By Erik L. Ridley, AuntMinnie staff writer

August 27, 2020 –– The combination of an artificial intelligence (AI)-based computer-aided detection (CAD) algorithm with radiologist interpretation can detect more cases of breast cancer on screening mammograms than double reading by radiologists, according to research published online August 27 in JAMA: Oncology.

Click here to read the complete article at

Researchers from the Karolinska University Hospital in Stockholm, Sweden, retrospectively compared three commercially available AI models in a case-control study involving nearly 9,000 women who had undergone screening mammography. They found that one of the models demonstrated sufficient diagnostic performance to merit further prospective evaluation as an independent reader.

What’s more, the best results — 88.6% sensitivity with 93% specificity — were achieved when utilizing that algorithm’s results along with the first radiologist interpretation.

“Combining the first readers with the best algorithm identified more cases positive for cancer than combining the first readers with second readers,” wrote the authors, led by Dr. Mattie Salim. “No other examined combination of AI algorithms and radiologists surpassed this sensitivity level.”

The researchers used a study sample of 8,805 women ages 40 to 74 who had received screening mammography at their academic hospital from 2008 to 2015 and who did not have implants or prior breast cancer. All exams were performed on a full-field digital mammography system from Hologic.

Of these women from the public mammography screening program, 8,066 were a random sample of healthy controls and 739 were diagnosed with breast cancer. These 739 cancer cases included 618 actual screening-detected cancers and 121 clinically detected cancers. In order to mimic the 0.5% screening-detected cancer rate in the source screening cohort, a stratified bootstrapping method was used to increase the simulated number of screenings to 113,663.

The researchers then applied AI CAD software from three different vendors, who asked to remain anonymous. None of the algorithms had been trained on the mammograms in the study.

After processing the images, the CAD software provided a prediction score for each breast ranging from 0 (lowest suspicion) to 1 (highest suspicion). To enable comparison of the algorithm’s results with the recorded radiologist decisions, the researchers elected to choose an algorithm output cutpoint that corresponded as closely as possible to the specificity of that of the first-reader radiologists, i.e. 96.6%.

Breast cancer detection performance
First-reader radiologists Second-reader radiologists Double reading consensus AI algorithm #3 AI algorithm #2 AI algorithm #1 Combination of AI algorithm #1 and first-reader radiologists
Area under the curve n/a n/a n/a 0.920 0.922 0.956 n/a
Sensitivity 77.4% 80.1% 85% 67.4% 67% 81.9% 88.6%
Specificity 96.6% 97.2% 98.5% 96.7% 96.6% 96.6% 93%

The researchers noted that the differences in sensitivity between AI algorithm #1 and the other two algorithms and the first reader were statistically significant (p < 0.001 and p = 0.03, respectively).

In an accompanying commentary, Dr. Constance Lehman, PhD, of Harvard Medical School in Boston said that it’s now time to move beyond simulation and reader studies and enter the critical phase of rigorous, prospective clinical evaluation of AI.

“The need is great and a more rapid pace of research in this domain can be partnered with safe, careful, and effective testing in prospective clinical trials,” she wrote. “If AI models can sort women with cancer detected on their mammograms from those without cancer detected on their mammograms, the value of screening mammography can be made available and affordable to a large population of women globally who currently have no access to the life-saving potential of quality screening mammography.”

Click here to read the complete article at

By Erik L. Ridley, AuntMinnieEurope staff writer

August 10, 2020 — Artificial intelligence (AI)-based software can reliably categorize a significant percentage of negative screening mammograms as normal, potentially decreasing mammography reading workload for radiologists by more than half, according to two presentations made at the recent ECR 2020 virtual meeting.

In separate studies that simulated outcomes from the use of AI algorithms to evaluate screening mammograms and set aside certain cases that are highly likely to be normal, Danish and U.S. researchers shared their experiences about how software can decrease the interpretation burden of radiologists without having a negative impact on cancer detection.

Pressure on radiologists

With the vast amount of women enrolled in breast cancer screening programs worldwide, there’s pressure on radiologists to read a substantial amount of mammograms — the majority of which are normal. The use of AI to help radiologists automatically detect a large number of these normal mammograms could possibly increase the performance of the screening program, while also making it more effective, explained Andreas Lauritzen of the University of Copenhagen in Denmark.

