1
|
Shihabul Hassan M, Stevenson J, Gandikota G, Veeratterapillay A, Bhamidipaty K, Botchu R. Current updates in MSK infection imaging: A narrative review. J Clin Orthop Trauma 2024; 51:102396. [PMID: 38585385 PMCID: PMC10998214 DOI: 10.1016/j.jcot.2024.102396] [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: 01/23/2024] [Revised: 02/28/2024] [Accepted: 03/18/2024] [Indexed: 04/09/2024] Open
Abstract
This article presents a comprehensive overview of the diagnostic utility of existing imaging techniques including radiography, computed tomography, ultrasonography, magnetic resonance imaging (MRI), and radionuclide imaging in the context of the most common orthopaedic or musculoskeletal infections. It also includes illustrative images showcasing significant findings in various musculoskeletal infections including osteomyelitis, cellulitis, septic arthritis, necrotising infections and peri-prosthetic joint infections and their associated complications.
Collapse
Affiliation(s)
- M. Shihabul Hassan
- College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK
| | - J. Stevenson
- Department of Orthopedics, Royal Orthopedic Hospital, Birmingham, UK
| | - G. Gandikota
- Department of Radiology, University of North Carolina, USA
| | | | | | - R. Botchu
- Department of Musculoskeletal Radiology, Royal Orthopedic Hospital, Birmingham, UK
| |
Collapse
|
2
|
Li J, Li S, Li X, Miao S, Dong C, Gao C, Liu X, Hao D, Xu W, Huang M, Cui J. Primary bone tumor detection and classification in full-field bone radiographs via YOLO deep learning model. Eur Radiol 2022; 33:4237-4248. [PMID: 36449060 DOI: 10.1007/s00330-022-09289-y] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2022] [Revised: 11/02/2022] [Accepted: 11/07/2022] [Indexed: 12/02/2022]
Abstract
OBJECTIVES Automatic bone lesions detection and classifications present a critical challenge and are essential to support radiologists in making an accurate diagnosis of bone lesions. In this paper, we aimed to develop a novel deep learning model called You Only Look Once (YOLO) to handle detecting and classifying bone lesions on full-field radiographs with limited manual intervention. METHODS In this retrospective study, we used 1085 bone tumor radiographs and 345 normal bone radiographs from two centers between January 2009 and December 2020 to train and test our YOLO deep learning (DL) model. The trained model detected bone lesions and then classified these radiographs into normal, benign, intermediate, or malignant types. The intersection over union (IoU) was used to assess the model's performance in the detection task. Confusion matrices and Cohen's kappa scores were used for evaluating classification performance. Two radiologists compared diagnostic performance with the trained model using the external validation set. RESULTS In the detection task, the model achieved accuracies of 86.36% and 85.37% in the internal and external validation sets, respectively. In the DL model, radiologist 1 and radiologist 2 achieved Cohen's kappa scores of 0.8187, 0.7927, and 0.9077 for four-way classification in the external validation set, respectively. The YOLO DL model illustrated a significantly higher accuracy for intermediate bone tumor classification than radiologist 1 (95.73% vs 88.08%, p = 0.004). CONCLUSIONS The developed YOLO DL model could be used to assist radiologists at all stages of bone lesion detection and classification in full-field bone radiographs. KEY POINTS • YOLO DL model can automatically detect bone neoplasms from full-field radiographs in one shot and then simultaneously classify radiographs into normal, benign, intermediate, or malignant. • The dataset used in this retrospective study includes normal bone radiographs. • YOLO can detect even some challenging cases with small volumes.
Collapse
Affiliation(s)
- Jie Li
- Department of Radiology, The Affiliated Hospital of Qingdao University, 16 Jiangsu Road, Qingdao, 266003, Shandong, China
| | - Sudong Li
- College of Computer Science and Technology, Qingdao University, Qingdao, 266071, China
| | - Xiaoli Li
- Department of Radiology, The Affiliated Hospital of Qingdao University, 16 Jiangsu Road, Qingdao, 266003, Shandong, China
| | - Sheng Miao
- School of Information and Control Engineering, Qingdao University of Technology, Qingdao, 266520, China
| | - Cheng Dong
- Department of Radiology, The Affiliated Hospital of Qingdao University, 16 Jiangsu Road, Qingdao, 266003, Shandong, China
| | - Chuanping Gao
- Department of Radiology, The Affiliated Hospital of Qingdao University, 16 Jiangsu Road, Qingdao, 266003, Shandong, China
| | - Xuejun Liu
- Department of Radiology, The Affiliated Hospital of Qingdao University, 16 Jiangsu Road, Qingdao, 266003, Shandong, China
| | - Dapeng Hao
- Department of Radiology, The Affiliated Hospital of Qingdao University, 16 Jiangsu Road, Qingdao, 266003, Shandong, China
| | - Wenjian Xu
- Department of Radiology, The Affiliated Hospital of Qingdao University, 16 Jiangsu Road, Qingdao, 266003, Shandong, China
| | - Mingqian Huang
- Department of Radiology, The Mount Sinai Hospital, New York, NY, 10029-0310, USA
| | - Jiufa Cui
- Department of Radiology, The Affiliated Hospital of Qingdao University, 16 Jiangsu Road, Qingdao, 266003, Shandong, China.
