Academic Journal
Detecting Uniformity Artifacts in Ultrasound Transducers: Insights from Clinical Median Images and Deep Learning for Automatic Detection.
| Τίτλος: | Detecting Uniformity Artifacts in Ultrasound Transducers: Insights from Clinical Median Images and Deep Learning for Automatic Detection. |
|---|---|
| Συγγραφείς: | Gu C; Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA., Brom K; Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA., Stekel S; Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA., Tradup DJ; Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA., Xin Z; Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland, USA., Hangiandreou NJ; Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA., Dave JK; Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA., Long Z; Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA. |
| Πηγή: | Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine [J Ultrasound Med] 2026 Sep; Vol. 45 (9), pp. 1889-1896. Date of Electronic Publication: 2026 Apr 01. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: John Wiley and Sons Country of Publication: England NLM ID: 8211547 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1550-9613 (Electronic) Linking ISSN: 02784297 NLM ISO Abbreviation: J Ultrasound Med Subsets: MEDLINE |
| Imprint Name(s): | Publication: 2017- : Oxford, UK : John Wiley and Sons Original Publication: [Philadelphia, Pa.] : W.B. Saunders, c1982- |
| Ιατρικοί όροι (MeSH): | Image Processing, Computer-Assisted*/methods , Deep Learning* , Artifacts* , Transducers*, Ultrasonography/instrumentation ; Ultrasonography/methods ; Humans ; Phantoms, Imaging ; Sensitivity and Specificity ; Reproducibility of Results ; Detection Algorithms |
| Περίληψη: | Objectives: Uniformity artifacts caused by defective transducer elements or scanner malfunctions degrade diagnostic image quality. Traditional quality control (QC) methods, such as phantom testing and visual or quantitative image analysis, can be labor-intensive and limited in test frequency. This study aims to develop a deep learning framework to detect uniformity artifacts and complement traditional QC. Methods: Clinical median images were generated by aggregating co-registered grayscale ultrasound images acquired by each transducer and computing median intensity values across the image stack. A pretrained ResNet-18 model was fine-tuned on a dataset consisting of clinical median images from linear and curvilinear transducers. The dataset was divided into training, validation, and testing subsets, ensuring no overlap between training and test transducers. To assess generalizability, the model was also evaluated on an independent test set of 396 phantom-validated images from linear and curvilinear transducers. Results: The model achieved 100% accuracy on the first dataset's test set. On the independent test set, it attained 87.4% accuracy with high sensitivity (0.84) and specificity (0.88), demonstrating robust generalization. Occlusion sensitivity maps confirmed the model's attention to uniformity artifact regions. Conclusion: The deep learning framework using clinical median images demonstrated robust performance across several linear and curvilinear transducer models. It could be integrated into the clinical QC workflow by automating artifact detection in an effective and timely manner. In our practice, it can flag median images classified as artifact-present, reducing human review time by approximately 80% while preserving detection accuracy. (© 2026 American Institute of Ultrasound in Medicine.) |
| References: | Nature. 2023 Oct;622(7981):156-163. (PMID: 37704728) J Appl Clin Med Phys. 2019 Mar;20(3):105-114. (PMID: 30861275) Annu Rev Biomed Eng. 2017 Jun 21;19:221-248. (PMID: 28301734) Phys Med. 2021 Apr;84:33-40. (PMID: 33836374) J Appl Clin Med Phys. 2018 Mar;19(2):265-274. (PMID: 29322614) Int J Mol Sci. 2023 Nov 01;24(21):. (PMID: 37958843) Ultrason Imaging. 2014 Jan;36(1):18-34. (PMID: 24275537) Ultrasound Med Biol. 2011 Aug;37(8):1350-7. (PMID: 21683511) Phys Med Biol. 2020 Feb 04;65(3):035007. (PMID: 31881547) |
| Contributed Indexing: | Keywords: automated artifact detection; deep learning; image processing; ultrasound Imaging; uniformity artifacts |
| Entry Date(s): | Date Created: 20260401 Date Completed: 20260819 Latest Revision: 20260821 |
| Update Code: | 20260821 |
| PubMed Central ID: | PMC13489656 |
| DOI: | 10.1002/jum.70239 |
| PMID: | 41919451 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1550-9613 |
|---|---|
| DOI: | 10.1002/jum.70239 |