Analyzing white blood cells in blood samples using deep learning techniques

2019-10-03T12:21:27Z

Mattias: Created page with "{{StudentProjectTemplate |Summary=To analyze white blood cell content in blood samples using deep learning techniques. |TimeFrame=Fall 2019 |Prerequisites=Good knowledge of ma..."

{{StudentProjectTemplate
|Summary=To analyze white blood cell content in blood samples using deep learning techniques.
|TimeFrame=Fall 2019
|Prerequisites=Good knowledge of machine learning, convolutional neural networks and programming skills for implementing machine learning algorithms
|Supervisor=Mattias Ohlsson
|Level=Master
|Status=Open
}}
To measure the amount of white blood cells in blood samples a combination of image analysis and machine learning can be used. This is the case for the instrument WBC-Diff manufactured by HemoCue. It uses a neural network classifier based on manually calculated features from images of blood cells. The WBC-Diff instrument can also detect subtypes of white blood cells.

The aim of this project is to investigate if other machine learning approaches, such as convolutional neural networks, can improve their current state-of-the-art when analyzing blood cells in blood samples. Specific questions to study include:

1. Prediction of blood cell or not a blood cell

2. White blood cell type prediction (5 different types)

The training material consists of 2000-5000 images per class with a resolution of 48x48 pixels in approximately 40 images slices.

This master project is a collaboration with the company HemoCue. HemoCue will provide domain knowledge and all the necessary image material.

Name of the new projectEstimating agricultural development indicators over large areas from satellite images – an approach using convolutional neural networks and transfer learning

2019-10-01T07:41:18Z

Mattias: Created page with "{{StudentProjectTemplate |Summary=In this project you will use deep learning models, specifically convolutional neural networks (CNN), to analyze satellite imagery to estimate..."

{{StudentProjectTemplate
|Summary=In this project you will use deep learning models, specifically convolutional neural networks (CNN), to analyze satellite imagery to estimate agricultural development indicators.
|TimeFrame=Fall 2019
|References=Xie, M., N. Jean, M. Burke, D. Lobell & S. Ermon (2015) Transfer learning from deep features for remote sensing and poverty mapping. arXiv preprint arXiv:1510.00098.

Jean, N., M. Burke, et al (2016) Combining satellite imagery and machine learning to predict poverty. Science, 353, 790-794.

|Prerequisites=Good knowledge of machine learning, convolutional neural networks and programming skills for implementing machine learning algorithms
|Supervisor=Mattias Ohlsson, Thorsteinn Rögnvaldsson
|Level=Master
|Status=Open
}}
In this project you will use deep learning models, specifically convolutional neural networks (CNN), to analyze satellite imagery to estimate agricultural development indicators. This project is connected to an overall aim of enhancing our understanding of the pace of agricultural and rural transformation in contemporary sub-Saharan Africa, its poverty and distributional impacts and drivers.

Due to the lack of large labeled data sets, the approach will build upon transfer learning where day-time satellite images will be used to estimate the distribution of light during night (nighttime lights) or vegetation indices (VI). This idea builds upon the connection between nighttime lights and economic activity, and the fact that VIs can be used as proxy for biomass (and thus yield). The features extracted from the trained CNNs can then be used to estimate indicators related to e.g. poverty, structural transformation, and settlements. In this project we will focus on indicators that measure the presence of a settlement, eg. are there buildings or not?

This project build upon a collaboration between Halmstad University and the Department of Human Geography, Lund University (LU). LU will provide all necessary data (satellite imagery and indicators).

ISLAB/CAISR - User contributions [en]

Analyzing white blood cells in blood samples using deep learning techniques

Name of the new projectEstimating agricultural development indicators over large areas from satellite images – an approach using convolutional neural networks and transfer learning