Deep learning predicts woman's risk for breast cancer: RSNA

▴ Deep learning predicts woman's risk for breast cancer: RSNA
The 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

Researchers at Massachusetts General Hospital (MGH) 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. Results of the study are being presented at the annual meeting of the Radiological Society of North America.

"Traditional risk assessment models do not leverage the level of detail that is contained within a mammogram," said Leslie Lamb, M.D., M.Sc., breast radiologist at MGH. "Even the best existing traditional risk models may separate sub-groups of patients but are not as precise on the individual level."

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

"Why should we limit ourselves to only breast density when there is such rich digital data embedded in every woman's mammogram?" said senior author Constance D. Lehman, M.D., Ph.D., division chief of breast imaging at MGH. "Every woman's mammogram is unique to her just like her thumbprint. It contains imaging biomarkers that are highly predictive of future cancer risk, but until we had the tools of deep learning, we were not able to extract this information to improve patient care."

Dr Lamb and a team of researchers developed the 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.

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

Dr Lamb said the new deep learning model has been externally validated in Sweden and Taiwan, and additional studies are planned for larger African-American and minority populations.

At MGH, deep learning risk information is available on reporting software when the radiologist reads a patient's screening mammogram.

"Traditional risk models can be time-consuming to acquire and rely on inconsistent or missing data," Dr Lamb said. "A deep learning image-only risk model can provide increased access to more accurate, less costly risk assessment and help deliver on the promise of precision medicine."

Tags : #RadiologicalSocietyofNorthAmerica #LatestPharmaNews30thNov #LatestResearchonBreastCancer30thNov #MassachusettsGeneralHospital

About the Author


Team Medicircle

Related Stories

02 Apr

World Autism Awareness Day: Breaking the Chains of Stigma in India

Are we ready to create a world that embraces neurodiversity, or will we continue to let ignorance dictate the lives of millions?

View
02 Apr

The Digital Sleep Thief: How Night-time Screen Addiction is Robbing You of Bed-time Rest

By implementing screen-free bedtime routines, reducing blue light exposure, and prioritizing sleep hygiene, we can reclaim the restful nights we deserve.

View
02 Apr

DCDC’s $150 Crore Expansion: Can Innovative Clinics End India's Kidney Crisis?

As the healthcare landscape evolves, initiatives like these will determine the future of medical care in the country.

View
02 Apr

From Scroll to Squint: How Reels Are Reshaping Your Vision

By adopting healthier screen habits and prioritizing eye care, we can prevent the irreversible damage caused by prolonged digital exposure.

View
02 Apr

High-Rise Heart Attacks: Are Skyscrapers Turning Survival into a Race Against Time?

It’s time to prioritize human life over convenience and invest in smarter urban designs to empower communities with the knowledge and tools needed to act swiftly in times of crisis.

View
31 Mar

Essential Medicines Price Surge: Are Patients Paying the Price?

As the pharmaceutical landscape evolves, the focus must remain on ensuring that life-saving medicines are within everyone’s reach.

View
31 Mar

Tired of Stomach Cramps? These Simple Foods Can Heal Your Gut

By making mindful food choices, one can significantly reduce symptoms, avoid severe complications, and improve quality of life.

View
31 Mar

Doomscrolling at Midnight: How Indians Are Sacrificing Sleep for Screens

Public health initiatives should address sleep disorders with the same urgency as other health concerns. By prioritizing sleep, India can take a major step towards improving overall well-being and productivity.

View
28 Mar

10 New HIV Cases in 2 Months: Has Kerala’s Drug Problem Gone Too Far?

The rise in HIV cases linked to syringe-sharing in Malappuram is a serious reminder that public health efforts must constantly adapt to new challenges.

View
28 Mar

Type 2 Diabetes Under Attack: The Unexpected Power of Wearable Tech

As research continues to explore the benefits of digital health interventions, it is clear that the future of diabetes care lies at the intersection of technology and lifestyle.

View

-Advertisements-




Trending Now

The Digital Sleep Thief: How Night-time Screen Addiction is Robbing You of Bed-time RestApril 02, 2025
KKR Launches ‘Knight Bite’ – A Digital Series That Serves Up Food, Fun, and Cricket!April 02, 2025
Crompton rolls out its all new range of Aura, Avancer & Jedi Air Coolers for an effortless summer cooling experienceApril 02, 2025
CARE Hospitals, Hi-Tech City Strengthens Orthopaedics Department with Renowned SurgeonsApril 02, 2025
World Autism Awareness Day: Breaking the Chains of Stigma in IndiaApril 02, 2025
From Scroll to Squint: How Reels Are Reshaping Your VisionApril 02, 2025
Moscow Center for Diagnostics and Telemedicine Receives License for Radiology Residency ProgramApril 02, 2025
CARE Hospitals Launches AI-Powered Non-Invasive Therapy – An innovative modality introduced in Telangana & Andhra PradeshApril 02, 2025
High-Rise Heart Attacks: Are Skyscrapers Turning Survival into a Race Against Time?April 02, 2025
DCDC’s $150 Crore Expansion: Can Innovative Clinics End India's Kidney Crisis?April 02, 2025
Medanta Rolls Out ‘Colon Tunnel on Wheels’ to Drive Awareness on Colorectal Cancer Prevention & Early DetectionApril 01, 2025
Zigly launches 2 pet hospitals, opens 4 new stores; expects ARR to more than double in 1-2 yearsApril 01, 2025
University of Leeds Announces International Masters Regional Scholarships for 2025April 01, 2025
Avantor Recognized with Two Prestigious Awards at Asia-Pacific Biopharma Excellence Awards 2025April 01, 2025
Foundation Stone Laid for Madhav Netralaya Eye Hospital & Research CentreApril 01, 2025
Doomscrolling at Midnight: How Indians Are Sacrificing Sleep for ScreensMarch 31, 2025
Essential Medicines Price Surge: Are Patients Paying the Price?March 31, 2025
Prioritize your health during the holy days of RamzanMarch 31, 2025
Tired of Stomach Cramps? These Simple Foods Can Heal Your GutMarch 31, 2025
Regional growth booming for startups in 2024 - QBO Innovation studyMarch 31, 2025