CT radiomics-based machine learning model for differentiating between enchondroma and low-grade chondrosarcoma.

It may be difficult to distinguish between enchondroma and low-grade malignant cartilage tumors (grade 1) radiologically. This study aimed to construct machine learning models using 3D computed tomography (CT)-based radiomics analysis to differentiate low-grade chondrosarcoma from enchondroma. A total of 30 patients with enchondroma and 26 with chondrosarcoma were included in this retrospective study. Tumor volume segmentation was manually performed by 2 musculoskeletal radiologists. In total, 107 radiomic features were obtained for each patient. The intraclass correlation coefficient was used to assess interobserver reliability and estimate the absolute agreement between the 2 radiologists. Algorithm-based information gain was used as a feature reduction method, and the 5 most important features were detected. For classification, 7 machine learning models were utilized. Classification was carried out using either all features or 5 features. There was good to excellent agreement between the 2 radiologists for the 107 features of each patient. Therefore, a dataset containing 107 features was used for machine learning classification. When assessed based on area under curve (AUC) values, classification using all features revealed that naive Bayes was the best model (AUC = 0.950), while classification using 5 features revealed that random forest was the best model for differentiating chondrosarcoma from enchondroma (AUC = 0.967). In conclusion, machine learning models using CT-based radiomics analysis can be used to differentiate between low-grade chondrosarcoma and enchondroma.

Enchondroma on Bone Scan and PSMA PET/CT in a Patient With Prostate cancer.

ABSTRACT: A 54-year-old man with Gleason 9 prostate cancer with reported nodal and skeletal metastases was referred to us. Outside hospital reports described abnormal left proximal humerus activity on bone scan concerning for metastasis; however, concurrent PSMA PET/CT did not show activity in this lesion. Further review of the PET/CT images revealed characteristic features of enchondroma in the left humeral lesion.

Actualización de los tumores cartilaginosos según la clasificación de la OMS de 2020 / Update of cartilaginous tumours according to the WHO classification 2020

Los tumores cartilaginosos son un grupo amplio y heterogéneo de neoplasias caracterizadas por la presencia de una matriz condroide que presenta crecimiento lobular y patrones de calcificación en arcos y anillos o en palomitas de maíz. En RM destaca su hiperintensidad en las secuencias potenciadas en T2, y en las imágenes poscontraste, un relace lobulado o septal. En la clasificación de 2020 de la OMS, los tumores de estirpe condral se clasifican en benignos, intermedios o malignos. A pesar de los avances tecnológicos, siguen suponiendo un reto tanto para el radiólogo como para el patólogo, siendo la principal dificultad la diferenciación entre los tumores benignos y malignos, razón por la que requieren un abordaje multidisciplinar. Este trabajo recoge los principales cambios introducidos en la actualización de 2020, describe las características de imagen de los principales tumores cartilaginosos y proporciona las claves radiológicas para diferenciar entre tumores benignos y malignos.(AU)

Cartilaginous tumours are a large and heterogeneous group of neoplasms characterised by the presence of a chondroid matrix, with lobular growth and arcuate, ring-like or popcorn-like calcification patterns. MRI shows hyperintensity in T2-weighted sequences and a lobulated or septal relief in postcontrast images. In the WHO 2020 classification, chondral tumours are classified as benign, intermediate or malignant. Despite technological advances, they continue to pose a challenge for both the radiologist and the pathologist, being the main difficulty the differentiation between benign and malignant tumours, which is why they require a multidisciplinary approach. This paper describes the main changes introduced in the 2020 update, describes the imaging characteristics of the main cartilaginous tumours and provides the radiological keys to differentiate between benign and malignant tumours.(AU)

A retrospective external validation study of the Birmingham Atypical Cartilage Tumour Imaging Protocol (BACTIP) for the management of solitary central cartilage tumours of the proximal humerus and around the knee.

