Literature DB >> 33001309

Prediction of breast cancer molecular subtypes on DCE-MRI using convolutional neural network with transfer learning between two centers.

Yang Zhang1, Jeon-Hor Chen2, Yezhi Lin3, Siwa Chan4, Jiejie Zhou3, Daniel Chow1, Peter Chang1, Tiffany Kwong1, Dah-Cherng Yeh4, Xinxin Wang1, Ritesh Parajuli5, Rita S Mehta5, Meihao Wang6, Min-Ying Su7,8.   

Abstract

OBJECTIVES: To apply deep learning algorithms using a conventional convolutional neural network (CNN) and a recurrent CNN to differentiate three breast cancer molecular subtypes on MRI.
METHODS: A total of 244 patients were analyzed, 99 in training dataset scanned at 1.5 T and 83 in testing-1 and 62 in testing-2 scanned at 3 T. Patients were classified into 3 subtypes based on hormonal receptor (HR) and HER2 receptor: (HR+/HER2-), HER2+, and triple negative (TN). Only images acquired in the DCE sequence were used in the analysis. The smallest bounding box covering tumor ROI was used as the input for deep learning to develop the model in the training dataset, by using a conventional CNN and the convolutional long short-term memory (CLSTM). Then, transfer learning was applied to re-tune the model using testing-1(2) and evaluated in testing-2(1).
RESULTS: In the training dataset, the mean accuracy evaluated using tenfold cross-validation was higher by using CLSTM (0.91) than by using CNN (0.79). When the developed model was applied to the independent testing datasets, the accuracy was 0.4-0.5. With transfer learning by re-tuning parameters in testing-1, the mean accuracy reached 0.91 by CNN and 0.83 by CLSTM, and improved accuracy in testing-2 from 0.47 to 0.78 by CNN and from 0.39 to 0.74 by CLSTM. Overall, transfer learning could improve the classification accuracy by greater than 30%.
CONCLUSIONS: The recurrent network using CLSTM could track changes in signal intensity during DCE acquisition, and achieved a higher accuracy compared with conventional CNN during training. For datasets acquired using different settings, transfer learning can be applied to re-tune the model and improve accuracy. KEY POINTS: • Deep learning can be applied to differentiate breast cancer molecular subtypes. • The recurrent neural network using CLSTM could track the change of signal intensity in DCE images, and achieved a higher accuracy compared with conventional CNN during training. • For datasets acquired using different scanners with different imaging protocols, transfer learning provided an efficient method to re-tune the classification model and improve accuracy.

Entities:  

Keywords:  Breast neoplasms; Machine learning; Magnetic resonance imaging; Receptor, ErbB-2; Receptors, estrogen

Mesh:

Year:  2020        PMID: 33001309     DOI: 10.1007/s00330-020-07274-x

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  8 in total

Review 1.  AI in spotting high-risk characteristics of medical imaging and molecular pathology.

Authors:  Chong Zhang; Jionghui Gu; Yangyang Zhu; Zheling Meng; Tong Tong; Dongyang Li; Zhenyu Liu; Yang Du; Kun Wang; Jie Tian
Journal:  Precis Clin Med       Date:  2021-12-04

2.  BI-RADS Reading of Non-Mass Lesions on DCE-MRI and Differential Diagnosis Performed by Radiomics and Deep Learning.

Authors:  Jiejie Zhou; Yan-Lin Liu; Yang Zhang; Jeon-Hor Chen; Freddie J Combs; Ritesh Parajuli; Rita S Mehta; Huiru Liu; Zhongwei Chen; Youfan Zhao; Zhifang Pan; Meihao Wang; Risheng Yu; Min-Ying Su
Journal:  Front Oncol       Date:  2021-11-01       Impact factor: 6.244

3.  Breast cancer diagnosis in an early stage using novel deep learning with hybrid optimization technique.

Authors:  Kranti Kumar Dewangan; Deepak Kumar Dewangan; Satya Prakash Sahu; Rekhram Janghel
Journal:  Multimed Tools Appl       Date:  2022-02-25       Impact factor: 2.577

4.  ABCanDroid: A Cloud Integrated Android App for Noninvasive Early Breast Cancer Detection Using Transfer Learning.

Authors:  Deepraj Chowdhury; Anik Das; Ajoy Dey; Shreya Sarkar; Ashutosh Dhar Dwivedi; Raghava Rao Mukkamala; Lakhindar Murmu
Journal:  Sensors (Basel)       Date:  2022-01-22       Impact factor: 3.576

5.  Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients.

Authors:  Hyun-Soo Park; Kwang-Sig Lee; Bo-Kyoung Seo; Eun-Sil Kim; Kyu-Ran Cho; Ok-Hee Woo; Sung-Eun Song; Ji-Young Lee; Jaehyung Cha
Journal:  Cancers (Basel)       Date:  2021-11-29       Impact factor: 6.639

6.  BRCA Variations Risk Assessment in Breast Cancers Using Different Artificial Intelligence Models.

Authors:  Niyazi Senturk; Gulten Tuncel; Berkcan Dogan; Lamiya Aliyeva; Mehmet Sait Dundar; Sebnem Ozemri Sag; Gamze Mocan; Sehime Gulsun Temel; Munis Dundar; Mahmut Cerkez Ergoren
Journal:  Genes (Basel)       Date:  2021-11-09       Impact factor: 4.096

7.  Development and validation of a deep learning model for breast lesion segmentation and characterization in multiparametric MRI.

Authors:  Jingjin Zhu; Jiahui Geng; Wei Shan; Boya Zhang; Huaqing Shen; Xiaohan Dong; Mei Liu; Xiru Li; Liuquan Cheng
Journal:  Front Oncol       Date:  2022-08-11       Impact factor: 5.738

Review 8.  Deep learning in breast imaging.

Authors:  Arka Bhowmik; Sarah Eskreis-Winkler
Journal:  BJR Open       Date:  2022-05-13
  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.