AI revolutionizes malaria diagnosis with 97.57% accuracy using EfficientNet

Published

11 months ago

June 13, 2024

admin

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

UK

Fourteen children arrested on suspicion of manslaughter over Gateshead fire released on bail

Published

3 hours ago

May 5, 2025

admin

Fourteen children arrested on suspicion of manslaughter over Gateshead fire released on bail

All 14 children arrested on suspicion of manslaughter after a boy died in a fire have been released on police bail, officers said.

Layton Carr, 14, was found dead near the site of a fire at Fairfield industrial park in the Bill Quay area of Gateshead on Friday.

Northumbria Police said on Saturday that they had arrested 11 boys and three girls in connection with the incident.

In an update on Sunday, a Northumbria Police spokesman said: “All those arrested have since been released on police bail pending further inquiries.”

Firefighters raced to the industrial site shortly after 8pm on Friday, putting out the blaze a short time later.

Police then issued an appeal for Carr, who was believed to be in the area at that time.

In a statement on Saturday, the force said that “sadly, following searches, a body believed to be that of 14-year-old Layton Carr was located deceased inside the building”.

David Thompson, headteacher of Hebburn Comprehensive School, where Layton was a pupil, said the school community was “heartbroken”.

Mr Thompson described him as a “valued and much-loved member of Year 9” and said he would be “greatly missed by everyone”.

He added that the school’s “sincere condolences” were with Layton’s family and that the community would “rally together to support one another through this tragedy”.

A fundraising page on GoFundMe has been set up to help Layton’s mother pay for funeral costs.

Organiser Stephanie Simpson said: “The last thing Georgia needs to stress trying to pay for a funeral for her Boy Any donations will help thank you.”

One tribute in a Facebook post read: “Can’t believe I’m writing this my nephew RIP Layton 💔 forever 14 you’ll be a massive miss, thinking of my sister and 2 beautiful nieces right now.”

Detective Chief Inspector Louise Jenkins, of Northumbria Police, also said: “This is an extremely tragic incident where a boy has sadly lost his life.”

She added that the force’s “thoughts are with Layton’s family as they begin to attempt to process the loss of their loved one”.

They are working to establish “the full circumstances surrounding the incident” and officers will be in the area to “offer reassurance to the public”, she added.

A cordon remains in place at the site while police carry out enquiries.

UK

Football bodies could be forced to pay towards brain injury care costs of ex-players

Published

3 hours ago

May 5, 2025

admin

Football bodies could be forced to pay towards brain injury care costs of ex-players

Football bodies could be forced to pay towards the care costs of ex-players who have been diagnosed with brain conditions, under proposals set to be considered by MPs.

Campaigners are drafting amendments to the Football Governance Bill, which would treat conditions caused by heading balls as an “industrial injuries issue”.

The proposals seek to require the football industry to provide the necessary financial support.

Campaigners say existing support is not fit for purpose, including the Brain Health Fund which was set up with an initial £1m by the Professional Footballers’ Association (PFA), supported by the Premier League.

But the Premier League said the fund has supported 121 families with at-home adaptations and care home fees.

From England‘s 1966 World Cup-winning team, both Jack and Bobby Charlton died with dementia, as did Martin Peters, Ray Wilson and Nobby Stiles.

Ex-players, including former Liverpool defender Neil Ruddock, went to parliament last week to lobby MPs.

Ruddock told Sky News he had joined campaigners “for the families who’ve gone through hell”.

“A professional footballer, greatest job in the world, but no one knew the dangers, and that’s scary,” he said.

“Every time someone heads a ball it’s got to be dangerous to you. You know, I used to head 100 balls a day in training. I didn’t realise that might affect my future.”

A study co-funded by the PFA and the Football Association (FA) in 2019 found footballers were three and a half times more likely to die of a neurodegenerative disease than members of the public of the same age.

‘In denial’

Among those calling on football authorities to contribute towards the care costs of ex-players who have gone on to develop conditions such as Alzheimer’s and dementia is Labour MP Chris Evans.

Mr Evans, who represents Caerphilly in South Wales, hopes to amend the Bill to establish a care and financial support scheme for ex-footballers and told a recent event in parliament that affected ex-players “deserve to be compensated”.

Greater Manchester Mayor Andy Burnham, who helped to draft the amendment, said the game was “in denial about the whole thing”.

Mr Burnham called for it to be seen as “an industrial injuries issue in the same way with mining”.

In January, David Beckham lent his support to calls for greater support for footballers affected by dementia.

One of the amendments says that “the industry rather than the public should bear the financial burden”.

A spokesperson for the FA said it was taking a “leading role in reviewing and improving the safety of our game” and that it had “already taken many proactive steps to review and address potential risk factors”.

An English Football League spokesperson said it was “working closely with other football bodies” to ensure both professional and grassroots football are “as safe as it can be”.

The PFA and Premier League declined to comment.

UK

Terror arrests came in context of raised warnings about Iran, with ongoing chaos in its own backyard

Published

3 hours ago

May 5, 2025

admin

Terror arrests came in context of raised warnings about Iran, with ongoing chaos in its own backyard

These are two separate and unrelated investigations by counter-terror officers.

But the common thread is nationality – seven out of the eight people arrested are Iranian.

And that comes in the context of increased warnings from government and the security services about Iranian activity on British soil.

Last year, the director general of MI5, Ken McCallum, said his organisation and police had responded to 20 Iran-backed plots presenting potentially lethal threats to British citizens and UK residents since January 2022.

He linked that increase to the ongoing situation in Iran’s own backyard.

“As events unfold in the Middle East, we will give our fullest attention to the risk of an increase in – or a broadening of – Iranian state aggression in the UK,” he said.

The implication is that even as Iran grapples with a rapidly changing situation in its own region, having seen its proxies, Hezbollah in Lebanon and Hamas in Gaza, decimated and itself coming under Israeli attack, it may seek avenues further abroad.

The government reiterated this warning only a few weeks ago, with security minister Dan Jarvis addressing parliament.

“The threat from Iran sits in a wider context of the growing, diversifying and evolving threat that the UK faces from malign activity by a number of states,” Jarvis said.

“The threat from states has become increasingly interconnected in nature, blurring the lines between: domestic and international; online and offline; and states and their proxies.

“Turning specifically to Iran, the regime has become increasingly emboldened, asserting itself more aggressively to advance their objectives and undermine ours.”

As part of that address, Jarvis highlighted the National Security Act 2023, which “criminalises assisting a foreign intelligence service”, among other things.

So it was notable that this was the act used in one of this weekend’s investigations.

The suspects were detained under section 27 of the same act, which allows police to arrest those suspected of being “involved in foreign power threat activity”.

Those powers are apparently being put to use.