We cordially invite you to the Ph.D. Seminar, which will be held on November 28, 2025 at 10.30 in the Konorski room (2nd floor).

There will be 1 presentation:

Information about the speaker and abstract can be found below.

MSc Adam Datta

Laboratory of Neuroinformatics
Supervisor: Dr. Piotr Majka, PhD, DSc.
Title: Quantitive characterization of the cerebral cortex in the non-human primate brain with use of deep learning techniques

Abstract:

Understanding how the cerebral cortex processes information involves laborious and knowledgeable characterization of its cytoarchitectonic properties. However, there is still no consensus regarding its structural and functional parcellation. Ongoing development of deep learning techniques provides rapid processing of large amounts of data, bringing a chance to alleviate these obstacles.

The study has two primary goals: to expand knowledge about the common marmoset (Callithrix jacchus) cerebral cortex features through quantitative characterization based on observer-independent segmentation, and to identify delineation criteria established by the deep-learning model while assessing its biological plausibility. To ensure a valid delineation of the cortex into layers and areas, we: (1) estimated neuronal density and size, (2) extracted one-dimensional cortical profiles, (3) trained U-Net deep-learning model, (4) applied Gradient-weighted Class Activation Mapping (Grad-CAM), and (5) measured cortical depth along 3D profiles to quantify laminar thickness and spatial organization across the cerebral cortex. Further evaluation revealed increased performance when all estimates contributed to the training process. Additionally, the model was capable of correctly assigning area labels based on learned features.

Beyond automating identification and quantification of individual layers and areas, our solution provides valuable insight into cytoarchitectonic properties by highlighting the most contributive parts of the cerebral cortex.

With best regards,
Anna Filipek & Anna Nowicka