| |
Collapse
|
3
|
Update of pediatric bone tumors-notochordal tumors, chondrogenic tumors, and vascular tumors of the bone. Skeletal Radiol 2022; 52:1101-1117. [PMID: 36369290 DOI: 10.1007/s00256-022-04235-x] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/21/2022] [Revised: 11/04/2022] [Accepted: 11/06/2022] [Indexed: 11/12/2022]
Abstract
There are numerous bone tumors in the pediatric population, with imaging playing an essential role in diagnosis and management. Our understanding of certain bone tumors has rapidly evolved over the past decade with advancements in next-generation genetic sequencing techniques. This increased level of understanding has altered the nomenclature, management approach, and prognosis of certain lesions. We provide a detailed update of bone tumors that occur in the pediatric population with emphasis on the recently released nomenclature provided in the 5th edition of the World Health Organization Classification of Soft Tissue and Bone Tumours. In the current manuscript, we address notochordal tumors, chondrogenic tumors, and vascular tumors of the bone.
Collapse
|
4
|
Imaging Diagnosis of Primary Solitary Bone Neoplasts and Its Comparison with Tumor-like Lesions. EVIDENCE-BASED COMPLEMENTARY AND ALTERNATIVE MEDICINE 2022; 2022:2692539. [PMID: 35990818 PMCID: PMC9391113 DOI: 10.1155/2022/2692539] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/16/2022] [Revised: 06/07/2022] [Accepted: 06/08/2022] [Indexed: 11/17/2022]
Abstract
Objective. To explore the imaging diagnostic value of primary solitary bone tumor and tumor-like lesion of iliac crest. Methods. A total of 156 patients with primary solitary bone tumors and tumor-like lesions of the iliac bone treated in our hospital were selected, and the patients were diagnosed by X-ray, CT, and MRI. Sexual analysis of single diagnostic and combined diagnostic value was carried out. Results. Round high-density shadow, soft tissue mass shadow, soft tissue mass, right intestinal tube, and bladder obvious pressure were observed. The detection rates of giant cell tumor of bone, myeloma, osteochondroma, chondroma, eosinophilic granuloma, osteosarcoma, fibrous dysplasia, and Hodgkin lymphoma were 34.6%, 12.8%, 11.5%, 10.3%, 7.7%, 6.4%, 3.8%, and 2.6%, and the differences were statistically significant (P < 005); X-ray, CT, MR single diagnostic comparison, three methods joint diagnostic missed diagnosis rate and misdiagnosis rate, higher detection rate (
); combined with X-ray, CT, MR single diagnosis, three methods joint diagnosis sensitivity, specificity, accuracy, statistical significance (
); comparison with X-ray, CT, MR single diagnosis, three methods jointly diagnosed positive predictive value, negative predictive value higher, difference statistics significance (
); there is a significant difference in the near-end, backbone, and distal detection rate of different bone tumors and tumor lesions, including the humerus and tibia. There is a statistical significance of the detection rate, and the difference is
. Conclusion. X-ray plays an important role in the diagnosis of primary solitary bone tumor and tumor-like lesion of iliac crest and is the first choice in clinical diagnosis. In the diagnosis of tumor disease, range, and soft tissue mass, MRI and CT diagnostic value can provide effective theoretical basis for patient clinical treatment. Therefore, the appropriate diagnostic method should be selected according to the specific situation of the patient, so that the efficiency of the clinical feature is improved.
Collapse
|
5
|
Wiesinger F, Ho ML. Zero-TE MRI: principles and applications in the head and neck. Br J Radiol 2022; 95:20220059. [PMID: 35616709 PMCID: PMC10162052 DOI: 10.1259/bjr.20220059] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022] Open
Abstract
Zero echo-time (ZTE) MRI is a novel imaging technique that utilizes ultrafast readouts to capture signal from short-T2 tissues. Additional sequence advantages include rapid imaging times, silent scanning, and artifact resistance. A robust application of this technology is imaging of cortical bone without the use of ionizing radiation, thus representing a viable alternative to CT for both rapid screening and "one-stop-shop" MRI. Although ZTE is increasingly used in musculoskeletal and body imaging, neuroimaging applications have historically been limited by complex anatomy and pathology. In this article, we review the imaging physics of ZTE including pulse sequence options, practical limitations, and image reconstruction. We then discuss optimization of settings for ZTE bone neuroimaging including acquisition, processing, segmentation, synthetic CT generation, and artifacts. Finally, we examine clinical utility of ZTE in the head and neck with imaging examples including malformations, trauma, tumors, and interventional procedures.
Collapse
Affiliation(s)
- Florian Wiesinger
- Department for Neuroimaging, Institute of Psychiatry & Neuroscience, King's College London, London, UK.,Principal Scientist at GE Healthcare, Munich, Germany
| | - Mai-Lan Ho
- Nationwide Children's Hospital and The Ohio State University, Columbus, USA
| |
Collapse
|