Find in Library

Tumor-infiltrating lymphocytes (TILs) act as immune cells against cancer tissues. The manual assessment of TILs is usually erroneous, tedious, costly and subject to inter- and intraobserver variability. Machine learning approaches can solve these issues, but they require a large amount of labeled data for model training, which is expensive and not readily available. In this study, we present an efficient generative adversarial network, <italic>TilGAN</italic>, to generate high-quality synthetic pathology images followed by classification of TIL and non-TIL regions. Our proposed architecture is constructed with a generator network and a discriminator network. The novelty exists in the <italic>TilGAN</italic> architecture, loss functions, and evaluation techniques. Our <italic>TilGAN</italic>-generated images achieved a higher Inception score than the real images (2.90 vs. 2.32, respectively). They also achieved a lower kernel Inception distance (1.44) and a lower Fr&#x00E9;chet Inception distance (0.312). It also passed the Turing test performed by experienced pathologists and clinicians. We further extended our evaluation studies and used almost one million synthetic data, generated by <italic>TilGAN</italic>, to train a classification model. Our proposed classification model achieved a 97.83&#x0025; accuracy, a 97.37&#x0025; F1-score, and a 97&#x0025; area under the curve. Our extensive experiments and superior outcomes show the efficiency and effectiveness of our proposed <italic>TilGAN</italic> architecture. This architecture can also be used for other types of images for image synthesis.