In a retrospective study, the investigators assessed the potential clinical impact of using AI software to reduce the screening mammography workload, specifically examining cases where an AI system could substitute for two radiologists when mammograms are very likely to be normal, he noted.

The team analyzed 53,948 mammography exams acquired in the Danish Capital Region breast cancer screening program from November 1, 2012, to December 31, 2013, in women ages 50-70. All exams included four full-field digital mammography (FFDM) images — two mediolateral oblique and two craniocaudal views — that were acquired on a Mammomat Inspiration FFDM system (Siemens Healthineers). Two radiologists read each of the exams, with agreement established in consensus.

The 53,948 exams included 418 screening-detected cancers, 150 interval cancers, and 812 long-term cancers that were confirmed by mammography, ultrasound, and biopsy. There were also 1,306 exams that were noncancer recalls.

The researchers then retrospectively applied version 1.6 of the Transpara AI-based software (ScreenPoint Medical) to these exams. Transpara provides a score of 1-10 to indicate the likelihood of a visible malignancy.

The experiment was set up to have radiologists not read exams deemed by the software to be very likely normal and then double-read the rest of the exams. The researchers then compared the outcome of these experiments with the original screening outcomes.

Lower workload

Lauritzen and colleagues found that the AI software yielded an area under the curve (AUC) of 0.95 for screening-detected cancers and 0.66 for interval cancers. If an AI software scoring threshold of 5 was used, 32,054 exams would be considered likely normal and not read by radiologists, reducing mammography workload by 59.42%.

Screening mammography program outcomes in study of 53,948 screening mammograms from Danish Capital Region
Original screening outcomes Screening outcomes if AI software scoring threshold of 5 was automatically used to determine a normal mammogram
Recall rate 3.18% 2.48%
Positive predictive value 24.34% 30.04%

With this strategy, 16 (3.83%) of the screening-detected cancers that were detected during the normal double reading process would have been missed. However, if this AI strategy was expanded to recall all women with an exam score > 9.96, 16 new cancers would be detected, including five interval cancers and 11 long-term cancers. These added detections would come at the cost of only 91 new noncancer recalls, Lauritzen said.

This demonstrates that it’s possible to maintain a stable cancer detection rate and still avoid a large number of noncancer recalls, he pointed out.

“This study suggests that an AI system can be used to maintain safety of the breast screening program, possibly increase performance, while reducing the number of mammograms that have to be read by radiologists by a considerable amount,” Lauritzen said.

Click here to read the complete article at


Dr. Peña describes herself as a coach’s wife and full-time working mom of three.  She is also a clinical pharmacist, passionate public speaker, and breast cancer survivor.

She is  founder and president of a non-profit organization;  The M.o.C.h.A.™️Tribe” (Mom Of a Child that Has Autism).  She writes a blog called The M.o.C.h.A Tribe Diaries — a website devoted to squashing the idea that autism has a single story.  She is also the Author of “Waiting for the Lightbulb” and a Today Show parenting team contributor.

Dr. Peña caught our attention with her video describing her personal experience with breast cancer beginning with consultation at the High-Risk Screening and Genetics Clinic at MD Anderson Center.  We were so moved with the video and her insightful emphasis on the lifesaving importance of early cancer detection, we wanted to share it with our readers.

SOUND ON🔈This 5 min video could save your life or the life of someone you love..It saved mine..You will want to click this link when your done.’re welcome for the grapefruit visual… there were other contenders… but they were inappropriate and not as comically subtle. Whatev..✌🏼&❤️#livinginthe5percent #cancersucks #purposeinpink #fightlikeagirl #survivor #breastcancerawareness The BreastiesSurvivorNet

Posted by Lisa A Peña on Wednesday, October 30, 2019


By Simon Häger, contributing writer

July 2, 2020 — Dr. László Tabár, a radiologist and oncologist from Falun, Sweden, is known worldwide as the “father” of mammography screening. He is certainly one of the key people behind the current national screening program for breast cancer in Sweden, but his research has also formed the basis for the introduction of screening programs in many other countries.

