Connect with us

Published

on

By Dr. Chinta Sidharthan Jun 12 2024 Reviewed by Lily Ramsey, LLM

In a recent study published in Scientific Reports, a team of researchers proposed using an artificial intelligence (AI) tool that uses deep learning to examine red blood cell images in blood smears for the timely detection of malaria.

Study:  Efficient deep learning-based approach for malaria detection using red blood cell smears . Image Credit: cones/Shutterstock.com Background

The World Health Organization report from 2015 shows that in subtropical and tropical regions of the world, the parasite of the genus Plasmodium that causes malaria was responsible for over 400,000 deaths.

Malaria is usually detected through microscopic analysis of blood smear slides, which reveal infected erythrocytes or red blood cells.

Given that regions in Africa, South East Asia, and the Mediterranean experience over 70% of malaria cases, the process of detecting malaria through blood smears becomes very laborious and significantly increases the pathologist’s workload.

AI-based tools involving machine learning and deep-learning approaches have been widely explored in recent studies for automated screening and applications in clinical diagnoses.

However, traditional AI approaches such as neural networks have faced challenges in detecting and identifying malarial parasites in blood smears due to the small size and substantial disparity in blood cells.

Furthermore, these methods still require qualified pathologists for feature vector extraction, making it difficult to automate the screening and detection process completely. About the study

In the present study, the researchers proposed a deep-learning-based AI tool to detect malaria from images of red blood cells accurately. They also compared the proposed EfficientNet-B2 model against other deep-learning models and used ten-fold cross-validation for efficacy validation. Related StoriesUsing AI to revolutionize mosquito surveillance to help combat malaria in AfricaAfrican regions at risk for malaria transmission may decline more than previously expectedMinisters of Health commit to accelerated action against malaria in Africa

A dataset consisting of 27,558 blood cell images, of which half were those from uninfected individuals and the other half had parasitized cells, was used in the study. Expert pathologists manually annotated the images.

The preprocessing step involved resizing the images to standardize the size of the images since the model necessitates that the size of the input be fixed or equal.

The images were then split into training and test datasets. The researchers used 80% of the images as the training dataset, while the remaining were used to test the performance and efficacy of the model.

The deep-learning model EfficientNet-B2 used in this study was a Convolutional Neural Networks (CNN) model, which has been widely employed for problems involving image classification.

The model provides accurate classification results by efficiently scaling the images using depth-wise separable convolutions. An added benefit is the small size of the model, requiring lower computing resources.

The researchers used batch normalization to increase the accuracy of the model. This process calculates the mean and standard deviation of each feature using a smaller dataset, which is then used to standardize the input.

A set of classifications for blood cell images obtained from experts was employed to train the deep-learning model to recognize symptoms of malaria.

The study also compared the performance of numerous pre-trained models such as CNN, Visual Geometry Group (VGG16), Inception, DenseNet121, MobileNet, and ResNet, compared to the deep-learning model proposed in this study.

Some of the measures along which the performance of these models was evaluated included false positive, false negative, true positive, and true negative rates, as well as precision, accuracy, and recall. Results

The study showed that the model proposed in the present study had higher accuracy, area under the curve (AUC), precision, and F1 value, which is the average of precision and recall, compared to the other pre-trained models. Additionally, the testing loss for the proposed model was lower than that of the other models.

After 80% of the dataset was used to train the model, testing the model on the remaining 20% provided an accuracy score of 0.9757, which was higher than the accuracy score obtained when 90% of the dataset was used for the training.

Furthermore, the ten-fold cross-validation indicated that the detection of malaria by the proposed model was highly accurate, with high recall and AUC scores and exceptionally low testing loss.

The model exhibited 98.59% accuracy in detecting cells containing parasites, while the detection of uninfected cells was found to be 100% accurate from the results of the confusion matrix. Conclusions

Overall, the study showed that the proposed model EfficientNet-B2 exhibited high accuracy and precision in detecting symptoms of malaria from images of blood cells obtained from blood smears. The model outperformed the other existing deep-learning-based models in all the performance parameters.

