EENet: Application of convolutional neural network‐based deep learning methods in bone tumor pathological diagnosis

The aim of this study was to assess the ability of a new magnetic resonance (MR) angiography technique that does not use contrast enhancement medium to depict the vascularity of musculoskeletal neoplasms, and evaluate its clinical utility. We performed 3D fresh blood imaging (FBI) MR angiography in 57 patients with bone or soft tissue tumors, and the detection of vessels in and around the tumor was evaluated. Moreover, differences in vascularity between benign and malignant tumors were analyzed. In the lower leg, large arteries such as femoral or popliteal arteries were visible. In the trunk or arm, large vessels such as subclavian or iliac arteries were visible. Discrimination between benign and malignant tumors was impossible in bone tumors; however, the mean value of vascularity differed between benign and malignant tumors in the soft tissue tumors. This is the first trial of the FBI method for bone and soft tissue tumors. The still developing method of MRA without contrast materials could clearly depict major arteries in the trunk and the extremities, this method may replace conventional MRA of bone and soft tissue tumors because it produces vivid images while being non-invasive.

Molecular diagnostics have greatly advanced our understanding of the pathogenesis of soft tissue and bone neoplasms and have led to the development of numerous useful diagnostic tools. Definitive cytologic diagnosis is now possible for many soft tissue and bone tumors with judicious application of immunohistochemistry and numerous molecular technologies. Immunohistochemistry is primarily used to identify the line of differentiation and protein correlates of underlying molecular alterations and can guide appropriate selection of molecular tests. Currently, the most commonly employed molecular diagnostic approaches are fluorescence in situ hybridization and reverse transcription-polymerase chain reaction. High-throughput molecular techniques (e.g., whole-exome or targeted panel next-generation sequencing) have potential exciting applications for cytology practice, and these platforms can provide useful diagnostic and prognostic information in the diagnosis of soft tissue and bone tumors. While ancillary tests allow for more accurate classification of many soft tissue and bone neoplasms on cytologic material, immunohistochemical and molecular tests always should be interpreted in the context of the clinical, radiologic, and cytomorphologic features, and the cytopathologist must be aware of the pitfalls and limitations of these assays. This chapter reviews the applications of molecular diagnostics, including integration of immunohistochemical markers, in the cytologic diagnosis of soft tissue and bone neoplasms.

Objective To present recent concepts on the molecular pathogenesis of tumors of soft tissue and bone, and on the use of molecular genetic methods, including their significance as diagnostic markers and prognostic indicators. Data sources and study selection Reports on tumors of bone and/or soft tissue published in the English language literature and observations made using specimens available at the Departments of Pathology at Albany Medical College and Loyola University Medical Center. Data extraction and synthesis Studies on bone and soft tissue tumors containing chromosomal or genetic evaluation were selected for further analysis. Specific chromosomal abnormalities, such as numerical aberrations or translocations with production of fusion genes, were classified according to the tumor of origin. Data were also collected on mutations in tumor suppressor genes, genes coding for growth factors or their receptors, and genes coding for tyrosine kinases. Also noted were mutations of uncertain significance, for which the pathogenic connection between tumor production and mutated gene function is still unclear. Conclusions In general, the mutations reported interfere with the action of peptide growth factors coordinating mesenchyme proliferation and differentiation, although membrane-bound receptors expressing the intracellular signaling modifier, tyrosine kinase activity, have also been involved. Functional types of genes most commonly affected include tumor suppressors, oncogenes, and nuclear transcription factors. Thus, the mutations involved in the pathogenesis of soft tissue and bone tumors have affected multiple genes. Moreover, aberrant fusion gene products may be formed in tumoral tissue and may then act as transcription regulators stimulating cellular proliferation. Cytogenetic studies help at the clinical level by demonstrating aneuploidy and increased ploidy, which may correlate with malignant behavior. Diagnostic tumor-specific chromosomal translocations may be detected with Southern hybridization analysis, polymerase chain reaction, reverse-transcription polymerase chain reaction, or with the fluorescence in situ hybridization technique. Notably, early metastatic disease may be detectable in blood specimens using polymerase chain reaction or reverse-transcription polymerase chain reaction techniques.

