RSNA 2017 Women's Informatics Preview
By Wayne Forrest, staff writer
November 9, 2017

RSNA 2017 might be remembered as the annual meeting when women's imaging took a quantum leap forward with the burgeoning utilization of artificial intelligence (AI), machine learning, deep learning, and computer-aided detection/diagnosis (CAD/CADx).

During the week, dozens of scientific sessions, refresher courses, educational exhibits, and poster discussions will explore how these advanced technologies will benefit breast imaging and have an expanding influence on a number of levels and a wide range of clinical applications.

AI and its related technological counterparts will help clinicians advance the capabilities of digital mammography, ultrasound, and MRI to improve the detection and diagnosis of breast cancer, supplement biopsies, or avoid invasive procedures altogether.

Researchers will show how CAD/CADx increases the ability of radiologists to identify and characterize lesions with accuracy approaching 100%. When coupled with imaging modalities, deep learning and CAD enhances specificity, accuracy, and positive predictive value for various abnormalities.

With bolstered computing power, researchers are combining routine clinical data and natural language processing to create very large datasets for deep learning to perform multiple tasks in much less time than it would a team of radiologists and clinicians. In addition, deep learning can produce super-high-resolution mammography images, which has the potential to replace magnification mammography without any additional dose exposure for patients.

Below is a sampling of what is available for your introduction to and education on the current state of women's imaging informatics and what the future holds with the further adoption of AI technologies.

And, to view a complete listing of abstracts for the RSNA 2017 scientific and educational program, click here.

Scientific and Educational Presentations
U.K. group studes link between cancer detection, age, and breast density
Sunday, November 26 | 11:05 a.m.-11:15 a.m. | SSA01-03 | Arie Crown Theater
In this Sunday morning talk, researchers from the U.K. will discuss their investigation of the relationship between breast density, age, and cancer detection rates in a large breast screening program.
Breast MRI neural network predicts treatment response
Monday, November 27 | 11:50 a.m.-12:00 p.m. | RC215-17 | Arie Crown Theater
In this session, researchers will discuss how neural networks based on a breast MRI tumor dataset can help clinicians predict patient response to neoadjuvant chemotherapy.
Deep learning with breast MRI helps with lesion detection
Tuesday, November 28 | 11:20 a.m.-11:30 a.m. | RC315-14 | Arie Crown Theater
A deep-learning method using multiparametric breast MRI improves automated detection and characterization of breast lesions, according to research being presented at this Tuesday morning session.
Deep learning improves mammography multitasking
Tuesday, November 28 | 11:30 a.m.-11:40 a.m. | SSG13-07 | Room S404AB
Everyone can use some help when multitasking. Researchers from the University of Michigan will present the benefits to mammography from a deep convolutional neural network based on a multitask transfer learning algorithm.
CAD boosts performance of contrast spectral mammography
Tuesday, November 28 | 12:15 p.m.-12:45 p.m. | BR234-SD-TUA2 | Lakeside, BR Community, Station 2
Computer-aided diagnosis of contrast-enhanced spectral mammography (CAD-CESM) can help reduce false positives, according to this Tuesday afternoon poster presentation.
Deep-learning software improves breast US performance
Tuesday, November 28 | 3:40 p.m.-3:50 p.m. | SSJ02-05 | Room E450A
When it comes to identifying breast cancer, deep-learning software for breast ultrasound achieves diagnostic accuracy comparable to that of radiologists, Swiss researchers have found.
Deep learning could lend a hand with digital mammo
Wednesday, November 29 | 10:40 a.m.-10:50 a.m. | SSK02-02 | Room E451A
A computer system based on deep-learning technology was as efficient as radiologists in detecting breast cancer on digital mammography exams in a study by a group from Sweden and the Netherlands.
Deep-learning CAD adds to breast ultrasound findings
Wednesday, November 29 | 10:50 a.m.-11:00 a.m. | SSK02-03 | Room E451A
The potential benefits of deep-learning computer-aided detection (CAD) for breast ultrasound will be outlined in this Wednesday morning presentation by researchers from South Korea.
Novel deep-learning process aids breast cancer detection
Wednesday, November 29 | 11:10 a.m.-11:20 a.m. | SSK02-05 | Room E451A
In this talk, researchers will present a method of combining routine clinical data and natural language processing to create large datasets for deep learning and enhancing breast cancer diagnosis.
AI-based software could reduce unnecessary biopsies
Wednesday, November 29 | 11:20 a.m.-11:30 a.m. | SSK01-06 | Room E450A
A group from the University of Southern California will discuss the performance of a quantitative computer-aided detection software application that uses deep learning and artificial intelligence (AI) to improve mammography screening.
Breast parenchymal patterns aid breast cancer evaluation
Wednesday, November 29 | 11:30 a.m.-11:40 a.m. | SSK02-07 | Room E451A
Using automated measurements of breast parenchymal patterns derived from synthesized digital breast tomosynthesis exams could help assess cancer risk, according to researchers from the University of Pennsylvania.
Machine-learning method shows promise for assessing breast cancer risk
Wednesday, November 29 | 11:40 a.m.-11:50 a.m. | SSK02-08 | Room E451A
In this session, researchers will present a machine-learning method for analyzing parenchymal patterns from digital mammography screening to assess breast cancer risk and how it may change over time.
Deep-learning method creates super-resolution mammo images
Thursday, November 30 | 12:15 p.m.-12:45 p.m. | PH257-SD-THA3 | Lakeside, PH Community, Station 3
In this poster presentation, Japanese researchers will present a deep-learning technique that enhances mammography results to create super-resolution images.
Breast MRI neural networks predict recurrence scores
Friday, December 1 | 11:20 a.m.-11:30 a.m. | SST01-06 | Room E450B
Researchers in New York have found that deep-learning networks can be trained with breast MRI data to predict Oncotype DX recurrence scores.