm Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray Journal of Craniovertebral Junction and Spine convolutional neural networks deep neural networks instance segmentation lumbar vertebrae machine learning postoperative image analysis semantic segmentation x-ray |
| title | Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray |
| title_full | Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray |
| title_fullStr | Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray |
| title_full_unstemmed | Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray |
| title_short | Convolutional neural network-based automated segmentation and labeling of the lumbar spine X-ray |
| title_sort | convolutional neural network based automated segmentation and labeling of the lumbar spine x ray |
| topic | convolutional neural networks deep neural networks instance segmentation lumbar vertebrae machine learning postoperative image analysis semantic segmentation x-ray |
| url | http://www.jcvjs.com/article.asp?issn=0974-8237;year=2021;volume=12;issue=2;spage=136;epage=143;aulast=Konya |
| work_keys_str_mv | AT sandorkonya convolutionalneuralnetworkbasedautomatedsegmentationandlabelingofthelumbarspinexray AT trsainatarajan convolutionalneuralnetworkbasedautomatedsegmentationandlabelingofthelumbarspinexray AT hassanallouch convolutionalneuralnetworkbasedautomatedsegmentationandlabelingofthelumbarspinexray AT kaisabunahleh convolutionalneuralnetworkbasedautomatedsegmentationandlabelingofthelumbarspinexray AT omneyayakoutdogheim convolutionalneuralnetworkbasedautomatedsegmentationandlabelingofthelumbarspinexray AT heinrichboehm convolutionalneuralnetworkbasedautomatedsegmentationandlabelingofthelumbarspinexray |