Advancing musculoskeletal tumor diagnosis: Automated segmentation and predictive classification using deep learning and radiomics.

OBJECTIVES: Musculoskeletal (MSK) tumors, given their high mortality rate and heterogeneity, necessitate precise examination and diagnosis to guide clinical treatment effectively. Magnetic resonance imaging (MRI) is pivotal in detecting MSK tumors, as it offers exceptional image contrast between bone and soft tissue. This study aims to enhance the speed of detection and the diagnostic accuracy of MSK tumors through automated segmentation and grading utilizing MRI. MATERIALS AND METHODS: The research included 170 patients (mean age, 58 years ±12 (standard deviation), 84 men) with MSK lesions, who underwent MRI scans from April 2021 to May 2023. We proposed a deep learning (DL) segmentation model MSAPN based on multi-scale attention and pixel-level reconstruction, and compared it with existing algorithms. Using MSAPN-segmented lesions to extract their radiomic features for the benign and malignant classification of tumors. RESULTS: Compared to the most advanced segmentation algorithms, MSAPN demonstrates better performance. The Dice similarity coefficients (DSC) are 0.871 and 0.815 in the testing set and independent validation set, respectively. The radiomics model for classifying benign and malignant lesions achieves an accuracy of 0.890. Moreover, there is no statistically significant difference between the radiomics model based on manual segmentation and MSAPN segmentation. CONCLUSION: This research contributes to the advancement of MSK tumor diagnosis through automated segmentation and predictive classification. The integration of DL algorithms and radiomics shows promising results, and the visualization analysis of feature maps enhances clinical interpretability.

Updates on WHO classification for small round cell tumors: Ewing sarcoma vs. everything else.

The WHO Classification of Soft Tissue and Bone Tumours currently recognizes four categories of undifferentiated small round cell sarcoma: Ewing sarcoma, round cell sarcoma with EWSR1-non-ETS fusions including NFATc2 and PATZ1, CIC-rearranged sarcoma, and sarcoma with BCOR genetic alterations. These neoplasms frequently pose significant diagnostic challenges due to rarity and overlapping morphologic and immunohistochemical findings. Further, molecular testing, with accompanying pitfalls, may be needed to establish a definitive diagnosis. This review summarizes the clinical, histologic, immunohistochemical, and molecular features of these neoplasms. In addition, differential diagnosis and areas of uncertainty and ongoing investigation are discussed.

Artificial intelligence-based classification of bone tumors in the proximal femur on plain radiographs: System development and validation.

PURPOSE: Early detection and classification of bone tumors in the proximal femur is crucial for their successful treatment. This study aimed to develop an artificial intelligence (AI) model to classify bone tumors in the proximal femur on plain radiographs. METHODS: Standard anteroposterior hip radiographs were obtained from a single tertiary referral center. A total of 538 femoral images were set for the AI model training, including 94 with malignant, 120 with benign, and 324 without tumors. The image data were pre-processed to be optimized for training of the deep learning model. The state-of-the-art convolutional neural network (CNN) algorithms were applied to pre-processed images to perform three-label classification (benign, malignant, or no tumor) on each femur. The performance of the CNN model was verified using fivefold cross-validation and was compared against that of four human doctors. RESULTS: The area under the receiver operating characteristic (AUROC) of the best performing CNN model for the three-label classification was 0.953 (95% confidence interval, 0.926-0.980). The diagnostic accuracy of the model (0.853) was significantly higher than that of the four doctors (0.794) (P = 0.001) and also that of each doctor individually (0.811, 0.796, 0.757, and 0.814, respectively) (P<0.05). The mean sensitivity, specificity, precision, and F1 score of the CNN models were 0.822, 0.912, 0.829, and 0.822, respectively, whereas the mean values of four doctors were 0.751, 0.889, 0.762, and 0.797, respectively. CONCLUSIONS: The AI-based model demonstrated high performance in classifying the presence of bone tumors in the proximal femur on plain radiographs. Our findings suggest that AI-based technology can potentially reduce the misdiagnosis of doctors who are not specialists in musculoskeletal oncology.

