An initial investigation on developing a new method to predict short-term breast cancer risk based on deep learning technology

2016 ◽  
Author(s):  
Yuchen Qiu ◽  
Yunzhi Wang ◽  
Shiju Yan ◽  
Maxine Tan ◽  
Samuel Cheng ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
New Method ◽  
Learning Technology ◽  
Short Term ◽  
Initial Investigation

Prediction of Short-Term Breast Cancer Risk Based on Deep Convolutional Neural Networks in Mammography

2019 ◽  
Vol 9 (8) ◽  
pp. 1663-1672
Author(s):  
Yane Li ◽  
Ming Fan ◽  
Shichen Liu ◽  
Bin Zheng ◽  
Lihua Li
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Risk Model ◽  
Risk Scores ◽  
Learning Models ◽  
Short Term ◽  
Deep Convolutional Neural Networks ◽  
Central Regions

This work investigated a novel framework of predicting short-term breast cancer risk by using a deep learning approach in mammography. A dataset of 675 negative screening cases were applied. 333 cases were cancer diagnosed at next screening, while 342 cases remained negative. In order to stratify these patients into high and low cancer risk group, we first used an automatically method to segment bilateral matched central regions from right and left mammography respectively. Then, three AlexNet, GoogLeNet and ResNet based deep learning models were established with ten-fold cross validation method for both difference image of bilateral matched central regions and two whole regions of bilateral breasts respectively. Using AlexNet-, GoogLeNet- and ResNet-based risk model, areas under ROC curves (AUC) are 0.56, 0.62 and 0.64 for central regions and 0.59, 0.57 and 0.65 for whole regions, respectively. When combining prediction scores of three deep learning models with a multi-agent fusion algorithm, AUCs are 0.67 and 0.67 for central regions and whole regions respectively. When fusing scores of central region-based risk model and whole region-based risk model, AUC significantly increases to 0.71 (p < 0.01). By dividing 675 cases into five subgroups based on sorting results of risk scores, the odds ratios had an significant increasing trend as the scores increased (p = 0 003). This study demonstrates feasibility of applying deep learning technology to assist investigating novel markers in mammography for helping assessment of short-term breast cancer risk and improving the efficiency of breast cancer screening in the future.

scholarly journals Transiently increased risk of breast cancer after childbirth: implications for fertility treatments and surrogacy

2020 ◽  
Vol 35 (6) ◽  
pp. 1253-1255
Author(s):  
Zeev Blumenfeld ◽  
Norbert Gleicher ◽  
Eli Y Adashi
Keyword(s):  
Breast Cancer ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Meta Analysis ◽  
Small Degree ◽  
Short Term ◽  
Benefit Ratio ◽  
Professional Societies ◽  
Fertility Treatments ◽  
Increased Risk

Abstract Whereas longstanding dogma has purported that pregnancies protect women from breast cancer, a recent meta-analysis now mandates reconsideration since it reported an actual higher breast cancer risk for more than two decades after childbirth before the relative risk turns negative. Moreover, the risk of breast cancer appears higher for women having their first birth at an older age and with a family history and it is not reduced by breastfeeding. The process of obtaining informed consent for all fertility treatments, therefore, must make patients aware of the facts that every pregnancy, to a small degree, will increase the short-term breast cancer risk. This observation may be even more relevant in cases of surrogacy where women agree to conceive without deriving benefits of offspring from assuming the risk, thus creating a substantially different risk-benefit ratio. Consequently, it appears prudent for professional societies in the field to update recommendations regarding consent information for all fertility treatments but especially for treatments involving surrogacy.

scholarly journals Deep learning modeling using normal mammograms for predicting breast cancer risk

2019 ◽  
Vol 47 (1) ◽  
pp. 110-118 ◽  
Author(s):  
Dooman Arefan ◽  
Aly A. Mohamed ◽  
Wendie A. Berg ◽  
Margarita L. Zuley ◽  
Jules H. Sumkin ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Breast Cancer Risk ◽  
Cancer Risk

