Deep transfer learning radiomics for distinguishing sinonasal malignancies: a preliminary MRI study.

in Future oncology (London, England) by Naier Lin, Yiqian Shi, Min Ye, Yiyin Zhang, Xianhao Jia

TLDR

  • This study combined MRI-based hand-crafted radiomics features with deep transfer learning to identify sinonasal SCC, NHL, and ACC with high accuracy using machine learning models.

Abstract

This study aimed to assess the diagnostic accuracy of combining MRI hand-crafted (HC) radiomics features with deep transfer learning (DTL) in identifying sinonasal squamous cell carcinoma (SCC), adenoid cystic carcinoma (ACC), and non-Hodgkin's lymphoma (NHL) using various machine learning (ML) models. A retrospective analysis of 132 patients (50 with SCC, 42 with NHL, 40 with ACC) was conducted. The dataset was split 80/20 into training and testing cohorts. HC radiomics and DTL features were extracted from T2-weighted, ADC, and contrast-enhanced T1-weighted MRI images. ResNet50, a pre-trained convolutional neural network, was used for DTL feature extraction. LASSO regression was applied to select features and create radiomic signatures. Seven ML models were evaluated for classification performance. The radiomic signature included 24 hC and 8 DTL features. The support vector machine (SVM) model achieved the highest accuracy (92.6%) in the testing cohort. The SVM model's ROC analysis showed macro-average and micro-average AUC values of 0.98 and 0.99. AUCs for ACC, NHL, and SCC were 0.99, 0.97, and 1.00. K-nearest neighbors (KNN) and XGBoost also showed AUC values above 0.90. Combining MRI-based HC radiomics and DTL features with the SVM model enhanced differentiation between sinonasal SCC, NHL, and ACC.

Overview

  • The study aimed to combine MRI hand-crafted radiomics features with deep transfer learning to identify sinonasal squamous cell carcinoma, adenoid cystic carcinoma, and non-Hodgkin's lymphoma using machine learning models.
  • A retrospective analysis of 132 patients was conducted, with 80/20 split for training and testing datasets.
  • Features were extracted from T2-weighted, ADC, and contrast-enhanced T1-weighted MRI images, and radiomic signatures were created using LASSO regression and ResNet50.

Comparative Analysis & Findings

  • The support vector machine (SVM) model achieved the highest accuracy (92.6%) in the testing cohort, with macro-average and micro-average AUC values of 0.98 and 0.99.
  • K-nearest neighbors (KNN) and XGBoost models also showed AUC values above 0.90.
  • The combination of MRI-based HC radiomics and DTL features with the SVM model enhanced differentiation between sinonasal SCC, NHL, and ACC.

Implications and Future Directions

  • The study's findings suggest that combining MRI-based HC radiomics and DTL features can improve diagnostic accuracy for sinonasal SCC, NHL, and ACC.
  • Future studies can explore the use of this approach in other oncological applications and assess its potential in clinical practice.
  • The limitations of the study, such as the small sample size, should be addressed in future research to further validate the findings.
Read Full Article