Purpose
To evaluate stability and machine learning-based classification performance of radiomic features of spine bone tumors using diffusion- and T2-weighted magnetic resonance imaging (MRI).
...Material and methods
This retrospective study included 101 patients with histology-proven spine bone tumor (22 benign; 38 primary malignant; 41 metastatic). All tumor volumes were manually segmented on morphologic T2-weighted sequences. The same region of interest (ROI) was used to perform radiomic analysis on ADC map. A total of 1702 radiomic features was considered. Feature stability was assessed through small geometrical transformations of the ROIs mimicking multiple manual delineations. Intraclass correlation coefficient (ICC) quantified feature stability. Feature selection consisted of stability-based (ICC > 0.75) and significance-based selections (ranking features by decreasing Mann–Whitney p-value). Class balancing was performed to oversample the minority (i.e., benign) class. Selected features were used to train and test a support vector machine (SVM) to discriminate benign from malignant spine tumors using tenfold cross-validation.
Results
A total of 76.4% radiomic features were stable. The quality metrics for the SVM were evaluated as a function of the number of selected features. The radiomic model with the best performance and the lowest number of features for classifying tumor types included 8 features. The metrics were 78% sensitivity, 68% specificity, 76% accuracy and AUC 0.78.
Conclusion
SVM classifiers based on radiomic features extracted from T2- and diffusion-weighted imaging with ADC map are promising for classification of spine bone tumors. Radiomic features of spine bone tumors show good reproducibility rates.
Clinical management ranges from surveillance or curettage to wide resection for atypical to higher-grade cartilaginous tumours, respectively. Our aim was to investigate the performance of computed ...tomography (CT) radiomics-based machine learning for classification of atypical cartilaginous tumours and higher-grade chondrosarcomas of long bones.
One-hundred-twenty patients with histology-proven lesions were retrospectively included. The training cohort consisted of 84 CT scans from centre 1 (n=55 G1 or atypical cartilaginous tumours; n=29 G2-G4 chondrosarcomas). The external test cohort consisted of the CT component of 36 positron emission tomography-CT scans from centre 2 (n=16 G1 or atypical cartilaginous tumours; n=20 G2-G4 chondrosarcomas). Bidimensional segmentation was performed on preoperative CT. Radiomic features were extracted. After dimensionality reduction and class balancing in centre 1, the performance of a machine-learning classifier (LogitBoost) was assessed on the training cohort using 10-fold cross-validation and on the external test cohort. In centre 2, its performance was compared with preoperative biopsy and an experienced radiologist using McNemar's test.
The classifier had 81% (AUC=0.89) and 75% (AUC=0.78) accuracy in identifying the lesions in the training and external test cohorts, respectively. Specifically, its accuracy in classifying atypical cartilaginous tumours and higher-grade chondrosarcomas was 84% and 78% in the training cohort, and 81% and 70% in the external test cohort, respectively. Preoperative biopsy had 64% (AUC=0.66) accuracy (p=0.29). The radiologist had 81% accuracy (p=0.75).
Machine learning showed good accuracy in classifying atypical and higher-grade cartilaginous tumours of long bones based on preoperative CT radiomic features.
ESSR Young Researchers Grant.
Conventional central chondrosarcoma (CCC) is a malignant bone tumor that is characterized by the production of chondroid tissue. Since radiation therapy and chemotherapy have limited effects on CCC, ...treatment of most patients depends on surgical resection. This study aimed to identify the expression profiles of microRNAs (miRNAs) and isomiRs in CCC tissues to highlight their possible participation to the regulation of pathways critical for the formation and growth of this type of tumor. Our study analyzed miRNAs and isomiRs from Grade I (GI), Grade II (GII), and Grade III (GIII) histologically validated CCC tissue samples. While the different histological grades shared a similar expression profile for the top abundant miRNAs, we found several microRNAs and isomiRs showing a strong different modulation in GII + GIII vs GI grade samples and their involvement in tumor biology could be consistently hypothesized. We then in silico validated these differently expressed miRNAs in a larger chondrosarcoma public dataset and confirmed the expression trend for 17 out of 34 miRNAs. Our results clearly suggests that the contribution of miRNA deregulation, and their targeted pathways, to the progression of CCC could be relevant and strongly indicates that when studying miRNA deregulation in tumors, not only the canonical miRNAs, but the whole set of corresponding isomiRs should be taken in account. Improving understanding of the precise roles of miRNAs and isomiRs over the course of central chondrosarcoma progression could help identifying possible targets for precision medicine therapeutic intervention.
Purpose
To determine diagnostic performance of MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor (ALT) of the extremities.
