Objectives: We aimed to assess the performance of radiomics and machine learning (ML) for classification of non-cystic benign and malignant breast lesions on ultrasound images, compare ML's accuracy with that of a breast radiologist, and verify if the radiologist's performance is improved by using ML.
Methods: Our retrospective study included patients from two institutions. A total of 135 lesions from Institution 1 were used to train and test the ML model with cross-validation. Radiomic features were extracted from manually annotated images and underwent a multistep feature selection process. Not reproducible, low variance, and highly intercorrelated features were removed from the dataset. Then, 66 lesions from Institution 2 were used as an external test set for ML and to assess the performance of a radiologist without and with the aid of ML, using McNemar's test.
Results: After feature selection, 10 of the 520 features extracted were employed to train a random forest algorithm. Its accuracy in the training set was 82% (standard deviation, SD, ± 6%), with an AUC of 0.90 (SD ± 0.06), while the performance on the test set was 82% (95% confidence intervals (CI) = 70-90%) with an AUC of 0.82 (95% CI = 0.70-0.93). It resulted in being significantly better than the baseline reference (p = 0.0098), but not different from the radiologist (79.4%, p = 0.815). The radiologist's performance improved when using ML (80.2%), but not significantly (p = 0.508).
Conclusions: A radiomic analysis combined with ML showed promising results to differentiate benign from malignant breast lesions on ultrasound images.
Key Points: • Machine learning showed good accuracy in discriminating benign from malignant breast lesions • The machine learning classifier's performance was comparable to that of a breast radiologist • The radiologist's accuracy improved with machine learning, but not significantly.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8589755 | PMC |
| http://dx.doi.org/10.1007/s00330-021-08009-2 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Enhanced brain tumor detection and segmentation using densely connected convolutional networks with stacking ensemble learning.
Comput Biol Med
January 2025
Emerging Technologies Research Lab (ETRL), College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia; Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia. Electronic address:
- Brain tumors (BT), both benign and malignant, pose a substantial impact on human health and need precise and early detection for successful treatment. Analysing magnetic resonance imaging (MRI) image is a common method for BT diagnosis and segmentation, yet misdiagnoses yield effective medical responses, impacting patient survival rates. Recent technological advancements have popularized deep learning-based medical image analysis, leveraging transfer learning to reuse pre-trained models for various applications.
View Article and Find Full Text PDFLigand-Conditioned Side Chain Packing for Flexible Molecular Docking.
J Chem Theory Comput
January 2025
State Key Laboratory of Physical Chemistry of Solid Surfaces and Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, P. R. China.
Molecular docking is a crucial technique for elucidating protein-ligand interactions. Machine learning-based docking methods offer promising advantages over traditional approaches, with significant potential for further development. However, many current machine learning-based methods face challenges in ensuring the physical plausibility of generated docking poses.
View Article and Find Full Text PDFEnhancing Activation Energy Predictions under Data Constraints Using Graph Neural Networks.
J Chem Inf Model
January 2025
Department of Chemical Engineering, National Taiwan University, No. 1, Section 4, Roosevelt Road, Taipei 10617, Taiwan.
Accurately predicting activation energies is crucial for understanding chemical reactions and modeling complex reaction systems. However, the high computational cost of quantum chemistry methods often limits the feasibility of large-scale studies, leading to a scarcity of high-quality activation energy data. In this work, we explore and compare three innovative approaches (transfer learning, delta learning, and feature engineering) to enhance the accuracy of activation energy predictions using graph neural networks, specifically focusing on methods that incorporate low-cost, low-level computational data.
View Article and Find Full Text PDFVirtual screening: hope, hype, and the fine line in between.
Expert Opin Drug Discov
January 2025
Department of Radiology, Molecular Imaging Innovations Institute (MI3), Weill Cornell Medicine, New York, NY, USA.
Introduction: Technological advancements in virtual screening (VS) have rapidly accelerated its application in drug discovery, as reflected by the exponential growth in VS-related publications. However, a significant gap remains between the volume of computational predictions and their experimental validation. This discrepancy has led to a rise in the number of unverified 'claimed' hits which impedes the drug discovery efforts.
View Article and Find Full Text PDFDetecting noncredible symptomology in ADHD evaluations using machine learning.
J Clin Exp Neuropsychol
January 2025
Department of Psychology, University of Illinois at Urbana-Champaign, Champaign, IL, USA.
Introduction: Diagnostic evaluations for attention-deficit/hyperactivity disorder (ADHD) are becoming increasingly complicated by the number of adults who fabricate or exaggerate symptoms. Novel methods are needed to improve the assessment process required to detect these noncredible symptoms. The present study investigated whether unsupervised machine learning (ML) could serve as one such method, and detect noncredible symptom reporting in adults undergoing ADHD evaluations.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!