Cell Differentiation Trajectory-Associated Molecular Classification of Osteosarcoma.

This study aims to investigate the differentiation trajectory of osteosarcoma cells and to construct molecular subtypes with their respective characteristics and generate a multi-gene signature for predicting prognosis. Integrated single-cell RNA-sequencing (scRNA-seq) data, bulk RNA-seq data and microarray data from osteosarcoma samples were used for analysis. Via scRNA-seq data, time-related as well as differentiation-related genes were recognized as osteosarcoma tumor stem cell-related genes (OSCGs). In Gene Expression Omnibus (GEO) cohort, osteosarcoma patients were classified into two subtypes based on prognostic OSCGs and it was found that molecular typing successfully predicted overall survival, tumor microenvironment and immune infiltration status. Further, available drugs for influencing osteosarcoma via prognostic OSCGs were revealed. A 3-OSCG-based prognostic risk score signature was generated and by combining other clinic-pathological independent prognostic factor, stage at diagnosis, a nomogram was established to predict individual survival probability. In external independent TARGET cohort, the molecular types, the 3-gene signature as well as nomogram were validated. In conclusion, osteosarcoma cell differentiation occupies a crucial position in many facets, such as tumor prognosis and microenvironment, suggesting promising therapeutic targets for this disease.

Identification of a 3-gene signature based on differentially expressed invasion genes related to cancer molecular subtypes to predict the prognosis of osteosarcoma patients.

Invasion is a critical pathway leading to tumor metastasis. This study constructed an invasion-related polygenic signature to predict osteosarcoma prognosis. We initially determined two molecular subtypes of osteosarcoma, Cluster1 (C1) and Cluster2 (C2).. A 3 invasive-gene signature was established by univariate Cox analysis and least absolute shrinkage and selection operator (LASSO) Cox regression analysis of the differentially expressed genes (DEGs) between the two subtypes, and was validated in internal and two external data sets (GSE21257 and GSE39058). Patients were divided into high- and low-risk groups by their signature, and the prognosis of osteosarcoma patients in the high-risk group was poor. Based on the time-independent receiver operating characteristic (ROC) curve, the area under the curve (AUC) for 1-year and 2-year OS were higher than 0.75 in internal and external cohorts. This signature also showed a high accuracy and independence in predicting osteosarcoma prognosis and a higher AUC in predicting 1-year osteosarcoma survival than other four existing models. In a word, a 3 invasive gene-based signature was developed, showing a high performance in predicting osteosarcoma prognosis. This signature could facilitate clinical prognostic analysis of osteosarcoma.

Advances in targeted therapy for osteosarcoma based on molecular classification.

Osteosarcoma, a highly malignant tumor, is characterized by widespread and recurrent chromosomal and genetic abnormalities. In recent years, a number of elaborated sequencing analyses have made it possible to cluster the osteosarcoma based on the identification of candidate driver genes and develop targeted therapy. Here, we reviewed recent next-generation genome sequencing studies and advances in targeted therapies for osteosarcoma based on molecular classification. First, we stratified osteosarcomas into ten molecular subtypes based on genetic changes. And we analyzed potential targeted therapies for osteosarcoma based on the identified molecular subtypes. Finally, the development of targeted therapies for osteosarcoma investigated in clinical trials were further summarized and discussed. Therefore, we indicated the importance of molecular classification on the targeted therapy for osteosarcoma. And the stratification of patients based on the genetic characteristics of osteosarcoma will help to obtain a better therapeutic response to targeted therapies, bringing us closer to the era of personalized medicine.

DNA methylation-based profiling of bone and soft tissue tumours: a validation study of the 'DKFZ Sarcoma Classifier'.

