Saliency-driven system models for cell analysis with deep learning

• Published in: Computer methods and programs in biomedicine Vol. 182; no. C
• Main Authors: Ferreira, Daniel S., Ramalho, Geraldo L. B., Torres, Débora, Tobias, Alessandra H. G., Rezende, Mariana T., Medeiros, Fátima N. S., Bianchi, Andrea G. C., Carneiro, Cláudia M., Ushizima, Daniela M.
• Format: Journal Article
• Language: English
• Published: United States Elsevier 26.08.2019
• Subjects: 60 APPLIED LIFE SCIENCES; cell analysis; cervical; convolutional neural network; eye tracking experiment; MATHEMATICS AND COMPUTING; saliency prediction
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2019.105053

Saliency refers to the visual perception quality that makes objects in a scene to stand out from others and attract attention. While computational saliency models can simulate the expert's visual attention, there is little evidence about how these models perform when used to predict the cytopathologist's eye fixations. Saliency models may be the key to instrumenting fast object detection on large Pap smear slides under real noisy conditions, artifacts, and cell occlusions. This paper describes how our computational schemes retrieve regions of interest (ROI) of clinical relevance using visual attention models. We also compare the performance of different computed saliency models as part of cell screening tasks, aiming to design a computer-aided diagnosis systems that supports cytopathologists. We record eye fixation maps from cytopathologists at work, and compare with 13 different saliency prediction algorithms, including deep learning. We develop cell-specific convolutional neural networks (CNN) to investigate the impact of bottom-up and top-down factors on saliency prediction from real routine exams. By combining the eye tracking data from pathologists with computed saliency models, we assess algorithms reliability in identifying clinically relevant cells. The proposed cell-specific CNN model outperforms all other saliency prediction methods, particularly regarding the number of false positives. Our algorithm also detects the most clinically relevant cells, which are among the three top salient regions, with accuracy above 98% for all diseases, except carcinoma (87%). Bottom-up methods performed satisfactorily, with saliency maps that enabled ROI detection above 75% for carcinoma and 86% for other pathologies. ROIs extraction using our saliency prediction methods enabled ranking the most relevant clinical areas within the image, a viable data reduction strategy to guide automatic analyses of Pap smear slides. Top-down factors for saliency prediction on cell images increases the accuracy of the estimated maps while bottom-up algorithms proved to be useful for predicting the cytopathologist's eye fixations depending on parameters, such as the number of false positive and negative. Finally, our contributions are: comparison among 13 state-of-the-art saliency models to cytopathologists' visual attention and deliver a method that the associate the most conspicuous regions to clinically relevant cells.