Image Processing
image processing
Dr. Pradeep Reddy Raamana
Few projects we will be pursuing include but not limited to: 1) Development of multimodal imaging biomarkers, targeting high-impact applications from early detection of Alzheimer’s disease and differential diagnosis to predicting response to treatment in Major Depression, 2) Development of standards for biomarker performance evaluation, 3) Quality control protocols for neuroimaging data (niQC), 4) Development of various other techniques and tools to achieve the above objectives, including multi-site data harmonization, conquering confounds in predictive analysis, advancing machine learning techniques for multimodal analysis (such as kernel methods, graph kernels and multiple kernel learning) and many others.
Ioan Marius BILASCO
The FOX team from the CRIStAL laboratory (UMR CNRS), Lille France and the PR team from the MIS Laboratory, Amiens France are looking to recruit a joint PhD student for a project titled 'EventSpike - Asynchronous computer vision from event cameras'. The project aims to develop new models of spiking neural networks (SNN) capable of directly processing visual information in the form of spike trains for applications in autonomous driving. The thesis will focus on weakly supervised learning methods based on spiking learning mechanisms to exploit the flow of impulses generated by an event camera.
Kerstin Bunte
We are looking to fill a two-year postdoctoral researcher position in 'Machine Learning for Image Processing on Embedded Devices' at the Faculty of Science and Engineering at the University of Groningen. The position is part of the newly launched collaborative initiative DigiAgro3 focused on developing novel agricultural robots, featuring a vibrant consortium of industrial and academic partners. The main goal of the project will be to develop machine learning models capable of robustly classifying images of agricultural crops based on markers for health state of the crop and deploying those models on a variety of low-power edge devices. We focus on sustainable and robust methods to enable precision farming practices.
Elena Gheorghiu
A cross-disciplinary team of researchers from the Universities of Stirling, York, Cardiff, Manchester, and Southampton are working together on an EPSRC-funded project, Edgy Organism, to develop a novel end-to-end neuromorphic design approach drawing inspiration from how data is processed and represented in the brain and build an efficient hardware architecture based on spiking neural networks. The project aims to develop novel computing solutions, that can autonomously and reliably detect illegal or harmful activities in crowded public spaces, with minimum intrusion of personal space and privacy. We are recruiting a team of outstanding researchers from Visual Neuroscience, Psychology, Edge Computing, AI/ML, and Neuromorphic Engineering, to work with us on achieving Edgy Organism project’s ambitious objectives. As part of this project, Psychology, Faculty of Natural Sciences, University of Stirling is offering a fixed term (27 months) full-time Postdoctoral Research Fellow position to work with Dr Elena Gheorghiu and the cross-disciplinary team of researchers.
I-Chun Lin, PhD
The Gatsby Computational Neuroscience Unit is a leading research centre focused on theoretical neuroscience and machine learning. We study (un)supervised and reinforcement learning in brains and machines; inference, coding and neural dynamics; Bayesian and kernel methods, and deep learning; with applications to the analysis of perceptual processing and cognition, neural data, signal and image processing, machine vision, network data and nonparametric hypothesis testing. The Unit provides a unique opportunity for a critical mass of theoreticians to interact closely with one another and with researchers at the Sainsbury Wellcome Centre for Neural Circuits and Behaviour (SWC), the Centre for Computational Statistics and Machine Learning (CSML) and related UCL departments such as Computer Science; Statistical Science; Artificial Intelligence; the ELLIS Unit at UCL; Neuroscience; and the nearby Alan Turing and Francis Crick Institutes. Our PhD programme provides a rigorous preparation for a research career. Students complete a 4-year PhD in either machine learning or theoretical/computational neuroscience, with minor emphasis in the complementary field. Courses in the first year provide a comprehensive introduction to both fields and systems neuroscience. Students are encouraged to work and interact closely with SWC/CSML researchers to take advantage of this uniquely multidisciplinary research environment.
Ioan Marius Bilasco
The FOX team of the CRIStAL laboratory (UMR CNRS), Lille, France, and the PR team of the MIS Laboratory, Amiens, France, are looking to recruit a post-doc starting as soon as possible and a joint PhD student starting in October 2025 in the field of asynchronous computer vision from event cameras. The main objective is to develop new models of spiking neural networks (SNN) capable of directly processing visual information in the form of spike trains. The proposed models must be validated experimentally on dynamic vision databases, following standard protocols and best practices. The PhD candidate will be funded for 3 years (grant application pending) and is expected to defend his/her thesis and graduate by the end of the contract. The monthly gross salary is around 2000€, including benefits. The post-doc will be hired for 18 months starting from March 2025 (this is a fully-funded position). The monthly gross salary is around 2500-3000€, including benefits.
