News | Artificial Intelligence | December 18, 2019

AI Improves Breast Cancer Risk Prediction

A new study published in Radiology suggests that a type of AI can outperform existing breast cancer screening models

Patient inclusion flowchart shows selection of women in the training and validation samples used for deep neural network development, as well as in the test sample (current study sample). Exclusions are detailed in the footnote. PACS = picture archiving and communication system. Image courtesy of Radiological Society of North America.

Patient inclusion flowchart shows selection of women in the training and validation samples used for deep neural network development, as well as in the test sample (current study sample). Exclusions are detailed in the footnote. PACS = picture archiving and communication system. Image courtesy of Radiological Society of North America.

December 17, 2019 — A sophisticated type of artificial intelligence (AI) can outperform existing models at predicting which women are at future risk of breast cancer, according to a study published in the journal Radiology.

Most existing breast cancer screening programs are based on mammography at similar time intervals — typically, annually or every two years — for all women. This “one size fits all” approach is not optimized for cancer detection on an individual level and may hamper the effectiveness of screening programs.

“Risk prediction is an important building block of an individually adapted screening policy,” said study lead author Karin Dembrower, M.D., breast radiologist and Ph.D. candidate from the Karolinska Institute in Stockholm, Sweden. “Effective risk prediction can improve attendance and confidence in screening programs.”

High breast density, or a greater amount of glandular and connective tissue compared to fat, is considered a risk factor for cancer. While density may be incorporated into risk assessment, current prediction models may fail to fully take advantage of all the rich information found in mammograms. This information has the potential to identify women who would benefit from additional screening with magnetic resonance imaging (MRI).

Dembrower and colleagues developed a risk model that relies on a deep neural network, a type of AI that can extract vast amounts of information from mammographic images. It has inherent advantages over other methods like visual assessment of mammographic density by the radiologist that may not be able to capture all risk-relevant information in the image. The new model was developed and trained on mammograms from cases diagnosed between 2008 and 2012 and then studied on more than 2,000 women ages 40 to 74 who had undergone mammography in the Karolinska University Hospital system. Of the 2,283 women in the study, 278 were later diagnosed with breast cancer.

The deep neural network showed a higher risk association for breast cancer compared to the best mammographic density model. The false negative rate — the rate at which women who were not categorized as high-risk were later diagnosed with breast cancer — was lower for the deep neural network than for the best mammographic density model.

“The deep neural network overall was better than density-based models,” Dembrower said. “And it did not have the same bias as the density-based model. Its predictive accuracy was not negatively affected by more aggressive cancer subtypes.”

The study findings support a future role for AI in breast cancer risk assessment.

“We are not reporting mammographic density currently,” Dembrower said. “In the introduction of individually adapted screening, we use deep learning networks trained to predict cancer rather than taking the indirect route that density offers.”

As an additional benefit, the AI approach can continually be improved with exposure to more high-quality data sets.

“Our deep learning experts at the Royal Institute of Technology in Stockholm are working on an update to the model,” Dembrower said. “After that, we aim to test the model clinically next year by offering MRI to the women who stand to benefit the most.”

For more information: www.rsna.org

 

Related content:

Hologic Announces FDA Approval of 3DQuorum Imaging Technology, Powered by Genius AI

Study Finds iCAD's ProFound AI Improves Efficiency and Accuracy in Breast Cancer Detection

Related Content

Findings indicate that PPC and GG are highly predictive of overall upstaging by PSMA PET/CT for patients with high-risk prostate cancer

Image courtesy of UCLA Health

News | PET-CT | February 23, 2021
February 23, 2021 — A...
icobrain cva allows the quantitative assessment of tissue perfusion by reporting the volume of core and perfusion lesion by quantifying Tmax abnormality and CBF abnormality together with the mismatch volume and ratio
News | Artificial Intelligence | February 23, 2021
February 23, 2021 — icometrix, world leader in imaging...
F-18 FES PET images of patients with ER+/PR+/HER2- invasive ductal carcinoma. Left panel: Progressive disease seen at the 8-week time-point in a patient on sequential therapy. Right panel: Stable disease through all 3 time-points, remaining on study therapy for 6.7 months until disease progression on combined vorinostat aromatase inhibitor therapy. Image created by Lanell M Peterson, Research Scientist, University of Washington Medical Oncology, Seattle WA.

F-18 FES PET images of patients with ER+/PR+/HER2- invasive ductal carcinoma. Left panel: Progressive disease seen at the 8-week time-point in a patient on sequential therapy. Right panel: Stable disease through all 3 time-points, remaining on study therapy for 6.7 months until disease progression on combined vorinostat aromatase inhibitor therapy. Image created by Lanell M Peterson, Research Scientist, University of Washington Medical Oncology, Seattle WA.