OBJECTIVES: This study aimed to externally validate the Birmingham Atypical Cartilage Tumour Imaging Protocol (BACTIP) recommendations for differentiation/follow-up of central cartilage tumours (CCTs) of the proximal humerus, distal femur, and proximal tibia and to propose BACTIP adaptations if the results provide new insights. METHODS: MRIs of 123 patients (45 ± 11 years, 37 men) with an untreated CCT with MRI follow-up (n = 62) or histopathological confirmation (n = 61) were retrospectively/consecutively included and categorised following the BACTIP (2003-2020 / Ghent University Hospital/Belgium). Tumour length and endosteal scalloping differences between enchondroma, atypical cartilaginous tumour (ACT), and high-grade chondrosarcoma (CS II/III/dedifferentiated) were evaluated. ROC-curve analysis for differentiating benign from malignant CCTs and for evaluating the BACTIP was performed. RESULTS: For lesion length and endosteal scalloping, ROC-AUCs were poor and fair-excellent, respectively, for differentiating different CCT groups (0.59-0.69 versus 0.73-0.91). The diagnostic performance of endosteal scalloping and the BACTIP was higher than that of lesion length. A 1° endosteal scalloping cut-off differentiated enchondroma from ACT + high-grade chondrosarcoma with a sensitivity of 90%, reducing the potential diagnostic delay. However, the specificity was 29%, inducing overmedicalisation (excessive follow-up). ROC-AUC of the BACTIP was poor for differentiating enchondroma from ACT (ROC-AUC = 0.69; 95%CI = 0.51-0.87; p = 0.041) and fair-good for differentiation between other CCT groups (ROC-AUC = 0.72-0.81). BACTIP recommendations were incorrect/unsafe in five ACTs and one CSII, potentially inducing diagnostic delay. Eleven enchondromas received unnecessary referrals/follow-up. CONCLUSION: Although promising as a useful tool for management/follow-up of CCTs of the proximal humerus, distal femur, and proximal tibia, five ACTs and one chondrosarcoma grade II were discharged, potentially inducing diagnostic delay, which could be reduced by adapting BACTIP cut-off values. CLINICAL RELEVANCE STATEMENT: Mostly, Birmingham Atypical Cartilage Tumour Imaging Protocol (BACTIP) assesses central cartilage tumours of the proximal humerus and the knee correctly. Both when using the BACTIP and when adapting cut-offs, caution should be taken for the trade-off between underdiagnosis/potential diagnostic delay in chondrosarcomas and overmedicalisation in enchondromas. KEY POINTS: • This retrospective external validation confirms the Birmingham Atypical Cartilage Tumour Imaging Protocol as a useful tool for initial assessment and follow-up recommendation of central cartilage tumours in the proximal humerus and around the knee in the majority of cases. • Using only the Birmingham Atypical Cartilage Tumour Imaging Protocol, both atypical cartilaginous tumours and high-grade chondrosarcomas (grade II, grade III, and dedifferentiated chondrosarcomas) can be misdiagnosed, excluding them from specialist referral and further follow-up, thus creating a potential risk of delayed diagnosis and worse prognosis. • Adapted cut-offs to maximise detection of atypical cartilaginous tumours and high-grade chondrosarcomas, minimise underdiagnosis and reduce potential diagnostic delay in malignant tumours but increase unnecessary referral and follow-up of benign tumours.

SPECT/CT Radiomics for Differentiating between Enchondroma and Grade I Chondrosarcoma.

This study was performed to assess the value of SPECT/CT radiomics parameters in differentiating enchondroma and atypical cartilaginous tumors (ACTs) located in the long bones. Quantitative HDP SPECT/CT data of 49 patients with enchondromas or ACTs in the long bones were retrospectively reviewed. Patients were randomly split into training (n = 32) and test (n = 17) data, and SPECT/CT radiomics parameters were extracted. In training data, LASSO was employed for feature reduction. Selected parameters were compared with classic quantitative parameters for the prediction of diagnosis. Significant parameters from training data were again tested in the test data. A total of 12 (37.5%) and 6 (35.2%) patients were diagnosed as ACTs in training and test data, respectively. LASSO regression selected two radiomics features, zone-length non-uniformity for zone (ZLNUGLZLM) and coarseness for neighborhood grey-level difference (CoarsenessNGLDM). Multivariate analysis revealed higher ZLNUGLZLM as the only significant independent factor for the prediction of ACTs, with sensitivity and specificity of 85.0% and 58.3%, respectively, with a cut-off value of 191.26. In test data, higher ZLNUGLZLM was again associated with the diagnosis of ACTs, with sensitivity and specificity of 83.3% and 90.9%, respectively. HDP SPECT/CT radiomics may provide added value for differentiating between enchondromas and ACTs.

