Siemens Healthcare Gmbh

Iulian Ionut Stroia

Shaohua Kevin Zhou

Lucian Mihai Itu

Daguang Xu

Olivier Pauly

Siqi Liu

Anamaria Vizitiu

Philipp Seegerer

Alexandru Turcea

Laszlo Lazar

A method, apparatus and non-transitory computer readable medium are for segmenting different types of structures, including cancerous lesions and regular structures like vessels and skin, in a digital breast tomosynthesis (DBT) volume. In an embodiment, the method includes: pre-classification of the DBT volume in dense and fatty tissue and based on the result; localizing a set of structures in the DBT volume by using a multi-stream deep convolutional neural network; and segmenting the localized structures by calculating a probability for belonging to a specific type of structure for each voxel in the DBT volume by using a deep convolutional neural network for providing a three-dimensional probabilistic map.

Semantic segmentation for cancer detection in digital breast tomosynthesis

Growing community of inventors

Brasov, Romania

Iulian Ionut Stroia