Daniel Franco-Barranco

The female larval fly CNS connectome: first draft

The paper releases a complete larval Drosophila CNS connectome with automated segmentations and highlights the need for improved machine vision for proofreading.

SpineDL: a Deep Learning-based approach for neuron andanatomical structure segmentation in immunofluorescenceimages of damaged spinal cords

SpineDL is a deep learning tool for segmenting neurons and anatomical structures in spinal cord immunofluorescence images, achieving expert-level performance.

3D Mapping of Intact Ovaries Reveals the Aging Dynamics of the Ovarian Reserve

This study maps over 85,000 oocytes in mouse ovaries across their reproductive lifespan, revealing spatial patterns and a bimodal size distribution, along with a mathematical model of oocyte activation and loss.

Beyond Agreement: Standardizing Crowdsourced Synapse Annotations through Proofreading in EM Connectomics

The paper introduces a standardized proofreading protocol for improving synapse annotations in EM connectomics by combining machine learning with multi-rater calibration and probabilistic modeling.

Mapping the nervous system of the Idiosepius hallami pygmy squid: insights from whole-animal X-ray nanotomography imaging.

The paper presents a high-resolution 3D X-ray nanotomography dataset of the pygmy squid Idiosepius hallami, mapping large-scale neural connectivity.

BiaPy: Accessible deep learning on bioimages

BiaPy provides an open-source library for deep learning in bioimage analysis, offering tools for 2D/3D image data with multi-GPU support and customizable workflows.

Self-supervised Vision Transformers for image-to-image labeling: a BiaPy solution to the LightMyCells Challenge

The paper develops self-supervised Vision Transformers for predicting fluorescence images from label-free transmitted light microscopy inputs, using the LightMyCells challenge as a benchmark.

CartoCell, a high-content pipeline for 3D image analysis, unveils cell morphology patterns in epithelia.

CartoCell is a deep learning pipeline that analyzes 3D epithelial images to quantify cell morphology and packing patterns, revealing insights into tissue self-organization.

A quantitative biophysical principle to explain the 3D cellular connectivity in curved epithelia

The paper investigates how energy drivers affect 3D cellular connectivity in tubular epithelia and identifies a biophysical principle linking tissue geometry and energetics to average cellular connectivity.