News | Molecular Imaging | February 22, 2021
February 22, 2021 — Molecular imaging
Axial FLAIR MR image shows T2 prolongation in bilateral middle cerebellar peduncles (arrows). Findings were associated with restricted diffusion and areas of T1 hypointense signal without enhancement or abnormal susceptibility. Image courtesy of American Roentgen Ray Society (ARRS), American Journal of Roentgenology (AJR)

Axial FLAIR MR image shows T2 prolongation in bilateral middle cerebellar peduncles (arrows). Findings were associated with restricted diffusion and areas of T1 hypointense signal without enhancement or abnormal susceptibility. Image courtesy of American Roentgen Ray Society (ARRS), American Journal of Roentgenology (AJR)

News | Coronavirus (COVID-19) | February 22, 2021
February 22, 2021 — According to an...
Examples of the imaging performance of XPCI-CT (b,e) compared to conventional specimen radiography (a,d) and benchmarked against histopathology (c,f). he top row focuses on the similarity between the XPCI-CT slice in (b) and the histological slice in (c). Arrow 1 indicates margin involvement, arrow 2 a variation in density in the internal structure of the tumour mass, arrow 3 tumour-induced inflammation. All this is confirmed by the histological slice in (c), and hardly visible in the conventional image in

Examples of the imaging performance of XPCI-CT (b,e) compared to conventional specimen radiography (a,d) and benchmarked against histopathology (c,f). he top row focuses on the similarity between the XPCI-CT slice in (b) and the histological slice in (c). Arrow 1 indicates margin involvement, arrow 2 a variation in density in the internal structure of the tumour mass, arrow 3 tumour-induced inflammation. All this is confirmed by the histological slice in (c), and hardly visible in the conventional image in (a). The bottom row focuses on the detection of small calcifications, a key feature in DCIS. These are undetectable in (d), detected in (e), enhanced in the maximum intensity projection (MIP) image at the bottom of (f), and confirmed by histopathology in the top part of (f). The scale bar [shown in (b) and (e)] is the same for all images apart from (f), which has its own scale. Red arrows in (e) and (f) indicate the microcalcifications. Image courtesy of Professor Alessandro Olivo

News | Breast Imaging | February 22, 2021
February 22, 2021 — A new X-ray imaging scanne
GE Healthcare introduced its artificial intelligence (AI) automation features on its Voluson Swift ultrasound platform at the 2020 Radiological Society of North America (RSNA) virtual meeting. Features of this system include semi-automated contouring, auto identification of fetal anatomy and positioning on imaging. AI is seeing increasing integration in ultrasound systems from numerous vendors.

GE Healthcare introduced its artificial intelligence (AI) automation features on its Voluson Swift ultrasound platform at the 2020 Radiological Society of North America (RSNA) virtual meeting. Features of this system include semi-automated contouring, auto identification of fetal anatomy and positioning on imaging. AI is seeing increasing integration in ultrasound systems from numerous vendors.

Feature | Ultrasound Imaging | February 18, 2021 | By Dave Fornell, Editor
Recent advances in ultrasound image sy...
Example MR images from paediatric brain tumour patients. This first column shows T1-weighted images following the injection of gadolinium contrast agent. The second column shows T2-weighted images and the final column shows apparent diffusion coefficient maps calculated from diffusion-weighted images. (a–c) are taken from a patient with a Pilocytic Astrocytoma, (d–f) are from a patient with an Ependymoma and (g–i) were acquired from a patient with a Medulloblastoma.

Example MR images from paediatric brain tumour patients. This first column shows T1-weighted images following the injection of gadolinium contrast agent. The second column shows T2-weighted images and the final column shows apparent diffusion coefficient maps calculated from diffusion-weighted images. (ac) are taken from a patient with a Pilocytic Astrocytoma, (df) are from a patient with an Ependymoma and (gi) were acquired from a patient with a Medulloblastoma. Image courtesy of Nature Research Journal

News | Pediatric Imaging | February 17, 2021
February 17, 2021 — Diffusio...
A comparison of standard mammography imaging (left) in a woman with dense breasts and a breast MRI imaging study (right) showing a clearly defined cancer and is extremely hard to detect on the mammograms.

A comparison of standard mammography imaging (left) in a woman with dense breasts and a breast MRI imaging study (right) showing a clearly defined cancer and is extremely hard to detect on the mammograms. Images from Christiane Kuhl, M.D.

Feature | MRI Breast | February 17, 2021 | By Dave Fornell, Editor
Dense breast tissue can hide cancers i
T1 structural images for the two sequences, MPRAGE and MPRAGE+PMC. The top row shows the MPRAGE sequence, while the bottom row shows the images that were generated with the MPRAGE+PMC sequence. Columns represent two different participants, one with minimal head motion (left, Low-Mover) and another with a large quantity of motion (right, High-Mover). Pial and white matter (WM) surface reconstruction from Freesurfer are also shown.

T1 structural images for the two sequences, MPRAGE and MPRAGE+PMC. The top row shows the MPRAGE sequence, while the bottom row shows the images that were generated with the MPRAGE+PMC sequence. Columns represent two different participants, one with minimal head motion (left, Low-Mover) and another with a large quantity of motion (right, High-Mover). Pial and white matter (WM) surface reconstruction from Freesurfer are also shown.

News | Magnetic Resonance Imaging (MRI) | February 17, 2021
February 17, 2021 — A new paper,...