Literature DB >> 29398498

Prediction of Occult Invasive Disease in Ductal Carcinoma in Situ Using Deep Learning Features.

Bibo Shi1, Lars J Grimm2, Maciej A Mazurowski2, Jay A Baker2, Jeffrey R Marks3, Lorraine M King3, Carlo C Maley4, E Shelley Hwang3, Joseph Y Lo2.   

Abstract

PURPOSE: The aim of this study was to determine whether deep features extracted from digital mammograms using a pretrained deep convolutional neural network are prognostic of occult invasive disease for patients with ductal carcinoma in situ (DCIS) on core needle biopsy.
METHODS: In this retrospective study, digital mammographic magnification views were collected for 99 subjects with DCIS at biopsy, 25 of which were subsequently upstaged to invasive cancer. A deep convolutional neural network model that was pretrained on nonmedical images (eg, animals, plants, instruments) was used as the feature extractor. Through a statistical pooling strategy, deep features were extracted at different levels of convolutional layers from the lesion areas, without sacrificing the original resolution or distorting the underlying topology. A multivariate classifier was then trained to predict which tumors contain occult invasive disease. This was compared with the performance of traditional "handcrafted" computer vision (CV) features previously developed specifically to assess mammographic calcifications. The generalization performance was assessed using Monte Carlo cross-validation and receiver operating characteristic curve analysis.
RESULTS: Deep features were able to distinguish DCIS with occult invasion from pure DCIS, with an area under the receiver operating characteristic curve of 0.70 (95% confidence interval, 0.68-0.73). This performance was comparable with the handcrafted CV features (area under the curve = 0.68; 95% confidence interval, 0.66-0.71) that were designed with prior domain knowledge.
CONCLUSIONS: Despite being pretrained on only nonmedical images, the deep features extracted from digital mammograms demonstrated comparable performance with handcrafted CV features for the challenging task of predicting DCIS upstaging.
Copyright © 2017 American College of Radiology. Published by Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Ductal carcinoma in situ; computer vision; convolution neural network; deep learning; digital mammography

Mesh:

Year:  2018        PMID: 29398498      PMCID: PMC5837927          DOI: 10.1016/j.jacr.2017.11.036

Source DB:  PubMed          Journal:  J Am Coll Radiol        ISSN: 1546-1440            Impact factor:   5.532


  24 in total

1.  Predicting invasion in mammographically detected microcalcification.

Authors:  M J Bagnall; A J Evans; A R Wilson; S E Pinder; H Denley; J G Geraghty; I O Ellis
Journal:  Clin Radiol       Date:  2001-10       Impact factor: 2.350

2.  Computationally efficient confidence intervals for cross-validated area under the ROC curve estimates.

Authors:  Erin LeDell; Maya Petersen; Mark van der Laan
Journal:  Electron J Stat       Date:  2015       Impact factor: 1.125

3.  Transfer representation learning for medical image analysis.

Authors:  Edward Y Chang
Journal:  Conf Proc IEEE Eng Med Biol Soc       Date:  2015-08

4.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.

Authors:  Varun Gulshan; Lily Peng; Marc Coram; Martin C Stumpe; Derek Wu; Arunachalam Narayanaswamy; Subhashini Venugopalan; Kasumi Widner; Tom Madams; Jorge Cuadros; Ramasamy Kim; Rajiv Raman; Philip C Nelson; Jessica L Mega; Dale R Webster
Journal:  JAMA       Date:  2016-12-13       Impact factor: 56.272

5.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases.

Authors:  J A Hanley; B J McNeil
Journal:  Radiology       Date:  1983-09       Impact factor: 11.105

6.  Ductal carcinoma in situ diagnosed with stereotactic core needle biopsy: can invasion be predicted?

Authors:  C H Lee; D Carter; L E Philpotts; M E Couce; L J Horvath; R C Lange; I Tocino
Journal:  Radiology       Date:  2000-11       Impact factor: 11.105

7.  Predictors of invasive disease in breast cancer when core biopsy demonstrates DCIS only.

Authors:  Mary F Dillon; Enda W McDermott; Cecily M Quinn; Ann O'Doherty; Niall O'Higgins; Arnold D K Hill
Journal:  J Surg Oncol       Date:  2006-06-01       Impact factor: 3.454

Review 8.  The natural history of ductal carcinoma in situ of the breast: a review.

