Deep Learning for Fully Automated Radiographic Measurements of the Pelvis and Hip
The morphometry of the hip and pelvis can be evaluated in native radiographs. Artificial-intelligence-assisted analyses provide objective, accurate, and reproducible results. This study investigates the performance of an artificial intelligence (AI)-based software using deep learning algorithms to m...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/3/497 |
| _version_ | 1797624830753767424 |
|---|---|
| author | Christoph Stotter Thomas Klestil Christoph Röder Philippe Reuter Kenneth Chen Robert Emprechtinger Allan Hummer Christoph Salzlechner Matthew DiFranco Stefan Nehrer |
| author_facet | Christoph Stotter Thomas Klestil Christoph Röder Philippe Reuter Kenneth Chen Robert Emprechtinger Allan Hummer Christoph Salzlechner Matthew DiFranco Stefan Nehrer |
| author_sort | Christoph Stotter |
| collection | DOAJ |
| description | The morphometry of the hip and pelvis can be evaluated in native radiographs. Artificial-intelligence-assisted analyses provide objective, accurate, and reproducible results. This study investigates the performance of an artificial intelligence (AI)-based software using deep learning algorithms to measure radiological parameters that identify femoroacetabular impingement and hip dysplasia. Sixty-two radiographs (124 hips) were manually evaluated by three observers and fully automated analyses were performed by an AI-driven software (HIPPO™, ImageBiopsy Lab, Vienna, Austria). We compared the performance of the three human readers with the HIPPO™ using a Bayesian mixed model. For this purpose, we used the absolute deviation from the median ratings of all readers and HIPPO™. Our results indicate a high probability that the AI-driven software ranks better than at least one manual reader for the majority of outcome measures. Hence, fully automated analyses could provide reproducible results and facilitate identifying radiographic signs of hip disorders. |
| first_indexed | 2024-03-11T09:48:14Z |
| format | Article |
| id | doaj.art-8e461a6aadff455b99c4f227baa98fa6 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T09:48:14Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-8e461a6aadff455b99c4f227baa98fa62023-11-16T16:25:32ZengMDPI AGDiagnostics2075-44182023-01-0113349710.3390/diagnostics13030497Deep Learning for Fully Automated Radiographic Measurements of the Pelvis and HipChristoph Stotter0Thomas Klestil1Christoph Röder2Philippe Reuter3Kenneth Chen4Robert Emprechtinger5Allan Hummer6Christoph Salzlechner7Matthew DiFranco8Stefan Nehrer9Department for Orthopedics and Traumatology, Landesklinikum Baden-Mödling, 2340 Mödling, AustriaDepartment for Orthopedics and Traumatology, Landesklinikum Baden-Mödling, 2340 Mödling, AustriaDepartment for Orthopedics and Traumatology, Landesklinikum Baden-Mödling, 2340 Mödling, AustriaDepartment for Orthopedics and Traumatology, Landesklinikum Baden-Mödling, 2340 Mödling, AustriaDepartment for Orthopedics and Traumatology, Landesklinikum Baden-Mödling, 2340 Mödling, AustriaDepartment for Health Sciences, Medicine and Research, University for Continuing Education Krems, 3500 Krems, AustriaImageBiopsy Lab, 1140 Vienna, AustriaImageBiopsy Lab, 1140 Vienna, AustriaImageBiopsy Lab, 1140 Vienna, AustriaDepartment for Health Sciences, Medicine and Research, University for Continuing Education Krems, 3500 Krems, AustriaThe morphometry of the hip and pelvis can be evaluated in native radiographs. Artificial-intelligence-assisted analyses provide objective, accurate, and reproducible results. This study investigates the performance of an artificial intelligence (AI)-based software using deep learning algorithms to measure radiological parameters that identify femoroacetabular impingement and hip dysplasia. Sixty-two radiographs (124 hips) were manually evaluated by three observers and fully automated analyses were performed by an AI-driven software (HIPPO™, ImageBiopsy Lab, Vienna, Austria). We compared the performance of the three human readers with the HIPPO™ using a Bayesian mixed model. For this purpose, we used the absolute deviation from the median ratings of all readers and HIPPO™. Our results indicate a high probability that the AI-driven software ranks better than at least one manual reader for the majority of outcome measures. Hence, fully automated analyses could provide reproducible results and facilitate identifying radiographic signs of hip disorders.https://www.mdpi.com/2075-4418/13/3/497femoroacetabular impingementhip dysplasiaX-rayradiographsartificial intelligencemachine learning |
| spellingShingle | Christoph Stotter Thomas Klestil Christoph Röder Philippe Reuter Kenneth Chen Robert Emprechtinger Allan Hummer Christoph Salzlechner Matthew DiFranco Stefan Nehrer Deep Learning for Fully Automated Radiographic Measurements of the Pelvis and Hip Diagnostics femoroacetabular impingement hip dysplasia X-ray radiographs artificial intelligence machine learning |
| title | Deep Learning for Fully Automated Radiographic Measurements of the Pelvis and Hip |
| title_full | Deep Learning for Fully Automated Radiographic Measurements of the Pelvis and Hip |
| title_fullStr | Deep Learning for Fully Automated Radiographic Measurements of the Pelvis and Hip |
| title_full_unstemmed | Deep Learning for Fully Automated Radiographic Measurements of the Pelvis and Hip |
| title_short | Deep Learning for Fully Automated Radiographic Measurements of the Pelvis and Hip |
| title_sort | deep learning for fully automated radiographic measurements of the pelvis and hip |
| topic | femoroacetabular impingement hip dysplasia X-ray radiographs artificial intelligence machine learning |
| url | https://www.mdpi.com/2075-4418/13/3/497 |
| work_keys_str_mv | AT christophstotter deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip AT thomasklestil deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip AT christophroder deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip AT philippereuter deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip AT kennethchen deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip AT robertemprechtinger deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip AT allanhummer deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip AT christophsalzlechner deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip AT matthewdifranco deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip AT stefannehrer deeplearningforfullyautomatedradiographicmeasurementsofthepelvisandhip |