Anti-cancer immunotherapy dramatically changes the clinical management of many types of tumours towards less harmful and more personalized treatment plans than conventional chemotherapy or radiation. Precise analysis of the spatial distribution of immune cells in the tumourous tissue is necessary to select patients that would best respond to the treatment. Here, we introduce a deep learning-based workflow for cell nuclei segmentation and subsequent immune cell identification in routine diagnostic images. We applied our workflow on a set of hematoxylin and eosin (H&E) stained breast cancer and colorectal cancer tissue images to detect tumour-infiltrating lymphocytes. Firstly, to segment all nuclei in the tissue, we applied the multiple-image input layer architecture (Micro-Net, Dice coefficient (DC) $0.79\pm 0.02$). We supplemented the Micro-Net with an introduced texture block to increase segmentation accuracy (DC = $0.80\pm 0.02$). We preserved the shallow architecture of the segmentation network with only 280 K trainable parameters (e.g. U-net with ∼1900 K parameters, DC = $0.78\pm 0.03$). Subsequently, we added an active contour layer to the ground truth images to further increase the performance (DC = $0.81\pm 0.02$). Secondly, to discriminate lymphocytes from the set of all segmented nuclei, we explored multilayer perceptron and achieved a 0.70 classification f-score. Remarkably, the binary classification of segmented nuclei was significantly improved (f-score = 0.80) by colour normalization. To inspect model generalization, we have evaluated trained models on a public dataset that was not put to use during training. We conclude that the proposed workflow achieved promising results and, with little effort, can be employed in multi-class nuclei segmentation and identification tasks.
Pub. online:17 Jun 2020Type:Research ArticleOpen Access
Journal:Informatica
Volume 31, Issue 3 (2020), pp. 561–578
Abstract
This paper presents a non-iterative deep learning approach to compressive sensing (CS) image reconstruction using a convolutional autoencoder and a residual learning network. An efficient measurement design is proposed in order to enable training of the compressive sensing models on normalized and mean-centred measurements, along with a practical network initialization method based on principal component analysis (PCA). Finally, perceptual residual learning is proposed in order to obtain semantically informative image reconstructions along with high pixel-wise reconstruction accuracy at low measurement rates.