The researchers believe this model could be employed to improve the accuracy of malaria detection from blood smear samples and significantly reduce the workload of pathologists. Journal reference:

Mujahid, M., Rustam, F., Shafique, R., Montero, E. C., Alvarado, E. S., Isabel, & Ashraf, I. (2024). Efficient deep learning-based approach for malaria detection using red blood cell smears. Scientific Reports, 14(1), 13249. doi:https://doi.org/10.1038/s41598024638310. https://www.nature.com/articles/s41598-024-63831-0

Continue Reading

US

Plane plunges 300ft in 36 seconds to avoid another aircraft

Published

on

By

Plane plunges 300ft in 36 seconds to avoid another aircraft

A US passenger plane made a dramatic plunge minutes after take-off to dodge another aircraft – injuring two cabin crew and causing passengers to shoot out of their seats.

The Southwest flight had just taken off from Burbank in California when the pilot received an alert about a nearby plane.

Data from FlightAware shows the aircraft dropped by 91m (300ft) in just 36 seconds. Those on board said they felt panicked, and some feared the plane was about to crash.

Comedian Jimmy Dore posted on X: “Pilot had to dive aggressively to avoid mid-air collision … myself and plenty of people flew out of their seats and bumped heads on ceiling, a flight attendant needed medical attention.”

Stef Zambrano saw a woman who wasn’t wearing her seatbelt thrown out of her seat, who then said: “I want to get off this plane. I want to be on the ground.”

Another passenger, Steve Ulasewicz, told NBC Los Angeles that it felt like the plane was in freefall for 10 seconds.

“People were screaming. You know, it was pandemonium. People thought the plane was going down,” he added.

More from US

The aircraft was able to continue to its destination of Las Vegas, where it safely landed without any further incident.

It is believed the Boeing 737 was in the same vicinity as a Hawker Hunter Mk. 58, a British fighter jet.

Southwest is now working with the Federal Aviation Administration “to further understand the circumstances” of the event.

Read more US news:
Trump issues warning as he arrives in Scotland
US justice department interviews Ghislaine Maxwell

Please use Chrome browser for a more accessible video player

January: Footage of Washington plane crash

This is the second time in a week that a passenger plane has had to make abrupt flight manoeuvres to avoid a potential mid-air collision.

Concerns have been raised about aviation safety in the US following a series of recent incidents.

In January, a mid-air collision in Washington DC killed 67 people.

Continue Reading

US

Snipers, Secret Service sweeps and a personal chef on standby: Scotland awaits Trump’s arrival

Published

on

By

Snipers, Secret Service sweeps and a personal chef on standby: Scotland awaits Trump's arrival

Donald Trump likes a wall. And now he has his very own 10ft-high metal barrier creating a fortress as he tees off for a weekend of politics, play and precision in Scotland.

An almost surreal contrast now exists in the tiny Ayrshire village of Turnberry.

On one side, the stunning coastline and luxury hotel that bears the president’s name. And on the other, an armed buffer zone with sniper teams and road checkpoints.

This visit is unlike those that have gone before.

The threat level and associated security on display is unprecedented following the attempted assassination of Trump at a campaign rally in the US.

“It would be inappropriate for me to plan an operation and not bear in mind what has happened,” the senior officer in charge of this weekend’s policing efforts told me.

Green military-type truck
Image:
Military trucks are part of a security effort that comes just a year after an attempted assassination

Fence
Black security van
Image:
A ‘counter terror’ firm was spotted near the area, which is ringed by a 10ft fence

Turnberry, and its population of about 200 people, have this week witnessed a never-ending stream of Army trucks, terrorist sweeps, road checkpoints, airspace restrictions, sniper positions being erected and Secret Service agents roaming around.

More on Donald Trump

It is the most extensive security deployment in Scotland since the death of the late Queen in 2022.

It is estimated around 5,000 officers will be on the streets, with teams coming from across the UK to assist.

The spectacle primarily centres on Donald Trump coming to play golf before the arrival of Prime Minister Sir Keir Starmer for talks, likely on Monday.

