Never miss a story

Get subscribed to our newsletter


×
Deep learning algorithm to predict breast cancer risk using data from five MGH breast cancer screening sites. Pixabay

Researchers have developed a deep learning model that identifies imaging biomarkers on screening mammograms to predict a patient’s risk for developing breast cancer with greater accuracy than traditional risk assessment tools.

Traditional risk assessment models do not leverage the level of detail that is contained within a mammogram,” said study author Leslie Lamb from the Massachusetts General Hospital (MGH) in the US.


“Even the best existing traditional risk models may separate sub-groups of patients but are not as precise on the individual level,” Lamb added.

Currently, available risk assessment models incorporate only a small fraction of patient data such as family history, prior breast biopsies, and hormonal and reproductive history.

Follow NewsGram on Instagram to keep yourself updated.

Only one feature from the screening mammogram itself, breast density, is incorporated into traditional models.

The research team has developed a new deep learning algorithm to predict breast cancer risk using data from five MGH breast cancer screening sites.

The model was developed on a population that included women with a personal history of breast cancer, implants, or prior biopsies.


Traditional risk assessment models do not leverage the level of detail that is contained within a mammogram. Pixabay

The study included 245,753 consecutive 2D digital bilateral screening mammograms performed in 80,818 patients between 2009 and 2016.

Want to read more in Hindi? Checkout: भारत में मलेरिया के मामलों में करोड़ों का सुधार – डब्ल्यू.एच.ओ

From the total mammograms, 210,819 exams in 56,831 patients were used for training, 25,644 exams from 7,021 patients for testing, and 9,290 exams from 3,961 patients for validation.

Using statistical analysis, the researchers compared the accuracy of the deep learning image-only model to a commercially available risk assessment model (Tyrer-Cuzick version 8) in predicting future breast cancer within five years of the index mammogram.

The deep learning model achieved a predictive rate of 0.71, significantly outperforming the traditional risk model, which achieved a rate of 0.61.

“Our deep learning model is able to translate the full diversity of subtle imaging biomarkers in the mammogram that can predict a woman’s future risk for breast cancer,” Lamb said.

ALSO READ: Women Face 20 Percent Risk Of Heart Failure Other Than Men

The study is scheduled to be presented at the annual meeting of the Radiological Society of North America (RSNA) from November 29 to December 5. (IANS)


Popular

Photo by Pixabay

Indian astronomers have found an active galaxy in a very bright state with 10 times more X-ray emission than normal

Indian astronomers have found an active galaxy in a very bright state with 10 times more X-ray emission than normal, equivalent to more than 10 trillion of the sun, and located five billion light years away that could help probe how particles behave under intense gravity and acceleration to the speed of light.

It could help study the role of strong gravity and acceleration of matter in the formation, interaction and evolution of galaxies in the early universe.

Every galaxy in the universe is believed to host a supermassive black hole at its centre. In some galaxies, the black hole is actively devouring a large amount of material and shooting a jet of plasma almost at the speed of light towards us. These are called blazars.

OJ 287 belongs to a class of blazars known as BL Lacertae objects which show very rapid and large amplitude flux variations but barely discernible emission line features.

This class of sources emit in the whole electromagnetic spectrum, a rather uncommon phenomenon which requires extreme physical conditions. Hence, a study of such sources tells us about the behaviour of matter in an extreme gravitational field where it is difficult for light to escape from the vicinity of the black hole.

Astronomers at Aryabhatta Research Institute of Observational Sciences, an autonomous institute of the Department of Science and Technology, Government of India, have been monitoring one such black hole system named 'OJ 287' since 2015. This source shows a repeated optical brightness enhancement almost every 12 years.

"The repeated optical enhancement makes OJ 287 very intriguing as this class of sources does not show any repeating features in flux variations. The repeated optical enhancement made the researchers believe that the system hosts a binary black hole," said a release from the Ministry of Science and Technology.

In 2020, the source was very bright at optical and X-ray bands with X-ray flux more than 10 times the normal (non-active phase) flux. This flare was very different as it was not expected in models proposed for this source and thus, indicated a more complex system and physical conditions.

Investigating the extreme brightness shown by OJ 287 at optical and X-ray bands, astronomers led by Pankaj Kushwaha and Alok C. Gupta reported the source in a completely new spectral state.

The team argued that this change of state holds clues to the researcher's quest to understand how matter behaves in very strong gravity and how it accelerates the particle to almost the speed of light -- a feat that is out of the scope of even the most advanced CERN accelerator.

The research published in 'The Astrophysical Journal' tracked the details of changes in optical to the X-ray emission spectrum of the source with time from 2017 to 2020 -- after the second brightest X-ray flare of the source. It revealed how the source gradually started to change its spectral behaviour from mid-2018 to the new spectral state in 2020.

The study included data recorded by the ground-based facility operated by Physical Research Laboratory, Ahmedabad, operated Mount Abu observing facility in near infra-red bands and the space-based NASA's satellites -- the Niels Gherel Swift satellite at optical, UV and X-rays with gamma ray data from the Fermi satellite, the release added. (IANS/JB)

Keywords: Science, NASA, Satellites, Black Hole, Gravity, India


Photo by Flickr

Tospread awareness about the significance of reading, Rachna Kalra, who hails from Gurugram (Haryana), started the Silent Book Club in the year 2019.

Who doesn't like reading, and that, too, reading along the company of mother nature? Well, this book club is truly a fantasy turned to reality.

As said by a regular reader at the Silent Book Club, “There is something meditative about reading. Sitting quietly with a book, without any distractions, is almost spiritual for me," this exactly is the case with many such readers.

Keep Reading Show less
Unsplash

Ninety-eight per cent of Indian travellers say they want to stay in a sustainable accommodation in the coming year.

A Travel Sustainable badge, provides highly coveted information to travellers all over the world looking to make more sustainable travel choices. Booking.com has launched the Travel Sustainable Badge, a first of its kind in the industry, designed to be applicable to a wide range of property types, from apartments, B&Bs, and vacation homes to hotels, resorts, and even treehouses, and adaptable to local realities and considerations.

Ninety-eight per cent of Indian travellers say they want to stay in a sustainable accommodation in the coming year, and with more than 28 million listings on Booking.com, the company sees a huge opportunity to highlight more of the impactful efforts its partners are making to create more sustainable experiences, making it easier for travellers to find a sustainable way to stay.

Follow NewsGram on Facebook to stay updated.

With 88 percent of Indian travellers indicating that they would be more likely to choose a specific accommodation that implements sustainable practices, it rewards and encourages providers to take the next steps on their individual sustainability journeys.

Keep reading... Show less