Enhanced enchondroma detection from x-ray images using deep learning: A step towards accurate and cost-effective diagnosis

This study investigates the automated detection of enchondromas, benign cartilage tumors, from x-ray images using deep learning techniques. Enchondromas pose diagnostic challenges due to their potential for malignant transformation and overlapping radiographic features with other conditions. Leveraging a data set comprising 1645 x-ray images from 1173 patients, a deep-learning model implemented with Detectron2 achieved an accuracy of 0.9899 in detecting enchondromas. The study employed rigorous validation processes and compared its findings with the existing literature, highlighting the superior performance of the deep learning approach. Results indicate the potential of machine learning in improving diagnostic accuracy and reducing healthcare costs associated with advanced imaging modalities. The study underscores the significance of early and accurate detection of enchondromas for effective patient management and suggests avenues for further research in musculoskeletal tumor detection.

Cost of Low-Value Imaging Worldwide: A Systematic Review

BACKGROUND AND OBJECTIVE

Imaging with low or no benefit for the patient undermines the quality of care and amounts to vast opportunity costs. More than 3.6 billion imaging examinations are performed annually, and about 20-50% of these are of low value. This study aimed to synthesize knowledge of the costs of low-value imaging worldwide.

METHODS

This systematic review was based on the PRISMA statement. The database search was developed in Medline and further adapted to Embase-Ovid, Cochrane Library, and Scopus. Primary empirical studies assessing the costs of low-value diagnostic imaging were included if published between 2012 and March 2022. Studies designed as randomized controlled trials, non-randomized trials, cohort studies, cross-sectional studies, descriptive studies, cost analysis, cost-effectiveness analysis, and mixed-methods studies were eligible. The analysis was descriptive.

RESULTS

Of 5,567 records identified, 106 were included. Most of the studies included were conducted in the USA (n = 76), and a hospital or medical center was the most common setting (n = 82). Thirty-eight of the included studies calculated the costs of multiple imaging modalities; in studies with only one imaging modality included, conventional radiography was the most common (n = 32). Aggregated costs for low-value examinations amounts to billions of dollars per year globally. Initiatives to reduce low-value imaging may reduce costs by up to 95% without harming patients.

CONCLUSIONS

This study is the first systematic review of the cost of low-value imaging worldwide, documenting a high potential for cost reduction. Given the universal challenges with resource allocation, the large amount used for low-value imaging represents a vast opportunity cost and offers great potential to improve the quality and efficiency of care.

Characterizing and quantifying low-value diagnostic imaging internationally: a scoping review

BACKGROUND

Inappropriate and wasteful use of health care resources is a common problem, constituting 10-34% of health services spending in the western world. Even though diagnostic imaging is vital for identifying correct diagnoses and administrating the right treatment, low-value imaging-in which the diagnostic test confers little to no clinical benefit-is common and contributes to inappropriate and wasteful use of health care resources. There is a lack of knowledge on the types and extent of low-value imaging. Accordingly, the objective of this study was to identify, characterize, and quantify the extent of low-value diagnostic imaging examinations for adults and children.

METHODS

A scoping review of the published literature was performed. Medline-Ovid, Embase-Ovid, Scopus, and Cochrane Library were searched for studies published from 2010 to September 2020. The search strategy was built from medical subject headings (Mesh) for Diagnostic imaging/Radiology OR Health service misuse/Medical overuse OR Procedures and Techniques Utilization/Facilities and Services Utilization. Articles in English, German, Dutch, Swedish, Danish, or Norwegian were included.

RESULTS

A total of 39,986 records were identified and, of these, 370 studies were included in the final synthesis. Eighty-four low-value imaging examinations were identified. Imaging of atraumatic pain, routine imaging in minor head injury, trauma, thrombosis, urolithiasis, after thoracic interventions, fracture follow-up and cancer staging/follow-up were the most frequently identified low-value imaging examinations. The proportion of low-value imaging varied between 2 and 100% inappropriate or unnecessary examinations.

CONCLUSIONS

A comprehensive list of identified low-value radiological examinations for both adults and children are presented. Future research should focus on reasons for low-value imaging utilization and interventions to reduce the use of low-value imaging internationally.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO: CRD42020208072.

