Meeting Banner
Abstract #1706

InvYNet: an inverted Y shape network for prostate cancer segmentation using prostate zones information

Yuying Liu1,2, ZHENGYANG ZHU1, Xin Zhang1, and Bing Zhang1
1Department of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing University, Nanjing, China, 2National Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University, Nanjing, China

Synopsis

Keywords: AI/ML Software, AI/ML Software, Prostate cancer, segmentation

Motivation: Accurate segmentation of prostate cancer is vital for effective treatment, yet challenging due

Goal(s): We aim to enhance prostate cancer segmentation by leveraging anatomical zones of the prostate.

Approach: Our novel InvYNet model features two branches: an auxiliary branch for segmenting anatomical zones and a main branch that utilizes this information, enhanced by a Dual Attention Gate (DAG).

Results: Extensive experiments on public datasets show that InvYNet outperforms existing models, achieving a 5% improvement over the second-place method on the PROSTATEx dataset.

Impact: InvYNet is the first model to integrate anatomical zones for prostate cancer segmentation, setting a new standard in this field.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords