Skip to main content
Fig. 6 | BMC Medicine

Fig. 6

From: Deep learning radiomics based on contrast-enhanced ultrasound images for assisted diagnosis of pancreatic ductal adenocarcinoma and chronic pancreatitis

Fig. 6

A summary of the total scores from five radiologists before and after DLR model assistance for every lesion in the validation cohorts. The red and green circles indicate the total score without and with DLR model assistance, respectively. The blue circles indicate that the lesion has the same score before and after AI assistance. The arrows indicate the trend of the total score after AI assistance. The total score is obtained by the sum of the scores of five radiologists individually. If a radiologist believes that a lesion is PDAC, it is scored as one point leading to a maximum score of five. The higher the score, the more experts believe that the lesion is PDAC. PDAC, pancreatic ductal adenocarcinoma; CP, chronic pancreatitis; AI, artificial intelligence; DLR, deep learning radiomics

Back to article page