Patent · US Active

Semantic segmentation for cancer detection in digital breast tomosynthesis

US10779785B2 · kind B2 · utility

3Cited by

0References

23Claims

0Family size

Assignee

Siemens Healthcare Limited · DE

Inventors

Lucian Mihai Itu · Brașov, RO
Laszlo Lazar · Gheorgheni, RO
Siqi LIU · Dongguan, CN
Olivier Pauly · Munich, DE
Philipp Seegerer · Ortenburg, DE
Iulian Ionut Stroia · Brașov, RO
Alexandru Turcea · Bușteni, RO
Anamaria Vizitiu · Sfântu Gheorghe, RO
Daguang Xu · Princeton, US
Shaohua Kevin Zhou · Plainsboro, US

Key dates

Filing date	Jul 12, 2018
Grant date	Sep 22, 2020
Priority date	—
Expiry date	Feb 4, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06T2207/30068
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.