Could We Generate Cytology Images from Histopathology Images? An Empirical Study
This addresses data scarcity for medical imaging automation in breast cancer diagnosis, but it is incremental as it applies existing image-to-image translation methods to a new domain.
The study tackled the problem of scarce annotated cytology images for breast malignancy identification by generating synthetic cytology images from publicly available histopathology samples using models like CycleGAN and Neural Style Transfer, achieving similarity to real samples as measured by FID and KID scores.
Automation in medical imaging is quite challenging due to the unavailability of annotated datasets and the scarcity of domain experts. In recent years, deep learning techniques have solved some complex medical imaging tasks like disease classification, important object localization, segmentation, etc. However, most of the task requires a large amount of annotated data for their successful implementation. To mitigate the shortage of data, different generative models are proposed for data augmentation purposes which can boost the classification performances. For this, different synthetic medical image data generation models are developed to increase the dataset. Unpaired image-to-image translation models here shift the source domain to the target domain. In the breast malignancy identification domain, FNAC is one of the low-cost low-invasive modalities normally used by medical practitioners. But availability of public datasets in this domain is very poor. Whereas, for automation of cytology images, we need a large amount of annotated data. Therefore synthetic cytology images are generated by translating breast histopathology samples which are publicly available. In this study, we have explored traditional image-to-image transfer models like CycleGAN, and Neural Style Transfer. Further, it is observed that the generated cytology images are quite similar to real breast cytology samples by measuring FID and KID scores.