1
|
Ruitenbeek HC, Oei EHG, Visser JJ, Kijowski R. Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade. Skeletal Radiol 2024:10.1007/s00256-024-04684-6. [PMID: 38902420 DOI: 10.1007/s00256-024-04684-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/01/2024] [Revised: 04/06/2024] [Accepted: 04/15/2024] [Indexed: 06/22/2024]
Abstract
This article will provide a perspective review of the most extensively investigated deep learning (DL) applications for musculoskeletal disease detection that have the best potential to translate into routine clinical practice over the next decade. Deep learning methods for detecting fractures, estimating pediatric bone age, calculating bone measurements such as lower extremity alignment and Cobb angle, and grading osteoarthritis on radiographs have been shown to have high diagnostic performance with many of these applications now commercially available for use in clinical practice. Many studies have also documented the feasibility of using DL methods for detecting joint pathology and characterizing bone tumors on magnetic resonance imaging (MRI). However, musculoskeletal disease detection on MRI is difficult as it requires multi-task, multi-class detection of complex abnormalities on multiple image slices with different tissue contrasts. The generalizability of DL methods for musculoskeletal disease detection on MRI is also challenging due to fluctuations in image quality caused by the wide variety of scanners and pulse sequences used in routine MRI protocols. The diagnostic performance of current DL methods for musculoskeletal disease detection must be further evaluated in well-designed prospective studies using large image datasets acquired at different institutions with different imaging parameters and imaging hardware before they can be fully implemented in clinical practice. Future studies must also investigate the true clinical benefits of current DL methods and determine whether they could enhance quality, reduce error rates, improve workflow, and decrease radiologist fatigue and burnout with all of this weighed against the costs.
Collapse
Affiliation(s)
- Huibert C Ruitenbeek
- Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands
| | - Edwin H G Oei
- Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands
| | - Jacob J Visser
- Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center, P.O. Box 2040, 3000 CA, Rotterdam, The Netherlands
| | - Richard Kijowski
- Department of Radiology, New York University Grossman School of Medicine, 660 First Avenue, 3rd Floor, New York, NY, 10016, USA.
| |
Collapse
|
2
|
Löchel J, Putzier M, Dreischarf M, Grover P, Urinbayev K, Abbas F, Labbus K, Zahn R. Deep learning algorithm for fully automated measurement of sagittal balance in adult spinal deformity. EUROPEAN SPINE JOURNAL : OFFICIAL PUBLICATION OF THE EUROPEAN SPINE SOCIETY, THE EUROPEAN SPINAL DEFORMITY SOCIETY, AND THE EUROPEAN SECTION OF THE CERVICAL SPINE RESEARCH SOCIETY 2024:10.1007/s00586-023-08109-1. [PMID: 38231388 DOI: 10.1007/s00586-023-08109-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/05/2023] [Revised: 11/03/2023] [Accepted: 12/15/2023] [Indexed: 01/18/2024]
Abstract
AIM Deep learning (DL) algorithms can be used for automated analysis of medical imaging. The aim of this study was to assess the accuracy of an innovative, fully automated DL algorithm for analysis of sagittal balance in adult spinal deformity (ASD). MATERIAL AND METHODS Sagittal balance (sacral slope, pelvic tilt, pelvic incidence, lumbar lordosis and sagittal vertical axis) was evaluated in 141 preoperative and postoperative radiographs of patients with ASD. The DL, landmark-based measurements, were compared with the ground truth values from validated manual measurements. RESULTS The DL algorithm showed an excellent consistency with the ground truth measurements. The intra-class correlation coefficient between the DL and ground truth measurements was 0.71-0.99 for preoperative and 0.72-0.96 for postoperative measurements. The DL detection rate was 91.5% and 84% for preoperative and postoperative images, respectively. CONCLUSION This is the first study evaluating a complete automated DL algorithm for analysis of sagittal balance with high accuracy for all evaluated parameters. The excellent accuracy in the challenging pathology of ASD with long construct instrumentation demonstrates the eligibility and possibility for implementation in clinical routine.