Encondroma osificado en fémur. Una localización atípica. A propósito de un caso / Ossified enchondroma in femur. An atypical location. Case study

Presentamos el caso de un hombre de 61 años en el que se halló de forma incidental un encondroma a nivel proximal de fémur. Tras seguimiento, se observó la estabilidad de la lesión. El encondroma es un tumor de origen cartilaginoso benigno. Se localiza principalmente en las falanges de las manos y los pies, aunque puede observarse en húmero o fémur. Por lo general, es una lesión asintomática y se halla de manera incidental. En las radiografías suelen verse lesiones redondeadas bien definidas con radiolucidez central. Se recomienda el seguimiento con radiografías seriadas para comprobar la progresión o estabilidad de la lesión y hacer su diagnóstico diferencial con el condrosarcoma.(AU)

We report the case of a 61-year-old man in whom an enchondroma was incidentally detected at the proximal level of the femur. After follow-up the lesion was stable. Enchondroma is a benign cartilaginous tumor. It is located mainly in the phalanges of the hands and feet, although it can be seen in the humerus or femur. It is usually an asymptomatic lesion, found incidentally. On x-rays, well-defined round lesions with central radiolucency are usually observed. Follow-up with serial x-rays is recommended to verify the lesion’s course or stability and make its differential diagnosis with chondrosarcoma.(AU)

Cemented K-wire external fixation in juxta-articular enchondroma-related phalangeal pathological fracture.

PURPOSE: This study aimed to introduce a technique of external fixation using a combination of bone cement and K-wires, to treat pathological fractures related to solitary digital enchondroma close to the finger joints. METHODS: From October 2015 to January 2021, 21 patients (8 males and 13 females) with acute pathological fracture due to solitary digital enchondroma close to the finger joints were treated with cemented K-wire external fixators. Mean age was 32 (19-51) years. The digits involved were the index (n = 4), long (n = 4), ring (n = 6), and little (n = 7) fingers. Time to bone healing and complications were assessed. At final follow-up, active range of motion, grip strength and key pinch strength of the tumor-involved and contralateral healthy digits were measured and compared. Functional outcomes were evaluated on Takigawa criteria. Pain was measured on a 10-cm visual analog scale. We assessed the affected upper extremity on the Musculoskeletal Tumor Society score questionnaire. RESULTS: Mean bone healing time was 5.5 (4-8) weeks. Pin site infection was observed in 1 patient and cured with dressing changes. Mean follow-up was 34 months, with no recurrences or refractures. Mean active range of motion of the proximal interphalangeal joint, grip and key pinch strength of the involved digits reached 92%, 97%, and 99% of the contralateral digits, respectively. On Takigawa criteria, 20 functional results were excellent and 1 good. Mean pain score was 1 (0-3) cm. Mean Musculoskeletal Tumor Society score was 95 (80-100). CONCLUSION: The combination of bone cement and K-wires is a reliable technique for pathological fracture related to solitary enchondroma close to the joints of the digits, leading to good functional outcomes. LEVEL OF EVIDENCE: Therapeutic study, Level IVa.

Chondroma Arising from the Temporomandibular Joint: A Case Report.

Periarticular chondromas are common in the humerus and femur but rarely occur in the temporomandibular joint. We report a case of a chondroma in the anterior part of the ear. One year prior to his visit, a 53-year-old man became aware of swelling in the right cheek region which gradually increased in size. In the anterior part of the right ear, there was a palpable 25 mm tumor, elastic and hard, with poor mobility and without tenderness. A contrast-enhanced computed tomography CT showed a mass lesion with diffuse calcification or ossification in the upper pole of the parotid gland and areas of poor contrast within. A magnetic resonance imaging showed a low-signal mass lesion at the parotid gland with some high signals in both T1 and T2. Fine-needle aspiration cytology did not lead to diagnosis. Using a nerve monitoring system, the tumor was resected with normal tissue of the upper pole of the parotid gland in the same way as for a benign parotid tumor. Distinguishing between pleomorphic adenoma, including diffuse microcalcification of the parotid gland and cartilaginous tumors of the temporomandibular joint, may be sometimes difficult. In such cases, surgical resection may be a beneficial treatment option.

Soft Tissue Chondroma of the Chin.

Soft tissue chondromas are benign tumors, generally of the hands or feet, very rarely of the head and neck region. Repeated microtrauma may be as an initiating factor. The authors describe a case of a soft tissue chondroma of the chin in a 58-year-old male who had used a continuous positive airway pressure face mask for obstructive sleep apnea for 3 years. The patient presented with a hard mass on his chin for 1 year. Computed tomography imaging showed a heterogeneous enhancing mass, with calcification in the subcutaneous layer. Intraoperatively, the mass was beneath the mentalis muscle and abutted the mental nerve, without bone involvement. The diagnosis was a soft tissue chondroma. The patient recovered fully, without recurrence. The primary cause of soft tissue chondromas is unknown. The authors consider that continuous use of a continuous positive airway pressure face mask may play a role in the etiology.

Prevalence and characteristics of benign cartilaginous tumours of the knee joint as identified on MRI scans.

