Meeting Banner
Abstract #1122

Knee Bone and Cartilage Segmentation using Deep Learning Model Trained with Heterogeneous Data: Preliminary Results

Xiaoxia Zhang1, Hector L. De Moura1, Marcelo V. W. Zibetti1, and Ravinder R. Regatte1
1Grossman School of Medicine, New York University, New York, NY, United States

Synopsis

Keywords: Cartilage, JointsIn this study, we pre-trained a deep learning model for knee bone and cartilage segmentation with open dataset (MICCAI grand challenge "K2S 2022"), and then fine-tuned it with a small size of locally acquired data for customized task, in which we explored different contrasts as well. We can benefit from the large dataset size to increase the segmentation accuracy and generalization capabilities while reducing the labor and time of manual segmentation for training data. The preliminary results of a small dataset with 10 subjects using a simple 2D U-net are promising for single contrast and multi contrast images.

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