Anatomical Data Augmentation For CNN based Pixel-wise Classification
This incremental improvement addresses data scarcity for medical imaging researchers and practitioners in liver lesion segmentation.
The paper tackled the problem of limited labeled data for pixel-wise classification of hepatic lesions in CT scans by proposing an anatomical data augmentation method using adjacent slices, achieving improvements of 3% in success rate, 5% in accuracy, and 4% in Dice score.
In this work we propose a method for anatomical data augmentation that is based on using slices of computed tomography (CT) examinations that are adjacent to labeled slices as another resource of labeled data for training the network. The extended labeled data is used to train a U-net network for a pixel-wise classification into different hepatic lesions and normal liver tissues. Our dataset contains CT examinations from 140 patients with 333 CT images annotated by an expert radiologist. We tested our approach and compared it to the conventional training process. Results indicate superiority of our method. Using the anatomical data augmentation we achieved an improvement of 3% in the success rate, 5% in the classification accuracy, and 4% in Dice.