Artificial intelligence and machine learning applications for the imaging of bone and soft tissue tumors.

Recent advancements in artificial intelligence (AI) and machine learning offer numerous opportunities in musculoskeletal radiology to potentially bolster diagnostic accuracy, workflow efficiency, and predictive modeling. AI tools have the capability to assist radiologists in many tasks ranging from image segmentation, lesion detection, and more. In bone and soft tissue tumor imaging, radiomics and deep learning show promise for malignancy stratification, grading, prognostication, and treatment planning. However, challenges such as standardization, data integration, and ethical concerns regarding patient data need to be addressed ahead of clinical translation. In the realm of musculoskeletal oncology, AI also faces obstacles in robust algorithm development due to limited disease incidence. While many initiatives aim to develop multitasking AI systems, multidisciplinary collaboration is crucial for successful AI integration into clinical practice. Robust approaches addressing challenges and embodying ethical practices are warranted to fully realize AI's potential for enhancing diagnostic accuracy and advancing patient care.

Risk Factors for Femoral Head Collapse in Osteonecrosis.

BACKGROUND: Osteonecrosis of the femoral head (ONFH) affects at least 20,000 patients annually in the United States; however, the pathophysiology of disease progression is poorly understood. The purpose of this study was to determine the relative importance of three distinct elements and their relationship to the collapse of the femoral head as follows: (1) identifiable risk factors, (2) femoral head anatomy, and (3) the extent of the necrotic lesion. METHODS: A single-center retrospective cohort study was performed on patients ≥ 18 year old who presented with ONFH. Ficat classification and femoral head anatomic parameters were measured on radiographs. Osteonecrotic lesion size was measured on magnetic resonance imaging using four validated methods. Multivariable regression analyses were performed to identify predictors of femoral head collapse. RESULTS: There were 105 patients and 137 hips included in the final cohort, of which 50 (36.5%) had collapse of the femoral head. Multivariable analyses demonstrated that medical risk factors (adjusted odds ratio (aOR): 1.15), alcohol exposure (aOR: 1.23), and increased alpha angle (aOR: 4.51) were predictive of femoral head collapse. Increased femoral head offset (aOR: 0.54) was protective against collapse. An increased size of the osteonecrotic lesion was significantly predictive of collapse with all four measurement methods evaluated: three-dimensional volumetric (aOR: 3.73), modified Kerboul (aOR: 2.92), index of necrotic extent (aOR: 1.91), and modified index of necrotic extent (aOR: 2.05). CONCLUSIONS: In an analysis of patients who had ONFH, we identified risk factors such as alcohol exposure, high alpha angle, increased lesion size, and decreased femoral offset as increasing the risk of femoral head collapse. Given the challenges of studying this patient population, large prospective studies of patients who have ONFH should seek to identify whether these factors are reliable indicators of femoral head collapse. LEVEL OF EVIDENCE: III.

Imaging of lower extremity infections: predisposing conditions, atypical infections, mimics, and differentiating features.

Imaging evaluation for lower extremity infections can be complicated, especially in the setting of underlying conditions and with atypical infections. Predisposing conditions are discussed, including diabetes mellitus, peripheral arterial disease, neuropathic arthropathy, and intravenous drug abuse, as well as differentiating features of infectious versus non-infectious disease. Atypical infections such as viral, mycobacterial, fungal, and parasitic infections and their imaging features are also reviewed. Potential mimics of lower extremity infection including chronic nonbacterial osteomyelitis, foreign body granuloma, gout, inflammatory arthropathies, lymphedema, and Morel-Lavallée lesions, and their differentiating features are also explored.

Lower extremity infections: Essential anatomy and multimodality imaging findings.

In modern practice, imaging plays an integral role in the diagnosis, evaluation of extent, and treatment planning for lower extremity infections. This review will illustrate the relevant compartment anatomy of the lower extremities and highlight the role of plain radiographs, CT, US, MRI, and nuclear medicine in the diagnostic workup. The imaging features of cellulitis, abscess and phlegmon, necrotizing soft tissue infection, pyomyositis, infectious tenosynovitis, septic arthritis, and osteomyelitis are reviewed. Differentiating features from noninfectious causes of swelling and edema are discussed.

Imaging Diagnosis and Management of Carpal Trauma and Instability-An Illustrated Guide.

Understanding the subtle signs of carpal instability and other unique injury patterns in the wrist is a critical skill for radiologists. Proper patient management and outcomes are directly dependent on the accurate interpretation of wrist imaging studies. This review will provide a detailed overview of typical imaging features of carpal trauma and instability, management, and complications, using multimodality imaging and original medical illustrations. A detailed overview of the osseous, ligamentous, arterial anatomy of the wrist, arcs of Gilula, and zones of vulnerability will be provided. Carpal fractures, dislocations, special radiographic views, and imaging pearls will be discussed. Instability patterns and the myriad of associate abbreviations (CID, CIND, CIC, CIA, VISI, DISI, SLD, LTD, MCI, SLAC, SNAC) will be clarified. Expected outcomes, potential complications, and management will be reviewed.