In this interview, Tabár shares the fascinating story of why he has dedicated the past 50 years of his life to introducing and improving mammography screening, and thereby reducing mortality in breast cancer — a journey colored by groundbreaking research results and success but also by opposition and a struggle to convince authorities of the benefits.

He gives us the story behind the introduction of mammography screening in Sweden and the intriguing results shown in two of his latest studies, published in 2018 and 2020, proving the benefits of screening independent of treatment regime — something he calls “one of the greatest accomplishments in clinical cancer research during the past 50 years.”


Dr. László Tabár in action by his breast imaging PACS workstation. Images courtesy of Dr. László Tabár.

Read the full article at Aunt Minnie

By Theresa Pablos, AuntMinnie — staff writer May 14, 2020 —

Many women want to learn about their risk status for breast cancer from a face-toface meeting with the radiologist who interpreted their screening mammograms, according to the findings of a study published on May 3 in Academic Radiology.

The study included the responses of more than 600 women who visited one of eight Massachusetts mammography centers for their regular screening. The desire to learn about their risk status from a radiologist was one of the top survey responses, regardless of whether the participants had an average or high risk of developing breast cancer in a hypothetical scenario.

“As an increasing number of breast imaging facilities incorporate risk assessment into their screening mammography routine, radiologists now have an opportunity to communicate estimated breast cancer risk with patients,” wrote the authors, led by Dr. Nita Amornsiripanitch from the University of Massachusetts Medical School.

The American Cancer Society recommends supplemental breast MRI screening for women who have an increased average risk of breast cancer. Yet many women, including high-risk women, don’t know their breast cancer risk status.

The authors asked a diverse group of women how they would like to receive information about their breast cancer risk status using a 21-question survey. The vast majority (87%) of the 683 survey respondents said they were interested in knowing their lifetime risk of breast cancer.

The few who didn’t want to know their risk status gave reasons such as already having a personal history of breast cancer, being older in age, or not having a family history of breast cancer. Women with a household income of less than $20,000 were also less interested in knowing their risk status than those with an income of $40,001 to $65,000 after the authors adjusted for confounding factors.

In a hypothetical scenario where the participants had an average risk of breast cancer, 57% of respondents said they’d like a letter accompanying their annual mammogram results. Another 34% said they’d like to meet face-to-face with the radiologist interpreting the results, and 30% wanted a face-to-face meeting with the referring provider.

When asked how they’d like to receive information about their risk status if they had an elevated risk of developing breast cancer, 43% of respondents said they’d like a face-to-face meeting with the radiologist, and the same percentage of respondents said they’d want a letter in the mail.

If the women could only choose one communication method in each scenario, more women chose to receive a letter if they had an average risk of breast cancer, but they preferred a face-to-face meeting with a radiologist or other provider if they had an elevated risk of breast cancer.

The authors also asked the women what level of detail they’d like to know about their risk status.  In the average-risk scenario, 57% of respondents said they’d want to receive very detailed information. That statistic rose to 80% of respondents for the high-risk scenario.

After controlling for confounding factors, such as age, income, education, and personal breast cancer history, the authors found non-Hispanic African-American women were the only race/ethnicity to 5/14/2020 Women want breast cancer risk info from radiologists prefer less detailed information in the high-risk scenario than the average-risk one. However, nonHispanic African American women were also underrepresented in the study, they noted.

“Further research is needed to confirm whether increased access to breast cancer risk assessment would increase appropriate use of supplemental screening modalities, adherence to risk reduction strategies, and ultimately, early cancer detection,” the authors wrote. “However, as the trend toward performing risk assessment at time of screening mammography continues, it is critical that radiologists are conscientious of vulnerable populations and their preferences for receiving risk assessment results in order to provide patient-centered care to all women.”

Read full article here: http://Aunt Minnie

Ikonopedia is Providing Web-Based Training and Installation to Help Customer Base Leverage Efficiency Gains to Handle Anticipated Patient Volumes Post COVID-19

RICHARDSON, TexasApril 16, 2020 /PRNewswire/ — Ikonopedia announced the completion of an implementation of its structured breast reporting and risk assessment tools at Marshfield Clinic in Eau Claire, Wisconsin. The remote, Cloud-based implementation, which was completed in February prior to COVID-19 related shelter in place orders, involves eight imaging centers and three mobile mammography units. Ikonopedia’s next generation breast reporting software is designed to help improve reporting efficiency and optimize facility operations.

