What does this research mean for the field?

DeepOxyMap achieved 82.0% classification accuracy for myocardial scar patterns, outperforming traditional methods and aligning closely with expert-identified images. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop DeepOxyMap, an AI-based model for classifying myocardial pathology via oxygenation-sensitive imaging without the use of contrast agents.

February 8, 2026

DeepOxyMap: AI-driven feature mapping of oxygenation-sensitive CMR for cardiomyopathy classification

Resultado clave

DeepOxyMap achieved 82% accuracy and 0.94-0.98 ROC-AUC in classifying myocardial scar types from contrast-free OS-CMR, matching expert LGE localization.

Puntos clave

To develop DeepOxyMap, an AI-based model for classifying myocardial pathology via oxygenation-sensitive imaging without the use of contrast agents.
Used OS-CMR images along with LGE, T1, and T2 maps from two cohorts comprising 190 subjects.
Implemented VGG19 architecture for deep learning with transfer learning techniques.
Conducted preprocessing with image resizing, normalization, and random augmentations for model robustness.
Evaluated model performance using accuracy, precision, recall, and ROC-AUC metrics on training and validation datasets.
Achieved a classification accuracy of 82.0% on the test set and 78.0% on the validation set.
Precision and recall scores were 86.0% and 78.0%, respectively, indicating reliable predictions.
Demonstrated strong discriminatory power in multi-class ROC-AUC analysis, with values of up to 0.98 for edema cases.
Feature maps closely aligned with expert-identified LGE, T1, and T2 maps, showcasing accurate localization of myocardial pathology.

PICO estructurado

Does DeepOxyMap accurately classify and visualize myocardial scar patterns on contrast-free oxygenation-sensitive CMR compared to standard LGE?

Población

190 subjects from two independent cohorts (n=160 and n=30) comprising ischemic (n=42), non-ischemic (n=33), edema (n=47), and healthy (n=68) cases.

Intervención

DeepOxyMap, an AI-powered VGG19-based convolutional neural network for feature mapping and classification of oxygenation-sensitive cardiovascular magnetic resonance (OS-CMR) images.

Comparador

ResNet50 and EfficientNetB0 models, with late gadolinium enhancement (LGE), T1, and T2 maps serving as the clinical reference.

Resultado

Classification accuracy, precision, recall, and multi-class ROC-AUC scores for detecting ischemic, non-ischemic, edema, and healthy patterns.surrogate

DeepOxyMap, an AI-driven model, accurately classifies and visualizes myocardial scar patterns on contrast-free oxygenation-sensitive CMR, offering a potential alternative to late gadolinium enhancement.

Resultado numérico

Tasa de eventos absoluta: 0% vs 0%

Resumen

Abstract Background Cardiovascular disease remains a major global health concern, necessitating advanced, non-invasive diagnostic techniques. 1Oxygenation-sensitive cardiovascular magnetic resonance (OS-CMR) imaging provides a promising contrast-free approach for myocardial assessment. 2 This study introduces DeepOxyMap, OS-CMR imaging, combined with AI-powered feature mapping, enables myocardial pathology detection without contrast agents. DeepOxyMap classifies and visualize patterns of myocardial scars into ischemic (42), non-ischemic (33), edema (47), and healthy (68) cases, providing the AI-based feature visualization. Purpose Develop DeepOxyMap, a deep learning-based classification model that not only enhances diagnostic precision but also visualizes scar patterns on OS-CMR for the first time, offering a contrast-free alternative to late gadolinium enhancement (LGE). Methods The dataset comprised short-axis OS-CMR images, LGE, T1, and T2 maps from two independent research cohorts, totaling 160 subjects (43.1 ± 15.3 years, 30.0% female) from the first study and 30 participants (54.93 ± 9.73 years, 50.0% female) from the second study to improve generalizability. A VGG19-based convolutional neural network was employed using transfer learning. Preprocessing included image resizing, normalization, and augmentation with random rotations (±20°, ±40°, ±60°, ±180°) and horizontal flipping (50% probability) to improve model robustness. The dataset was split based on 80% policy and model performance was evaluated using accuracy, precision, recall, and ROC-AUC scores. DeepOxyMap’s feature maps were extracted to visualize pathological patterns and compared against LGE images, serving as the clinical reference. Results DeepOxyMap achieved a classification accuracy of 82.0% on the test set, with precision and recall scores of 86.0% and 78.0%, respectively. On the validation set, the model achieved an accuracy of 78.0% and a precision of 84.0%, demonstrating consistency across datasets. Multi-class ROC-AUC analysis showed strong discriminatory power (healthy: 0.94, ischemic: 0.88, non-ischemic: 0.93, edema: 0.98), outperforming ResNet50 (AUC of 0.87) and EfficientNetB0 (0.79) (see Figure 1). Most notably, DeepOxyMap’s feature maps closely aligned with expert-identified LGE, T1, and T2 maps, demonstrating its ability to localize myocardial pathology accurately. For the first time, OS-CMR feature maps exhibited scar patterns comparable to those observed on LGE, reinforcing the potential of this contrast-free imaging approach in clinical settings (see Figure 2). Conclusions DeepOxyMap is a clinically viable, AI-driven OS-CMR framework for contrast-free myocardial scar classification and visualization. By generating feature maps that align with LGE, the model enhances diagnostic precision and offers a safer, more accessible alternative to conventional imaging.

Preguntar a la IA

Me gusta

Guardar