Literature DB >> 31667873

Deep learning modeling using normal mammograms for predicting breast cancer risk.

Dooman Arefan1, Aly A Mohamed1, Wendie A Berg1,2, Margarita L Zuley1,2, Jules H Sumkin1,2, Shandong Wu3.   

Abstract

PURPOSE: To investigate two deep learning-based modeling schemes for predicting short-term risk of developing breast cancer using prior normal screening digital mammograms in a case-control setting.
METHODS: We conducted a retrospective Institutional Review Board-approved study on a case-control cohort of 226 patients (including 113 women diagnosed with breast cancer and 113 controls) who underwent general population breast cancer screening. For each patient, a prior normal (i.e., with negative or benign findings) digital mammogram examination [including mediolateral oblique (MLO) view and craniocaudal (CC) view two images] was collected. Thus, a total of 452 normal images (226 MLO view images and 226 CC view images) of this case-control cohort were analyzed to predict the outcome, i.e., developing breast cancer (cancer cases) or remaining breast cancer-free (controls) within the follow-up period. We implemented an end-to-end deep learning model and a GoogLeNet-LDA model and compared their effects in several experimental settings using two mammographic view images and inputting two different subregions of the images to the models. The proposed models were also compared to logistic regression modeling of mammographic breast density. Area under the receiver operating characteristic curve (AUC) was used as the model performance metric.
RESULTS: The highest AUC was 0.73 [95% Confidence Interval (CI): 0.68-0.78; GoogLeNet-LDA model on CC view] when using the whole-breast and was 0.72 (95% CI: 0.67-0.76; GoogLeNet-LDA model on MLO + CC view) when using the dense tissue, respectively, as the model input. The GoogleNet-LDA model significantly (all P < 0.05) outperformed the end-to-end GoogLeNet model in all experiments. CC view was consistently more predictive than MLO view in both deep learning models, regardless of the input subregions. Both models exhibited superior performance than the percent breast density (AUC = 0.54; 95% CI: 0.49-0.59).
CONCLUSIONS: The proposed deep learning modeling approach can predict short-term breast cancer risk using normal screening mammogram images. Larger studies are needed to further reveal the promise of deep learning in enhancing imaging-based breast cancer risk assessment.
© 2019 American Association of Physicists in Medicine.

Entities:  

Keywords:  breast cancer; breast density; deep learning; digital mammography; risk biomarkers

Mesh:

Year:  2019        PMID: 31667873      PMCID: PMC6980268          DOI: 10.1002/mp.13886

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  35 in total

1.  Mammographic density and the risk and detection of breast cancer.

Authors:  Norman F Boyd; Helen Guo; Lisa J Martin; Limei Sun; Jennifer Stone; Eve Fishell; Roberta A Jong; Greg Hislop; Anna Chiarelli; Salomon Minkin; Martin J Yaffe
Journal:  N Engl J Med       Date:  2007-01-18       Impact factor: 91.245

2.  Breast Cancer Surveillance Consortium: a national mammography screening and outcomes database.

Authors:  R Ballard-Barbash; S H Taplin; B C Yankaskas; V L Ernster; R D Rosenberg; P A Carney; W E Barlow; B M Geller; K Kerlikowske; B K Edwards; C F Lynch; N Urban; C A Chrvala; C R Key; S P Poplack; J K Worden; L G Kessler
Journal:  AJR Am J Roentgenol       Date:  1997-10       Impact factor: 3.959

3.  Improving the Mann-Whitney statistical test for feature selection: an approach in breast cancer diagnosis on mammography.

Authors:  Noel Pérez Pérez; Miguel A Guevara López; Augusto Silva; Isabel Ramos
Journal:  Artif Intell Med       Date:  2014-12-12       Impact factor: 5.326

4.  Validation studies for models projecting the risk of invasive and total breast cancer incidence.

Authors:  J P Costantino; M H Gail; D Pee; S Anderson; C K Redmond; J Benichou; H S Wieand
Journal:  J Natl Cancer Inst       Date:  1999-09-15       Impact factor: 13.506

5.  Estimation of breast percent density in raw and processed full field digital mammography images via adaptive fuzzy c-means clustering and support vector machine segmentation.

