Machine learning radically reduces workload of cell counting for disease diagnosis – Tech Xplore


Forget Password?
Learn more
share this!
38
19
Share
Email
May 20, 2022
by Beijing Institute of Technology Press Co., Ltd
The use of machine learning to perform blood cell counts for diagnosis of disease instead of expensive and often less accurate cell analyzer machines has nevertheless been very labor-intensive as it takes an enormous amount of manual annotation work by humans in the training of the machine learning model. However, researchers at Benihang University have developed a new training method that automates much of this activity.

googletag.cmd.push(function() { googletag.display(‘div-gpt-ad-1453799284784-2’); });

Their new training scheme is described in a paper published in the journal Cyborg and Bionic Systems on April 9.
The number and type of cells in the blood often play a crucial role in disease diagnosis, but the cell analysis techniques commonly used to perform such counting of blood cells—involving the detection and measurement of physical and chemical characteristics of cells suspended in fluid—are expensive and require complex preparations. Worse still, the accuracy of cell analyzer machines is only about 90 percent due to various influences such as temperature, pH, voltage, and magnetic field that can confuse the equipment.
In order to improve accuracy, reduce complexity and lower costs, much research into alternatives has lately focused on the use of computer programs to perform “segmentation” on photographs of the blood taken by a high-definition camera connected to a microscope. Segmentation involves algorithms that perform pixel-by-pixel labeling of what appears in a photo, in this case, what parts of the image are cells and which are not—in essence, counting the number of cells in an image.
For images in which only a single type of cell appears, such methods achieve a decent level of accuracy, but they perform poorly when confronting images with multiple types of cells. So in recent years, in attempts to solve the problem, researchers have turned to convolutional neural networks (CNNs)—a type of machine learning that mirrors the connection structure of the human visual cortex.
For the CNN to perform this task, it must first be “trained” to understand what is and is not a cell on many thousands of images of cells that humans have manually labeled. Then, when fed a novel, unlabeled image, it recognizes and can count the cells in it.
“But such manual labeling is laborious and expensive, even when done with the assistance of experts,” said Guangdong Zhan, a co-author of the paper and professor with the Department of Mechanical Engineering and Automation at Beihang University, “which defeats the purpose of an alternative that is supposed to be simpler and cheaper than cell analyzers.”
So the researchers at Beihang University developed a new scheme for training the CNN, in this case, U-Net, a fully convolutional network segmentation model that has been widely used in medical image segmentation since it was first developed in 2015.
In the new training scheme, the CNN is first trained on a set of many thousands of images with only one type of cell (taken from the blood of mice).
These single-cell-type images are “preprocessed” automatically by conventional algorithms that reduce noise in the images, enhance their quality, and detect the contours of objects in the image. They then perform adaptive image segmentation. This latter algorithm calculates the various levels of gray in a black and white image, and if a part of the image lies beyond a certain threshold of gray, the algorithm segments that out as a distinct object. What makes the process adaptive is that rather than segmenting out parts of the image segments according to a fixed gray threshold, it does this according to the local features of the image.
After the single-cell-type training set is presented to the U-Net model, the model is fine-tuned using a small set of manually annotated images of multiple cell types. In comparison, a certain amount of manual annotation remains, and the number of images needed to be labeled by humans drops from what was previously many thousands to just 600.
To test their training scheme, the researchers first used a traditional cell analyzer on the same mouse blood samples to do an independent cell count against which they could compare their new approach. They found that the accuracy of their training scheme on segmentation of multiple-cell-type images was 94.85 percent, which is the same level achieved by training with manually annotated multiple-cell-type images.
The technique can also be applied to more advanced models to consider more complex segmentation problems.
As the new training technique still involves some level of manual annotation, the researchers hope to go on to develop a fully automatic algorithm for annotating and training models.


Explore further

A weakly supervised machine learning model to extract features from microscopy images


More information: Guangdong Zhan et al, Auto-CSC: A Transfer Learning Based Automatic Cell Segmentation and Count Framework, Cyborg and Bionic Systems (2022). DOI: 10.34133/2022/9842349
Provided by Beijing Institute of Technology Press Co., Ltd

Citation: Machine learning radically reduces workload of cell counting for disease diagnosis (2022, May 20) retrieved 20 May 2022 from https://techxplore.com/news/2022-05-machine-radically-workload-cell-disease.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further
Facebook
Twitter
Email
Feedback to editors
12 hours ago
0
May 19, 2022
1
May 19, 2022
0
May 17, 2022
0
May 17, 2022
0
6 hours ago
10 hours ago
10 hours ago
10 hours ago
12 hours ago
18 hours ago
18 hours ago
May 16, 2022
Nov 16, 2021
Dec 22, 2020
Feb 24, 2021
Mar 25, 2022
Apr 21, 2020
6 hours ago
10 hours ago
18 hours ago
May 19, 2022
May 19, 2022
May 19, 2022
Use this form if you have come across a typo, inaccuracy or would like to send an edit request for the content on this page. For general inquiries, please use our contact form. For general feedback, use the public comments section below (please adhere to guidelines).
Please select the most appropriate category to facilitate processing of your request
Thank you for taking time to provide your feedback to the editors.
Your feedback is important to us. However, we do not guarantee individual replies due to the high volume of messages.
Your email address is used only to let the recipient know who sent the email. Neither your address nor the recipient’s address will be used for any other purpose. The information you enter will appear in your e-mail message and is not retained by Tech Xplore in any form.

Daily science news on research developments and the latest scientific innovations
Medical research advances and health news
The most comprehensive sci-tech news coverage on the web
This site uses cookies to assist with navigation, analyse your use of our services, collect data for ads personalisation and provide content from third parties. By using our site, you acknowledge that you have read and understand our Privacy Policy and Terms of Use.

source

Share:

More Posts

Market Research

Pulse Surveys

Turn feedback into action

Our survey platform makes it easy to measure and understand feedback so you can drive growth and innovation

Pulse Handshak

Pulse Handshak

Collaborative online survey tool for the market research industry. Remote assisted surveying just like face-to-face interviews. Here interviewers can talk to the respondent over the web-console without the need for any other communication channel and share the same Q're with responses and click actions.

Pulse FE

Pulse FE

Pulse Field Expert or Pulse FE is the main platform for both offline and online survey at softofficepro.com. It is robust and used by hundreds of clients over tens of years with millions of responses. Do it once Q're and deploy on both offline devices (android) and online forms makes it a great cost effective platform for any kind of responses

Pulse Ultimate

Pulse Ultimate

Pulse Ultimate is targeted for tracking studies and retail audits. An offline survey system offering extreme field control including processes like data quality check, back-check, rework, comparison with previous wave data etc. helps to get the best results on a day-to-day basis

Pulse LS

Pulse LS

Use a managed Limesurvey and our expertise for creating complex forms and token based user management. Use optional mailing system to send survey invitation to each participant and track progress of the response status. Industry standard SPSS / R output supported