Raneem Mohammed Al Saqer

Raneem Mohammed Al Saqer

Auto-generated profile, based on publicly available information

Raneem Mohammed Al Saqer

Medical Imaging Department, King Abdulaziz Medical City, Riyadh, Saudi Arabia

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 October 2025 in IEEE Access
Verified
Journal Article
Open access
FAFahad Muflih AlShagathrh
Fahad Muflih AlShagathrh
HZHaider Dhia Zubaydi
Haider Dhia Zubaydi
MAMahmood Alzubaidi
Mahmood Alzubaidi
AAAbdulaziz Alosaimi
Abdulaziz Alosaimi
RSRaneem Mohammed Al Saqer
Raneem Mohammed Al Saqer
MHMowafa Househ
Mowafa Househ
Non-alcoholic fatty liver disease (NAFLD) is a growing public health challenge, underscoring the need for scalable, non-invasive tools to grade hepatic steatosis. Although B-mode ultrasound is accessible and safe, its reliability is limited by operator and scanner variability. We present the Deep Domain Adaptation Neural Network (DDANN), a deep learning system for multiclass steatosis classification (Normal, Mild, Moderate, Severe) from ultrasound that emphasizes cross-device generalizability. To mitigate distribution shifts across scanners (LOGIQ, iU22, EPIQ), DDANN combines a MobileNetV2 backbone with triplet loss, entropy-based domain adaptation, and preprocessing that includes speckle suppression, percentile normalization, and LOGIQ-specific harmonization. Trained on a biopsy-confirmed, multi-institutional cohort (primarily LOGIQ and iU22), the model was externally validated on an unseen EPIQ test set of 1,083 images from 47 patients, achieving 98.71% accuracy, 0.9872 macro F1-score, and 0.9998 AUC-ROC, outperforming baselines. In a separate radiologist–AI comparison on 224 biopsy-confirmed images not used for training or validation, the AI reached 91.96% accuracy, significantly exceeding radiologists’ 19.64%–31.70% (McNemar’s test, p < 0.001), with strong agreement to ground truth (κ = 0.893) versus radiologists’ poor-to-slight agreement (κ = 0.006–0.194). The AI maintained balanced class-wise F1-scores (0.90–0.94), while radiologists struggled, particularly with Mild and Moderate cases, and exhibited substantial inter-reader variability (κ = 0.068–0.648). These results demonstrate robust cross-device performance and support integrating AI as a reliable second reader or primary screening tool to reduce subjectivity in steatosis assessment.