Authors:  Bircan Erbas; Elena Provenzano; Jane Armes; Dorota Gertig
Journal:  Breast Cancer Res Treat       Date:  2005-12-01       Impact factor: 4.872

9.  Preoperative clinicopathologic factors and breast magnetic resonance imaging features can predict ductal carcinoma in situ with invasive components.

Authors:  Chih-Wei Lee; Hwa-Koon Wu; Hung-Wen Lai; Wen-Pei Wu; Shou-Tung Chen; Dar-Ren Chen; Chih-Jung Chen; Shou-Jen Kuo
Journal:  Eur J Radiol       Date:  2016-01-02       Impact factor: 3.528

10.  Deep Feature Transfer Learning in Combination with Traditional Features Predicts Survival Among Patients with Lung Adenocarcinoma.

Authors:  Rahul Paul; Samuel H Hawkins; Yoganand Balagurunathan; Matthew B Schabath; Robert J Gillies; Lawrence O Hall; Dmitry B Goldgof
Journal:  Tomography       Date:  2016-12
View more
  19 in total

Review 1.  Deep learning in breast radiology: current progress and future directions.

Authors:  William C Ou; Dogan Polat; Basak E Dogan
Journal:  Eur Radiol       Date:  2021-01-15       Impact factor: 5.315

2.  Artificial intelligence using neural network architecture for radiology (AINNAR): classification of MR imaging sequences.

Authors:  Tomoyuki Noguchi; Daichi Higa; Takashi Asada; Yusuke Kawata; Akihiro Machitori; Yoshitaka Shida; Takashi Okafuji; Kota Yokoyama; Fumiya Uchiyama; Tsuyoshi Tajima
Journal:  Jpn J Radiol       Date:  2018-09-19       Impact factor: 2.374

Review 3.  Intratumoral Heterogeneity in Ductal Carcinoma In Situ: Chaos and Consequence.

Authors:  Vidya C Sinha; Helen Piwnica-Worms
Journal:  J Mammary Gland Biol Neoplasia       Date:  2018-09-07       Impact factor: 2.673

Review 4.  Ductal carcinoma in situ of breast: update 2019.

Authors:  Sunil S Badve; Yesim Gökmen-Polar
Journal:  Pathology       Date:  2019-08-28       Impact factor: 5.306

Review 5.  CAD and AI for breast cancer-recent development and challenges.

Authors:  Heang-Ping Chan; Ravi K Samala; Lubomir M Hadjiiski
Journal:  Br J Radiol       Date:  2019-12-16       Impact factor: 3.039

Review 6.  Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives.

Authors:  Krzysztof J Geras; Ritse M Mann; Linda Moy
Journal:  Radiology       Date:  2019-09-24       Impact factor: 11.105

7.  Artificial Intelligence in Imaging: The Radiologist's Role.

Authors:  Daniel L Rubin
Journal:  J Am Coll Radiol       Date:  2019-09       Impact factor: 5.532

Review 8.  Artificial Intelligence: A Primer for Breast Imaging Radiologists.

Authors:  Manisha Bahl
Journal:  J Breast Imaging       Date:  2020-06-19

9.  Prediction of Upstaged Ductal Carcinoma In Situ Using Forced Labeling and Domain Adaptation.

Authors:  Rui Hou; Maciej A Mazurowski; Lars J Grimm; Jeffrey R Marks; Lorraine M King; Carlo C Maley; Eun-Sil Shelley Hwang; Joseph Y Lo
Journal:  IEEE Trans Biomed Eng       Date:  2019-09-09       Impact factor: 4.538

10.  Potential Role of Convolutional Neural Network Based Algorithm in Patient Selection for DCIS Observation Trials Using a Mammogram Dataset.

Authors:  Simukayi Mutasa; Peter Chang; Eduardo P Van Sant; John Nemer; Michael Liu; Jenika Karcich; Gita Patel; Sachin Jambawalikar; Richard Ha
Journal:  Acad Radiol       Date:  2019-09-14       Impact factor: 3.173

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.