Role of Imaging in Initial Prognostication of Locally Advanced Soft Tissue Sarcomas.

BACKGROUND: Although imaging is central in the initial staging of patients with soft tissue sarcomas (STS), it remains underused and few radiological features are currently used in practice for prognostication and to help guide the best therapeutic strategy. Yet, several prognostic qualitative and quantitative characteristics from magnetic resonance imaging (MRI) and positron emission tomography (PET) have been identified over these last decades. OBJECTIVE: After an overview of the current validated prognostic features based on baseline imaging and their integration into prognostic tools, such as nomograms used by clinicians, the aim of this review is to summarize more complex and innovative MRI, PET, and radiomics features, and to highlight their role to predict indirectly (through histologic grade) or directly the patients' outcomes.

Imaging of Musculoskeletal Soft-Tissue Infections in Clinical Practice: A Comprehensive Updated Review.

Musculoskeletal soft-tissue infections include a wide range of clinical conditions that are commonly encountered in both emergency departments and non-emergency clinical settings. Since clinical signs, symptoms, and even laboratory tests can be unremarkable or non-specific, imaging plays a key role in many cases. MRI is considered the most comprehensive and sensitive imaging tool available for the assessment of musculoskeletal infections. Ultrasound is a fundamental tool, especially for the evaluation of superficially located diseases and for US-guided interventional procedures, such as biopsy, needle-aspiration, and drainage. Conventional radiographs can be very helpful, especially for the detection of foreign bodies and in cases of infections with delayed diagnosis displaying bone involvement. This review article aims to provide a comprehensive overview of the radiological tools available and the imaging features of the most common musculoskeletal soft-tissue infections, including cellulitis, necrotizing and non-necrotizing fasciitis, foreign bodies, abscess, pyomyositis, infectious tenosynovitis, and bursitis.

Illustrative review of knee meniscal tear patterns, repair and replacement options, and imaging evaluation.

This review article aims to reinforce anatomical concepts about meniscal tears while linking associated treatment options. The main teaching points start with the basic meniscal anatomy and key differences between the medial and lateral menisci. Subsequently, various meniscal tear patterns along with their associated history and physical exam findings will be discussed with corresponding illustrations and MR images. Additional discussion will involve the different surgical repair techniques (with arthroscopic correlates), their indications with pertinent imaging findings, imaging related to previous meniscal tear repairs, and novel surgical techniques. Lastly, keys to evaluating for retear with an emphasis on MRI arthrogram findings will be reviewed. While each of these topics is not discussed in totality, the key points of the review article will enforce key concepts and help radiologists evaluate the menisci on imaging.

Spindle cell carcinoma of the breast managed with neoadjuvant AIM: A case report.

Spindle cell carcinoma (SpC), also known as metaplastic carcinoma-spindle cell type, is a subtype of metaplastic carcinoma. Metaplastic carcinomas of the breast are rare but are thought to be more aggressive than invasive ductal carcinomas. Due to their rarity, there are few randomized trials that can inform any standardized approaches to treatment. Treatment is instead extrapolated from other types of breast cancer or metaplastic carcinomas of different locations. Here we present the first known case report of a patient with spindle cell carcinoma of the breast successfully treated with a standard sarcoma neoadjuvant regimen of doxorubicin, ifosfamide, and mesna (AIM) that resulted in >99% necrosis of the tumor and negative margins at the time of resection.

Imaging Coccygeal Trauma and Coccydynia.

The coccygeal region has complex anatomy, much of which may contribute to or be the cause of coccyx region pain (coccydynia). This anatomy is well depicted at imaging, and management is often dictated by what structures are involved. Coccydynia is a common condition that is known to be difficult to evaluate and treat. However, imaging can aid in determining potential causes of pain to help guide management. Commonly, coccydynia (coccygodynia) occurs after trauma and appears with normal imaging features at static neutral radiography, but dynamic imaging with standing and seated lateral radiography may reveal pathologic coccygeal motion that is predictive of pain. In addition, several findings seen at cross-sectional imaging in patients with coccydynia can point to a source of pain that may be subtle and easily overlooked. Radiology can also offer a role in management of coccygeal region pain with image-guided pain management procedures such as ganglion impar block. In addition to mechanical coccyx pain, a host of other conditions involving the sacrococcygeal region may cause coccydynia, which are well depicted at imaging. These include neoplasm, infection, crystal deposition, and cystic formations such as pilonidal cyst. The authors review a variety of coccydynia causes, their respective imaging features, and common management strategies.©RSNA, 2020.