Authors:  Brad M Keller; Diane L Nathan; Yan Wang; Yuanjie Zheng; James C Gee; Emily F Conant; Despina Kontos
Journal:  Med Phys       Date:  2012-08       Impact factor: 4.071

6.  An evaluation of image descriptors combined with clinical data for breast cancer diagnosis.

Authors:  Daniel C Moura; Miguel A Guevara López
Journal:  Int J Comput Assist Radiol Surg       Date:  2013-04-13       Impact factor: 2.924

7.  SD-CNN: A shallow-deep CNN for improved breast cancer diagnosis.

Authors:  Fei Gao; Teresa Wu; Jing Li; Bin Zheng; Lingxiang Ruan; Desheng Shang; Bhavika Patel
Journal:  Comput Med Imaging Graph       Date:  2018-09-22       Impact factor: 4.790

8.  Deep Learning to Distinguish Recalled but Benign Mammography Images in Breast Cancer Screening.

Authors:  Sarah S Aboutalib; Aly A Mohamed; Wendie A Berg; Margarita L Zuley; Jules H Sumkin; Shandong Wu
Journal:  Clin Cancer Res       Date:  2018-10-11       Impact factor: 12.531

9.  Classification of Whole Mammogram and Tomosynthesis Images Using Deep Convolutional Neural Networks.

Authors:  Xiaofei Zhang; Yi Zhang; Erik Y Han; Nathan Jacobs; Qiong Han; Xiaoqin Wang; Jinze Liu
Journal:  IEEE Trans Nanobioscience       Date:  2018-06-07       Impact factor: 2.935

Review 10.  Beyond breast density: a review on the advancing role of parenchymal texture analysis in breast cancer risk assessment.

Authors:  Aimilia Gastounioti; Emily F Conant; Despina Kontos
Journal:  Breast Cancer Res       Date:  2016-09-20       Impact factor: 6.466

View more
  6 in total

1.  Prediction of Breast Cancer using Machine Learning Approaches.

Authors:  Reza Rabiei; Seyed Mohammad Ayyoubzadeh; Solmaz Sohrabei; Marzieh Esmaeili; Alireza Atashi
Journal:  J Biomed Phys Eng       Date:  2022-06-01

2.  Biosignal Compression Toolbox for Digital Biomarker Discovery.

Authors:  Brinnae Bent; Baiying Lu; Juseong Kim; Jessilyn P Dunn
Journal:  Sensors (Basel)       Date:  2021-01-13       Impact factor: 3.576

3.  The digital biomarker discovery pipeline: An open-source software platform for the development of digital biomarkers using mHealth and wearables data.

Authors:  Brinnae Bent; Ke Wang; Emilia Grzesiak; Chentian Jiang; Yuankai Qi; Yihang Jiang; Peter Cho; Kyle Zingler; Felix Ikponmwosa Ogbeide; Arthur Zhao; Ryan Runge; Ida Sim; Jessilyn Dunn
Journal:  J Clin Transl Sci       Date:  2020-07-14

4.  Breast lesions classifications of mammographic images using a deep convolutional neural network-based approach.

Authors:  Tariq Mahmood; Jianqiang Li; Yan Pei; Faheem Akhtar; Mujeeb Ur Rehman; Shahbaz Hassan Wasti
Journal:  PLoS One       Date:  2022-01-27       Impact factor: 3.240

Review 5.  Artificial intelligence in mammographic phenotyping of breast cancer risk: a narrative review.

Authors:  Aimilia Gastounioti; Shyam Desai; Vinayak S Ahluwalia; Emily F Conant; Despina Kontos
Journal:  Breast Cancer Res       Date:  2022-02-20       Impact factor: 8.408

6.  Deep learning-based breast region extraction of mammographic images combining pre-processing methods and semantic segmentation supported by Deeplab v3.

Authors:  Kuochen Zhou; Wei Li; Dazhe Zhao
Journal:  Technol Health Care       Date:  2022       Impact factor: 1.205

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.