The only Cloud-based software provider in its space, Ikonopedia has been providing off-site, remote training and implementation since 2014. As other breast imaging sites implement Ikonopedia software during COVID-19, the company is hosting web-based training sessions for radiologists and center staff to learn how to use the software to facilitate quick adoption and readiness for the resumption of routine patient screening.

Marshfield Clinic Health System is the largest private group medical practice in Wisconsin and one of the largest in the United States, with more than 1,200 medical providers representing more than 86 specialties and subspecialties. The System has more than 50 locations in 34 Wisconsin communities, including hospitals in Marshfield, Eau Claire, Park Falls and Rice Lake.  The practice also opted to utilize the additional language options for patient questionnaires and patient letters to best serve and communicate with their patient population which includes a high Hmong speaking population.

“Our entire team is focused on providing the highest quality care to our patients and Ikonopedia’s innovative Cloud-based structured breast reporting system has helped support that goal by eliminating any errors and helping us be more efficient,” said Sarah Nielsen, DO, Section Head Breast Imaging, Marshfield Clinic. “Prior to scaling back patients due to COVID-19, the intuitive, easy to use reporting and risk assessment tools helped improve our productivity.  As we anticipate high patient volumes once we’re able to re-open, the ability for our radiologists to read faster, while delivering accurate, high quality reports to our referring physicians, will be extremely important.”  

Ikonopedia is an innovative structured breast reporting and MQSA management system designed to dramatically improve reporting efficiency, and optimize facility operations. Ikonopedia’s integrated risk assessment tool is now available in dozens of languages and risk data is used to create alerts for the radiologist, populate the clinical section of the report, and automatically update the patient letter. A high-risk patient alert identifies patients with a 20% or greater lifetime risk and information about the score is instantly viewable.

Ikonopedia makes it possible to eliminate laterality errors, automatically choose exam-appropriate patient letters and pull forward findings from past exams along with many other time-saving features.  All findings are saved as discrete data which allows Ikonopedia to prevent errors, maintain BI-RADS-compliant language and automate many time-consuming processes.

“We are excited to have a customer like Marshfield Clinic that is known for such high quality patient care,” said Emily Crane, CEO of Ikonopedia, “We are excited to help Marshfield and our entire customer base put these efficiency gains to good use once they re-start screening patients after COVID-19.” 

About Ikonopedia
Ikonopedia was founded by three expert breast imaging Radiologists: László Tabár, MD is the author of 6 books in 10 languages on mammography and a world renowned educator;  A. Thomas Stavros, MD is the author of one of the most popular reference books in the field of breast ultrasound; and Michael J. Vendrell, MD is an expert in breast MRI and CAD design with extensive experience in breast-imaging software. For more information, visit

Jan 17 – 19, 2020 | San Antonio, Texas

Breast Ultrasound CME Course with Tom Stavros – Hot Topics in Advanced Screening and Diagnosis is organized by World Class CME. The symposium is held from Jan 17 – 19, 2020 at The Westin Riverwalk, San Antonio, San Antonio, Texas, United States of America.

Target Audience:
Radiologists and radiology residents/fellows, breast surgeons, sonographers, radiology technologists and advanced practitioners who seek to learn, in-depth, how to use breast ultrasound in a clinical practice setting for diagnosis, screening and staging of breast disease.

• 20.75 AMA PRA Category 1 Credits™
These credits can be used toward ABR MOC Part 2 requirements

• 6.0 SAMs Credits
These credits can be used toward ABR MOC Part 2 SA-CME requirements

ASRT approved for 21.5 Category A CE Credits for Sonographers and Technologists:
• Friday AM Session – 4.75
• Friday PM Session – 4.25
• Saturday AM Session – 4.75
• Saturday PM Session – 2.5
• Sunday Session – 5.25