Diagnosing bone and soft tissue neoplasms remains challenging because of the large number of subtypes, many of which lack diagnostic biomarkers. DNA methylation profiles have proven to be a reliable basis for the classification of brain tumours and, following this success, a DNA methylation-based sarcoma classification tool from the Deutsches Krebsforschungszentrum (DKFZ) in Heidelberg has been developed. In this study, we assessed the performance of their classifier on DNA methylation profiles of an independent data set of 986 bone and soft tissue tumours and controls. We found that the 'DKFZ Sarcoma Classifier' was able to produce a diagnostic prediction for 55% of the 986 samples, with 83% of these predictions concordant with the histological diagnosis. On limiting the validation to the 820 cases with histological diagnoses for which the DKFZ Classifier was trained, 61% of cases received a prediction, and the histological diagnosis was concordant with the predicted methylation class in 88% of these cases, findings comparable to those reported in the DKFZ Classifier paper. The classifier performed best when diagnosing mesenchymal chondrosarcomas (CHSs, 88% sensitivity), chordomas (85% sensitivity), and fibrous dysplasia (83% sensitivity). Amongst the subtypes least often classified correctly were clear cell CHSs (14% sensitivity), malignant peripheral nerve sheath tumours (27% sensitivity), and pleomorphic liposarcomas (29% sensitivity). The classifier predictions resulted in revision of the histological diagnosis in six of our cases. We observed that, although a higher tumour purity resulted in a greater likelihood of a prediction being made, it did not correlate with classifier accuracy. Our results show that the DKFZ Classifier represents a powerful research tool for exploring the pathogenesis of sarcoma; with refinement, it has the potential to be a valuable diagnostic tool.

Using Machine Learning to Unravel the Value of Radiographic Features for the Classification of Bone Tumors.

OBJECTIVES: To build and validate random forest (RF) models for the classification of bone tumors based on the conventional radiographic features of the lesion and patients' clinical characteristics, and identify the most essential features for the classification of bone tumors. MATERIALS AND METHODS: In this retrospective study, 796 patients (benign bone tumors: 412 cases, malignant bone tumors: 215 cases, intermediate bone tumors: 169 cases) with pathologically confirmed bone tumors from Nanfang Hospital of Southern Medical University, Foshan Hospital of TCM, and University of Hong Kong-Shenzhen Hospital were enrolled. RF models were built to classify tumors as benign, malignant, or intermediate based on conventional radiographic features and potentially relevant clinical characteristics extracted by three musculoskeletal radiologists with ten years of experience. SHapley Additive exPlanations (SHAP) was used to identify the most essential features for the classification of bone tumors. The diagnostic performance of the RF models was quantified using receiver operating characteristic (ROC) curves. RESULTS: The features extracted by the three radiologists had a satisfactory agreement and the minimum intraclass correlation coefficient (ICC) was 0.761 (CI: 0.686-0.824, P < .001). The binary and tertiary models were built to classify tumors as benign, malignant, or intermediate based on the imaging and clinical features from 627 and 796 patients. The AUC of the binary (19 variables) and tertiary (22 variables) models were 0.97 and 0.94, respectively. The accuracy of binary and tertiary models were 94.71% and 82.77%, respectively. In descending order, the most important features influencing classification in the binary model were margin, cortex involvement, and the pattern of bone destruction, and the most important features in the tertiary model were margin, high-density components, and cortex involvement. CONCLUSIONS: This study developed interpretable models to classify bone tumors with great performance. These should allow radiographers to identify imaging features that are important for the classification of bone tumors in the clinical setting.

Staging and Classification of Primary Musculoskeletal Bone and Soft-Tissue Tumors According to the 2020 WHO Update, From the AJR Special Series on Cancer Staging.