Material and ...methods
This retrospective study was performed at three tertiary sarcoma centers and included 150 patients with surgically treated and histology-proven lesions. The training-validation cohort consisted of 114 patients from centers 1 and 2 (n = 64 lipoma, n = 50 ALT). The external test cohort consisted of 36 patients from center 3 (n = 24 lipoma, n = 12 ALT). 3D segmentation was manually performed on T1- and T2-weighted MRI. After extraction and selection of radiomic features, three machine learning classifiers were trained and validated using nested fivefold cross-validation. The best-performing classifier according to previous analysis was evaluated and compared to an experienced musculoskeletal radiologist in the external test cohort.
Results
Eight features passed feature selection and were incorporated into the machine learning models. After training and validation (74% ROC-AUC), the best-performing classifier (Random Forest) showed 92% sensitivity and 33% specificity in the external test cohort with no statistical difference compared to the radiologist (
p
= 0.474).
Conclusion
MRI radiomics-based machine learning may classify deep-seated lipoma and ALT of the extremities with high sensitivity and negative predictive value, thus potentially serving as a non-invasive screening tool to reduce unnecessary referral to tertiary tumor centers.
Bizarre parosteal osteochondromatous proliferation (BPOP) is a surface-based bone lesion belonging to the group of benign chondrogenic tumors. The aim of this review is to familiarize the readers ...with imaging features and differential diagnosis of BPOP, also addressing pathological presentation and treatment options. The peak of incidence of BPOP is in the third and fourth decades of life, although it can occur at any age. Hands are the most common location of BPOP (55%), followed by feet (15%) and long bones (25%). On imaging, BPOP appears as a well-marginated mass of heterotopic mineralization arising from the periosteal aspect of the bone. Typical features of BPOP are contiguity with the underlying bone and lack of cortico-medullary continuity, although cortical interruption and medullary involvement have been rarely reported. Histologically, BPOP is a benign bone surface lesion characterized by osteocartilaginous proliferation with disorganized admixture of cartilage with bizarre features, bone and spindle cells. Differential diagnosis includes both benign—such as florid reactive periostitis, osteochondroma, subungual exostosis, periosteal chondroma and myositis ossificans—and malignant lesions—such as periosteal chondrosarcoma and surface-based osteosarcoma. Treatment consists of surgical resection. Local recurrences are common and treated with re-excision.
Critical relevance statement
Bizarre parosteal osteochondromatous proliferation is a benign mineralized mass arising from the periosteal aspect of bone cortex. Multi-modality imaging characteristics, pathology features and differential diagnosis are here highlighted to familiarize the readers with this entity and offer optimal patient care.
Key points
Bizarre parosteal osteochondromatous proliferation (BPOP) is a benign surface-based bone lesion.
Hands are the most common location, followed by long bones and feet.
BPOP is a mineralized mass arising from the periosteal aspect of bones.
Histologically, it is composed of a mixture of cartilage, bone, fibrous tissue.
Treatment consists of surgical resection, but local recurrences are common.
ObjectivesThis study investigates the diagnostic role of synovial tissue analysis in children presenting with arthritis and assesses its prognostic significance to predict clinical outcome in ...juvenile idiopathic arthritis (JIA).MethodsSynovial samples of paediatric patients undergoing synovial biopsy between 1995 and 2020 were analysed histologically and immunohistochemically. Relationships between histological/immunohistochemical parameters and clinical variables were assessed.ResultsSynovial biopsy was performed for diagnosis in 65 cases allowing to correctly classify 79% of patients.At histological analysis on 42 JIA samples, any difference in the number of synovial lining layers, subsynovial elementary lesions, fibrin deposit, Krenn Synovitis Score, inflammatory infiltrate score and pattern emerged between JIA subsets or on treatment exposure. Synovial tissue analysis predicted outcome: higher number of synovial layers predicted worse disease course (>4 flares during follow-up; 4.5 vs 3.0, p=0.035), even after adjusting for age at diagnosis and observation time (OR 2.2, p=0.007); subjects who had switched>2 biological disease-modifying antirheumatic drugs had higher prevalence of subsynovial elementary lesions (55.6% vs 10.3%, p=0.005) and fibrin deposits in synovial lining (60.0% vs 22.6%, p=0.049), even after adjustment for observation time and age at diagnosis (OR 8.1, p=0.047). At immunohistochemistry on 31 JIA samples, higher CD3 expression was described in polyarticular compared with oligoarticular subset (p=0.040). Patients with severe disease course had higher CD20+ rate (OR 7, p=0.023), regardless of JIA subset and treatment exposure.ConclusionsSynovial tissue analysis might support the clinicians in the diagnostic approach of paediatric patients presenting with arthritis and guide the clinical management in JIA.
