Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Aug;128(8):989-998.
doi: 10.1007/s11547-023-01657-y. Epub 2023 Jun 19.

MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor of the extremities

Salvatore Gitto  1   2 , Matteo Interlenghi  3 , Renato Cuocolo  4   5 , Christian Salvatore  3   6 , Vincenzo Giannetta  7 , Julietta Badalyan  8 , Enrico Gallazzi  9 , Maria Silvia Spinelli  10 , Mauro Gallazzi  11 , Francesca Serpi  2 , Carmelo Messina  1   2 , Domenico Albano  1 , Alessio Annovazzi  12 , Vincenzo Anelli  13 , Jacopo Baldi  14 , Alberto Aliprandi  15 , Elisabetta Armiraglio  16 , Antonina Parafioriti  16 , Primo Andrea Daolio  10 , Alessandro Luzzati  1 , Roberto Biagini  14 , Isabella Castiglioni  17   18 , Luca Maria Sconfienza  19   20
Affiliations

MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor of the extremities

Salvatore Gitto et al. Radiol Med. 2023 Aug.

Abstract

Purpose: To determine diagnostic performance of MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor (ALT) of the extremities.

Material and methods: This retrospective study was performed at three tertiary sarcoma centers and included 150 patients with surgically treated and histology-proven lesions. The training-validation cohort consisted of 114 patients from centers 1 and 2 (n = 64 lipoma, n = 50 ALT). The external test cohort consisted of 36 patients from center 3 (n = 24 lipoma, n = 12 ALT). 3D segmentation was manually performed on T1- and T2-weighted MRI. After extraction and selection of radiomic features, three machine learning classifiers were trained and validated using nested fivefold cross-validation. The best-performing classifier according to previous analysis was evaluated and compared to an experienced musculoskeletal radiologist in the external test cohort.

Results: Eight features passed feature selection and were incorporated into the machine learning models. After training and validation (74% ROC-AUC), the best-performing classifier (Random Forest) showed 92% sensitivity and 33% specificity in the external test cohort with no statistical difference compared to the radiologist (p = 0.474).

Conclusion: MRI radiomics-based machine learning may classify deep-seated lipoma and ALT of the extremities with high sensitivity and negative predictive value, thus potentially serving as a non-invasive screening tool to reduce unnecessary referral to tertiary tumor centers.

Keywords: Artificial intelligence; Lipoma; Liposarcoma; Machine learning; Radiomics; Soft-tissue; Tumor.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no conflicts of interest related to this work.

Figures

Fig. 1
Fig. 1
Violin and box plots of the radiomic predictors ranked from 1 to 8. Violin and box plots of “ALT” and “lipoma” classes are reported in red and green, respectively
Fig. 2
Fig. 2
ROC curves for the models consisting of 10 ensembles of Random Forest (a), Support Vector Machine (b) and k nearest neighbors (c) classifiers from internal testing
Fig. 3
Fig. 3
True negative (a, correctly classified lipoma), false positive (b, lipoma misdiagnosed as ALT) and true positive (c, correctly classified ALT) according to both radiomics-based machine learning and qualitative assessment performed by the radiologist. In (a), correctly classified lipoma shows homogeneous signal with complete fat suppression. Intralesional septations are seen in correctly classified ALT (c) but also lipoma misdiagnosed as ALT (b). Fat-suppressed T2-weighted sequences were used only for qualitative assessment performed by the radiologist. Radiomics-based machine learning analysis included T1- and T2-weighted sequences without fat suppression
See this image and copyright information in PMC

References

    1. Yee EJ, Stewart CL, Clay MR, McCarter MM. Lipoma and Its doppelganger. Surg Clin North Am. 2022;102:637–656. doi: 10.1016/j.suc.2022.04.006. - DOI - PubMed
    1. WHO Classification of Tumours Editorial Board . WHO classification of tumours: soft tissue and bone tumours. Lyon: International Agency for Research on Cancer Press; 2020.
    1. Murphey MD, Carroll JF, Flemming DJ, et al. From the archives of the AFIP: benign musculoskeletal lipomatous lesions. Radiographics. 2004;24:1433–1466. doi: 10.1148/rg.245045120. - DOI - PubMed
    1. Gronchi A, Miah AB, Dei Tos AP, et al. Soft tissue and visceral sarcomas: ESMO–EURACAN–GENTURIS Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol. 2021;32:1348–1365. doi: 10.1016/j.annonc.2021.07.006. - DOI - PubMed
    1. Thavikulwat AC, Wu JS, Chen X, et al. Image-guided core needle biopsy of adipocytic tumors: diagnostic accuracy and concordance with final surgical pathology. AJR Am J Roentgenol. 2021;216:997–1002. doi: 10.2214/AJR.20.23080. - DOI - PubMed