FP-PET: Large Model, Multiple Loss And Focused Practice

TL;DR

This paper introduces FP-PET, a comprehensive medical image segmentation approach using multiple models and loss functions, evaluated with a new aggregated score on CT and PET images, addressing computational challenges and refining results with preprocessing techniques.

Contribution

The study presents FP-PET, integrating multiple models, loss functions, and an aggregated evaluation score for improved medical image segmentation performance.

Findings

Achieved state-of-the-art segmentation performance on AutoPet2023 dataset.

Developed an aggregated score combining Dice, FPV, and FNV metrics.

Explored preprocessing and postprocessing techniques to enhance segmentation accuracy.

Abstract

This study presents FP-PET, a comprehensive approach to medical image segmentation with a focus on CT and PET images. Utilizing a dataset from the AutoPet2023 Challenge, the research employs a variety of machine learning models, including STUNet-large, SwinUNETR, and VNet, to achieve state-of-the-art segmentation performance. The paper introduces an aggregated score that combines multiple evaluation metrics such as Dice score, false positive volume (FPV), and false negative volume (FNV) to provide a holistic measure of model effectiveness. The study also discusses the computational challenges and solutions related to model training, which was conducted on high-performance GPUs. Preprocessing and postprocessing techniques, including gaussian weighting schemes and morphological operations, are explored to further refine the segmentation output. The research offers valuable insights into the challenges and solutions for advanced medical image segmentation.