Skip to main content
European Radiology Experimental
Fig. 5 | European Radiology Experimental

Fig. 5

From: Diagnostic performance of machine learning applied to texture analysis-derived features for breast lesion characterisation at automated breast ultrasound: a pilot study

Fig. 5

Lesions falsely classified as normal tissue using machine learning with the reduced feature set but correctly classified with the full feature set: invasive ductal carcinoma (maximal diameter 10 mm) in a 74-year-old patient (a) and fibroadenoma (maximal diameter 9 mm) in a 46-year-old patient (b). Lesion (a) was also falsely classified as benign in the comparison between malignant and benign lesions

Back to article page