Deep Semantic Segmentation of Mammographic Images

MIAS and INbreast are mammographic datasets for the detection and diagnosis of breast cancer. With the dawn of digital mammograms, one important preprocessing step for the tasks of detection and diagnosis is the removal of the pectoral muscle and background area from the images, therefore this task has been tackled by the literature over the last decades. The suplementary material below is a complement to the contents in the paper Deep Semantic Segmentation of Mammographic Images, awaiting acceptance in the 21st International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI) 2018. This page contains:

 

  • the pretrained Deep Neural Networks (DNNs) used in the paper;
  • the predictions made by the DNNs over the datasets;
  • python source codes with the modified versions of the networks used in the paper;
  • the complete spreadsheets with all the results from the paper; and
  • a python source code for forwarding mammograms through the pretrained models.
Pretrained models
Segmentation predictions
Python code for the modified DNN models
Complete set of results
Python code for testing in your own datasets
Categories: DownloadsSource codes

Related Posts

Datasets

Fashion Dataset

Fashion Dataset This dataset is a composition of fashion images and associated tags and comments crawled from two fashion-related social networks, namely pose.com and chictopia.com. The first part of this dataset (related to the pose.com Read more…

Datasets

Region-based Annotated Child Pornography Dataset

This dataset is a private database that belongs to the Brazilian Federal Police. The paper "A Benchmark Methodology for Child Pornography Detection" describes the structure of the dataset. The aim of the dataset is to assess and compare the performance of child pornography detection methods.

Datasets

Brazilian Cerrado-Savanna Scenes Dataset

The dataset is composed of 1,311 multi-spectral scenes extracted from images acquired by the RapidEye satellite sensors over the Serra do Cipó region, a mountainous and highly biodiverse and heterogenous landscape in southern-central Brazil mainly constituted of Cerrado-Savanna Vegetation. From the 5 bands (blue, green, red, red edge and near infrared) that the images acquired by the RapidEye satellite sensors have, we have selected three (near-infrared, green, and red bands), which are the most useful and representative ones for discriminating vegetation areas. It is a very challenging dataset given its high intraclass variance, caused by different spatial configurations and densities of the same vegetation type, as well as its high interclass similarity, given similar appearance of different types of vegetation species.

Top