Normal Appearance Autoencoder for Lung Cancer Detection and Segmentation
One of the major differences between medical doctor training and machine learning is that doctors are trained to recognize normal/healthy anatomy first. Knowing the healthy appearance of anatomy structures helps doctors to make better judgement when some abnormality shows up in an image. In this study, we propose a normal appearance autoencoder (NAA), that removes abnormalities from a diseased image. This autoencoder is semi-automatically trained using another partial convolutional in-paint network that is trained using healthy subjects only. The output of the autoencoder is then fed to a segmentation net in addition to the original input image, i.e. the latter gets both the diseased image and a simulated healthy image where the lesion is artificially removed. By getting access to knowledge of how the abnormal region is supposed to look, we hypothesized that the segmentation network could perform better than just being shown the original slice. We tested the proposed network on the LIDC-IDRI dataset for lung cancer detection and segmentation. The preliminary results show the NAA approach improved segmentation accuracy substantially in comparison with the conventional U-Net architecture.
KeywordsLung nodule segmentation Anomaly detection Convolutional variational autoencoder
This study was supported by the Swedish Childhood Cancer Foundation (grant no. MT2016-0016) and the Swedish innovation agency Vinnova (grant no. 2017-01247).
- 3.Baur, C., Wiestler, B., Albarqouni, S., Navab, N.: Deep autoencoding models for unsupervised anomaly segmentation in brain MR images. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11383, pp. 161–169. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11723-8_16CrossRefGoogle Scholar
- 4.Chen, X., Konukoglu, E.: Unsupervised detection of lesions in brain MRI using constrained adversarial auto-encoders (2018)Google Scholar
- 5.Schlegl, T., Seeböck, P., Waldstein, S.M., Schmidt-Erfurth, U., Langs, G.: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 146–157. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59050-9_12CrossRefGoogle Scholar
- 6.Liu, G., Reda, F.A., Shih, K.J., Wang, T.-C., Tao, A., Catanzaro, B.: Image inpainting for irregular holes using partial convolutions (2018)Google Scholar
- 7.Alex, V., Mohammed Safwan, K.P., Chennamsetty, S.S., Krishnamurthi, G.: Generative adversarial networks for brain lesion detection. Presented at the 24 February (2017)Google Scholar
- 11.Wang, Z., Yuan, H., Ji, S.: Spatial variational auto-encoding via matrix-variate normal distributions (2017)Google Scholar