Staging of primary musculoskeletal bone and soft-tissue tumors is most commonly performed using the AJCC and the Enneking or Musculoskeletal Tumor Society (MSTS) staging systems. Radiologic imaging is integral in achieving adequate musculoskeletal neoplastic staging by defining lesion extent and identifying regional lymph node involvement and distant metastatic disease. Additional important features in surgical planning, though not distinct components of the staging systems, include cortical involvement, joint invasion, and neurovascular encasement; these features are optimally evaluated by MRI. In 2020, the WHO updated the classification of primary musculoskeletal tumors of soft tissue and bone. The update reflects the continued explosion in identification of novel gene alterations in many bone and soft-tissue neoplasms. This growth in gene alteration identification has resulted in newly designated lesions, reclassification of lesion categories, and improved specificity of diagnosis. Although radiologists do not need to have a comprehensive knowledge of the pathologic details, a broad working understanding of the most recent update is important to aid accurate and timely diagnosis given that histologic grading is a component of all staging systems. By using a multidisciplinary approach for primary musculoskeletal neoplasms involving colleagues in pathology, orthopedic oncology, radiation oncology, and medical oncology, radiologists may promote improved diagnosis, treatment, and outcomes.

Surgical Treatment and Proposed Modified Classification for Harrington Class III Periacetabular Metastases.

OBJECTIVES: This study aims to: (i) evaluate the outcome of patients with Harrington class III lesions who were treated according to Harrington classification; (ii) propose a modified surgical classification for Harrington class III lesions; and (iii) assess the efficiency of the proposed modified classification. METHODS: This study composes two phases. During phase 1 (2006 to 2011), the clinical data of 16 patients with Harrington class III lesions who were treated by intralesional excision followed by reconstruction of antegrade/retrograde Steinmann pins/screws with cemented total hip arthroplasty (Harrington/modified Harrington procedure) were retrospectively reviewed and further analyzed synthetically to design a modified surgical classification system. In phase 2 (2013 to 2019), 62 patients with Harrington class III lesions were classified and surgically treated according to our modified classification. Functional outcome was assessed using the Musculoskeletal Tumor Society (MSTS) 93 scoring system. The outcome of local control was described using 2-year recurrence-free survival (RFS). Owing to the limited sample size, we considered P < 0.1 as significant. RESULTS: In phase 1, the mean surgical time was 273.1 (180 to 390) min and the mean intraoperative hemorrhage was 2425.0 (400.0 to 8000.0) mL, respectively. The mean follow-up time was 18.5 (2 to 54) months. Recurrence was found in 4 patients and the 2-year RFS rate was 62.4% (95% confidence interval [CI] 31.6% to 93.2%). The mean postoperative MSTS93 score was 56.5% (20% to 90%). Based on the periacetabular bone destruction, we categorized the lesions into two subgroups: with the bone destruction distal to or around the inferior border of the sacroiliac joint (IIIa) and the bone destruction extended proximal to inferior border of the sacroiliac joint (IIIb). Six patients with IIIb lesions had significant prolonged surgical time (313.3 vs 249.0 min, P = 0.022), massive intraoperative hemorrhage (3533.3 vs 1760.0 mL, P = 0.093), poor functional outcome (46.7% vs 62.3%, P = 0.093), and unfavorable local control (31.3% vs 80.0%, P = 0.037) compared to the 10 patients with IIIa lesions. We then modified the surgical strategy for two subgroup of class III lesions: Harrington/modified Harrington procedure for IIIa lesions and en bloc resection followed by modular hemipelvic endoprosthesis replacement for IIIb lesions. Using the proposed modified surgical classification, 62 patients in the phase 2 study demonstrated improved surgical time (245.3 min, P = 0.086), intraoperative hemorrhage (1466.0 mL, P = 0.092), postoperative MSTS 93 scores (65.3%, P = 0.067), and 2-year RFS rate (91.3%, P = 0.002) during a mean follow-up time of 19.9 (1 to 60) months compared to those in the phase 1 study. CONCLUSION: The Harrington surgical classification is insufficient for class III lesions. We proposed modification of the classification for Harrington class III lesions by adding two subgroups and corresponding surgical strategies according to the involvement of bone destruction. Our proposed modified classification showed significant improvement in functional outcome and local control, along with acceptable surgical complexity in surgical management for Harrington class III lesions.

