Dataset Information

Variation in the Thickness of Knee Cartilage. The Use of a Novel Machine Learning Algorithm for Cartilage Segmentation of Magnetic Resonance Images.

ABSTRACT: BACKGROUND:The variation in articular cartilage thickness (ACT) in healthy knees is difficult to quantify and therefore poorly documented. Our aims are to (1) define how machine learning (ML) algorithms can automate the segmentation and measurement of ACT on magnetic resonance imaging (MRI) (2) use ML to provide reference data on ACT in healthy knees, and (3) identify whether demographic variables impact these results. METHODS:Patients recruited into the Osteoarthritis Initiative with a radiographic Kellgren-Lawrence grade of 0 or 1 with 3D double-echo steady-state MRIs were included and their gender, age, and body mass index were collected. Using a validated ML algorithm, 2 orthogonal points on each femoral condyle were identified (distal and posterior) and ACT was measured on each MRI. Site-specific ACT was compared using paired t-tests, and multivariate regression was used to investigate the risk-adjusted effect of each demographic variable on ACT. RESULTS:A total of 3910 MRI were included. The average femoral ACT was 2.34 mm (standard deviation, 0.71; 95% confidence interval, 0.95-3.73). In multivariate analysis, distal-medial (-0.17 mm) and distal-lateral cartilage (-0.32 mm) were found to be thinner than posterior-lateral cartilage, while posterior-medial cartilage was found to be thicker (0.21 mm). In addition, female sex was found to negatively impact cartilage thickness (OR, -0.36; all values: P < .001). CONCLUSION:ML was effectively used to automate the segmentation and measurement of cartilage thickness on a large number of MRIs of healthy knees to provide normative data on the variation in ACT in this population. We further report patient variables that can influence ACT. Further validation will determine whether this technique represents a powerful new tool for tracking the impact of medical intervention on the progression of articular cartilage degeneration.

SUBMITTER: Shah RF

PROVIDER: S-EPMC7251923 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Variation in the Thickness of Knee Cartilage. The Use of a Novel Machine Learning Algorithm for Cartilage Segmentation of Magnetic Resonance Images.

Shah Romil F RF Martinez Alejandro M AM Pedoia Valentina V Majumdar Sharmila S Vail Thomas P TP Bini Stefano A SA

The Journal of arthroplasty 20190724 10

<h4>Background</h4>The variation in articular cartilage thickness (ACT) in healthy knees is difficult to quantify and therefore poorly documented. Our aims are to (1) define how machine learning (ML) algorithms can automate the segmentation and measurement of ACT on magnetic resonance imaging (MRI) (2) use ML to provide reference data on ACT in healthy knees, and (3) identify whether demographic variables impact these results.<h4>Methods</h4>Patients recruited into the Osteoarthritis Initiative ...[more]

PMID: 31445869

Similar Datasets

Project description:BackgroundCartilage morphometry based on magnetic resonance images (MRIs) is an emerging outcome measure for clinical trials among patients with knee osteoarthritis (KOA). However, current methods for cartilage morphometry take many hours per knee and require extensive training on the use of the associated software. In this study we tested the feasibility, reliability, and construct validity of a novel osteoarthritis cartilage damage quantification method (Cartilage Damage Index [CDI]) that utilizes informative locations on knee MRIs.MethodsWe selected 102 knee MRIs from the Osteoarthritis Initiative that represented a range of KOA structural severity (Kellgren Lawrence [KL] Grade 0 - 4). We tested the intra- and inter-tester reliability of the CDI and compared the CDI scores against different measures of severity (radiographic joint space narrowing [JSN] grade, KL score, joint space width [JSW]) and static knee alignment, both cross-sectionally and longitudinally.ResultsDetermination of the CDI took on average14.4 minutes (s.d. 2.1) per knee pair (baseline and follow-up of one knee). Repeatability was good (intra- and inter-tester reliability: intraclass correlation coefficient >0.86). The mean CDI scores related to all four measures of osteoarthritis severity (JSN grade, KL score, JSW, and knee alignment; all p values < 0.05). Baseline JSN grade and knee alignment also predicted subsequent 24-month longitudinal change in the CDI (p trends <0.05). During 24 months, knees with worsening in JSN or KL grade (i.e. progressors) had greater change in CDI score.ConclusionsThe CDI is a novel knee cartilage quantification method that is rapid, reliable, and has construct validity for assessment of medial tibiofemoral osteoarthritis structural severity and its progression. It has the potential to addresses the barriers inherent to studies requiring assessment of cartilage damage on large numbers of knees, and as a biomarker for knee osteoarthritis progression.