I-Chun Lin
The Gatsby Computational Neuroscience Unit is a leading research centre focused on theoretical neuroscience and machine learning. We study (un)supervised and reinforcement learning in brains and machines; inference, coding and neural dynamics; Bayesian and kernel methods, and deep learning; with applications to the analysis of perceptual processing and cognition, neural data, signal and image processing, machine vision, network data and nonparametric hypothesis testing. The Unit provides a unique opportunity for a critical mass of theoreticians to interact closely with one another and with researchers at the Sainsbury Wellcome Centre for Neural Circuits and Behaviour (SWC), the Centre for Computational Statistics and Machine Learning (CSML) and related UCL departments such as Computer Science; Statistical Science; Artificial Intelligence; the ELLIS Unit at UCL; Neuroscience; and the nearby Alan Turing and Francis Crick Institutes. Our PhD programme provides a rigorous preparation for a research career. Students complete a 4-year PhD in either machine learning or theoretical/computational neuroscience, with minor emphasis in the complementary field. Courses in the first year provide a comprehensive introduction to both fields and systems neuroscience. Students are encouraged to work and interact closely with SWC/CSML researchers to take advantage of this uniquely multidisciplinary research environment.
Seeing things clearly: Image understanding through hard-attention and reasoning with structured knowledges
In this talk, Jonathan aims to frame the current challenges of explainability and understanding in ML-driven approaches to image processing, and their potential solution through explicit inference techniques.
Introducing YAPiC: An Open Source tool for biologists to perform complex image segmentation with deep learning
Robust detection of biological structures such as neuronal dendrites in brightfield micrographs, tumor tissue in histological slides, or pathological brain regions in MRI scans is a fundamental task in bio-image analysis. Detection of those structures requests complex decision making which is often impossible with current image analysis software, and therefore typically executed by humans in a tedious and time-consuming manual procedure. Supervised pixel classification based on Deep Convolutional Neural Networks (DNNs) is currently emerging as the most promising technique to solve such complex region detection tasks. Here, a self-learning artificial neural network is trained with a small set of manually annotated images to eventually identify the trained structures from large image data sets in a fully automated way. While supervised pixel classification based on faster machine learning algorithms like Random Forests are nowadays part of the standard toolbox of bio-image analysts (e.g. Ilastik), the currently emerging tools based on deep learning are still rarely used. There is also not much experience in the community how much training data has to be collected, to obtain a reasonable prediction result with deep learning based approaches. Our software YAPiC (Yet Another Pixel Classifier) provides an easy-to-use Python- and command line interface and is purely designed for intuitive pixel classification of multidimensional images with DNNs. With the aim to integrate well in the current open source ecosystem, YAPiC utilizes the Ilastik user interface in combination with a high performance GPU server for model training and prediction. Numerous research groups at our institute have already successfully applied YAPiC for a variety of tasks. From our experience, a surprisingly low amount of sparse label data is needed to train a sufficiently working classifier for typical bioimaging applications. Not least because of this, YAPiC has become the "standard weapon” for our core facility to detect objects in hard-to-segement images. We would like to present some use cases like cell classification in high content screening, tissue detection in histological slides, quantification of neural outgrowth in phase contrast time series, or actin filament detection in transmission electron microscopy.
Suite2p: a multipurpose functional segmentation pipeline for cellular imaging
The combination of two-photon microscopy recordings and powerful calcium-dependent fluorescent sensors enables simultaneous recording of unprecedentedly large populations of neurons. While these sensors have matured over several generations of development, computational methods to process their fluorescence are often inefficient and the results hard to interpret. Here we introduce Suite2p: a fast, accurate, parameter-free and complete pipeline that registers raw movies, detects active and/or inactive cells (using Cellpose), extracts their calcium traces and infers their spike times. Suite2p runs faster than real time on standard workstations and outperforms state-of-the-art methods on newly developed ground-truth benchmarks for motion correction and cell detection.
Computer vision and image processing applications on astrocyte-glioma interactions in 3D cell culture
FENS Forum 2024
Mooney Face Image Processing in Deep Convolutional Neural Networks Compared to Humans
Neuromatch 5