Midterm MRI Follow-Up of Untreated Enchondroma and Atypical Cartilaginous Tumors in the Long Bones

Simple Summary

Over the last decade the incidence of enchondroma and atypical cartilaginous bone tumors (ACTs) increased enormously. Management of these tumors in the long bones is shifting towards active surveillance, as negative side effects of surgical treatment seem to outweigh the potential benefits. To support development of evidence-based guidelines for active surveillance, we studied the natural course of enchondroma and ACTs in the long bones. In this study, MRI analysis of 128 cases was performed with a minimum interval of 24 months between baseline and last MRI. Our data showed that the majority of the cartilaginous tumors (87%) remained stable or showed regression on MRI. Only 13% showed some progression on MRI, although none of the tumors developed characteristics of high-grade chondrosarcoma. Based on our results, active surveillance is considered safe for enchondroma and ACTs of the long bones, and follow-up schemes should be tailored on natural course.

Abstract

Management of atypical cartilaginous tumors (ACTs) in the long bones is shifting towards active surveillance to avoid unnecessary surgeries. The frequency and duration of active surveillance for these tumors is unclear as there is little knowledge of its biological behavior. In this retrospective study, we examined the natural course of enchondroma and ACTs through active surveillance. A total of 128 central cartilaginous tumors, located in the long bones, with a minimum interval of 24 months between baseline and last MRI were included. MRI characteristics (e.g., size, scalloping, fat entrapment) were scored and tumors were classified according to the changes between MRIs. Mean follow-up of this study was 50 months, range = 25–138 months. The majority of the cartilaginous tumors (87%) remained stable (n = 65) or showed regression (n = 46) on MRI. A total of 87% of the cases that developed tumor regression presented with entrapped fat at diagnosis. Only 13% (n = 17) showed some progression on MRI, although none of the tumors developed characteristics of high-grade chondrosarcoma. Based on our results, active surveillance is considered safe for enchondroma and ACTs of the long bones. We propose active surveillance for all asymptomatic enchondroma or ACTs in the long bones irrespective of tumor size, and follow-up schemes should be tailored on natural course.

Team Approach: Evaluation and Management of Low-Grade Cartilaginous Lesions

» Assessment of chondral lesions begins with a clinical evaluation and radiographs. » Longitudinal follow-up with serial radiographs is appropriate in cases without evidence of aggressive radiographic features. » Concerning radiographic features include periosteal reaction, soft-tissue extension, cortical destruction, endosteal scalloping of greater than two-thirds of the native cortex, larger lesion size (≥5 cm), and location in the axial skeleton. » Biomarkers such as IMP3, SOX4, microRNA, and periostin may be used as an adjunct in histologic assessment to help differentiate benign enchondroma from a low-grade chondrosarcoma. » Advanced-imaging studies, such as computed tomography (CT), bone scans, magnetic resonance imaging (MRI), dynamic contrast-enhanced MRI, and fluorodeoxyglucose positron emission tomography (FDG-PET), may be considered for borderline cases. » Aggressive or concerning radiographic features should prompt evaluation with advanced imaging or referral to an orthopaedic oncologist.

The changing face of central chondrosarcoma of bone. One UK-based orthopaedic oncology unit's experience of 33 years referrals

AIM

To ascertain the changing incidence over time of the three commonest primary sarcomas of bone. Data obtained with particular reference to central chondrosarcoma from the annual referral rate to a large UK-based specialist orthopaedic oncology unit. To discuss how the "barnyard pen" analogy of cancers previously applied to certain commoner cancers can also be applicable to central chondrosarcoma (CS) of bone.

MATERIALS AND METHODS

A retrospective review was conducted of a computerised database identifying all central cartilage tumours (CCT) of bone, including enchondroma and CS subtypes, between 1985 and 2018. These were compared with the referrals of the other two commonest primary sarcomas of bone, osteosarcoma and Ewing sarcoma.

RESULTS

There was a total of 1507 CS showing a 68% overall increase in annual referral rate/incidence over the study period. 68% cases were the borderline malignant lesions now known as atypical cartilaginous tumour (ACT). The annual referral rate/incidence of this entity increased by 194% over the 30 years. Whereas, the annual referral rate/incidence for osteosarcoma and Ewing sarcoma was static for the past 20 years.

