Automatic semantic segmentation of breast tumors in ultrasound images based on combining fuzzy logic and deep learning—A feasibility study

doi:10.1371/journal.pone.0251899

Automatic semantic segmentation of breast tumors in ultrasound images based on combining fuzzy logic and deep learning—A feasibility study

Fig 5

Eight samples from 200 BUS benign images’ results for ResNet18 (batch processing).

Each sample consist of four images: 1^st the original image from the prepared small dataset, 2^nd the segmentation results without applying fuzzy enhancement, 3^rd the segmentation result after applying fuzzy based enhancement to the input image, and 4^th the original ground truth.

doi: https://doi.org/10.1371/journal.pone.0251899.g005