scholarly journals Pilot study to differentiate lipoma from atypical lipomatous tumour/well-differentiated liposarcoma using MR radiomics-based texture analysis

2020 ◽  
Vol 49 (11) ◽  
pp. 1719-1729 ◽  
Author(s):  
Ian Pressney ◽  
Michael Khoo ◽  
Raymond Endozo ◽  
Balaji Ganeshan ◽  
Paul O’Donnell
2020 ◽  
Vol 49 (1) ◽  
pp. 34-38
Author(s):  
David M. Sawyer ◽  
Travis W. Sawyer ◽  
Naghmehossadat Eshghi ◽  
Charles Hsu ◽  
Russell J. Hamilton ◽  
...  

2019 ◽  
Vol 3 (1) ◽  
Author(s):  
Magda Marcon ◽  
Alexander Ciritsis ◽  
Cristina Rossi ◽  
Anton S. Becker ◽  
Nicole Berger ◽  
...  

Abstract Background Our aims were to determine if features derived from texture analysis (TA) can distinguish normal, benign, and malignant tissue on automated breast ultrasound (ABUS); to evaluate whether machine learning (ML) applied to TA can categorise ABUS findings; and to compare ML to the analysis of single texture features for lesion classification. Methods This ethically approved retrospective pilot study included 54 women with benign (n = 38) and malignant (n = 32) solid breast lesions who underwent ABUS. After manual region of interest placement along the lesions’ margin as well as the surrounding fat and glandular breast tissue, 47 texture features (TFs) were calculated for each category. Statistical analysis (ANOVA) and a support vector machine (SVM) algorithm were applied to the texture feature to evaluate the accuracy in distinguishing (i) lesions versus normal tissue and (ii) benign versus malignant lesions. Results Skewness and kurtosis were the only TF significantly different among all the four categories (p < 0.000001). In subsets (i) and (ii), a maximum area under the curve of 0.86 (95% confidence interval [CI] 0.82–0.88) for energy and 0.86 (95% CI 0.82–0.89) for entropy were obtained. Using the SVM algorithm, a maximum area under the curve of 0.98 for both subsets was obtained with a maximum accuracy of 94.4% in subset (i) and 90.7% in subset (ii). Conclusions TA in combination with ML might represent a useful diagnostic tool in the evaluation of breast imaging findings in ABUS. Applying ML techniques to TFs might be superior compared to the analysis of single TF.


Sarcoma ◽  
2010 ◽  
Vol 2010 ◽  
pp. 1-4 ◽  
Author(s):  
J. Patel ◽  
R. Deb ◽  
W. Speake ◽  
T. A. MacCulloch

Primary small intestinal liposarcomas originating in the small bowel are uncommon with a generally poor prognosis due to the advanced stage at the time of diagnosis. We describe a case of primary small bowel dedifferentiated liposarcoma presenting as a solid mass in the right iliac fossa. The current case is unusual as the tumour seemingly originated from the bowel and the well-differentiated component was seen extensively infiltrating the bowel wall including the small bowel submucosa.


Author(s):  
Jisa Elizabath Sabu ◽  
Bharat Mishra ◽  
Angelin Jaimon Augustine ◽  
Aleesha R

Lipomas are benign soft tissue fatty tumours that most commonly appear in the third decade of life when fatty tissue accumulates. Histologically, lipoma is composed of mature fat cells with a thin fibrous capsule. Simple lipomas account for 80% of adipose tissue tumours. The aetiology may be genetic like Familial Multiple Lipomatosis. Some tumours, like the well differentiated Liposarcomas never metastasize unless they undergo de-differentiation. They can be introduced as Atypical Lipomatous Tissue, ALT. Southern blot analysis is performed by obtaining DNA from ALT, cases in which most of them are characterized by the presence of supernumerary ring and long marker chromosomes. The complex chromosome region contains genes MDM2, CDK4, HMGI- C, SAS, GLI, CHOP, OS4 and OSP. Most of ALTs, after analysis revealed amplification of CDK4 and MDM2 proto- oncogenes that play major role in permitting over ride of block operated on cell proliferation.  Immuno-histochemical results have shown MDM2 over expression in about 50% of ALTs along with weak CDK4 immuno-positivity. Also the lipomas with Gene fusion transcripts have the expression of certain genes, HMGA2/LPP, HMGA2/RDCI and HMGA2/NFIB. Of these 98% of cases were analyzed for the possible expression of HMGA2/LPP and LPP- HMGA2 fusion genes using reverse transcription polymerase chain reaction. Over all these cases, shows non-enhanced adipocyte apoptosis and enhanced adipogenesis in lipoma tissue. Thus studies provide insights into molecular pathogenesis of lipomatous tumour and representation of distinctive subset of mesenchymal neoplasms with mature adipocyte differentiation.


Sign in / Sign up

Export Citation Format

Share Document