Aims:The aim of this study is to evaluate the data belonging to patients who were diagnosed with benign or malignant soft tissue and bone tumors and tumor-like lesions evaluated by musculoskeletal tumor study group of Trakya University Faculty of Medicine in between January 2013 and June 2017 and the relationship between the frequency of benign, malignant bone and soft tissue tumors and tumor-like lesions, with the patients' age and gender. Methods:The data of 687 patients who were evaluated by the musculoskeletal tumor study group of Trakya University Faculty of Medicine between January 2013-June 2017 were analyzed retrospectively.All of the data was analyzed by using SPSS.Chi-square analysis was used to obtain categorical data in order to point out the distribution of age and gender of patients with musculoskeletal system tumors and tumor-like lesions. Results:The number of patients over the period from January 2013 to June 2017 was 687.The number of patients who were evaluated by biopsy and acquired histopathologic confirmation of their condition was 341.The mean of patients' ages was 44.3±21.4(4-92).Among 341 patients, 106 (47.1%) patients were female and 119 (52.9%) patients were male.The mean of females' ages was 43.7±20.4(4-92).The mean of males' ages was 44.7±22.4(5-90). Conclusion:Benign bone and soft tissue tumors were more common than malignant tumors.Benign bone tumors were predominantly seen in young adults.Our results was consistent with the literature however due to some patients who did not need a pathological sampling, our sample size was smaller than intended.With better archived information, more consistent results could be obtained in further studies.

Most of the current clinical data on the role of 2-[(18)F]fluoro-2-deoxy-D -glucose positron emission tomography ((18)F-FDG-PET) in musculoskeletal tumors come from patients studied with PET and less frequently with hardware fusion PET/computed tomography (CT). And the number of cases in each report is too small to clarify the exact clinical efficacy of PET or PET/CT. This prompted us to analyze our experience with (18)F-FDG-PET/CT in a relatively large group of patients with musculoskeletal tumors. (18)F-FDG-PET/CT was performed on 91 patients from May 2004 to June 2007. The final diagnosis was obtained from surgical biopsy in 83 patients (91%) and clinical follow-up in 8 (9%). We analyzed the characteristics and amount of (18)F-FDG uptake in soft tissue and bone tumors, and investigated the ability of (18)F-FDG-PET/CT to differentiate malignant from benign tumors. The cutoff maximum standardized uptake value (SUV(max)) was calculated using the receiver-operation characteristic curve method. Sensitivity, specificity, and diagnostic accuracy were calculated with cutoff SUV(max) and the final diagnosis. Unpaired t test was used for the statistical analysis. Final diagnosis revealed 19 benign soft tissue tumors (mean SUV(max) 4.7), 27 benign bone tumors (5.1), 25 malignant soft tissue tumors (8.8), and 20 malignant bone tumors (10.8). There was a significant difference in SUV(max) between benign and malignant musculoskeletal tumors in total (P < 0.002), soft tissue tumors (P < 0.05), and bone tumors (P < 0.02). Sensitivity, specificity, and diagnostic accuracy were 80%, 65.2%, and 73% in total with cutoff SUV(max) 3.8, 80%, 68.4%, and 75% in the soft tissue tumors with cutoff SUV(max) 3.8, and 80%, 63%, and 70% in the bone tumors with cutoff SUV(max) 3.7. (18)F-FDG-PET/CT reliably differentiated malignant soft tissue and bone tumors from benign ones, although there were many false-positive and false negative lesions. Further studies with all kinds of musculoskeletal tumors in large numbers are needed to improve the diagnostic accuracy of (18)F-FDG-PET/CT.

