Meeting Banner
Abstract #4013

Advancing Parotid Tumor Diagnosis with KAN Transformer: Precise Differentiation of Pleomorphic Adenoma and Warthin Tumor: A Multicenter Study

Wenfeng Mai1, Lingtao Zhang1, Dong Zhang1, Jiayi Zhong2, Jingyi Tan3, Yaxi Chen1, Weiyin Vivian Liu4, Xiangning Liu1, Xiaoyu Hua1,5, and Changzheng Shi1
1the First Affiliated Hospital of Jinan University, Guangzhou, China, 2Huizhou Tradit Chinese Medicine Hospital, Huizhou, China, 3YueBei People’s hospital, Shaoguan, China, 4GE Healthcare, MR Research China, Beijing, China, 5Shenzhen Second People's Hospital, Shenzhen, China

Synopsis

Keywords: AI/ML Image Reconstruction, Head & Neck/ENT

Motivation: Parotid gland pleomorphic adenomas (PPAs) and Warthin tumors (PWTs) have overlapping imaging features, making preoperative differentiation challenging. Accurate differentiation is needed to guide individualized treatment and improve patient outcomes.

Goal(s): This study aims to develop an AI model for accurate preoperative prediction of parotid PPAs and PWTs.

Approach: A parotid tumor segmentation model was developed using the MONAI framework with Unet network, followed by MRI-based predictive models: a radiomics model and deep learning models, Kolmogorov-Arnold Network Transformer (KAT) and Vision Transformer (VIT).

Results: The KAT model demonstrated superior accuracy over VIT and radiomics in distinguishing PPAs from PWTs, even with limited imaging data.

Impact: The KAT model provides precise early diagnosis of benign parotid tumors, even with limited MRI data. These findings could extend to other tumor types, improving diagnostic accuracy and supporting individualized treatment.

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