CONCLUSION

The annual incidence of central CS of bone showed a marked increase over the 33-year period as compared with both osteosarcoma and Ewing sarcoma. This is especially in the ACT category and is thought to be due to the increased provision of MRI scanning flagging up a rise in incidental findings. The spectrum of CCTs from benign to highly malignant elegantly fits the "barn yard" pen analogy and could prove useful as an explanatory tool for patients and clinicians unfamiliar with these diseases.

The role of imaging in differentiating low-grade and high-grade central chondral tumours

Chondrosarcoma is a malignant cartilage matrix-producing tumour. Those arising de novo are called primary chondrosarcomas and are the second commonest primary malignant bone tumours. Numerous types of primary chondrosarcoma exist, namely conventional central (intramedullary), periosteal (juxta-cortical), clear cell, mesenchymal, and dedifferentiated. The biologic aggressiveness, prognosis and thus management of chondrosarcoma are dependent on the histological sub-type and grade. Accurate pre-operative diagnosis is therefore essential in determining management and outcome which requires a multidisciplinary approach taking into account clinical features, imaging findings and histopathology. In this review, we present the pertinent multimodality imaging features which aid in the differentiation of low-grade and high-grade conventional central chondrosarcoma.

Solitary enchondromas-diagnosis and surveillance : Danish guidelines

Enchondromas (EC) are frequent incidental findings on magnetic resonance imaging (MRI) performed for the diagnosis of joint pathology, especially observed on MRI examinations of the knee and shoulder. Enchondroma has potential for malignant transformation to chondrosarcoma (CS), and it may be difficult to distinguish EC from low-malignant CS on the basis of imaging or histopathology studies. Therefore, EC is mostly followed up to monitor any growth and/or changes indicating aggressive tumor.There is no consensual evidence on when and how to follow up patients with EC with regard to potential malignant transformation. Therefore, the Danish Multidisciplinary Cancer Groups initiated and supported the elaboration of Danish guidelines in 2020 based on a literature review. The guidelines are presented here, in addition to a summary of the background literature.

The Impact of Pre-Referral Advanced Diagnostic Testing on Wait Time to See a Hand Surgeon for Common Upper-Extremity Conditions

PURPOSE

We sought to evaluate the use of pre- and post-referral advanced diagnostic testing among patients with 3 common hand conditions, rates of subsequent tests, and differences in wait time to see a hand surgeon.

METHODS

We analyzed a single academic tertiary care center administrative database of encounters from 2006 to 2015 to identify adult patients who were referred to a hand surgeon for 3 conditions (carpal tunnel syndrome [CTS], soft tissue masses [STM], and joint pain [JP]). We recorded patient characteristics, use and timing of diagnostic tests, and wait time for the initial hand surgeon evaluation.

RESULTS

Among patients who received advanced diagnostic tests before the surgeon evaluation, CTS patients had the highest rate of receiving pre-referral advanced testing (53.4%) compared with JP (10.6% ) and STM patients (5.8%). The CTS patients had the highest rates of repeat testing (19.5%) compared with patients with JP (1.4%) and STM (0%). Across all 3 conditions, patients who received pre-referral advanced testing waited an additional 19 to 94 days to see a surgeon, compared with patients who received only post-referral testing or no testing.

CONCLUSIONS

Use of pre-referral advanced diagnostic tests is associated with an increased time to see a hand surgeon for common hand conditions.

CLINICAL RELEVANCE

Hand surgeons should have a role in identifying patients who do or do not benefit from advanced testing before referral to ensure that tests ordered before consultation are useful to both patients and treating surgeons.

Methods to detect inappropriate use of MRI and CT for musculoskeletal conditions: A scoping review

OBJECTIVE

Identify and evaluate methods suitable for detecting inappropriate use of MRI or CT in the musculoskeletal system.

DESIGN

Systematic review of studies that described methods to measure inappropriate use of MRI or CT in the musculoskeletal system. We used a multi-step strategy to classify identified methods into categories. These categories were then analyzed according to the data needed and their limitations.

