{"title":"AutoPET Challenge: Tumour Synthesis for Data Augmentation","authors":"Lap Yan Lennon Chan, Chenxin Li, Yixuan Yuan","doi":"arxiv-2409.08068","DOIUrl":null,"url":null,"abstract":"Accurate lesion segmentation in whole-body PET/CT scans is crucial for cancer\ndiagnosis and treatment planning, but limited datasets often hinder the\nperformance of automated segmentation models. In this paper, we explore the\npotential of leveraging the deep prior from a generative model to serve as a\ndata augmenter for automated lesion segmentation in PET/CT scans. We adapt the\nDiffTumor method, originally designed for CT images, to generate synthetic\nPET-CT images with lesions. Our approach trains the generative model on the\nAutoPET dataset and uses it to expand the training data. We then compare the\nperformance of segmentation models trained on the original and augmented\ndatasets. Our findings show that the model trained on the augmented dataset\nachieves a higher Dice score, demonstrating the potential of our data\naugmentation approach. In a nutshell, this work presents a promising direction\nfor improving lesion segmentation in whole-body PET/CT scans with limited\ndatasets, potentially enhancing the accuracy and reliability of cancer\ndiagnostics.","PeriodicalId":501289,"journal":{"name":"arXiv - EE - Image and Video Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08068","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Accurate lesion segmentation in whole-body PET/CT scans is crucial for cancer
diagnosis and treatment planning, but limited datasets often hinder the
performance of automated segmentation models. In this paper, we explore the
potential of leveraging the deep prior from a generative model to serve as a
data augmenter for automated lesion segmentation in PET/CT scans. We adapt the
DiffTumor method, originally designed for CT images, to generate synthetic
PET-CT images with lesions. Our approach trains the generative model on the
AutoPET dataset and uses it to expand the training data. We then compare the
performance of segmentation models trained on the original and augmented
datasets. Our findings show that the model trained on the augmented dataset
achieves a higher Dice score, demonstrating the potential of our data
augmentation approach. In a nutshell, this work presents a promising direction
for improving lesion segmentation in whole-body PET/CT scans with limited
datasets, potentially enhancing the accuracy and reliability of cancer
diagnostics.