Literature DB >> 31675151

Diagnosis of Benign and Malignant Breast Lesions on DCE-MRI by Using Radiomics and Deep Learning With Consideration of Peritumor Tissue.

Jiejie Zhou1, Yang Zhang2, Kai-Ting Chang2, Kyoung Eun Lee3, Ouchen Wang4, Jiance Li1, Yezhi Lin5, Zhifang Pan5, Peter Chang2, Daniel Chow2, Meihao Wang1, Min-Ying Su2.   

Abstract

BACKGROUND: Computer-aided methods have been widely applied to diagnose lesions detected on breast MRI, but fully-automatic diagnosis using deep learning is rarely reported.
PURPOSE: To evaluate the diagnostic accuracy of mass lesions using region of interest (ROI)-based, radiomics and deep-learning methods, by taking peritumor tissues into consideration. STUDY TYPE: Retrospective. POPULATION: In all, 133 patients with histologically confirmed 91 malignant and 62 benign mass lesions for training (74 patients with 48 malignant and 26 benign lesions for testing). FIELD STRENGTH/SEQUENCE: 3T, using the volume imaging for breast assessment (VIBRANT) dynamic contrast-enhanced (DCE) sequence. ASSESSMENT: 3D tumor segmentation was done automatically by using fuzzy-C-means algorithm with connected-component labeling. A total of 99 texture and histogram parameters were calculated for each case, and 15 were selected using random forest to build a radiomics model. Deep learning was implemented using ResNet50, evaluated with 10-fold crossvalidation. The tumor alone, smallest bounding box, and 1.2, 1.5, 2.0 times enlarged boxes were used as inputs. STATISTICAL TESTS: The malignancy probability was calculated using each model, and the threshold of 0.5 was used to make a diagnosis.
RESULTS: In the training dataset, the diagnostic accuracy was 76% using three ROI-based parameters, 84% using the radiomics model, and 86% using ROI + radiomics model. In deep learning using the per-slice basis, the area under the receiver operating characteristic (ROC) was comparable for tumor alone, smallest and 1.2 times box (AUC = 0.97-0.99), which were significantly higher than 1.5 and 2.0 times box (AUC = 0.86 and 0.71, respectively). For per-lesion diagnosis, the highest accuracy of 91% was achieved when using the smallest bounding box, and that decreased to 84% for tumor alone and 1.2 times box, and further to 73% for 1.5 times box and 69% for 2.0 times box. In the independent testing dataset, the per-lesion diagnostic accuracy was also the highest when using the smallest bounding box, 89%. DATA
CONCLUSION: Deep learning using ResNet50 achieved a high diagnostic accuracy. Using the smallest bounding box containing proximal peritumor tissue as input had higher accuracy compared to using tumor alone or larger boxes. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2.
© 2019 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  DCE-MRI; ResNet; breast cancer diagnosis; deep learning; peritumor tissue; radiomics

Mesh:

Substances:

Year:  2019        PMID: 31675151      PMCID: PMC7709823          DOI: 10.1002/jmri.26981

Source DB:  PubMed          Journal:  J Magn Reson Imaging        ISSN: 1053-1807            Impact factor:   4.813


  41 in total

1.  Radiomic versus Convolutional Neural Networks Analysis for Classification of Contrast-enhancing Lesions at Multiparametric Breast MRI.

Authors:  Daniel Truhn; Simone Schrading; Christoph Haarburger; Hannah Schneider; Dorit Merhof; Christiane Kuhl
Journal:  Radiology       Date:  2018-11-13       Impact factor: 11.105

Review 2.  Field effect in cancer-an update.

Authors:  Hong Chai; Robert E Brown
Journal:  Ann Clin Lab Sci       Date:  2009       Impact factor: 1.256

Review 3.  The role of the microenvironment in tumor growth and invasion.

Authors:  Yangjin Kim; Magdalena A Stolarska; Hans G Othmer
Journal:  Prog Biophys Mol Biol       Date:  2011-06-28       Impact factor: 3.667

Review 4.  Artificial intelligence in the interpretation of breast cancer on MRI.

Authors:  Deepa Sheth; Maryellen L Giger
Journal:  J Magn Reson Imaging       Date:  2019-07-25       Impact factor: 4.813

Review 5.  Artificial intelligence in radiology.

Authors:  Ahmed Hosny; Chintan Parmar; John Quackenbush; Lawrence H Schwartz; Hugo J W L Aerts
Journal:  Nat Rev Cancer       Date:  2018-08       Impact factor: 60.716

6.  Quantitative analysis of lesion morphology and texture features for diagnostic prediction in breast MRI.

Authors:  Ke Nie; Jeon-Hor Chen; Hon J Yu; Yong Chu; Orhan Nalcioglu; Min-Ying Su
Journal:  Acad Radiol       Date:  2008-12       Impact factor: 3.173

7.  Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set.