Bone and soft-tissue tumor patients experience long-lasting physical and psychological challenges. It is unknown to what extent Health-Related Quality of Life (HRQoL) is already affected during the diagnostic process. This study assesses the HRQoL of bone and soft-tissue tumor patients around time of diagnosis and explores which patient or tumor characteristics are associated with a reduced HRQoL. All patients with a suspected benign/malignant bone tumor (BT), benign soft-tissue tumor (STT), or malignant soft-tissue sarcoma (STS) visiting the Leiden University Medical Center between 2016 and 2020 were invited to complete the Patient-Reported Outcomes Measurement Information System (PROMIS) 29-item profile questionnaire. Mean scores of all included patients and per diagnosis group were compared to mean scores of the general population using one-sample t-tests. Overall, patients (n = 637) reported statistically significantly worse HRQoL-scores on anxiety (51.3 ± 9.6), pain (55.3 ± 10.1), physical functioning (46.0 ± 9.7), and social functioning (48.1 ± 10.8) with the difference in pain and physical functioning being clinically relevant (based on a 3-point difference on t-metric). HRQoL-scores differed between diagnosis subgroups, i.e., patients with malignant tumors had higher anxiety levels and experienced more pain, where patients with bone tumors had worse physical functioning. The HRQoL of patients with suspected bone and soft-tissue tumors is already affected during the diagnostic process.

In 31 patients with 21 soft tissue and 10 bone tumors, magnetic resonance imaging (MRI) and computed tomography (CT) were equally effective in delineating the margins of most soft tissue tumors, and the margins of bone tumors from fat and adjacent normal bone. However, MRI was superior to CT in delineating bone tumors from adjacent muscle, and in showing the relationships to bone of the deep margins of some soft tissue tumors. This was true because the quality of CT images around thick cortical bone often was severely degraded by streak artifact, which does not occur in MRI. Excellent anatomic detail was achieved on MRI by spin echo pulse sequences with short repetition times. Bone tumors were delineated best by spin echo 1000/30 images, and soft tissue tumors by spin echo 1000/30 or inversion recovery images.

Background: The diagnostic work-up of musculoskeletal tumors is a multifactorial process. During the early phase, differential diagnoses are made using basic radiological imaging. In this phase, part of the decision making is based on the patient's age, as well as the incidence and predilection sites of different entities. Unfortunately, this information is based on older and fragmented data. In this study, we retrospectively evaluated all soft-tissue and bone tumors around the knee in children treated at our tertiary center in the last 20 years, with the aim of verifying the data used today. Methods: In this retrospective study, the databank of our tertiary center was used to give an overview of treated tumors around the knee in children. Results: We were able to include 224 children with bone and soft-tissue tumors around the knee. The cohort consisted of 184 bone tumors, of which 144 were benign and 40 malignant. The 40 soft-tissue tumors comprised 30 benign and 10 malignant masses. The most common lesions were osteochondromas (88) in the bone and tenosynovial giant-cell tumors (12) in the soft tissue. Conclusions: With this original work, we were able to verify and supplement earlier studies, as well as deepen our insight into these very rare diseases.

Background:The management of musculoskeletal neoplasms requires an accurate diagnosis, histologic type, and degree of tumor differentiation.Aim:The present study was undertaken to compare the accuracy of fine-needle aspiration cytology (FNAC) and core needle biopsy (CNB) in the diagnosis of musculoskeletal tumors and further to compare the results with histopathological examination of surgical specimens. Grading of malignant tumors was also compared on these techniques.Materials and Methods:This prospective study was conducted on 50 patients with musculoskeletal neoplasms. Detailed history, clinical examination, and radiological investigations were undertaken. FNAC followed by CNB were performed in each case. The tumors were categorized as benign and malignant with a definitive histotype diagnosis. For malignant neoplasms, cytologic and histologic gradings were done into three grades. The sensitivity and specificity of FNAC and CNB were compared.Results:Of the 50 cases with musculoskeletal neoplasms, 32 (64%) were bone tumors and 18 (36%) were soft tissue tumors. The sensitivity of FNAC and CNB for categorizing bone tumors into benign and malignant was 94.7%. For soft tissue tumors, FNAC had a sensitivity of 90.9% and CNB had a sensitivity of 100%. The specificity of both the techniques, FNA and CNB for bone and soft tissue tumors was 100%. For malignant bone tumors, cytologic grade was concordant with CNB grade in 72.2% of the cases. Cytologic grade was concordant with the grade on CNB in 81.8% cases for malignant soft tissue neoplasms.Conclusion:FNAC and CNB alleviate the need for an open biopsy in diagnosing and grading musculoskeletal neoplasms, thus facilitating appropriate therapeutic intervention.

