Skip to main content
Fig. 2 | Orphanet Journal of Rare Diseases

Fig. 2

From: Novel computer aided diagnostic models on multimodality medical images to differentiate well differentiated liposarcomas from lipomas approached by deep learning methods

Fig. 2

Feature heatmaps of representative patients on the deep learning ResNet50 algorithm via the Guided Grad-CAM. The original CT and MRI images and their corresponding feature heatmaps were shown from left to right. The red color highlighted the region of interest to classify lipoma and WDLPS. The red color focused on different area for lipomas (A) and WDLPS (B) on CT (Left), T1WI (Middle) and T2FS (Right) MRI images, respectively. CAM, Class activation mapping; CT, Computed tomography; MRI, Magnetic resonance imaging; WDLPS, Well differentiated liposarcoma; T1WI, T1-weighted MRI sequence; T2FS, Fat-saturated T2-weighted MRI sequence

Back to article page