Authors:  Hui Li; Yitan Zhu; Elizabeth S Burnside; Erich Huang; Karen Drukker; Katherine A Hoadley; Cheng Fan; Suzanne D Conzen; Margarita Zuley; Jose M Net; Elizabeth Sutton; Gary J Whitman; Elizabeth Morris; Charles M Perou; Yuan Ji; Maryellen L Giger
Journal:  NPJ Breast Cancer       Date:  2016-05-11

Review 8.  Contrast-enhanced MRI for breast cancer screening.

Authors:  Ritse M Mann; Christiane K Kuhl; Linda Moy
Journal:  J Magn Reson Imaging       Date:  2019-01-18       Impact factor: 4.813

9.  The relationship between lymphovascular invasion and angiogenesis, hormone receptors, cell proliferation and survival in patients with primary operable invasive ductal breast cancer.

Authors:  Donald C McMillan; Joanne Edwards; Elizabeth Mallon; Julie C Doughty; Clare Orange; James J Going; Zahra Ma Mohammed
Journal:  BMC Clin Pathol       Date:  2013-11-25

10.  Radiomics: Images Are More than Pictures, They Are Data.

Authors:  Robert J Gillies; Paul E Kinahan; Hedvig Hricak
Journal:  Radiology       Date:  2015-11-18       Impact factor: 11.105

View more
  29 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.  Ureteral calculi lithotripsy for single ureteral calculi: can DNN-assisted model help preoperatively predict risk factors for sepsis?

Authors:  Mingzhen Chen; Jiannan Yang; Junlin Lu; Ziling Zhou; Kun Huang; Sihan Zhang; Guanjie Yuan; Qingpeng Zhang; Zhen Li
Journal:  Eur Radiol       Date:  2022-06-22       Impact factor: 5.315

3.  Combined diagnosis of multiparametric MRI-based deep learning models facilitates differentiating triple-negative breast cancer from fibroadenoma magnetic resonance BI-RADS 4 lesions.

Authors:  Hao-Lin Yin; Yu Jiang; Zihan Xu; Hui-Hui Jia; Guang-Wu Lin
Journal:  J Cancer Res Clin Oncol       Date:  2022-06-30       Impact factor: 4.553

4.  Intratumoral and peritumoral radiomics based on dynamic contrast-enhanced MRI for preoperative prediction of intraductal component in invasive breast cancer.

Authors:  Hao Xu; Jieke Liu; Zhe Chen; Chunhua Wang; Yuanyuan Liu; Min Wang; Peng Zhou; Hongbing Luo; Jing Ren
Journal:  Eur Radiol       Date:  2022-01-25       Impact factor: 5.315

5.  A Bounding Box-Based Radiomics Model for Detecting Occult Peritoneal Metastasis in Advanced Gastric Cancer: A Multicenter Study.

Authors:  Dan Liu; Weihan Zhang; Fubi Hu; Pengxin Yu; Xiao Zhang; Hongkun Yin; Lanqing Yang; Xin Fang; Bin Song; Bing Wu; Jiankun Hu; Zixing Huang
Journal:  Front Oncol       Date:  2021-12-03       Impact factor: 6.244

6.  Intra- and peritumoral radiomics on assessment of breast cancer molecular subtypes based on mammography and MRI.

Authors:  Shuxian Niu; Wenyan Jiang; Nannan Zhao; Tao Jiang; Yue Dong; Yahong Luo; Tao Yu; Xiran Jiang
Journal:  J Cancer Res Clin Oncol       Date:  2021-10-08       Impact factor: 4.553

Review 7.  Radiomics in breast MRI: current progress toward clinical application in the era of artificial intelligence.

Authors:  Hiroko Satake; Satoko Ishigaki; Rintaro Ito; Shinji Naganawa
Journal:  Radiol Med       Date:  2021-10-26       Impact factor: 3.469

8.  Clinical-Radiomic Analysis for Pretreatment Prediction of Objective Response to First Transarterial Chemoembolization in Hepatocellular Carcinoma.

Authors:  Mingyu Chen; Jiasheng Cao; Jiahao Hu; Win Topatana; Shijie Li; Sarun Juengpanich; Jian Lin; Chenhao Tong; Jiliang Shen; Bin Zhang; Jennifer Wu; Christine Pocha; Masatoshi Kudo; Amedeo Amedei; Franco Trevisani; Pil Soo Sung; Victor M Zaydfudim; Tatsuo Kanda; Xiujun Cai
Journal:  Liver Cancer       Date:  2021-01-07       Impact factor: 11.740

9.  Diagnostic performance of perilesional radiomics analysis of contrast-enhanced mammography for the differentiation of benign and malignant breast lesions.

Authors:  Simin Wang; Yuqi Sun; Ruimin Li; Ning Mao; Qin Li; Tingting Jiang; Qianqian Chen; Shaofeng Duan; Haizhu Xie; Yajia Gu
Journal:  Eur Radiol       Date:  2021-06-29       Impact factor: 5.315

10.  Texture Analysis of DCE-MRI Intratumoral Subregions to Identify Benign and Malignant Breast Tumors.

Authors:  Bin Zhang; Lirong Song; Jiandong Yin
Journal:  Front Oncol       Date:  2021-07-08       Impact factor: 6.244

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.