Segmentation of supragranular and infragranular layers in ultra-high-resolution 7T ex vivo MRI of the human cerebral cortex.

Accurate labeling of specific layers in the human cerebral cortex is crucial for advancing our understanding of neurodevelopmental and neurodegenerative disorders. Building on recent advancements in ultra-high-resolution ex vivo MRI, we present a novel semi-supervised segmentation model capable of identifying supragranular and infragranular layers in ex vivo MRI with unprecedented precision. On a dataset consisting of 17 whole-hemisphere ex vivo scans at 120 $\mu $m, we propose a Multi-resolution U-Nets framework that integrates global and local structural information, achieving reliable segmentation maps of the entire hemisphere, with Dice scores over 0.8 for supra- and infragranular layers. This enables surface modeling, atlas construction, anomaly detection in disease states, and cross-modality validation while also paving the way for finer layer segmentation. Our approach offers a powerful tool for comprehensive neuroanatomical investigations and holds promise for advancing our mechanistic understanding of progression of neurodegenerative diseases.

Deep learning-based localization algorithms on fluorescence human brain 3D reconstruction: a comparative study using stereology as a reference.

3D reconstruction of human brain volumes at high resolution is now possible thanks to advancements in tissue clearing methods and fluorescence microscopy techniques. Analyzing the massive data produced with these approaches requires automatic methods able to perform fast and accurate cell counting and localization. Recent advances in deep learning have enabled the development of various tools for cell segmentation. However, accurate quantification of neurons in the human brain presents specific challenges, such as high pixel intensity variability, autofluorescence, non-specific fluorescence and very large size of data. In this paper, we provide a thorough empirical evaluation of three techniques based on deep learning (StarDist, CellPose and BCFind-v2, an updated version of BCFind) using a recently introduced three-dimensional stereological design as a reference for large-scale insights. As a representative problem in human brain analysis, we focus on a 4 -cm 3 portion of the Broca's area. We aim at helping users in selecting appropriate techniques depending on their research objectives. To this end, we compare methods along various dimensions of analysis, including correctness of the predicted density and localization, computational efficiency, and human annotation effort. Our results suggest that deep learning approaches are very effective, have a high throughput providing each cell 3D location, and obtain results comparable to the estimates of the adopted stereological design.

Optical Clearing and Labeling for Light-sheet Fluorescence Microscopy in Large-scale Human Brain Imaging.

Despite the numerous clearing techniques that emerged in the last decade, processing postmortem human brains remains a challenging task due to its dimensions and complexity, which make imaging with micrometer resolution particularly difficult. This paper presents a protocol to perform the reconstruction of volumetric portions of the human brain by simultaneously processing tens of sections with the SHORT (SWITCH - H2O2 - Antigen Retrieval - 2,2'-thiodiethanol [TDE]) tissue transformation protocol, which enables clearing, labeling, and sequential imaging of the samples with light-sheet fluorescence microscopy (LSFM). SHORT provides rapid tissue clearing and homogeneous multi-labeling of thick slices with several neuronal markers, enabling the identification of different neuronal subpopulations in both white and grey matter. After clearing, the slices are imaged via LSFM with micrometer resolution and in multiple channels simultaneously for a rapid 3D reconstruction. By combining SHORT with LSFM analysis within a routinely high-throughput protocol, it is possible to obtain the 3D cytoarchitecture reconstruction of large volumetric areas at high resolution in a short time, thus enabling comprehensive structural characterization of the human brain.

Quantitative cytoarchitectural phenotyping of deparaffinized human brain tissues.

Advanced 3D imaging techniques and image segmentation and classification methods can profoundly transform biomedical research by offering deep insights into the cytoarchitecture of the human brain in relation to pathological conditions. Here, we propose a comprehensive pipeline for performing 3D imaging and automated quantitative cellular phenotyping on Formalin-Fixed Paraffin-Embedded (FFPE) human brain specimens, a valuable yet underutilized resource. We exploited the versatility of our method by applying it to different human specimens from both adult and pediatric, normal and abnormal brain regions. Quantitative data on neuronal volume, ellipticity, local density, and spatial clustering level were obtained from a machine learning-based analysis of the 3D cytoarchitectural organization of cells identified by different molecular markers in two subjects with malformations of cortical development (MCD). This approach will grant access to a wide range of physiological and pathological paraffin-embedded clinical specimens, allowing for volumetric imaging and quantitative analysis of human brain samples at cellular resolution. Possible genotype-phenotype correlations can be unveiled, providing new insights into the pathogenesis of various brain diseases and enlarging treatment opportunities.

Segmentation of supragranular and infragranular layers in ultra-high resolution 7T ex vivo MRI of the human cerebral cortex.

Accurate labeling of specific layers in the human cerebral cortex is crucial for advancing our understanding of neurodevelopmental and neurodegenerative disorders. Leveraging recent advancements in ultra-high resolution ex vivo MRI, we present a novel semi-supervised segmentation model capable of identifying supragranular and infragranular layers in ex vivo MRI with unprecedented precision. On a dataset consisting of 17 whole-hemisphere ex vivo scans at 120 µm, we propose a multi-resolution U-Nets framework (MUS) that integrates global and local structural information, achieving reliable segmentation maps of the entire hemisphere, with Dice scores over 0.8 for supra- and infragranular layers. This enables surface modeling, atlas construction, anomaly detection in disease states, and cross-modality validation, while also paving the way for finer layer segmentation. Our approach offers a powerful tool for comprehensive neuroanatomical investigations and holds promise for advancing our mechanistic understanding of progression of neurodegenerative diseases.