“Welcome to San Antonio and the Hot Topics in Advanced Screening and Diagnosis. This session will emphasize a new classification system on breast cancer and will focus non-mass ultrasound findings, an analysis of causes of false-negative BI-RADS 3 classifications, and new ways of classifying breast nodules that can help objectively assign BI-RADS 4 subcategories and improve ultrasound’s ability to serve as a biomarker. I will lead interactive case readings with an audience response system, and we have time set aside for questions and answers.” – Tom Stavros

Course Objectives:
Upon completion of this conference, the participant will be able to:
• Understand the differences in pre-test probabilities and guidelines for interpretation between diagnostic, supplemental screening, and MRI-directed indications for breast ultrasound and how that affects management and interpretation
• Select the most appropriate ultrasound equipment, machine settings, and scan techniques for better diagnostic evaluations
• Understand the anatomic and histopathologic basis for ultrasound appearances
• Correlate areas of clinical, mammographic, screening ultrasound, or MRI concern with ultrasound, and understand the anatomic and histopathologic basis for ultrasound appearances
• Identify both mass and non-mass sonographic findings that are suspicious for malignancy, how to use them in classifying breast masses and in staging breast cancers
• Understand a new way of classifying ultrasound features that can aid in more objectively using and achieving ACR PPV benchmarks for BI-RADS 4 subcategories and function better as biomarkers than prior methods of classification
• Identify the few truly suspicious complex cystic and solid masses that require biopsy and distinguish them from the myriad of non-simple breast cysts that are definitively benign
• Understand the roles of ultrasound and galactography in diagnosis and guiding biopsy in patients presenting with nipple discharge
• Recognize the range of normal and abnormal appearances for breast implants
• Enhance ultrasound-guided breast biopsy and interventional skills
• Utilize the new classification system of breast malignancies that is based upon site of origin – within ducts, within TDLUs, or within peri-ductal mesenchymal tissues for better correlation with prognosis
• Understand the appropriate role for supplemental bilateral whole breast ultrasound as well as other ancillary imaging modalities in women with negative but dense mammograms
• Improve detection and correct classification of small invasive breast cancers while minimizing false positive
ultrasound examinations
• Learn how to overcome the headwinds in establishing a supplemental whole breast ultrasound program in women with dense breasts
• Learn to distinguish normal from abnormal regional lymph nodes, determine whether abnormal nodes are more likely metastatic or reactive, and how Z0011 might affect current management of nodes
• Become familiar with a new functional imaging platform called Opto-acoustic Imaging
• Understand the benefits of integrating this new technology into breast ultrasound, so that the radiologist can significantly increase specificity when analyzing a mass, and potentially obviate the need for many breast biopsies.

By Rebekah Moan, contributing writer

November 27, 2019 — With proper training and experience, breast ultrasound consistently improves detection of node-negative invasive cancer in women with dense breasts on mammography, according to a literature review in the Journal of Breast Imaging. Similar results have been observed after digital breast tomosynthesis (DBT).

Thirty-five studies that involved breast ultrasound — both compact and automated breast ultrasound (ABUS) — were reviewed by a team led by Dr. Wendie Berg, PhD, of the University of Pittsburgh, and Dr. Athina Vourtsis, PhD, from the Diagnostic Mammography Medical Diagnostic Imaging Unit in Athens, Greece. They found adding ultrasound to mammography results in low interval cancer rates and boosted cancer detection rates.

“I think it is important that there are now published results on over 400,000 screening breast ultrasound examinations and the results have been very consistent,” Berg told “In women with dense breasts, ultrasound will find another two to three cancers per 1,000 women screened each year.”

Why breast ultrasound?

Dense breast tissue can mask breast cancer on mammography, and furthermore, the denser the breast, the greater the risk of developing breast cancer — a fourfold increased risk, in fact. Dense breasts are so problematic that 38 states as well as Washington, DC, require some form of density information in mammography results letters sent to patients.

In addition, the February 15 federal budget law included a provision that the U.S. Food and Drug Administration (FDA) must update the national Mammography Quality Standards Act (MQSA) to require that breast density is included in mammography reports sent to providers and in results letters sent to patients. The new rule will likely be effective in early 2021.

Considering dense breasts are harder to image on mammography and more likely to conceal breast cancer, what are physicians supposed to do? The answer: Use supplemental ABUS or breast MRI.

Read full article at