[Adult non-Hodgkin bone lymphomas]. / Les lymphomes non-Hodgkiniens osseux de l'adulte.

Two forms of bone lymphomas can be distinguished: the primary bone lymphoma (PBL) and the secondary bone lymphoma (SBL). PBL is a rare disease with a good prognosis. Clinical manifestations and imaging findings are usually non-specific. Patient can present with pain, swelling of affected bone or pathologic fracture. Positron emission tomography-CT scan is a sensitive imaging modality and very useful for staging, restaging, surveillance of recurrence, and monitoring of treatment response of lymphoma. The diagnosis of PBL is often difficult and made after biopsy examination. Most patients have diffuse large B-cell lymphoma. Patients have been treated with radiotherapy, chemotherapy or combination of both. Localized disease, low IPI (International Prognostic Index) and complete remission after initial treatment were associated with a better outcome. Management of late sequelae deserves particular attention. SBL is more common than PBL; this is a disseminated lymphoma with concomitant involvement of the skeleton. We review the clinical, imaging and pathologic features of bone lymphomas; and discuss therapeutic modalities as well as prognosis of these lymphomas in the era of immunochemotherapy.

A comparison of depth of necrosis among adjuvant therapies used for the treatment of benign bone tumors.

BACKGROUND AND OBJECTIVES: Benign bone tumors are often treated with extended curettage utilizing an adjuvant therapy to eliminate any remaining tumor cells. The purpose of this study was to explore and compare the histologic depth of necrosis created by various adjuvant therapies used in the treatment of benign bone tumors. METHODS: A high-speed burr was utilized to create cortical defects within porcine humeri and femora. Phenol, polymethyl methacrylate (PMMA), argon beam coagulation (ABC), liquid nitrogen, and the Bipolar Hemostatic Sealer (BHS) were each applied to five defects, with an additional five defects left untreated as a control. The maximal depth of necrosis was determined under microscopic examination. RESULTS: The phenol, PMMA, ABC, liquid nitrogen, and BHS demonstrated an average histologic depth of necrosis of 0.30, 0.78, 2.54, 2.54, and 0.92 mm, respectively, each of which was significantly increased compared to the control group (p = .001, .003, .003, .01, and  <.001). Their respective variances, a measure of reproducibility, were 0.01, 0.09, 0.96, 1.93, and 0.03 mm2 . CONCLUSION: This study confirms, through histologic analysis, adjuvant therapies create a rim of cellular necrosis beyond that of burring during extended curettage, supporting their use in the treatment of benign bone tumors. Furthermore, it provides a head-to-head comparison.

Sarcoma classification by DNA methylation profiling.

Sarcomas are malignant soft tissue and bone tumours affecting adults, adolescents and children. They represent a morphologically heterogeneous class of tumours and some entities lack defining histopathological features. Therefore, the diagnosis of sarcomas is burdened with a high inter-observer variability and misclassification rate. Here, we demonstrate classification of soft tissue and bone tumours using a machine learning classifier algorithm based on array-generated DNA methylation data. This sarcoma classifier is trained using a dataset of 1077 methylation profiles from comprehensively pre-characterized cases comprising 62 tumour methylation classes constituting a broad range of soft tissue and bone sarcoma subtypes across the entire age spectrum. The performance is validated in a cohort of 428 sarcomatous tumours, of which 322 cases were classified by the sarcoma classifier. Our results demonstrate the potential of the DNA methylation-based sarcoma classification for research and future diagnostic applications.

The 2020 WHO Classification of Tumors of Bone: An Updated Review.

