Robust Real-time Segmentation of Bio-Morphological Features in Human Cherenkov Imaging during Radiotherapy via Deep Learning

TL;DR

This paper presents a deep learning framework for real-time segmentation of bio-morphological features in Cherenkov images during radiotherapy, enabling faster and more accurate patient verification and motion management.

Contribution

The study introduces the first deep learning approach for rapid, real-time segmentation of Cherenkov bio-morphological features, utilizing transfer learning from fundus images to overcome limited annotations.

Findings

Achieved Dice score of 0.85 in segmentation accuracy.

Processed images in less than 0.7 milliseconds per instance.

Demonstrated robustness and consistency across patient data.

Abstract

Cherenkov imaging enables real-time visualization of megavoltage X-ray or electron beam delivery to the patient during Radiation Therapy (RT). Bio-morphological features, such as vasculature, seen in these images are patient-specific signatures that can be used for verification of positioning and motion management that are essential to precise RT treatment. However until now, no concerted analysis of this biological feature-based tracking was utilized because of the slow speed and accuracy of conventional image processing for feature segmentation. This study demonstrated the first deep learning framework for such an application, achieving video frame rate processing. To address the challenge of limited annotation of these features in Cherenkov images, a transfer learning strategy was applied. A fundus photography dataset including 20,529 patch retina images with ground-truth vessel annotation was used to pre-train a ResNet segmentation framework. Subsequently, a small Cherenkov dataset (1,483 images from 212 treatment fractions of 19 breast cancer patients) with known annotated vasculature masks was used to fine-tune the model for accurate segmentation prediction. This deep learning framework achieved consistent and rapid segmentation of Cherenkov-imaged bio-morphological features on another 19 patients, including subcutaneous veins, scars, and pigmented skin. Average segmentation by the model achieved Dice score of 0.85 and required less than 0.7 milliseconds processing time per instance. The model demonstrated outstanding consistency against input image variances and speed compared to conventional manual segmentation methods, laying the foundation for online segmentation in real-time monitoring in a prospective setting.