Polymerized Feature-based Domain Adaptation for Cervical Cancer Dose Map Prediction

TL;DR

This paper introduces a Transformer-based domain adaptation method using polymerized features to improve cervical cancer dose map prediction by transferring knowledge from rectum cancer data, addressing data scarcity issues.

Contribution

It proposes a novel polymerized feature module (PFM) leveraging Transformer architecture for effective domain adaptation in medical dose prediction tasks.

Findings

Outperforms state-of-the-art methods on clinical datasets.

Effectively transfers knowledge from rectum to cervical cancer.

Improves dose map prediction accuracy with limited data.

Abstract

Recently, deep learning (DL) has automated and accelerated the clinical radiation therapy (RT) planning significantly by predicting accurate dose maps. However, most DL-based dose map prediction methods are data-driven and not applicable for cervical cancer where only a small amount of data is available. To address this problem, this paper proposes to transfer the rich knowledge learned from another cancer, i.e., rectum cancer, which has the same scanning area and more clinically available data, to improve the dose map prediction performance for cervical cancer through domain adaptation. In order to close the congenital domain gap between the source (i.e., rectum cancer) and the target (i.e., cervical cancer) domains, we develop an effective Transformer-based polymerized feature module (PFM), which can generate an optimal polymerized feature distribution to smoothly align the two input distributions. Experimental results on two in-house clinical datasets demonstrate the superiority of the proposed method compared with state-of-the-art methods.