Bone tumors are a rare and heterogeneous group of neoplasms that occur in the bone. The diversity and considerable morphologic overlap of bone tumors with other mesenchymal and nonmesenchymal bone lesions can complicate diagnosis. Accurate histologic diagnosis is crucial for appropriate management and prognostication. Since the publication of the fourth edition of the World Health Organization (WHO) classification of tumors of soft tissue and bone in 2013, significant advances have been made in our understanding of bone tumor molecular biology, classification, prognostication, and treatment. Detection of tumor-specific molecular alterations can facilitate the accurate diagnosis of histologically challenging cases. The fifth edition of the 2020 WHO classification of tumors of soft tissue and bone tumors provides an updated classification scheme and essential diagnostic criteria for bone tumors. Herein, we summarize these updates, focusing on major changes in each category of bone tumor, the newly described tumor entities and subtypes of existing tumor types, and newly described molecular and genetic data.

Management and retrospective analysis of tumors and tumor-like lesions localized in the talus.

OBJECTIVES: This study aims to investigate the characterization and follow-up results of tumors and tumor-like lesions in the talus. PATIENTS AND METHODS: Twenty-one patients (15 males, 6 females; mean age: 31.6±17 years; range, 4 to 67 years) with benign and malignant tumors or tumor-like lesions in the talus region treated and followed in our clinic between January 2007 and January 2019 were evaluated retrospectively. Radiological, pathological, surgical, and demographic features were scanned from the database. RESULTS: Patients were followed for mean 80±45.1 (range, 25 to 156) months. The most common complaint was pain and antalgic gait. Benign bone tumors were found in 15 (71%) of 21 patients, while tumor-like lesions (two intraosseous ganglia, osteomyelitis, and bone infarction) were found in four patients. The remaining two were patients with lung and bladder cancer metastasis. Lesion size was mean 2.1±0.5 (range, 1.1 to 3.3) cm. Recurrence developed in 14.3% (n=3) of the patients during follow-up. CONCLUSION: The talus is a rare location for tumors; however, benign and malignant tumors and tumor-like lesions may be localized in the talus.

Updates from the 2020 World Health Organization Classification of Soft Tissue and Bone Tumours.

The fifth edition of the World Health Organization (WHO) classification of soft tissue and bone tumours was published in May 2020. This 'Blue Book', which is also available digitally for the first time, incorporates an array of new information on these tumours, amassed in the 7 years since the previous edition. Major advances in molecular characterisation have driven further refinements in classification and the development of ancillary diagnostic tests, and have improved our understanding of disease pathogenesis. Several new entities are also included. This review summarises the main changes introduced in the 2020 WHO classification for each subcategory of soft tissue and bone tumours.

Clinicopathologic features of single bone metastasis in breast cancer.

ABSTRACT: The most common site for metastasis in patients with breast cancer is the bone. In this case series, we investigated patients whose surgical and medical treatment for primary breast cancer was conducted at our center and first disease recurrence was limited to only 1 bone.We analyzed 910 breast cancer patients, 863 had no metastasis and 47 cases had a single bone metastasis ≥ 6 months after their first diagnosis. Demographic, epidemiological, histopathological and intrinsic tumor subtype differences between the non-metastatic group and the group with solitary bone metastases and their statistical significance were examined. Among established breast cancer risk factors, we studied twenty-nine variables.Three variables (Type of tumor surgery, TNM Stage III tumors and mixed type (invasive ductalcarsinoma + invasive lobular carcinoma) histology) were significant in multivariate logistic regression analysis. Accordingly, the risk of developing single bone metastasis was approximately 15 times higher in patients who underwent mastectomy and 4.8 and 2.8 times higher in those with TNM Stage III tumors and with mixed type (invasive ductal carcinoma + invasive lobular carcinoma) histology, respectively.In conclusion, the risk of developing single bone metastasis is likely in non-metastatic patients with Stage III tumors and possibly in mixed type tumors. Knowing this risk, especially in patients with mixed type tumors, may be instrumental in taking measures with different adjuvant therapies in future studies. Among these, treatment modalities such as prolonged hormone therapy and addition of bisphosphonates to the adjuvant treatments of stage III and mixed breast cancer patients may be considered.

Derivation and validation of risk groups in patients with osteosarcoma utilizing regression tree analysis.

