Machine learning to differentiate small round cell malignant tumors and non-small round cell malignant tumors of the nasal and paranasal sinuses using apparent diffusion coefficient values

Objective We used radiomics feature–based machine learning classifiers of apparent diffusion coefficient (ADC) maps to differentiate small round cell malignant tumors (SRCMTs) and non-SRCMTs of the nasal and paranasal sinuses. Materials A total of 267 features were extracted from each region of interest (ROI). Datasets were randomized into two sets, a training set (∼70%) and a test set (∼30%). We performed dimensional reductions using the Pearson correlation coefficient and feature selection analyses (analysis of variance [ANOVA], relief, recursive feature elimination [RFE]) and classifications using 10 machine learning classifiers. Results were evaluated with a leave-one-out cross-validation analysis. Results We compared the AUC for all the pipelines in the validation dataset using FeAture Explorer (FAE) software. The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUCs with ten features. When the “one-standard error” rule was used, FAE produced a simpler model with eight features, including Perc.01%, Perc.10%, Perc.90%, Perc.99%, S(1,0) SumAverg, S(5,5) AngScMom, S(5,5) Correlat, and WavEnLH_s-2. The AUCs of the training, validation, and test datasets achieved 0.995, 0.902, and 0.710, respectively. For ANOVA, the pipeline with the auto-encoder classifier yielded the highest AUC using only one feature, Perc.10% (training/validation/test datasets: 0.886/0.895/0.809, respectively). For the relief, the AUCs of the training, validation, and test datasets that used the LRLasso classifier using five features (Perc.01%, Perc.10%, S(4,4) Correlat, S(5,0) SumAverg, S(5,0) Contrast) were 0.892, 0.886, and 0.787, respectively. Compared with the RFE and relief, the results of all algorithms of ANOVA feature selection were more stable with the AUC values higher than 0.800. Conclusions We demonstrated the feasibility of combining artificial intelligence with the radiomics from ADC values in the differential diagnosis of SRCMTs and non-SRCMTs and the potential of this non-invasive approach for clinical applications. Key Points • The parameter with the best diagnostic performance in differentiating SRCMTs from non-SRCMTs was the Perc.10% ADC value. • Results of all the algorithms of ANOVA feature selection were more stable and the AUCs were higher than 0.800, as compared with RFE and relief. • The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUC.

Primary desmoplastic small round cell tumor of the submandibular gland: a case report and literature review

Background Desmoplastic small round cell tumor (DSRCT) is a sporadic, highly malignant tumor with a poor prognosis. The abdomen and pelvis have been reported as the primary localization sites. However, to the best of our knowledge, there are few reports on primary DSRCT in the submandibular gland. Case presentation We report a case of a 26-year-old Chinese man with a mass in the right submandibular gland. Imaging studies showed a hypoechoic mass in the right submandibular region. Intraoperative pathology revealed that the tumor tissue was composed of small round tumor cells and a dense desmoplastic stroma. On immunostaining, the tumor cells showed markers of epithelial, mesenchymal, myogenic, and neural differentiation. The EWSR1 gene rearrangement was detected by fluorescence in situ hybridization. Based on the overall morphological features and immunohistochemical findings, a final diagnosis of DSRCT was made. The patient was treated with comprehensive anti-tumor therapy mainly based on radiotherapy and chemotherapy. Conclusions DSRCT is an uncommon malignant neoplasm with rare submandibular gland involvement. In this report, we have described a case of DSRCT in the submandibular gland and reviewed the literature on DSRCT over the past 5 years. Considering the importance of differential diagnosis between DSRCT, especially with rare extra-peritoneal involvement, and small round blue cell tumors, a full recognition of the clinicopathological features will help to better diagnose this neoplasm.

Parotid Salivary Gland Extramedullary Plasmacytoma with Local Lymph Node Metastasis in a Dog

ABSTRACT A 12 yr old spayed female mixed-breed dog presented for evaluation of a recurrent soft-tissue sarcoma. On physical examination, a firm mass was palpated ventral to the left ramus of the mandible. A fine-needle aspirate of the mass was suggestive of a round-cell neoplasm. A complete blood count, serum biochemical profile, and an abdominal ultrasound with liver and splenic aspirates were performed, and no clinically relevant abnormalities were identified. Advanced imaging of the skull identified an enlarged parotid salivary gland and an enlarged ipsilateral medial retropharyngeal lymph node. The medial retropharyngeal lymph node was sampled via fine-needle aspiration, and a round-cell population similar to what was present in the mass was identified. An incisional biopsy was performed under general anesthesia, which yielded a diagnosis of salivary gland extramedullary plasmacytoma, confirmed with immunohistochemistry (MUM-1). The parotid salivary gland and medial retropharyngeal lymph node were then surgically excised, and metastasis to the lymph node was confirmed by histopathology. The dog remained alive for 685 days after surgery until she was euthanized for hindlimb paresis of undetermined cause.

A Case Report on Malignant Rhabdoid Round Cell Tumor in Pelvis

The malignant neoplasm is called as malignant rhabdoid tumor or renal tumor. The Malignant tumor had the highest rate of proliferation. Tiny, round, and generally undifferentiated cells make up malignant small round cell tumours. A round cell tumor is a group of malignant tumors composed of relatively small and undifferentiated cells with an increased nuclear - cytoplasmic ratio. Soft tissue malignant tumours of the abdomen and pelvis are a rare but serious kind of cancer. Examples of these tumours include Ewing's sarcoma, peripheral neuroectodermal tumour, rhabdomyosarcoma, synovial sarcoma, non-lymphoma, Hodgkin's retinoblastoma, neuroblastoma, and hepatoblastoma. Mast cell tumour, histiocytoma, lymphoma, plasmacytoma, and transmissible venereal tumours are some of the different types of round cell tumours. Melanomas are the cytologic "great impostor," as they might look on cytology as round cell tumours despite being classed as mesenchymal cancers. Rhabdoid tumours have long been thought to be extremely malignant and have a bad prognosis. Children with this form of tumour have a six to eleven-month median survival duration. They're also less common. In 5% of small round cell tumor patients, can be curable, and it is best achieved by combining systemic chemotherapy with thorough cytoreductive surgery. Here we report a 9-year-old female child who was diagnosed with a malignant rhabdoid round cell tumor in the pelvis. She has undergone excision of pelvic floor tumor andfurther managed with Chemotherapy.

Case Report: Primary Diffuse Leptomeningeal Oligodendrogliomatosis in a Young Adult Cat

A 2-year-old cat was presented with progressive ataxia. Despite treatment the animal died. Pathomorphological examination revealed a widespread leptomeningeal mass at all levels of the central nervous system accentuated on the cervical spinal cord and the medulla oblongata without presence of a primary intraaxial tumor. The neoplasm was mainly composed of round, uninucleate cells with hyperchromatic nuclei, which were immunopositive for OLIG2, doublecortin, MAP2, synaptophysin, and vimentin, indicating components of both oligodendroglial and neuronal differentiation. Ki-67 immunohistochemistry indicated a high proliferation activity of the neoplasm. Few GFAP positive and Iba-1 positive cells were interpreted as reactive astrocytes and macrophages or microglia, respectively. The tumor was immunonegative for CD3, CD20, PAX5, MUM1, pan-cytokeratin, S100, NSE, p75NTR, NeuN and periaxin. These findings led to the diagnosis of primary diffuse leptomeningeal oligodendrogliomatosis. This is the first reported case of this entity in a young cat, which should be considered as a differential diagnosis for diffuse subarachnoidal round cell infiltrates.