The president, whose mother was born on the Scottish island of Lewis, is then scheduled to travel to his Aberdeenshire resort where a new golf course is set to open.

Police on buggies patrol as golfers play, near the Trump Turnberry golf course
Image:
Police on buggies are patrolling near the course on Scotland’s east coast

Police lorry
Police security tape is placed across a clothes recycling bin near the Trump Turnberry golf course.
Image:
Police have even taped off a clothes recycling bin near the course

‘Trump is a decent boss’

Stephanie Campbell and Leanne Maxwell live in Turnberry and used to work at the Trump-owned resort, like many other locals.

The pair told Sky News the very first lesson staff at the resort are given is not in fine service or guest etiquette, but in how to respond to a bomb threat.

It is claimed there are posters above the landline phones in the hotel with instructions on the worst-case scenario.

Stephanie Campbell and Leanne Maxwell work at the Trump course
Image:
Stephanie Campbell and Leanne Maxwell say staff are trained in dealing with bomb threats

Stephanie told Sky News: “I had no issues working for him, he is a really decent boss.

“The last time he came there was an element of excitement, I think this time there comes with an added element of concern.

“It brings a lot higher threats and security and it’s much more difficult for everybody in the area.”

Donald Trump waves to protesters while playing golf at Turnberry golf club, in  2018
Image:
Mr Trump at Turnberry in 2018 – he will also visit his Aberdeen course on this trip. Pic: AP

A flag flutters on the Ailsa Championship Course at the Trump Turnberry Golf Resort in Turnberry.
Image:
File pic: Reuters

Echoing her concerns, Leanne told Sky News: “Security is obviously being bumped up. It’s quite worrying. He’s quite a man, ain’t he?”

Sweeps of the rooms are carried out by US Secret Service agents after housekeeping staff complete their duties and Trump’s meals, they say, are prepared by a personal chef to avoid the risk of poisoning.

To the outside world, these measures seem standard for a US president. But to those who live in Turnberry, it’s far from normal when they have a date with the commander-in-chief.

Marine One helicopter
Image:
Marine One is in place awaiting the president’s arrival

A view of the hotel at the Trump Turnberry Golf Resort. File pic: Reuters
Image:
File pic: Reuters

Awkward encounters

Prestwick Airport has become something of an American airbase in recent days.

The infamous armoured limousine, known as “The Beast”, has been spotted being wheeled out of a US military plane as the presidential motorcade prepares for his arrival tonight.

Greeting the president at the doors of Air Force One will be the secretary of state for Scotland, Ian Murray, who previously supported a motion alleging Trump was guilty of “misogynism, racism and xenophobia”.

Another awkward encounter could come in the form of Scottish First Minister John Swinney’s showdown with Mr Trump next week.

Read more from Sky News:
Trump told in May his name in Epstein files – report
Trump says US will ‘win’ AI race as plan unveiled

The SNP leader, who publicly backed Kamala Harris in the presidential race, called for September’s state visit to be scrapped after the Ukrainian president’s visit to the White House descended into a shouting match live on TV earlier this year.

Demonstrations are planned throughout the weekend, with marches and protests announced in Glasgow, Edinburgh and Aberdeen.

Kirsty Haigh, from Scotland Against Trump, claims the president uses Scotland to “cleanse his image” and he should not be able to use the country as an “escape” from his views.

She told Sky News: “He should not be welcomed by us, by our leaders.

“We want to see a Scotland that is very different than [the] America that’s being created.”

Continue Reading

US

Ghislaine Maxwell answered justice department questions ‘about 100 different people’, her lawyer says

Published

on

By

Ghislaine Maxwell answered justice department questions 'about 100 different people', her lawyer says

Ghislaine Maxwell answered “every single question” from the US justice department, her lawyer has said.

The imprisoned former girlfriend of convicted sex offender Jeffrey Epstein answered questions “about 100 different people” during one-and-a-half days of questioning in the federal courthouse in Tallahassee, Florida, her attorney David Oscar Markus said.

A senior administration official has confirmed to Sky News’ US partner, NBC News, that Maxwell was granted limited immunity, meaning the information could not be used against her in any future cases or proceedings.

Mr Markus said Maxwell “answered those questions honestly, truthfully, to the best of her ability” when she met with deputy attorney general Todd Blanche.

“She never invoked a privilege. She never refused to answer a question, so we’re very proud of her,” Mr Markus added.

Undated picture of Ghislaine Maxwell with Jeffrey Epstein. File pic: US Department of Justice
Image:
Undated picture of Ghislaine Maxwell with Jeffrey Epstein. File pic: US Department of Justice

Maxwell, who was jailed in 2022 for luring young girls to massage rooms for Epstein to abuse, is currently serving a 20-year prison sentence.

Epstein, 66, was found dead in his cell at a Manhattan federal jail in August 2019 as he awaited trial on sex trafficking charges. His death was ruled a suicide.

His case has generated endless attention and conspiracy theories due to his and Maxwell’s links to famous people like royals, presidents and billionaires, including Donald Trump.

Mr Trump is facing ongoing questions about the Epstein case. He denied prior knowledge of Epstein’s crimes and claimed he cut off their relationship long ago.

Trump and Epstein at a party together in 1992
Image:
Trump and Epstein at a party together in 1992

The deputy US attorney general, Mr Blanche, announced earlier this week that Maxwell would be interviewed because of Mr Trump’s directive to gather and release any credible evidence about others who may have committed crimes.

Maxwell’s lawyer, Mr Markus, praised Mr Blanche’s approach.

“The deputy attorney general is seeking the truth. He asked every possible question, and he was doing an amazing job,” he said.

Please use Chrome browser for a more accessible video player

‘The truth will set you free’: Why is Maxwell meeting with the US government?

Maxwell’s immunity from future proceedings is “limited” because it only covers her if she tells the truth. Typically, prosecutors will consider the defendant’s cooperation in an investigation when recommending a lighter sentence as part of a plea deal.

But since Maxwell has already been convicted, it is not clear how she might benefit from the immunity.

Mr Markus said Maxwell did not receive anything in return for answering the questions, but he acknowledged that Mr Trump could pardon her. “We hope he exercises that power in the right and just way,” Mr Markus said.

Ghislaine Maxwell. Pic: US Department of Justice
Image:
Ghislaine Maxwell. Pic: US Department of Justice

When asked whether he had thought about a pardon or clemency for Maxwell, Mr Trump claimed he had not considered it.

“I’m allowed to do it, but it’s something I have not thought about,” he told reporters outside the White House.

He later shut down another question, saying: “I don’t want to talk about that.”

Read more from Sky News:
Analysis: Trump hopes to escape Epstein controversy
Scots divided as Trump heads to Turnberry

Meanwhile, Maxwell’s family have suggested the disgraced British socialite could use “government misconduct” to challenge her imprisonment.

Her family have frequently claimed she “did not receive a fair trial”, but legal appeals against her sex trafficking convictions have been rejected by the courts.

Undated handout file photo issued by US Department of Justice of Ghislaine Maxwell with Jeffrey Epstein, which was shown to the court during the sex trafficking trial of Maxwell in the Southern District of New York. British socialite Ghislaine Maxwell has been sentenced to 20 years years in prison for luring young girls to massage rooms to be molested by Jeffrey Epstein. Issue date: Tuesday June 28, 2022.
Image:
Ghislaine Maxwell with Jeffrey Epstein. Pic: US Department of Justice

Judges previously dismissed arguments from Maxwell’s lawyers that she “should never have been prosecuted” because of a “weird” agreement drafted more than 15 years ago.

The family argue that Maxwell should have been protected under an agreement Epstein had entered with the US Department of Justice in 2007, which agreed not to prosecute any of his co-conspirators.

During her trial in 2021, Maxwell was described as “dangerous” by prosecutors, who told jurors about how she would entice vulnerable girls to go to Epstein’s properties for him to sexually abuse.

In a statement, her family said: “Our sister Ghislaine did not receive a fair trial. Her legal team continues to fight her case in the courts and will file its reply in short order to the government’s opposition in the US Supreme Court.”

Continue Reading

Trending