BACKGROUND: Enchondromas (EC) and atypical cartilaginous tumours (ACT) of the knee joint represent benign/intermediate chondromatous neoplasms of the bone that are most commonly discovered incidentally. Based on small to intermediate-sized cohorts, the prevalence of cartilaginous tumours of the knee as visible in MRI is estimated at 0.2-2.9%. This study aimed at verifying/challenging these numbers via retrospective examination of a larger, uniform patient cohort. METHODS: Between 01.01.2007 and 01.03.2020, 44,762 patients had received an MRI of the knee for any indication at a radiologic centre. Of these, 697 patients presented with MRI reports positive for cartilaginous lesions. In a three-step workflow, 46 patients were excluded by a trained co-author, a radiologist and an orthopaedic oncologist, as wrongly being diagnosed for a cartilage tumour. RESULTS: Of 44,762 patients, 651 presented with at least one EC/ACT indicating a prevalence of 1.45% for benign/intermediate cartilaginous tumours of the knee joint (EC: 1.4%; ACTs: 0.05%). As 21 patients showed 2 chondromatous lesions, altogether 672 tumours (650 ECs [96.7%] and 22 ACTs [3.3%]) could be analysed in terms of tumour characteristics: With a mean size of 1.6 ± 1.1 cm, most lesions were located in the distal femur (72.9%), in the metaphysis of the respective bone (58.9%) and centrally in the medullary canal (57.4%). CONCLUSIONS: This study revealed an overall prevalence of 1.45% for cartilage lesions around the knee joint. Whilst a constant increase in prevalence was found for ECs over 13.2 years, prevalence remained constant for ACTs.

The use of radiomics and machine learning for the differentiation of chondrosarcoma from enchondroma.

PURPOSE: To construct and compare machine learning models for differentiating chondrosarcoma from enchondroma using radiomic features from T1 and fat suppressed Proton density (PD) magnetic resonance imaging (MRI). METHODS: Eighty-eight patients (57 with enchondroma, 31 with chondrosarcoma) were retrospectively included. Histogram matching and N4ITK MRI bias correction filters were applied. An experienced musculoskeletal radiologist and a senior resident in radiology performed manual segmentation. Voxel sizes were resampled. Laplacian of Gaussian filter and wavelet-based features were used. One thousand eight hundred eighty-eight features were obtained for each patient, with 944 from T1 and 944 from PD images. Sixty-four unstable features were removed. Seven machine learning models were used for classification. RESULTS: Classification with all features showed neural network was the best model for both readers' datasets with area under the curve (AUC), classification accuracy (CA), and F1 score of 0.979, 0.984; 0.920, 0.932; and 0.889, 0.903, respectively. Four features, including one common to both readers, were selected using fast correlation based filter. The best performing models with selected features were gradient boosting for Fatih Erdem's dataset and neural network for Gülen Demirpolat's dataset with AUC, CA, and F1 score of 0.990, 0.979; 0.943, 0.955; 0.921, 0.933, respectively. Neural Network was the second-best model for FE's dataset based on AUC (0.984). CONCLUSION: Using pathology as a gold standard, this study defined and compared seven well-performing models to distinguish enchondromas from chondrosarcomas and provided radiomic feature stability and reproducibility among the readers.

Clinical and Radiological Outcome of Osteoscopic-Assisted Treatment of Enchondroma in Hand with Artificial Bone Substitute or Bone Graft: A 7-Year Case Series and Literature Review.

Background: This study aims to look at the intermediate-term clinical, functional and radiological outcomes of patients with enchondroma in hand treated with osteoscopic-assisted curettage and artificial bone substitute or bone graft. The addition of osteoscopy allows direct visualisation of the bone cavity during and after curettage of tumour tissue without the need of creating a large opening in the bone cortex. This could lead to better clearance of tumour tissue and lower risk of iatrogenic fracture. Methods: A total of 11 patients who received surgery from December 2013 to November 2020 were retrospectively reviewed. All cases had histological diagnosis of enchondroma. Patients with a follow-up period of less than 3 months were excluded. The mean duration of follow-up was 20.9 months. For the clinical outcome, we measured the total active motion (TAM) and graded with Belsky score grip strength. For the functional outcome, the Quick Disabilities of the Arm, Shoulder and Hand Questionnaire (QuickDASH) score was used. For the radiological outcome, we evaluated the X-ray for bone cavity filling defect, new bone formation according to the system proposed by Tordai. Results: The mean TAM of patients was 257º. A total of 60% patients had Belsky score grading excellent, 40% patients had Belsky score grading good. The mean percentage of grip strength compared with the contralateral side was 86.2%. The mean QuickDASH score was 7.7. For the wound aesthetic rating by patients, 81.8% patients reported as excellent. For the radiological outcome, the postoperative X-ray of all patients showed bone filling defect less than 3 mm. The mean time to complete bone consolidation was 3.8 months. None of the patients showed any radiological signs of recurrence. Conclusions: Our study showed that patients with enchondromas in hand treated with this minimally invasive method demonstrated good functional and radiological outcome. Its application may also be extended into treating other benign bone lesions in hand. Level of Evidence: Level IV (Therapeutic).

