News | Artificial Intelligence | December 02, 2020

Recent Studies Reveal High Performance of Lunit AI in Breast Cancer Detection

Lunit’s algorithm showed the best performance compared to other commercialized AI algorithms, ultimately reducing the workload of radiologists to classify mammography screenings

Lunit’s algorithm showed the best performance compared to other commercialized AI algorithms, ultimately reducing the workload of radiologists to classify mammography screenings

December 2, 2020 — Recent studies have shown that Lunit’s AI solution is as accurate as average radiologists when it comes to identifying breast cancer and it could potentially have a role as independent reader in the future, to reduce radiologist workload and possibly to increase cancer detection.

A pair of studies conducted by Fredrik Strand, M.D., from Karolinska Institutet and his research team have been recently published in JAMA Oncology and The Lancet Digital Health, well-known to be among the leading peer-reviewed journals in medicine, featuring performance results of Lunit INSIGHT MMG, a commercial AI solution for breast cancer detection from mammograms. 

According to the study published in JAMA Oncology, the team conducted the first independent comparison of several commercialized AI. Three different AI algorithms were analyzed including Lunit’s solution (Lunit INSIGHT MMG) to identify breast cancer. They were evaluated in a large retrospective screening cohort.

Based on 8,805 cases, Lunit’s algorithm showed the best accuracy among others, showing around 15 percentage points higher sensitivity than the other two algorithms. It also surpassed the sensitivity of the first-reader radiologists, and achieved a synergistic sensitivity of 88.6% when combining first-readers and Lunit’s AI solution. 

“The significant leap in performance comes from our proprietary algorithm, meticulously trained by an unprecedented quantity of data with accurate ground truth,” said Ki Hwan Kim, Chief Medical Officer of Lunit. “Our training dataset includes 72,000 biopsy-proven breast cancer cases, which is considerably more than other algorithms mentioned in the study.”

In line with the high performance, the possibility for AI to triage certain screening examinations was suggested in the study published in The Lancet Digital Health. It focused on how AI-based scoring can be used to reallocate radiologist time from clearly negative mammograms to cases requiring additional attention by radiologists, ultimately reducing their workload and improving cancer detection.

The study proved that for the majority of mammograms receiving a low abnormality score Lunit AI rarely missed any cancers when assessing the data alone, with no radiologists involved. If no radiologist resources were used for 60% of women with the lowest AI scores and were invested into doing MRI for the top 2% AI scores (that were negative after radiologist double reading of the mammograms), a net of 103 of 547 cancers would potentially have been detected up to 2 years earlier, corresponding to a detection rate of 68 cancers per 1000 supplemental screening examinations.

Strand, a researcher at the Department of Oncology-Pathology at Karolinska Institutet and a radiologist at Karolinska University Hospital explained, “The studies show the potential of commercial AI algorithms as independent readers in screening mammography assessment on a clinically relevant level. The next step for us is to explore how well the Lunit AI algorithm works as an independent reader in a prospective clinical setting. In the future, I am convinced that AI image analysis will contribute to further improvements in overall survival for breast cancer patients.”

“As breast cancer is the second leading cause of death in women, early detection is the best defense in treating the disease,” says Brandon Suh, CEO of Lunit. “It is very meaningful for our algorithm’s high-performance level to be recognized in these well-designed studies based on a significant actual screening cohort data, and we hope to continuously provide the best solution for the right diagnosis of patients.”

For more information: www.lunit.io

Related Content

Steinberg Diagnostic Medical Imaging headquarters.

Steinberg Diagnostic Medical Imaging headquarters.

Sponsored Content | Case Study | Contrast Media Injectors | January 21, 2021
Steinberg Diagnostic Medical Imaging (SDMI) was founded 30 years a
For years telehealth has danced at the edges of healthcare
Feature | Teleradiology | January 21, 2021 | By Jef Williams
All indications point to 2021 being the year of the return path of this boomerang event that sent us all in a differe
Radiologists have recently taken on the role of activists and are tackling pressing issues in healthcare, including breast density

Getty Images

Feature | Women's Health | January 20, 2021 | By Fazila Seker, Ph.D.
Radiologists — who have long been professionals in the metaphorical and literal back-rooms of healthcare — have recen
The key trends Clinicians reviewing a COVID-19 patient's lung CT that reveals the severity of COVID-caused pneumonia. The impact of COVID on radiology was a major, over arching trend at  the 2020 Radiological Society of North America (RSNA) meeting. Getty Imagesbserved at 2020 Radiological Society of North America (RSNA) meeting all focused around COVID-19 (SARS-CoV-2) and the impact it has had on radiology. #RSNA #RSNA20 #RSNA2020

Clinicians reviewing a COVID-19 patient's lung CT that reveals the severity of COVID-caused pneumonia. The impact of COVID on radiology was a major, over arching trend at  the 2020 Radiological Society of North America (RSNA) meeting. Getty Images

Feature | RSNA | January 20, 2021 | By Melinda Taschetta-Millane and Dave Fornell
MRI Targeted biopsy is performed using cognitive fusion more easily with anatomical guidance based on the radiology report. MRI targets can be identified quickly in real-time along with micro-ultrasound targets, which may have been missed on MRI.

MRI Targeted biopsy is performed using cognitive fusion more easily with anatomical guidance based on the radiology report. MRI targets can be identified quickly in real-time along with micro-ultrasound targets, which may have been missed on MRI. Image courtesy of Exact Imaging

Feature | Prostate Cancer | January 20, 2021 | By Brian Wodlinger, Ph.D.
Historically when a patient had an elevated PSA (prostate specific antigen) test their urologist would take the next
An interview with Eric Liederman, M.D., MPH, Director of Medical Informatics for The Permanente Medical Group, in Kaiser Permanente’s Northern California Region, on the explosion of telemedicine in the COVID-19 era

Getty Images

Feature | Radiology Business | January 20, 2021 | By Melinda Taschetta-Millane
Vendor neutral archives enable a single, central location to store large volumes of radiology data, but now need to be able to house data from dozens of other departments with a wide array of data formats. This article originally ran as an introduction to the Vendor Neutral Archives comparison chart.
Feature | Vendor Neutral Archive (VNA) | January 20, 2021 | By Dave Fornell
Most radiologists and clinicians are not trained as...
According to a new research report1 on the contrast media injectors published by MarketsandMarkets, the market was estimated to be $1.3 billion in 2020 and projected to reach $1.9 billion by 2025, at a compound annual growth rate (CAGR) of 7.4 percent over 2020-2025.

The ulrich CTmotion

Feature | Contrast Media Injectors | January 20, 2021 | By Melinda Taschetta-Millane
According to a new...
Previously approved by FDA in the USA, MyLab X8 expands the reach of the MyLab Ultrasound Product Line with a fully featured premium imaging solution, integrating the latest technologies and delivering superior image quality without compromising workflow or efficiency.
News | Ultrasound Imaging | January 20, 2021
January 20, 2021 — Esaote North America announces that the...