Project description:Background: It was difficult to distinguish the cartilage thinning of an entire knee joint and to track the evolution of cartilage morphology alongside ages in the general population, which was of great significance for studying osteoarthritis until big imaging data and artificial intelligence are fused. The purposes of our study are (1) to explore the cartilage thickness in anatomical regions of the knee joint among a large collection of healthy knees, and (2) to investigate the relationship between the thinning pattern of the cartilages and the increasing ages. Methods: In this retrospective study, 2,481 healthy knees (subjects ranging from 15 to 64 years old, mean age: 35 ± 10 years) were recruited. With magnetic resonance images of knees acquired on a 3-T superconducting scanner, we automatically and precisely segmented the cartilage via deep learning and calculated the cartilage thickness in 14 anatomical regions. The thickness readings were compared using ANOVA by considering the factors of age, sex, and side. We further tracked the relationship between the thinning pattern of the cartilage thickness and the increasing ages by regression analysis. Results: The cartilage thickness was always thicker in the femur than corresponding regions in the tibia (p < 0.05). Regression analysis suggested cartilage thinning alongside ages in all regions (p < 0.05) except for medial and lateral anterior tibia in both females and males (p > 0.05). The thinning speed of men was faster than women in medial anterior and lateral anterior femur, yet slower in the medial patella (p < 0.05). Conclusion: We established the calculation method of cartilage thickness using big data and deep learning. We demonstrated that cartilage thickness differed across individual regions in the knee joint. Cartilage thinning alongside ages was identified, and the thinning pattern was consistent in the tibia while inconsistent in patellar and femoral between sexes. These findings provide a potential reference to detect cartilage anomaly.

Project description:Transcranial brain stimulation (TBS) has been established as a method for modulating and mapping the function of the human brain, and as a potential treatment tool in several brain disorders. Typically, the stimulation is applied using a one-size-fits-all approach with predetermined locations for the electrodes, in electric stimulation (TES), or the coil, in magnetic stimulation (TMS), which disregards anatomical variability between individuals. However, the induced electric field distribution in the head largely depends on anatomical features implying the need for individually tailored stimulation protocols for focal dosing. This requires detailed models of the individual head anatomy, combined with electric field simulations, to find an optimal stimulation protocol for a given cortical target. Considering the anatomical and functional complexity of different brain disorders and pathologies, it is crucial to account for the anatomical variability in order to translate TBS from a research tool into a viable option for treatment. In this article we present a new method, called CHARM, for automated segmentation of fifteen different head tissues from magnetic resonance (MR) scans. The new method compares favorably to two freely available software tools on a five-tissue segmentation task, while obtaining reasonable segmentation accuracy over all fifteen tissues. The method automatically adapts to variability in the input scans and can thus be directly applied to clinical or research scans acquired with different scanners, sequences or settings. We show that an increase in automated segmentation accuracy results in a lower relative error in electric field simulations when compared to anatomical head models constructed from reference segmentations. However, also the improved segmentations and, by implication, the electric field simulations are affected by systematic artifacts in the input MR scans. As long as the artifacts are unaccounted for, this can lead to local simulation differences up to 30% of the peak field strength on reference simulations. Finally, we exemplarily demonstrate the effect of including all fifteen tissue classes in the field simulations against the standard approach of using only five tissue classes and show that for specific stimulation configurations the local differences can reach 10% of the peak field strength.

Dataset Information

Variation in the Thickness of Knee Cartilage. The Use of a Novel Machine Learning Algorithm for Cartilage Segmentation of Magnetic Resonance Images.

Publications

Variation in the Thickness of Knee Cartilage. The Use of a Novel Machine Learning Algorithm for Cartilage Segmentation of Magnetic Resonance Images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets