Blog search results for Tag: imaging

Science & Innovation

Every day, there are subtle signs that machine learning is making our lives easier. It could be as simple as a Netflix series recommendation or your phone camera automatically adjusting to the light – or it could be something even more profound. In the case of two recent machine-learning developments, these advances could make a tangible difference to both microscopy, cancer treatment, and our health.

The first is an artificial intelligence (AI) tool that improves the information gleaned from microscopic images. Researchers at the University of Gothenburg have used this deep machine learning to enhance the accuracy and speed of analysis.

The tool uses deep learning to extract as much information as possible from data-packed images. The neural networks retrieve exactly what a scientist wants by looking through a huge trove of images (known as training data). These networks can process tens of thousands of images an hour whereas some manual methods deliver about a hundred a month.

SCIblog 23 March 2021 Machine Learning - image of herpes virus germs microorganism cells under microscope

Machine learning can be used to follow infections in a cell.

In practice, this algorithm makes it easier for researchers to count and classify cells and focus on specific material characteristics. For example, it can be used by companies to reduce emissions by showing workers in real time whether unwanted particles have been filtered out.

“This makes it possible to quickly extract more details from microscope images without needing to create a complicated analysis with traditional methods,” says Benjamin Midtvedt, a doctoral student in physics and the main author of the study. “In addition, the results are reproducible, and customised. Specific information can be retrieved for a specific purpose."

The University of Gothenburg tool could also be used in health care applications. The researchers believe it could be used to follow infections in a cell and map cellular defense mechanisms to aid the development of new medicines and treatments.

Machine learning by colour

On a similar thread, machine learning has been used to detect cancer by researchers from the National University of Singapore. The researchers have used a special dye to colour cells by pH and a machine learning algorithm to detect the changes in colour caused by cancer.

The researchers explain in their APL Bioengineering study that the pH (acidity level) of a cancerous cell is not the same as that of a healthy cell. So, you can tell if a cell is cancerous if you know its pH.

With this in mind, the researchers have treated cells with a pH-sensitive dye called bromothymol blue that changes colour depending on how acidic the solution is. Once dyed, each cell exudes its unique red, green, and blue fingerprint.

SCIblog 23 March 2021 Machine Learning - image of ph meter measuring acid alkaline balance

By isolating a cell’s pH, researchers can detect the presence of cancer.

The authors have also trained a machine learning algorithm to map combinations of colours to assess the state of cells and detect any worrying shifts. Once a sample of the cells is taken, medical professionals can use this non-invasive method to get a clearer picture of what is going on inside the body. And all they need to do all of this is an inverted microscope and a colour camera.

“Our method allowed us to classify single cells of various human tissues, both normal and cancerous, by focusing solely on the inherent acidity levels that each cell type tends to exhibit, and using simple and inexpensive equipment,” said Chwee Teck Lim, one of the study’s authors.

“One potential application of this technique would be in liquid biopsy, where tumour cells that escaped from the primary tumour can be isolated in a minimally invasive fashion from bodily fluids.”

The encouraging sign for all of us is that these two technologies are but two dots on a broad canvas, and machine learning will enhance analysis. There are certainly troubling elements to machine learning but anything that helps hinder disease is to be welcomed.

Machine Learning-Based Approach to pH Imaging and Classification of Single Cancer Cells:
https://aip.scitation.org/doi/10.1063/5.0031615

Quantitative Digital Microscopy with Deep Learning:
https://aip.scitation.org/doi/10.1063/5.0034891

Health & Wellbeing

Each year, the World Health Organisation celebrates World Heath Day, an international health awareness day which aims to draw attention particular health challenges across the world. The theme for 2019 is universal health coverage for everyone, everywhere.

world health day globe

In honour of World Health Day, held on 7 April 2019 annually, we have collated the five most innovative healthcare projects we have featured on SCI’s website over the past year. 


New cardiac MRI scan improves diagnostic accuracy

beating heart gif

Originally posted by medschoolgeek

Using 2D imaging techniques to diagnose problems with the heart can be challenging due to the constant movement of the cardiac system. Currently, when a patient undergoes a cardiac MRI scan they have to hold their breath while the scan takes snapshots in time with their heartbeat.