Horseshoe abscess of the hand with rice bodies secondary to mycobacterium avium intracellulare infection.

A horseshoe abscess is caused by infection that spreads between the flexor tendon sheath of the thumb or little finger through the radial and ulnar bursae through communication between the two and/or the space of Parona. We present a case of an 80-year-old woman with rheumatoid arthritis who presented with 6 months of right hand and wrist soft tissue swelling, initially treated as a rheumatoid arthritis flare. MRI demonstrates the horseshoe abscess and after surgical irrigation and debridement with synovectomy, cultures demonstrated infection with mycobacterium avium intracellulare (MAI). This case demonstrates the importance of MRI in diagnosing and evaluating the extent of hand infections and for considering mycobacterial organisms for appropriate treatment and antibiotic regimen.

MR imaging of cartilage repair surgery of the knee.

Articular cartilage is a complex tissue with unique properties that are essential for normal joint function. Many processes can result in cartilage injury, ranging from acute trauma to degenerative processes. Articular cartilage lacks vascularity, and therefore most chondral defects do not heal spontaneously and may require surgical repair. A variety of cartilage repair techniques have been developed and include bone marrow stimulation (microfracture), osteochondral autograft transfer system (OATS) or osteochondral allograft transplantation, autologous chondrocyte implantation (ACI), matrix-assisted chondrocyte implantation (MACI), and other newer processed allograft cartilage techniques. Although arthroscopy has long been considered as the gold standard for evaluation of cartilage after cartilage repair, magnetic resonance (MR) imaging is a non-invasive method to assess the repair site and can be scored using Magnetic resonance Observation of Cartilage Repair Tissue (MOCART). MR also provides additional evaluation of the subchondral bone and for other potential causes of knee pain or internal derangement. Conventional MR can be used to evaluate the status of cartilage repair and potential complications. Compositional MR sequences can provide supplementary information about the biochemical contents of the reparative tissue. This article reviews the various types of cartilage repair surgeries and their postoperative MR imaging appearances.

Coracoid process fractures: anatomy, injury patterns, multimodality imaging, and approach to management.

The coracoid process of the scapula is in close proximity to major neurovascular structures, including the brachial plexus and the axillary artery and vein. In addition, it serves as a major site of attachment for multiple tendons and ligaments about the shoulder. Isolated coracoid fractures are rare; however, they can be easily overlooked on routine shoulder radiographs. Importantly, when these fractures go undiagnosed, they are at high risk for nonunion. In this paper, we will review the relevant anatomy of the coracoid process, classification schemes for coracoid fractures, mechanisms of injury how these fractures typically present, multimodality imaging findings, and associated injuries. Finally, we will briefly discuss the clinical management of these fractures.

Adhesive capsulitis: review of imaging findings, pathophysiology, clinical presentation, and treatment options.

Adhesive capsulitis, commonly referred to as "frozen shoulder," is a debilitating condition characterized by progressive pain and limited range of motion about the glenohumeral joint. It is a condition that typically affects middle-aged women, with some evidence for an association with endocrinological, rheumatological, and autoimmune disease states. Management tends to be conservative, as most cases resolve spontaneously, although a subset of patients progress to permanent disability. Conventional arthrographic findings include decreased capsular distension and volume of the axillary recess when compared with the normal glenohumeral joint, in spite of the fact that fluoroscopic visualization alone is rarely carried out today in favor of magnetic resonance imaging (MRI). MRI and MR arthrography (MRA) have, in recent years, allowed for the visualization of several characteristic signs seen with this condition, including thickening of the coracohumeral ligament, axillary pouch and rotator interval joint capsule, in addition to the obliteration of the subcoracoid fat triangle. Additional findings include T2 signal hyperintensity and post-contrast enhancement of the joint capsule. Similar changes are observable on ultrasound. However, the use of ultrasound is most clearly established for image-guided injection therapy. More aggressive therapies, including arthroscopic release and open capsulotomy, may be indicated for refractory disease, with arthroscopic procedures favored because of their less invasive nature and relatively high success rate.

Fibular groove morphology and measurements on MRI: correlation with fibularis tendon abnormalities.

