Generalized Dice Focal Loss trained 3D Residual UNet for Automated Lesion Segmentation in Whole-Body FDG PET/CT Images
This work addresses the problem of accurate lesion segmentation for medical image analysis in oncology, though it appears incremental with a hybrid approach.
The paper tackled automated lesion segmentation in whole-body PET/CT images by training a 3D Residual UNet with Generalized Dice Focal Loss, achieving a Dice similarity coefficient of 0.5417 and false-positive/negative volumes around 0.8 ml and 0.25 ml on a test dataset.
Automated segmentation of cancerous lesions in PET/CT images is a vital initial task for quantitative analysis. However, it is often challenging to train deep learning-based segmentation methods to high degree of accuracy due to the diversity of lesions in terms of their shapes, sizes, and radiotracer uptake levels. These lesions can be found in various parts of the body, often close to healthy organs that also show significant uptake. Consequently, developing a comprehensive PET/CT lesion segmentation model is a demanding endeavor for routine quantitative image analysis. In this work, we train a 3D Residual UNet using Generalized Dice Focal Loss function on the AutoPET challenge 2023 training dataset. We develop our models in a 5-fold cross-validation setting and ensemble the five models via average and weighted-average ensembling. On the preliminary test phase, the average ensemble achieved a Dice similarity coefficient (DSC), false-positive volume (FPV) and false negative volume (FNV) of 0.5417, 0.8261 ml, and 0.2538 ml, respectively, while the weighted-average ensemble achieved 0.5417, 0.8186 ml, and 0.2538 ml, respectively. Our algorithm can be accessed via this link: https://github.com/ahxmeds/autosegnet.