Collapse
Affiliation(s)
- Jannis Löchel
- Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Augustenburger Platz 1, 13353, Berlin, Germany.
| | - Michael Putzier
- Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Charitéplatz 1, 10117, Berlin, Germany
| | - Marcel Dreischarf
- RAYLYTIC - medical data automation, Petersstr. 32-34, 04109, Leipzig, Germany
| | - Priyanka Grover
- RAYLYTIC - medical data automation, Petersstr. 32-34, 04109, Leipzig, Germany
| | | | - Fahad Abbas
- Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Augustenburger Platz 1, 13353, Berlin, Germany
| | - Kirsten Labbus
- Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Augustenburger Platz 1, 13353, Berlin, Germany
| | - Robert Zahn
- Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Augustenburger Platz 1, 13353, Berlin, Germany
| |
Collapse
|
3
|
Lacroix M, Khalifé M, Ferrero E, Clément O, Nguyen C, Feydy A. Scoliosis. Semin Musculoskelet Radiol 2023; 27:529-544. [PMID: 37816361 DOI: 10.1055/s-0043-1772168] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/12/2023]
Abstract
Scoliosis is a three-dimensional spinal deformity that can occur at any age. It may be idiopathic or secondary in children, idiopathic and degenerative in adults. Management of patients with scoliosis is multidisciplinary, involving rheumatologists, radiologists, orthopaedic surgeons, and prosthetists. Imaging plays a central role in diagnosis, including the search for secondary causes, follow-up, and preoperative work-up if surgery is required. Evaluating scoliosis involves obtaining frontal and lateral full-spine radiographs in the standing position, with analysis of coronal and sagittal alignment. For adolescent idiopathic scoliosis, imaging follow-up is often required, accomplished using low-dose stereoradiography such as EOS imaging. For adult degenerative scoliosis, the crucial characteristic is rotatory subluxation, also well detected on radiographs. Magnetic resonance imaging is usually more informative than computed tomography for visualizing associated canal and foraminal stenoses. Radiologists must also have a thorough understanding of postoperative features and complications of scoliosis surgery because aspects can be misleading.
Collapse
Affiliation(s)
- Maxime Lacroix
- Department of Radiology, Hôpital Européen Georges-Pompidou, AP-HP Centre, Université Paris Cité, Paris, France
- Department of Musculoskeletal Radiology, Hôpital Cochin, AP-HP Centre, Université Paris Cité, Paris, France
| | - Marc Khalifé
- Department of Orthopaedic Surgery, Hôpital Européen Georges- Pompidou, AP-HP Centre, Université Paris Cité, Paris, France
| | - Emmanuelle Ferrero
- Department of Orthopaedic Surgery, Hôpital Européen Georges- Pompidou, AP-HP Centre, Université Paris Cité, Paris, France
| | - Olivier Clément
- Department of Radiology, Hôpital Européen Georges-Pompidou, AP-HP Centre, Université Paris Cité, Paris, France
| | - Christelle Nguyen
- Department of Physical and Rehabilitation Medicine, Hôpital Cochin, Université Paris Cité, Paris, France
| | - Antoine Feydy
- Department of Musculoskeletal Radiology, Hôpital Cochin, AP-HP Centre, Université Paris Cité, Paris, France
| |
Collapse
|
4
|
Dalton J, Mohamed A, Akioyamen N, Schwab FJ, Lafage V. PreOperative Planning for Adult Spinal Deformity Goals: Level Selection and Alignment Goals. Neurosurg Clin N Am 2023; 34:527-536. [PMID: 37718099 DOI: 10.1016/j.nec.2023.06.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/19/2023]
Abstract
Adult Spinal Deformity (ASD) is a complex pathologic condition with significant impact on quality of life, including pain, loss of function, and fatigue. Achieving realignment goals is crucial for long-term results. Reliable preoperative planning strategies, including nomograms, measurement tools, and level selection, are key to maximizing the likelihood of achieving a good outcome following ASD corrective surgery. This review covers recent literature on such strategies, including review of the different targets for realignment and their association with outcomes (both patients-reported outcomes and complications), selection of upper and lower instrumented vertebrae, and the latest innovation in preoperative planning for deformity surgery.
Collapse
Affiliation(s)
- Jay Dalton
- Department of Orthopaedic Surgery, University of Pittsburgh Medical Center, 3471 Fifth Avenue, Pittsburgh, PA 15213, USA
| | - Ayman Mohamed
- Department of Orthopaedic Surgery, Lenox Hill Hospital, 130 East 77th Street, 11th Floor, New York, NY 10075, USA
| | - Noel Akioyamen
- Department of Orthopaedic Surgery, Monteriore Medical Center, 1250 Waters Place, Tower 1, 11th Floor, Bronx, NY 10461, USA
| | - Frank J Schwab
- Department of Orthopaedic Surgery, Lenox Hill Hospital, 130 East 77th Street, 11th Floor, New York, NY 10075, USA
| | - Virginie Lafage
- Department of Orthopaedic Surgery, Lenox Hill Hospital, 130 East 77th Street, 11th Floor, New York, NY 10075, USA.
| |
Collapse
|