Quail Egg Image Analysis

We are working with the Childrens Cancer Therapy Development Center to help automate testing with quail eggs. This project aims to automate the process of checking eggs for current and future viability during treatment.

=Problem Definition=

Background
Preclinical research goes from in vitro studies that are inexpensive and not necessarily indicative of the disease to mouse studies that are better models but prohibitively expensive at scale. Chorioallantoic membrane (CAM) assays utilizing Japanese quail (Coturnix Japonica) are a cost-effective screening method to precede murine xenografts. To increase the throughput of CAM assays, an optimized platform has been built for processing 100-200 quail a week to validate one or more in vitro hit per week. Concordance and divergence from in vitro data and concordance with murine in vivo studies is demonstrated, suggesting a role for ex ovo studies in the validation of new anticancer agents.

Automatic detection of shell-free quail embryos that will not be viable is needed before tumor cell engraftment and drug testing are done. The Egg Buddy MK2 digital heart monitor provides proof of concept that EKG is possible.

Deliverables
Our goal is to create a device that can determine viability in a dark room environment. The device will consist of a camera and additional sensors feeding input to a driving program. This program will constantly assess specified metrics and output live results of the eggs viability. These results will be displayed via a multi-platform GUI application.

Specifications
The device should determine the following metrics by a combination of touch-free or minimally-invasive, aseptic electrodes. Imaging can be taken from above or below using visible or near-infrared light. Nothing should touch the internal components of the plate if possible. Components should have minimal luminescence or light-scattering.
 * Heart rate
 * Oximetry (oxygen saturation)
 * CAM blood vessel area
 * Branch point count

The device should keep its environment within the following parameters to support normal incubation of Coturnix Japonica:

=Design Considerations= All processes must be conducted as non-invasively as possible to avoid affecting the eggs development. The measurements should be taken with as little human involvement as possible. In an ideal scenario, this design will be fully automated, only requiring intervention based on its output.

Andiogenesis Quantification
Measuring the growth and formation of new blood vessels in Chorioallantoic Membrane (CAM). The following parameters will need to be measured: These metrics are taken at specific sites and used to help determine viability. VESGEN will automatically compile these parameters as described in the Software section.
 * Dv Vessel Diameter
 * Nv Vessel Number Density
 * Bry Vessel Branch Point Density
 * Lv Vessel Length Density
 * Av Vessel Area Density

Heart Rate Monitoring
Heart rate is a useful metric for determining viability. The method needs to be non invasive, but still fairly accurate. The following methods are under consideration.
 * Ballistocardiography: Measuring heartbeats by detecting movement. Uses a sensitive piezoelectric effect and a Ballistocardiogram (BCG).
 * Ultrasound: Using sub-20kHz waves a positive doppler shift can be detected. Measuring this shift can give a useful metric for heartrate.
 * Photoplethysmography: Using a standard SpO2 sensor underneath the eggs to measure O2 saturation and heart rate. This method will need to filter out regular embryo movement.

pH Monitoring
When eggs consume O2 and produce CO2 they consequently lower albumen pH. Finding a minimally invasive way to measure an eggs pH change can help determine viability. Current plan is to use an electronic pH and ORP (oxidation-reduction potential) probe.

Hardware
The enclosure should contain a camera for imaging and additional sensors for tracking metrics such as heart rate, as well as environmental variables such as humidity and temperature. A system on a chip (SOC) should be mounted externally and connected to all sensors. A driver program connecting to this SOC should be able to run on various user devices. This connection can be made either by physical connection or a wireless protocol, such as Bluetooth.

Software
Vessel area and branch point count will be handled by NASA licensed software: Vessel Genration Analysis, (VESGEN). Receiving input for heart rate and oxygen saturation may require additional software, running on the SOC or driver program on a separate system. A driver program will run on the separate system, handling the processing and UI. This program should be multi-platform, running on Windows, OSX, and potentially Linux. Inputs should all be received by the SOC and then sent to the driver for processing and display.

This software should display all pertinent gathered or processed information. It should provide the status of each egg's viability in an intuitive and user-friendly form. It may also provide projections for future viability.

=Project Learning=

=Final Design=

=Validation=

=Team Members=

=Additional Documentation=

Project Schedule

Meeting Minutes

Presentations


 * Meet The Team
 * Snapshot I