Deep Generative Model of the Distal Tibial Classic Metaphyseal Lesion in Infants: Assessment of Synthetic Images
Radiology Advances · 04.07.2024
DOI: 10.1093/radadv/umae018 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiology Advances, online erschienen am 04.07.2024. Verfasst von Shaoju Wu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Boston Children's Hospital, Harvard Medical School, Boston, MA 02115, United States. Die Arbeit wurde bisher 4-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIDDK NIH HHS, NICHD NIH HHS.
Abstract (Originalsprache)
Background
The classic metaphyseal lesion (CML) is a distinctive fracture highly specific to infant abuse. To increase the size and diversity of the training CML database for automated deep-learning detection of this fracture, we developed a mask conditional diffusion model (MaC-DM) to generate synthetic images with and without CMLs.
Purpose
To objectively and subjectively assess the synthetic radiographic images with and without CMLs generated by MaC-DM. Materials and Methods For retrospective testing, we randomly chose 100 real images (50 normals and 50 with CMLs; 39 infants, male = 22, female = 17; mean age = 4.1 months; SD = 3.1 months) from an existing distal tibia dataset (177 normal, 73 with CMLs), and generated 100 synthetic distal tibia images via MaC-DM (50 normals and 50 with CMLs). These test images were shown to three blinded radiologists. In the 1st session, radiologists determined if the images were normal or had CMLs. In the 2nd session, they determined if the images were real or synthetic. We analyzed the radiologists’ interpretations, and employed t-distributed stochastic neighbor embedding (t-SNE) technique to analyze the data distribution of the test images.
Results
When presented with the 200 images (100 synthetic, 100 with CMLs), radiologists reliably and accurately diagnosed CMLs (kappa = 0.90, 95% CI = [0.88, 0.92]; accuracy = 92%, 95% CI = [89%, 97%]). However, they were inaccurate in differentiating between real and synthetic images (kappa = 0.05, 95% CI = [0.03, 0.07]; accuracy = 53%, 95% CI = [49%, 59%]). The t-SNE analysis showed substantial differences in the data distribution between normal images and those with CMLs (AUC = 0.996, 95% CI = [0.992, 1.000], P < 0.01), but minor differences between real and synthetic images (AUC = 0.566, 95% CI = [0.486, 0.647], P = 0.11).
Conclusion
Radiologists accurately diagnosed images with distal tibial CMLs but were unable to distinguish real from synthetically generated ones, indicating that our generative model could synthesize realistic images. Thus, MaC-DM holds promise as an effective strategy for data augmentation in training machine-learning models for diagnosis of distal tibial CMLs.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Boston Children's Hospital, Harvard Medical School, Boston, MA 02115, United States.
ORCID-Profile: Shaoju Wu
Förderung
- NIDDK NIH HHS
- NICHD NIH HHS
Zitieren
APA
Wu, S., Kurugol, S., Kleinman, P. K., Ecklund, K., Walters, M., Connolly, S. A., Johnston, P., & Tsai, A. (2024). Deep Generative Model of the Distal Tibial Classic Metaphyseal Lesion in Infants: Assessment of Synthetic Images. Radiology Advances. https://doi.org/10.1093/radadv/umae018
Vancouver
Wu S, Kurugol S, Kleinman PK, Ecklund K, Walters M, Connolly SA, et al. Deep Generative Model of the Distal Tibial Classic Metaphyseal Lesion in Infants: Assessment of Synthetic Images. Radiology Advances. 2024. doi:10.1093/radadv/umae018
BibTeX
@article{Wu2024,
author = {Wu, Shaoju and Kurugol, Sila and Kleinman, Paul K and Ecklund, Kirsten and Walters, Michele and Connolly, Susan A and Johnston, Patrick and Tsai, Andy},
title = {Deep Generative Model of the Distal Tibial Classic Metaphyseal Lesion in Infants: Assessment of Synthetic Images},
journal = {Radiology Advances},
year = {2024},
doi = {10.1093/radadv/umae018}
}
EUVIMED