BACKGROUND: For patients with osteosarcoma, apart from stage and primary site, we lack reliable prognostic factors for risk stratification at diagnosis. There is a need for further defined, discrete prognostic groups using presenting clinical features. METHODS: We analyzed a cohort of 3069 patients less than 50 years of age, diagnosed with primary osteosarcoma of the bone between 1986 and 2013 from the Surveillance, Epidemiology, and End Results (SEER) database. Patients were randomly split into test and validation cohorts. Optimal cut points for age, tumor size, and grade were identified using classification and regression tree analysis. Manual recursive partitioning was used to identify discrete prognostic groups within the test cohort. These groups were applied to the validation cohort, and overall survival was analyzed using Cox models, Kaplan Meier methods, and log-rank tests. RESULTS: After applying recursive partitioning to the test cohort, our initial model included six groups. Application of these groups to the validation cohort resulted in four final groups. Key risk factors included presence of metastases, tumor site, tumor grade, age, and tumor size. Patients with localized axial tumors were identified as having similar outcomes to patients with metastases. Age and tumor size were only prognostically important in patients with extremity tumors when assessed in the validation cohort. CONCLUSIONS: This analysis supports prior reports that patients with axial tumors are a high-risk group, and demonstrates the importance of age and tumor size in patients with appendicular tumors. Biologic and genetic markers are needed to further define subgroups in osteosarcoma.

Bone metastasis classification using whole body images from prostate cancer patients based on convolutional neural networks application.

Bone metastasis is one of the most frequent diseases in prostate cancer; scintigraphy imaging is particularly important for the clinical diagnosis of bone metastasis. Up to date, minimal research has been conducted regarding the application of machine learning with emphasis on modern efficient convolutional neural networks (CNNs) algorithms, for the diagnosis of prostate cancer metastasis from bone scintigraphy images. The advantageous and outstanding capabilities of deep learning, machine learning's groundbreaking technological advancement, have not yet been fully investigated regarding their application in computer-aided diagnosis systems in the field of medical image analysis, such as the problem of bone metastasis classification in whole-body scans. In particular, CNNs are gaining great attention due to their ability to recognize complex visual patterns, in the same way as human perception operates. Considering all these new enhancements in the field of deep learning, a set of simpler, faster and more accurate CNN architectures, designed for classification of metastatic prostate cancer in bones, is explored. This research study has a two-fold goal: to create and also demonstrate a set of simple but robust CNN models for automatic classification of whole-body scans in two categories, malignant (bone metastasis) or healthy, using solely the scans at the input level. Through a meticulous exploration of CNN hyper-parameter selection and fine-tuning, the best architecture is selected with respect to classification accuracy. Thus a CNN model with improved classification capabilities for bone metastasis diagnosis is produced, using bone scans from prostate cancer patients. The achieved classification testing accuracy is 97.38%, whereas the average sensitivity is approximately 95.8%. Finally, the best-performing CNN method is compared to other popular and well-known CNN architectures used for medical imaging, like VGG16, ResNet50, GoogleNet and MobileNet. The classification results show that the proposed CNN-based approach outperforms the popular CNN methods in nuclear medicine for metastatic prostate cancer diagnosis in bones.

Multilobular tumor of bone on the forehead of a guinea pig.

Multilobular tumor of bone (MLTB) is an infrequent, slow-growing, bone neoplasm formed predominantly on the head. These tumors can behave as malignant neoplasms clinically and pathologically and can metastasize occasionally. No cases of MLTB in rodents have been reported, to our knowledge. We describe a novel case of an MLTB in a guinea pig. An adult guinea pig had an exophytic mass fixed on the frontal bone, maxilla, and nasal bone. On radiography, the mass had a spherical contour and variable density and was formed on the surface of the cranial bones. The mass was excised surgically. The cut surface was light-yellow to milky-white and had a granular texture with fine fibrous septa. Histologically, the neoplasm had a multilobular pattern, which consisted of many islands of bone and/or cartilage matrix surrounded by small cells and separated by fibrous septa, which closely resembles the equivalent neoplasm in dogs.