Toward robust mammography-based models for breast cancer risk

2021 ◽  
Vol 13 (578) ◽  
pp. eaba4373 ◽  
Author(s):  
Adam Yala ◽  
Peter G. Mikhael ◽  
Fredrik Strand ◽  
Gigin Lin ◽  
Kevin Smith ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
High Risk ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Massachusetts General Hospital ◽  
The United States ◽  
University Hospital ◽  
Chang Gung Memorial Hospital ◽  
Risk Models

Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection and less screening harm than existing guidelines. To bring deep learning risk models to clinical practice, we need to further refine their accuracy, validate them across diverse populations, and demonstrate their potential to improve clinical workflows. We developed Mirai, a mammography-based deep learning model designed to predict risk at multiple timepoints, leverage potentially missing risk factor information, and produce predictions that are consistent across mammography machines. Mirai was trained on a large dataset from Massachusetts General Hospital (MGH) in the United States and tested on held-out test sets from MGH, Karolinska University Hospital in Sweden, and Chang Gung Memorial Hospital (CGMH) in Taiwan, obtaining C-indices of 0.76 (95% confidence interval, 0.74 to 0.80), 0.81 (0.79 to 0.82), and 0.79 (0.79 to 0.83), respectively. Mirai obtained significantly higher 5-year ROC AUCs than the Tyrer-Cuzick model (P < 0.001) and prior deep learning models Hybrid DL (P < 0.001) and Image-Only DL (P < 0.001), trained on the same dataset. Mirai more accurately identified high-risk patients than prior methods across all datasets. On the MGH test set, 41.5% (34.4 to 48.5) of patients who would develop cancer within 5 years were identified as high risk, compared with 36.1% (29.1 to 42.9) by Hybrid DL (P = 0.02) and 22.9% (15.9 to 29.6) by the Tyrer-Cuzick model (P < 0.001).

scholarly journals Short-term weight gain and breast cancer risk by hormone receptor classification among pre- and postmenopausal women

2015 ◽  
Vol 150 (3) ◽  
pp. 643-653 ◽  
Author(s):  
Bernard Rosner ◽  
A. Heather Eliassen ◽  
Adetunji T. Toriola ◽  
Susan E. Hankinson ◽  
Walter C. Willett ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Weight Gain ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Postmenopausal Women ◽  
Hormone Receptor ◽  
Short Term

Applying a CAD-generated imaging marker to assess short-term breast cancer risk

2018 ◽  
Author(s):  
Seyedehnafiseh Mirniaharikandehei ◽  
Ali Zarafshani ◽  
Morteza Heidari ◽  
Yunzhi Wang ◽  
Faranak Aghaei ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Short Term

Assessment of short-term breast cancer risk using a frequency domain correlation based imaging marker

2019 ◽  
Author(s):  
Morteza Heidari ◽  
Alan Hollingsworth ◽  
Seyedehnafiseh Mirniaharikandehei ◽  
Gopichandh Danala ◽  
Yuchen Qiu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Frequency Domain ◽  
Short Term

Automated breast cancer risk estimation on routine CT thorax scans by deep learning segmentation

2020 ◽  
Author(s):  
Stijn De Buck ◽  
Jeroen Bertels ◽  
Chelsey Vanbilsen ◽  
Tanguy Dewaele ◽  
Chantal Van Ongeval ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Risk Estimation

scholarly journals Detection of potential microcalcification clusters using multivendor for‐presentation digital mammograms for short‐term breast cancer risk estimation

2019 ◽  
Vol 46 (4) ◽  
pp. 1938-1946 ◽  
Author(s):  
Maya Alsheh Ali ◽  
Mikael Eriksson ◽  
Kamila Czene ◽  
Per Hall ◽  
Keith Humphreys
Keyword(s):  
Breast Cancer ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Risk Estimation ◽  
Short Term ◽  
Microcalcification Clusters
Sign in / Sign up

Export Citation Format

Share Document