The molecular mechanism responsible for Ewing's Sarcoma (ES) remains largely unknown. MicroRNAs (miRNAs), a class of small non-coding RNAs able to regulate gene expression, are deregulated in tumors ...and may serve as a tool for diagnosis and prediction. However, the status of miRNAs in ES has not yet been thoroughly investigated. This study compared global miRNAs expression in paraffin-embedded tumor tissue samples from 20 ES patients, affected by primary untreated tumors, with miRNAs expressed in normal human mesenchymal stromal cells (MSCs) by microarray analysis. A miRTarBase database was used to identify the predicted target genes for differentially expressed miRNAs. The miRNAs microarray analysis revealed distinct patterns of miRNAs expression between ES samples and normal MSCs. 58 of the 954 analyzed miRNAs were significantly differentially expressed in ES samples compared to MSCs. Moreover, the qRT-PCR analysis carried out on three selected miRNAs showed that miR-181b, miR-1915 and miR-1275 were significantly aberrantly regulated, confirming the microarray results. Bio-database analysis identified BCL-2 as a bona fide target gene of the miR-21, miR-181a, miR-181b, miR-29a, miR-29b, miR-497, miR-195, miR-let-7a, miR-34a and miR-1915. Using paraffin-embedded tissues from ES patients, this study has identified several potential target miRNAs and one gene that might be considered a novel critical biomarker for ES pathogenesis.
Background
Phosphaturic mesenchymal tumors are rare neoplasms, frequently presenting with osteomalacia. These neoplasms usually grow at a slow rate and are associated with unspecific symptoms.
Case
...In this study, we present the case of a 70‐year‐old woman who had been suffering from musculoskeletal pain, hypophosphatemia, and spontaneous fractures. Positron emission tomography with Gallium showed increase uptake in a subpleural lesion.
Conclusion
The patient underwent surgical excision of the subpleural lesion with a non‐intubated uniportal video‐assisted thoracoscopic surgery approach.
Summary Brown tumors are osteoclastic, benign lesions characterized by fibrotic stroma, intense vascularization and multinucleated giant cells. They are the terminal expression of the bone ...remodelling process occurring in advanced hyperparathyroidism. Nowadays, due to earlier diagnosis, primary hyperparathyroidism keeps few of the classical manifestations and brown tumors are definitely unexpected. Thus, it may happen that they are misdiagnosed as primary or metastatic bone cancer. Besides bone imaging, endocrine evaluation including measurement of serum parathyroid hormone and calcium (Ca) levels supports the pathologist to address the diagnosis. Herein, a case of multiple large brown tumors misdiagnosed as a non-treatable osteosarcoma is described, with special regards to diagnostic work-up. After selective parathyroidectomy, treatment with denosumab was initiated and a regular follow-up was established. The central role of multidisciplinary approach involving pathologist, endocrinologist and oncologist in the diagnostic and therapeutic work-up is reported. In our opinion, the discussion of this case would be functional especially for clinicians and pathologists not used to the differential diagnosis in uncommon bone disorders. Learning points: Brown tumors develop during the remodelling process of bone in advanced and long-lasting primary or secondary hyperparathyroidism. Although rare, they should be considered during the challenging diagnostic work-up of giant cell lesions. Coexistence of high parathyroid hormone levels and hypercalcemia in primary hyperparathyroidism is crucial for the diagnosis. A detailed imaging study includes bone X-ray, bone scintiscan and total body CT; to rule out bone malignancy, evaluation of bone lesion biopsy should include immunostaining for neoplastic markers as H3G34W and Ki67 index. If primary hyperparathyroidism is confirmed, selective parathyroidectomy is the first-line treatment. In advanced bone disease, treatment with denosumab should be considered, ensuring a strict control of Ca levels.
Selection of cancer patients for treatment with immune checkpoint inhibitors remains a challenge due to tumour heterogeneity and variable biomarker detection. PD-L1 expression in 24 surgical chordoma ...specimen was determined immunohistochemically with antibodies 28-8 and E1L3N. The ability of patient-derived organoids to detect treatment effects of nivolumab was explored by quantitative and qualitative immunofluorescence and FACS analysis. The more sensitive antibody, E1L3N (ROC = 0.896, p = 0.001), was associated with greater tumour diameters (p = 0.014) and detected both tumour cells and infiltrating lymphocytes in 54% of patients, but only 1-15% of their cells. Organoids generated from PD-L1-positive patients contained both tumour cells and PD-1/CD8-positive lymphocytes and responded to nivolumab treatment with marked dose-dependent diameter reductions of up to 50% and increased cell death in both PD-L1-positive and negative organoids. Patient-derived organoids may be valuable to predict individual responses to immunotherapy even in patients with low or no immunohistochemical PD-L1 expression.