Keywords: Uterus, DWI/DTI/DKI
Motivation: Convolution neural network (CNN) is widely used in image segmentation, tumour classification and recurrence risk prediction of cervical carcinoma (CC). However, deep learning (DL) studies based on diffusion kurtosis imaging (DKI) for histological subtyping has not been investigated in CC.
Goal(s): To evaluate the clinical ability of DKI-based CNN classification model in differentiating histological subtypes of CC.
Approach: The proposed uAInnovation portal using 3D CNN classification model was applied for DL modelling.
Results: The overall classification performances were good in both D and K models for predicting histological subtypes in testing set, suggesting the potential value of DKI in the characterisation of CC.
Impact: The proposed uAInnovation research platform designed for clinicians is efficient and helpful in deep learning deployment. DKI-based CNN classification model demonstrated good performance in differentiating histological subtypes, suggesting the potential clinicopathological value of DKI in cervical carcinoma.
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.
Keywords