Atypical Lipomatous Tumor/Well-Differentiated Liposarcoma With Features Mimicking Spindle Cell Lipoma

Large atypical lipomatous tumour of the neck with mediastinal extension managed by transcervical excision

Tumours of adipose tissue origin are relatively rare in the head and neck. Here, we report a case of an unfamiliar lipomatous lesion that involved the neck and mediastinum. A nil-comorbid man in his 40s presented with a slowly progressive anterior neck swelling of 3 years, which was diagnosed as lipoma by histopathological sampling. Computed tomography demonstrated the lesion to be involving parapharyngeal and retropharyngeal spaces with mediastinal extension. The lesion was removed by the transcervical approach. The final histology of the excised specimen, with immunohistochemistry for mouse double minute 2 (MDM2) and p16, suggested an atypical lipomatous tumour (ALT). This report accentuates the occurrence of this rare neoplasm in the neck, which often mimics lipoma clinically. Although radiology can demonstrate suggestive features, histology with MDM2 and/or p16 positivity can confirm the diagnosis of ALT as against the lipoma. A successful transcervical excision, despite the deeper extension of the lesion between the critical structures of the neck and mediastinum, demonstrates the non-infiltrating nature of the tumour.

Prediction of lipomatous soft tissue malignancy on MRI: comparison between machine learning applied to radiomics and deep learning

Objectives

Malignancy of lipomatous soft-tissue tumours diagnosis is suspected on magnetic resonance imaging (MRI) and requires a biopsy. The aim of this study is to compare the performances of MRI radiomic machine learning (ML) analysis with deep learning (DL) to predict malignancy in patients with lipomas oratypical lipomatous tumours.

Methods

Cohort include 145 patients affected by lipomatous soft tissue tumours with histology and fat-suppressed gadolinium contrast-enhanced T1-weighted MRI pulse sequence. Images were collected between 2010 and 2019 over 78 centres with non-uniform protocols (three different magnetic field strengths (1.0, 1.5 and 3.0 T) on 16 MR systems commercialised by four vendors (General Electric, Siemens, Philips, Toshiba)).

Two approaches have been compared: (i) ML from radiomic features with and without batch correction; and (ii) DL from images. Performances were assessed using 10 cross-validation folds from a test set and next in external validation data.

Results

The best DL model was obtained using ResNet50 (resulting into an area under the curve (AUC) of 0.87 ± 0.11 (95% CI 0.65−1). For ML/radiomics, performances reached AUCs equal to 0.83 ± 0.12 (95% CI 0.59−1) and 0.99 ± 0.02 (95% CI 0.95−1) on test cohort using gradient boosting without and with batch effect correction, respectively. On the external cohort, the AUC of the gradient boosting model was equal to 0.80 and for an optimised decision threshold sensitivity and specificity were equal to 100% and 32% respectively.

Conclusions

In this context of limited observations, batch-effect corrected ML/radiomics approaches outperformed DL-based models.

Supplementary Information

The online version contains supplementary material available at 10.1186/s41747-022-00295-9.

Spindle Cell Lipoma with Ossification Mimicking Atypical Lipomatous Tumor/Well-Differentiated Liposarcoma: A Case Report

Although spindle cell lipoma (SCL) is a subtype of lipoma, the characteristics of SCL are observed in both lipomatous and non-lipomatous tumors. In this article, we present a case of SCL with ossification mimicking atypical lipomatous tumors/well-differentiated liposarcomas (ALTs/WDLs). Considering the findings of magnetic resonance imaging and needle biopsy, which exhibited ALTs/WDLs, marginal resection was performed. Histopathological findings demonstrated mature adipocytes and spindle cells without atypia and no malignant osteoid tissue in the ossified region. In addition, immunohistochemistry (IHC) showed positive staining for CD34, heterogeneous retinoblastoma protein deficiency, and negative staining for mouse double minute 2 homolog (MDM2) and cyclin-dependent kinase. Fluorescence in-situ hybridization showed negative amplification of MDM2. The final diagnosis of the tumor was established using IHC as an extremely rare SCL with ossification.

Lessons learnt from MDM2 fluorescence in-situ hybridisation analysis of 439 mature lipomatous lesions with an emphasis on atypical lipomatous tumour/well-differentiated liposarcoma lacking cytological atypia

AIMS

Amplification of the murine double minute-2 (MDM2) gene, which is usually detected with fluorescence in-situ hybridisation (FISH), is the key driving event for atypical lipomatous tumours (ALTs)/well-differentiated liposarcomas (WDLs). We sought to determine the concordance between the histopathological findings and MDM2 FISH in the diagnosis of ALT/WDL, and to identify the histological features of MDM2-amplified tumours lacking classic atypia.

METHODS AND RESULTS

We performed a retrospective analysis of all mature lipomatous lesions subjected to MDM2 FISH analysis at our institution. MDM2 FISH analysis was performed on 439 mature lipomatous lesions: 364 (82.9%) were negative and 75 (17%) were positive. In 17 of 75 (22.6%) ALTs/WDLs, cytological atypia was not identified on initial histological assessment, thus favouring lipoma. On review, these cases shared common histological features, consisting of a very low number of relatively small stromal cells within the tumour lobules, with mildly coarse chromatin and oval nuclei, admixed with unremarkable adipocytes in a tumour background devoid of fibroconnective septa, areas of fibrosis, or blood vessels. These cells matched the cells in which FISH showed MDM2 amplification. In contrast, 13 cases (3.5%) regarded as suspicious for ALT/WDL on the basis of histology lacked MDM2 amplification and were reclassified following the FISH findings.

CONCLUSIONS

We conclude that a subset of lipoma-like ALTs/WDLs are not associated with any of the features typically described in ALT/WDL. Our study also showed that tumours >100 mm are more likely to be ALT/WDL; however, a history of recurrence or concerning clinical/radiological features was not significantly associated with classification as ALT/WDL.