Abstract
BackgroundManual assessment of bone marrow signal is time-consuming and requires meticulous standardisation to secure adequate precision of findings.ObjectiveWe examined the feasibility of using deep learning for automated segmentation of bone marrow signal in children and adolescents.Materials and methodsWe selected knee images from 95 whole-body MRI examinations of healthy individuals and of children with chronic non-bacterial osteomyelitis, ages 6–18 years, in a longitudinal prospective multi-centre study cohort. Bone marrow signal on T2-weighted Dixon water-only images was divided into three color-coded intensity-levels: 1 = slightly increased; 2 = mildly increased; 3 = moderately to highly increased, up to fluid-like signal. We trained a convolutional neural network on 85 examinations to perform bone marrow segmentation. Four readers manually segmented a test set of 10 examinations and calculated ground truth using simultaneous truth and performance level estimation (STAPLE). We evaluated model and rater performance through Dice similarity coefficient and in consensus.ResultsConsensus score of model performance showed acceptable results for all but one examination. Model performance and reader agreement had highest scores for level-1 signal (median Dice 0.68) and lowest scores for level-3 signal (median Dice 0.40), particularly in examinations where this signal was sparse.ConclusionIt is feasible to develop a deep-learning-based model for automated segmentation of bone marrow signal in children and adolescents. Our model performed poorest for the highest signal intensity in examinations where this signal was sparse. Further improvement requires training on larger and more balanced datasets and validation against ground truth, which should be established by radiologists from several institutions in consensus.
Highlights
Bone marrow oedema is an important feature on MRI in musculoskeletal disorders in children and adolescents for detecting disease and in scoring systems for monitoring disease activity [1,2,3,4,5,6]
This was in a healthy subject with no level-3 signal present in the segmentation masks performed by the Artificial intelligence (AI) model and reader 4, whereas a few small spots of high signal were defined to be present according to the ground truth and readers 1–3
We have shown that this model enables segmentation of a wide spectrum of bone marrow signal in children and adolescents where anatomy varies with age, while avoiding high signal structures other than bone marrow, on images obtained at two institutions on 1.5-T MRI machines from two vendors
Summary
Bone marrow oedema is an important feature on MRI in musculoskeletal disorders in children and adolescents for detecting disease and in scoring systems for monitoring disease activity [1,2,3,4,5,6]. The normal skeletal maturation processes can influence the MRI signal in a. Pathological and normal signal intensities and patterns can overlap [10,11,12], at the knee [13]. Objective We examined the feasibility of using deep learning for automated segmentation of bone marrow signal in children and adolescents. Model performance and reader agreement had highest scores for level-1 signal (median Dice 0.68) and lowest scores for level-3 signal (median Dice 0.40), in examinations where this signal was sparse. Conclusion It is feasible to develop a deep-learning-based model for automated segmentation of bone marrow signal in children and adolescents. Our model performed poorest for the highest signal intensity in examinations where this signal was sparse. Further improvement requires training on larger and more balanced datasets and validation against ground truth, which should be established by radiologists from several institutions in consensus
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
