Pre-Training, Transfer Learning and Pretext Learning for a Convolutional Neural Network Applied to Automated Assessment of Clinical PET Image Quality

Abstract

If citing, it is advised that you check and use the publisher's definitive version for pagination, volume/issue, and date of publication details. And where the final published version is provided on the Research Portal, if citing you are again advised to check the publisher's website for any subsequent corrections.

Automated size‐specific dose estimates framework in thoracic CT using convolutional neural network based on U‐Net model

“…To address the issue of limited patient data, this study used transfer learning with a pre‐trained model on the ImageNet dataset. This approach allowed the model to effectively handle small datasets and still produce accurate results 24,25 . The deep U‐Net structure with a ResNet34 encoder was implemented to perform automated segmentation of CT images, which provided a useful starting point for the study.…”

“…This approach allowed the model to effectively handle small datasets and still produce accurate results. 24 , 25 The deep U‐Net structure with a ResNet34 encoder was implemented to perform automated segmentation of CT images, which provided a useful starting point for the study.…”

“…The CNN architecture used the U‐Net with Resnet34 blocks in the down‐sampling path to achieve the desired segmentation 21 . Pre‐trained models from the ImageNet dataset were used as the starting point to enhance the training process and improve the model's performance 24,25 . The CNN architecture that was designed for automated segmentation of the three classes of tissues (lung, bone, and other tissues) and the background region used in calculating dimensions and the D eff corr is shown in Figure 2.…”

Large scale models in radiology: revolutionizing the future of medical imaging

“…Subsequently, transfer learning allows these large models to apply the generalized features acquired during pre-training to specific datasets under scrutiny [32]. Notably, Hopson et al [33] delved into the utilization of pre-trained CNN models for assessment of the quality of clinical PET images using transfer learning techniques. Hopson et al [33] demonstrated that pre-training significantly enhances the performance of CNN models in the task of assessing the quality of clinical images, particularly in automating the prediction of PET images.…”