Outcome of surgical interventions for solitary enchondromas of the hand : Controversial issues.

BACKGROUND: Enchondromas are the most common primary bone tumors of the hand and are benign cartilaginous tumors. This study evaluated the clinical and radiologic results of patients who underwent surgical interventions for isolated hand enchondromas with a minimum follow-up of 1 year and focused on controversial issues. METHODS: A retrospective study included 66 patients with solitary hand enchondromas with follow-up >12 months who underwent surgical interventions between January 2014 and July 2020. Patients with multiple enchondromas, low-grade chondrosarcoma, or who missed follow-up were excluded. All patients underwent thorough curettage with or without filling. Follow-up visits were done at 6 weeks, 3 months, 6 months, and annually. Demographic characteristics, clinical presentation, surgical details, final histologic examination, rehabilitation program, complications, and recurrences were recorded. The range of movement of the affected hand was compared to the contralateral one. Radiological evaluation of defect filling using the modified Neer classification was done. RESULTS: Of the patients 25 were male and 41 were female (38 right hand affection, 28 left hand affection), the mean age was 30.4 ± 11.9 years. Indications for surgery were local pain, swelling, and pathological fractures. The mean follow-up period was 28.8 ± 12.9 months (range 12-67 months). The mean MSTS score was 28.73 ± 1.6 (range 24-30). The middle finger was most frequently affected (18 cases, 27.3%) and the proximal phalanx was the most common location (37 cases, 56.1%). The mean length of lesions was 18.9 ± 6.67 mm and the mean width was 12.3 ± 4.1 mm. According to the modified Neer classification, 50 cases were classified as grade 1 (healed), 16 cases as grade 2 (healed with defects), and no case presented as persistent or recurrent lesions. CONCLUSION: Solitary hand enchondroma can be effectively treated with adequate curettage, with or without autologous bone grafting, with positive functional and radiological outcomes. When compared to grafting from the iliac crest, harvesting bone from the distal radius provides a shorter hospital stay and reduced complication rates.

Radiofrequency ablation for the treatment of a presumed enchondroma in the flat bones of the pelvis.

Herein, a 30-year-old Caucasian female who presented with a persistent pain in the right pelvic region due to an enchondroma and treated with RF ablation is described. An initial MRI of the pelvis revealed a well-circumscribed lesion in the right inferior ischiopubic ramus with a maximum diameter of 9.5 mm. The final diagnosis was established by a percutaneous CT-guided bone biopsy, which excluded malignancy and revealed an enchondroma. About a month after the biopsy, a percutaneous radiofrequency ablation (RFA) of the lesion was performed. The symptoms resolved completely gradually 2 months after the treatment and a follow-up imaging with MRI showed complete resolution of the pathological enhancement indicating necrosis of the lesion. RFA has not been previously reported as a treatment option of enchondromas found in flat bones of the pelvis and could be a safe alternative minimally invasive treatment option in such cases, avoiding major operations.

Intracapsular Chondroma Occurring in Metacarpophalangeal Joint of the Hand: A Rare Presentation.

Extraskeletal chondroma comprises synovial chondromatosis, intracapsular chondroma and soft tissue chondroma, its presentation in the hand, however, is very rare. A 42-year-old woman presented with a mass around right fourth metacarpophalangeal (MCP) joint. She had no pain or discomfort in activities. The radiographs showed soft tissue swelling, but no calcification or ossifying lesions. The magnetic resonance imaging (MRI) showed a lobulated juxta-cortical encircling mass existing around the fourth MCP joint. We did not suspect any cartilage-forming tumour in MRI. The mass was easily removed because there was no adhesion with surrounding tissues and the specimen had the appearance of a cartilage. The histological diagnosis was chondroma. Based on the tumour location and histological results, we diagnosed it as intracapsular chondroma. Although intracapsular chondroma is very rare-ly seen in the hands, it is important to consider an intracapsular chondroma when differentiating a tumour in the hand because it is difficult to diagnose one in an imaging examination. Level of Evidence: Level V (Therapeutic).