Wide surgical resection is the standard for primary malignant soft tissue and bone tumors, especially when the knee's intra-articular space is involved. Extraarticular Knee Joint Resection (EKJR) aims to remove the knee joint while preserving function. Considering the lack of literature present on these aspects, the purpose of this study is to analyze the data of a series of 30 patients affected by benign aggressive or malignant bone and soft tissue tumors who underwent EKJR with two different resection techniques. The study involved all patients treated with EKJR for tumors between October 2006 and March 2023. Two EKJR techniques were analyzed: Type-A (complete extensor mechanism excision) and Type-B (patellar coronal osteotomy sparing the extensor mechanism). Clinical outcomes, tumor characteristics, and complications were compared between the two techniques. For statistical analyses, the Mann-Whitney test or Kruskal-Wallis test was employed to explore differences between continuous variables. Relationships between categorical variables were assessed using Pearson's Chi-square test or Fisher's exact test. Correlations were evaluated using Spearman's correlation coefficient. Survival analyses were conducted using the Kaplan-Meier method. The cohort included 13 males and 17 females (16 Type-A, 14 Type-B resections). Histologically confirmed intra-articular involvement was found in 26.7% of cases. Late complications included infections and amputations, more frequently in Type-A resections. The 5-year Local Recurrence-Free Survival was 91.5%, Metastasis-Free Survival was 39.5%, and Overall Survival was 47.9%. Type-A resections lead to higher complication rates, including amputation, due to extensive vascular and tissue disruption. Type-B resections, preserving the extensor mechanism, result in better functional outcomes and faster recovery despite some residual weakness. EKJR is oncologically effective but carries significant functional and complication considerations. Type-B resection balances oncological safety and functional preservation, especially for benign aggressive tumors.

Detection of sarcoma fusions by a next-generation sequencing based–ligation-dependent multiplex RT-PCR assay

Management of malignant bone and soft tissue tumors remains an overwhelming confront to orthopedic surgeons. The challenge is discriminating in developing countries due to inadequate diagnostic and therapeutic amenities and unawareness. A lot has been discussed about the neglected orthopedic trauma, but the published literature on the causes and management of neglected bone and soft tissue tumors is sparse. Hence, current study was undertaken to highlight the causes of neglect and therapeutic challenges for managing these neglected tumors in developing countries. To determine the causes of neglect of malignant bone and soft tissue tumors, their epidemiology (including their relative frequencies, age, gender discrimination, anatomical sites of occurrence and histological characteristics) and difficult aspect of management due to neglect or delayed presentation. This was an appraisal of the neglected malignant bone and soft tissue tumors presented to J. N. Medical College and Hospital from June 2008 to May 2013. Criteria for labeling the tumor as neglected malignant bone and soft tissue tumor was delayed presentation (>3 months), locally advanced disease, ulceration, sepsis, fungating mass or metastasis at the time of presentation. All the cases were reviewed and analyzed for age, gender, histological types, educational status and socioeconomic status of the family, any prior treatment by traditional bone setters or registered medical practitioner, cause of delay for seeking medical advice. We have also analyzed the treatment given at our institute and the outcome of the tumor. Eighteen patients fulfilled the criteria for neglected malignant bone and soft tissue tumors, hence were included in study. Eight cases were of osteosarcoma, five cases were of Ewing's sarcoma, three cases were of chondrosarcoma and 1 case each was of pleomorphic liposarcoma and primary lymphoma of bone. According to Enneking staging system 11 cases were of stage III (distant metastasis) and 7 were stage II-B. Seven were females, and 11 were males. Age range was 5-68 years. 15 patients (83.3%) belonged to low socioeconomic status with 17 patients (94.4%) belonged to uneducated background. Cause of delay in seeking medical advice was neglect by the patient and family due to financial constraints, cultural and religious believes, lack of access to health care facilities, consultation with traditional bone setters and even misdiagnosis by qualified orthopedic surgeons. The tumors included were all unresectable and of huge sizes, hence were managed with amputation/dis-articulation, chemotherapy or radiation. The current study tries to highlight the causes and quantity of neglect of malignant bone and soft tissue tumors prevalent in our country, which poses a therapeutic challenge for management and consequent mutilating surgeries with poor outcome resulting in loss of extremity and existence.

