Towards detection of cancer biomarkers in human exhaled air by transfer-learning-powered analysis of odor-evoked calcium activity in rat olfactory bulb.

Detection of volatile organic compounds in exhaled air is a promising approach to non-invasive and scalable gastric cancer screening. This work proposes a new approach for the detection of volatile organic compounds by analyzing odor-evoked calcium responses in the rat olfactory bulb. We estimate the feasibility of gastric cancer biomarker detection added to the exhaled air of healthy participants. Our detector consists of a convolutional encoder and a similarity-based classifier over encoder outputs. To minimize overfitting on a small available training set, we involve a pre-training where the encoder is trained on synthetic data representing spatiotemporal patterns similar to real calcium responses in the olfactory bulb. We estimate the classification accuracy of exhaled air samples by matching their encodings with encodings of calibration samples of two classes: 1) exhaled air and 2) a mixture of exhaled air with the cancer biomarker. On our data, the accuracy increased from 0.68 on real data up to 0.74 if pre-training on synthetic data is involved. Our work is focused on proving the feasibility of proposed new approach rather than on comparing its efficiency with existing methods. Such detection is often performed with an electronic nose, but its output becomes unstable over time due to a sensor drift. In contrast to the electronic nose, rats can robustly detect low concentrations of biomarkers over lifetime. The feasibility of gastric cancer biomarker detection in exhaled air by bio-hybrid system is shown. Pre-training of neural models for images analysis increases the accuracy of detection.

The method for assessment of local permutations in the glomerular patterns of the rat olfactory bulb by aligning interindividual odor maps.

The comparison of odor functional maps in rodents demonstrates a high degree of inter-individual variability in glomerular activity patterns. There are substantial methodological difficulties in the interindividual assessment of local permutations in the glomerular patterns, since the position of anatomical extracranial landmarks, as well as the size, shape and angular orientation of olfactory bulbs can vary significantly. A new method for defining anatomical coordinates of active glomeruli in the rat olfactory bulb has been developed. The method compares the interindividual odor functional maps and calculates probabilistic maps of glomerular activity with adjustment. This adjustment involves rotation, scaling and shift of the functional map relative to its expected position in probabilistic map, computed according to the anatomical coordinates. The calculation of the probabilistic map of the odorant-specific response compensates for potential anatoamical errors due to individual variability in olfactory bulb dimensions and angular orientation. We show its efficiency on real data from a large animal sample recorded by two-photon calcium imaging in dorsal surface of the rat olfactory bulb. The proposed method with probabilistic map calculation enables the spatial consistency of the effects of individual odorants in different rats to be assessed and allow stereotypical positions of odor-specific clusters in the glomerular layer of the olfactory bulb to be identified.

Relation of Descriptor Completeness and Distinctiveness to Localization of the Most Informative Regions in Images.

Allocation of informative regions in images depends on a visual task. We propose two criteria for allocation of informative regions in images considering visual recognition of objects in images using a space-variant foveal filter. The first criterion relates to descriptor completeness. This criterion is formalized as a measure of similarity of an original image to an image reconstructed from foveal filter responses. The second criterion relates to descriptor distinctiveness. This criterion relates to the problem of retrieving discriminative and repeatable features in images of objects. It is formalized as a variation of descriptor elements of different objects within the same class. We reveal that regions of interest produced by these criteria are distributed in the areas of high variety of brightness gradients orientations.