ELIGIBILITY CRITERIA FOR SELECTING STUDIES

English or German language studies that measured inappropriate use of MRI or CT in the musculoskeletal system. Articles were also included if they reported a general approach to the measurement of inappropriate imaging regardless of body region. Expert opinions, unsystematic reviews, commentaries, articles without abstracts, and studies on cancer were excluded.

RESULTS

47 studies met the inclusion criteria. The categorization of the studies resulted in seven individual approaches to measure inappropriate use: (1) availability of meaningful diagnostic information; (2) predictors associated with imaging use; (3) comparison with guideline recommendations; (4) assessment by experts; (5) comparison or analysis of patients' paths; (6) comparison with surgery findings; (7) geographic variation. All these approaches have specific data requirements and individual advantages and disadvantages regarding risk of bias and needed data.

CONCLUSIONS

We could not find a single method of choice to detect inappropriate use of MRI or CT in the musculoskeletal system. A combination of different approaches is the preferred strategy to deal with the advantages and disadvantages of the individual methods.

Enchondromas and atypical cartilaginous tumors at the proximal humerus treated with intralesional resection and bone cement filling with or without osteosynthesis: retrospective analysis of 42 cases with 6 years mean follow-up

Background

Enchondromas and atypical cartilaginous tumors (ACT) are often located at the proximal humerus. Most lesions can be followed conservatively, but surgical resection may alleviate pain, avoid pathological fractures, and prevent transformation into higher grade chondrosarcomas. Rigorous intralesional resection and filling with polymethylmethacrylate bone cement has been proposed for enchondromas but also for ACT, as an alternative for extralesional resection. We intended to analyze radiological, clinical, and functional outcome of this strategy and compare bone cement without osteosynthesis to bone cement compound osteosynthesis, which has not been analyzed so far.

Methods

We retrospectively analyzed 42 consecutive patients (mean follow-up 73 months; range 8–224) after curettage and bone cement filling with or without osteosynthesis. Exclusion criteria were Ollier’s disease and cancellous bone filling. Twenty-five patients only received bone cement. Seventeen patients received additional proximal humerus plate for compound osteosynthesis to increase stability after curettage. Demographics and radiological and clinical outcome were analyzed including surgery time, blood loss, hospitalization, recurrences, and complications. An additional telephone interview at the final follow-up assessed postoperative satisfaction, pain, and function in the quick disabilities of the arm, shoulder, and hand (DASH) score and the Musculoskeletal Tumor Society (MSTS) score. Statistics included the Student T tests, Mann-Whitney U tests, and chi-square tests.

Results

No osteosynthesis compared to compound osteosynthesis showed smaller tumors (4.2 (± 1.5) cm versus 6.6 (± 3.0) cm; p = 0.005) and smaller bone cement fillings after curettage (5.7 (± 2.1) cm versus 9.6 (± 3.2) cm; p = 0.0001). A score evaluating preoperative scalloping and soft-tissue extension did not significantly differ (1.9 (± 0.9) versus 2.0 (± 1.0); rating scale 0–4; p = 0.7). Both groups showed high satisfaction (9.2 (± 1.5) versus 9.2 (± 0.9); p = 0.5) and low pain (1.0(±1.7) versus 1.9(±1.8); p = 0.1) in a rating scale from 0 to 10. Clinical and functional outcome was excellent for both groups in the DASH score (6.0 (± 11.8) versus 11.0 (± 13.2); rating scale 0–100; p = 0.2) and the MSTS score (29.0 (± 1.7) versus 28.7 (± 1.1); rating scale 0–30; p = 0.3). One enchondroma recurrence was found in the group without osteosynthesis. Complications (one fracture and one intra-articular screw) were only detected after osteosynthesis. Osteosynthesis had longer surgery time (70 (± 21) min versus 127 (± 22) min; p < 0.0001), more blood loss (220 (± 130) ml versus 460 (± 210) ml; p < 0.0001), and longer stay in the hospital (6 (± 2) days versus 8 (± 2) days; p = 0.004).

Conclusions

Intralesional tumor resection was oncologically safe and clinically successful with or without osteosynthesis. Osteosynthesis did not reduce the risk for fracture but was more invasive.