Still images are difficult to obtain with this traditional technique as a beating heart and blood flow can blur the picture. This method becomes trickier if the individual has existing breathing problems or an irregular heartbeat.


3D cell aggregates could improve accuracy of drug screening

 3d cell

An innovative new screening method using cell aggregates shaped like spheres may lead to the discovery of smarter cancer drugs, a team from the Scripps Research Institute, California, US, has reported.

The 3D aggregates, called spheroids, can be used to obtain data from potentially thousands of compounds using high throughput screening (HTS). HTS can quickly identify active compounds and genes in a specific biomolecular pathway using robotics and data processing.


Antibiotic combinations could slow resistance

 antibiotics

Several thousand antibiotic combinations have been found to be more effective in treating bacterial infections than first thought.

Antibiotic combination therapies are usually avoided when treating bacterial infections, with scientists believing combinations are likely to reduce the efficacy of the drugs used. Now, a group at UCLA, USA, have identified over 8,000 antibiotic combinations that work more effectively than predicted.


Mechanism that delays and repairs cancerous DNA damage discovered

 microscope

Researchers at the University of Copenhagen, Denmark, have identified a mechanism that prevents natural DNA errors in our cells. These errors can lead to permanent damage to our genetic code and potentially diseases such as cancer.

Mutations occurring in human DNA can lead to fatal diseases like cancer. It is well documented that DNA-damaging processes, such as smoking tobacco or being exposed to high levels of ultraviolet (UV) light through sunburn, can lead to increased risk of developing certain forms of cancer.


Alzheimer’s drugs made from Welsh daffodils

flowers gif

Originally posted by naturegifs

Treatments for Alzheimer’s disease can be expensive to produce, but by using novel cultivation of daffodils one small Welsh company has managed to find a cost-effective production method of one pharmaceutical drug, galanthamine.

Alzheimer’s disease is a neurodegenerative disease with a range of symptoms, including language problems, memory loss, disorientation and mood swings. Despite this, the cause of Alzheimer’s is very understood. The Alzheimer’s disease drug market is currently worth an estimated US$8bn.


Health & Wellbeing

Using 2D imaging techniques to diagnose problems with the heart can be challenging due to the constant movement of the cardiac system. Currently, when a patient undergoes a cardiac MRI scan they have to hold their breath while the scan takes snapshots in time with their heartbeat.

Still images are difficult to obtain with this traditional technique as a beating heart and blood flow can blur the picture. This method becomes trickier if the individual has existing breathing problems or an irregular heartbeat.

These problems can lead to trouble in acquiring accurate diagnostics.  

 beating heart still image

Now, a team based at the Cedars-Sinai Medical Center in California, US, have detailed a new technique – MR Multitasking – that can resolve these issues by improving patient comfort and shortening testing time.

‘It is challenging to obtain good cardiac magnetic resonance images because the heart is beating incessantly, and the patient is breathing, so the motion makes the test vulnerable to errors,’ said Shlomo Melmed, Dean of the Cedars-Sinai Center faculty.

 An MRI Scanner

An MRI Scanner. Image: Wikimedia Commons

‘By novel approaches to this longstanding problem, this research team has found a unique solution to improve cardiac care for patients around the world for years to come.’

By developing what the team consider a six-dimensional imaging technique, the Center has embraced the motion of a heartbeat by capturing image data continuously – creating a product similar to a video.

heartbeat detection gif

Originally posted by suckerfordeep

‘MR Multitasking continuously acquires image data and then, when the test is completed, the program separates out the overlapping sources of motion and other changes into multiple time dimensions,’ said Anthony Christodoulou, first author and PhD researcher at the Center’s Biomedical Imaging Research Institute.

‘If a picture is 2D, then a video is 3D because it adds the passage of time,’ said Christodoulou. ‘Our videos are 6D because we can play them back four different ways: We can playback cardiac motion, respiratory motion, and two different tissue processes that reveal cardiac health.’

Your guide to a cardiac MRI. Video: British Heart Foundation

Testing ten healthy volunteers and ten cardiac patients, the team said the group found that the method was more comfortable for patients and took just 90 seconds – significantly quicker than the conventional MRI scan used in hospitals. For each of the participants, the scan produced accurate results.

The team are now looking to extend its work into MR Multitasking by focusing on other disease areas, such as cancer.