Samia Boussouar

Objective: The diaphragm is central to respiratory mechanics and may be impaired in various diseases. Parametric magnetic resonance imaging (MRI) assessment is limited by time-consuming manual segmentation. We developed and validated fully automated diaphragm segmentation on two-dimensional (2D)-cine and three-dimensional (3D) thoracic MRI. Materials and methods: In this single-center study, eligible adults without known diaphragmatic disorders underwent 2D-cine MRI, 3D MRI, or both. Two U-Net models (2D/3D) were trained using expert manual contours as ground truth. Performance was evaluated with normalized surface Dice (NSD) with 3-voxel tolerance and average surface distance (ASSD). In the main cohort, five blinded radiologists rated segmentation usability and image quality. An additional separate pathology cohort was assessed by two blinded readers using the same scale. Results: Overall, 59 individuals contributed 70 MRI acquisitions: 29 women, 30 men; aged 49.3 ± 18.8 years (mean ± standard deviation). Inference required 5 s (2D) and 30 s (3D) versus 10 min and 4.5 h for manual annotation. Segmentation accuracy was high: NSD 0.95 ± 0.08 (2D) and 0.92 ± 0.06 (3D), with ASSD 1.97 ± 2.29 mm (2D) and 1.88 ± 1.97 mm (3D). In the main cohort, segmentations were rated clinically usable in 87.5% (2D) and 100% (3D). Mean image-quality scores were 4.0/5 (2D) and 4.2/5 (3D) and correlated with segmentation quality. In the pathology cohort ( n = 5), segmentation usability for 2D images was 75% for reader 1 and 70% for reader 2 for 2D images and 80% for both readers for 3D volumes. Conclusion: Automated diaphragm segmentation on 2D-cine and 3D MRI is feasible, accurate, and time-efficient, supporting scalable, standardized diaphragm analysis as a basis for deriving diaphragm biomarkers. Key Points: Question Can fully automated diaphragm segmentation make routine 2D-cine and 3D thoracic MRI analysis clinically feasible by replacing time-consuming manual delineation? Findings Automated segmentation achieved normalized surface Dice above 0.9, radiologist acceptability in 87.5–100% of cases, and inference times below 30 s Relevance statement Automated diaphragm segmentation on routine 2D-cine and 3D static MRI yields accurate, radiologist-acceptable segmentations with normalized surface Dice exceeding 0.9 and mean surface deviations below 2 mm. This approach may support standardized diaphragm assessment for objective quantification in thoracic and neuromuscular imaging pending larger multicenter validation.

Background: Interstitial lung disease (ILD) is a determinant of morbidity and mortality in idiopathic inflammatory myopathies (IIM), but chest HRCT evaluation remains observer-dependent. Artificial intelligence (AI) may provide reproducible quantitative assessment. We compared AI-based quantification of ILD with expert visual scoring in IIM. Methods: In this monocentric retrospective study, 107 patients with IIM-associated ILD from a national myositis registry were included. One representative chest HRCT per patient was evaluated by a thoracic radiologist using a semi-quantitative lobar score and by a commercially available AI tool for lung texture analysis. AI-derived volumes were converted to the same 5-point scale as the visual score. Correlations were assessed with Spearman coefficients and agreement with Cohen’s kappa. Results: All CTs were suitable for visual assessment and 106/107 (99%) for AI analysis. AI identified ground-glass opacities (GGO) as the predominant abnormality, with a lower-lobe predominance. Correlations between AI and radiologist scores were strong for normal lung ( r = 0.77) and moderate for GGO ( r = 0.64) and consolidation ( r = 0.60), but weaker for reticulations ( r = 0.34) and honeycombing ( r = 0.42). Agreement was good for GGO (κ = 0.70) and consolidation (κ = 0.60), moderate for reticulations (κ = 0.37) and low for honeycombing (κ = 0.16). Conclusion: In IIM-associated ILD, AI-based chest HRCT quantification showed good agreement with expert visual assessment, particularly for GGO and consolidation, but was less reliable for complex fibrotic patterns. AI may support more objective and reproducible evaluation of interstitial involvement, as a complement to expert interpretation.

Examples of cardiac and skeletal muscle pathology findings on autopsies of 2 patients

Treatment modalities and reported adverse events by quartile of period of inclusion.