Unmanned aerial vehicles (UAVs) are invaluable technologies concerning their remote control and monitoring capabilities. Convolutional neural networks (CNNs), known for their high pattern recognition capabilities, are appropriate for forest fire detection with UAVs. Deep convolutional neural networks show substantial performance on hardware with high processing capabilities. While these networks can be operated in unmanned aerial vehicles controlled from ground control stations equipped with GPU-supported hardware, the execution on a typical UAV’s limited computational resources necessitates the use of lightweight, small-sized networks. To overcome these impediments, this article presents a lightweight and attention-based approach for performing forest fire detection tasks using UAV vision data (images acquired by cameras mounted on UAVs). In this paper, we also present comprehensive research for different approaches such as transfer learning, deep CNNs, and lightweight CNNs. Among the experimented models, the attention-based EfficientNetB0 backboned model emerged as the most successful architecture for forest fire detection. With the test accuracy of , the F1-score of , the recall of , and the precision of have strongly reinforced the efficiency of the EfficientNetB0-based model in wildfire recognition. Moreover, the network has a less parameter size than the experimented networks. It proves the model’s suitability for wildfire detection with UAVs having limited hardware resources.

Value of thallium-201 scintigraphy in bone and soft tissue tumors

IntroductionThere has been an increased demand for mismatch repair (MMR) status testing in sarcoma patients after the success of immune checkpoint inhibition (ICI) in MMR deficient tumors. However, data on MMR deficiency in bone and soft tissue tumors is sparse, rendering it unclear if routine screening should be applied. Hence, we aimed to study the frequency of MMR deficiency in bone and soft tissue tumors after we were prompted by two (potential) Lynch syndrome patients developing sarcomas.MethodsImmunohistochemical expression of MLH1, PMS2, MSH2 and MSH6 was assessed on tissue micro arrays (TMAs), and included 353 bone and 539 soft tissue tumors. Molecular data was either retrieved from reports or microsatellite instability (MSI) analysis was performed. In MLH1 negative cases, additional MLH1 promoter hypermethylation analysis followed. Furthermore, a systematic literature review on MMR deficiency in bone and soft tissue tumors was conducted.ResultsEight MMR deficient tumors were identified (1%), which included four leiomyosarcoma, two rhabdomyosarcoma, one malignant peripheral nerve sheath tumor and one radiation‐associated sarcoma. Three patients were suspected for Lynch syndrome. Literature review revealed 30 MMR deficient sarcomas, of which 33% were undifferentiated/unclassifiable sarcomas. 57% of the patients were genetically predisposed.ConclusionMMR deficiency is rare in bone and soft tissue tumors. Screening focusing on tumors with myogenic differentiation, undifferentiated/unclassifiable sarcomas and in patients with a genetic predisposition / co‐occurrence of other malignancies can be helpful in identifying patients potentially eligible for ICI.