PURPOSE: Fibular (peroneal) groove morphology may influence fibularis tendon pathology, including tendinosis, tears, and luxation. The study goal was to evaluate the inter-reader agreement of morphologic characterization and measures of the fibular groove at two different levels on MRI and correlation with fibularis tendon pathology. MATERIALS AND METHODS: 47 ankle MRIs in patients without lateral ankle pain were reviewed by two musculoskeletal radiologists. Fibular groove morphology and various measurements were assessed at both the level of the tibial plafond and 1 cm proximal to the tip of the lateral malleolus. Fibularis tendon pathology and other variants were also recorded. Intraclass correlation (ICC) and kappa statistic (κ) were applied to assess inter-observer agreement. Receiver operating characteristic (ROC) and area under the curve (AUC) analysis were performed to determine correlation between fibular groove morphometry and fibularis (peroneus) brevis tendon tears. RESULTS: Between readers, there was fair-to-excellent agreement (ICC = 0.61-0.95) for performed fibular groove measurements and moderate-to-very good agreement for identification and description of fibular groove and fibularis tendon morphology and pathology and normal variants in this region (κ = 0.46-1), with the exception of fibular groove morphology at 1 cm proximal to the lateral malleolar tip (κ = 0.34). Individually, no measurement or description of pathology could discriminate between patients with or without fibularis brevis tendon tears except fibularis brevis tendinosis (AUC = 0.87 for reader 1). CONCLUSION: There is overall moderate-to-excellent inter-reader agreement for various measurements and descriptors of fibular groove and fibularis tendon morphometry and pathology, including novel measurements introduced in this study.

Intra-articular tongue-type fractures of the calcaneus: anatomy, injury patterns, and an approach to management.

Intra-articular tongue-type fractures may develop skin breakdown and often require urgent surgical reduction and fixation. Recognition of the imaging findings, accurate interpretation, and timely communication may prevent devastating clinical outcomes including soft tissue coverage procedures and amputation. This article reviews the anatomy of the calcaneus, as well as the clinical presentation and imaging findings of intra-articular tongue-type fractures. Imaging interpretation and clinical management of these fractures are discussed.

Detection of Traumatic Pediatric Elbow Joint Effusion Using a Deep Convolutional Neural Network.

OBJECTIVE: The purpose of this study is to determine whether a deep convolutional neural network (DCNN) trained on a dataset of limited size can accurately diagnose traumatic pediatric elbow effusion on lateral radiographs. MATERIALS AND METHODS: A total of 901 lateral elbow radiographs from 882 pediatric patients who presented to the emergency department with upper extremity trauma were divided into a training set (657 images), a validation set (115 images), and an independent test set (129 images). The training set was used to train DCNNs of varying depth, architecture, and parameter initialization, some trained from randomly initialized parameter weights and others trained using parameter weights derived from pretraining on an ImageNet dataset. Hyperparameters were optimized using the validation set, and the DCNN with the highest ROC AUC on the validation set was selected for further performance testing on the test set. RESULTS: The final trained DCNN model had an ROC AUC of 0.985 (95% CI, 0.966-1.000) on the validation set and 0.943 (95% CI, 0.884-1.000) on the test set. On the test set, sensitivity was 0.909 (95% CI, 0.788-1.000), specificity was 0.906 (95% CI, 0.844-0.958), and accuracy was 0.907 (95% CI, 0.843-0.951). CONCLUSION: Accurate diagnosis of traumatic pediatric elbow joint effusion can be achieved using a DCNN.

Imaging of soft tissue sarcomas.

Soft tissue sarcomas are rare and a heterogeneous group of neoplasms. Over the years imaging has played a crucial role in the initial staging, monitoring response to chemotherapy, and surveillance for recurrence. In the era of rapidly evolving individualized treatment due to evolving chemotherapies, increasing demand has been placed on the role of imaging in the management of this heterogeneous group. The rapidly evolving technologies in imaging are trying to keep up with the challenge, with development of newer strategies and hybrid imaging. However, many of these newer technologies are either not available or too costly, even in advanced countries, and hence their exact role remains uncertain. Due to this, and the vast diversity of sarcomas, the imaging appearance and management strategies vary and there is no universally accepted algorithm for the role of individual imaging technologies. The basic imaging techniques; however, remain the same, with these newer techniques and strategies vying for their roles in management. We review current imaging techniques and their role in the management of soft tissue sarcomas.

Musculoskeletal Pitfalls on Fluorodeoxyglucose F 18 PET-Computed Tomography: Pictorial Review.

A wide range of musculoskeletal processes can demonstrate increased uptake on PET-computed tomography (CT) with fluorodeoxyglucose (FDG) F 18, including reactive, benign neoplastic, inflammatory, traumatic, posttreatment, and arthritic conditions that may mimic malignancy. In addition, physiologic causes of increased FDG uptake such as asymmetric muscle use and presence of brown fat can lead to increased FDG uptake and potential false-positive results. This article presents various case examples of non-malignant musculoskeletal hypermetabolism on 18F-FDG PET-CT and describes useful tools to avoid the potential pitfall of misinterpreting these as malignancy.