EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists

Joshua M Lawrenz iD, Can Cui, Samuel R Johnson, Katherine S Hajdu, Stephen W Chenard iD, Akhil Rekulapelli, Cullen P Moran, John J Block, Nicholson S Chadwick, Joanna L Shechtel, Brian Bingham, Leo Y Luo und 6 weitere

PLOS ONE · 2025

DOI: 10.1371/journal.pone.0318072 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift PLOS ONE, 2025. Verfasst von Joshua M Lawrenz und 17 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedic Surgery, Division of Musculoskeletal Oncology, Vanderbilt University Medical Center, Nashville, Tennessee, United States of…. Hauptthemen laut MEDLINE: Soft Tissue Neoplasms, Radiologists, Myxoma. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, American Cancer Society.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Benign and malignant myxoid soft tissue tumors have shared clinical, imaging, and histologic features that can make diagnosis challenging. The purpose of this study is comparison of the diagnostic performance of a radiomic based machine learning (ML) model to musculoskeletal radiologists.

Methods

Manual segmentation of 90 myxoid soft tissue tumors (45 myxomas and 45 myxofibrosarcomas) was performed on axial T1, and T2FS or STIR magnetic resonance imaging sequences. Eighty-seven radiomic features from each modality were extracted. Five ML models were trained to classify tumors as benign or malignant in 40 tumors and then tested with an additional 50 tumors using cross validation. The accuracy of the best ML model based on area under the receiver operating characteristic curve (AUC) was compared to the consensus diagnosis of three musculoskeletal radiologists. Correlation between radiologist confidence (equivocal, probably, consistent with) and accuracy was tested.

Results

The best ML classifier was a logistic regression model (AUC 0.792). Using T1 + T2/STIR images, the ML model classified 78% (39/50) of tumors correctly at a similar rate compared to 74% (37/50) by radiologists. When radiologists disagreed, the consensus diagnosis classified 50% of tumors (7/14) correctly compared to 86% (12/14) by the ML model, though this did not reach statistical significance. Radiologists had a cumulative accuracy of 91% (30/33) when they rated their confidence ‘consistent with’ compared to 61% (31/51) when they rated their confidence ‘equivocal/probably’ (P = 0.006). For cases when radiologists rated their confidence ‘equivocal/probably’, the ML model had 76% accuracy (39/51).

Conclusions

A radiomic based ML model predicted benign or malignant diagnosis in myxoid soft tissue tumors similarly to the consensus diagnosis by three musculoskeletal radiologists. Radiologist confidence in the diagnosis strongly correlated with their diagnostic accuracy. Though radiomics and radiologists perform similarly overall, radiomics may provide novel diagnostic utility when radiologist confidence is low, or when radiologists disagree.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Soft Tissue NeoplasmsRadiologistsMyxomaHumansMagnetic Resonance ImagingFemaleMaleMiddle AgedAdultDiagnosis, DifferentialAgedMachine LearningROC CurveRadiomics

Autor:innen und Institutionen

  • Department of Orthopaedic Surgery, Division of Musculoskeletal Oncology, Vanderbilt University Medical Center, Nashville, Tennessee, United States of America.
  • Vanderbilt Institute of Surgery and Engineering, Vanderbilt University Medical Center, Nashville, Tennessee, United States of America.
  • Department of Radiology, Division of Musculoskeletal Radiology, Vanderbilt University Medical Center, Nashville, Tennessee, United States of America.
  • Department of Radiation Oncology, Vanderbilt University Medical Center, Nashville, Tennessee, United States of America.
  • Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, United States of America.

ORCID-Profile: Joshua M Lawrenz, Stephen W Chenard, Hakmook Kang

Förderung

  • NCI NIH HHS
  • American Cancer Society

Zitieren

APA

Lawrenz, J. M., Cui, C., Johnson, S. R., Hajdu, K. S., Chenard, S. W., Rekulapelli, A., Moran, C. P., Block, J. J., Chadwick, N. S., Shechtel, J. L., Bingham, B., Luo, L. Y., Halpern, J. L., Schwartz, H. S., Holt, G. E., Smith, D. S., Dawant, B., & Kang, H. (2025). Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists. PLOS ONE. https://doi.org/10.1371/journal.pone.0318072

Vancouver

Lawrenz JM, Cui C, Johnson SR, Hajdu KS, Chenard SW, Rekulapelli A, et al. Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists. PLOS ONE. 2025. doi:10.1371/journal.pone.0318072

BibTeX
@article{Lawrenz2025,
  author = {Lawrenz, Joshua M and Cui, Can and Johnson, Samuel R and Hajdu, Katherine S and Chenard, Stephen W and Rekulapelli, Akhil and Moran, Cullen P and Block, John J and Chadwick, Nicholson S and Shechtel, Joanna L and Bingham, Brian and Luo, Leo Y and Halpern, Jennifer L and Schwartz, Herbert S and Holt, Ginger E and Smith, David S and Dawant, Benoit and Kang, Hakmook},
  title = {Distinguishing benign and malignant myxoid soft tissue tumors: Performance of radiomics vs. radiologists},
  journal = {PLOS ONE},
  year = {2025},
  doi = {10.1371/journal.pone.0318072}
}
Kostenlos starten →