A Robust and Efficient AI Assistant for Breast Tumor Segmentation from DCE-MRI Via a Spatial-temporal Framework

Overview

Journal Patterns (N Y)

Date 2023 Sep 18

PMID 37720328

Authors

Jiadong Zhang

Zhiming Cui

Zhenwei Shi

Yingjia Jiang

Zhiliang Zhang

Xiaoting Dai

Zhenlu Yang

Yuning Gu

Lei Zhou

Chu Han

Xiaomei Huang

Chenglu Ke

Suyun Li

Zeyan Xu

Fei Gao

Luping Zhou

Rongpin Wang

Jun Liu

Jiayin Zhang

Zhongxiang Ding

Kun Sun

Zhenhui Li

Zaiyi Liu

Dinggang Shen

Affiliations

Soon will be listed here.

Abstract

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) allows screening, follow up, and diagnosis for breast tumor with high sensitivity. Accurate tumor segmentation from DCE-MRI can provide crucial information of tumor location and shape, which significantly influences the downstream clinical decisions. In this paper, we aim to develop an artificial intelligence (AI) assistant to automatically segment breast tumors by capturing dynamic changes in multi-phase DCE-MRI with a spatial-temporal framework. The main advantages of our AI assistant include (1) robustness, i.e., our model can handle MR data with different phase numbers and imaging intervals, as demonstrated on a large-scale dataset from seven medical centers, and (2) efficiency, i.e., our AI assistant significantly reduces the time required for manual annotation by a factor of 20, while maintaining accuracy comparable to that of physicians. More importantly, as the fundamental step to build an AI-assisted breast cancer diagnosis system, our AI assistant will promote the application of AI in more clinical diagnostic practices regarding breast cancer.

Citing Articles

Reducing the workload of medical diagnosis through artificial intelligence: A narrative review.

Jeong J, Kim S, Pan L, Hwang D, Kim D, Choi J Medicine (Baltimore). 2025; 104(6):e41470.

PMID: 39928829 PMC: 11813001. DOI: 10.1097/MD.0000000000041470.

Performance of an AI-powered visualization software platform for precision surgery in breast cancer patients.

Weitz M, Pfeiffer J, Patel S, Biancalana M, Pekis A, Kannan V NPJ Breast Cancer. 2024; 10(1):98.

PMID: 39543194 PMC: 11564706. DOI: 10.1038/s41523-024-00696-6.

Radiomics in breast cancer: Current advances and future directions.

Qi Y, Su G, You C, Zhang X, Xiao Y, Jiang Y Cell Rep Med. 2024; 5(9):101719.

PMID: 39293402 PMC: 11528234. DOI: 10.1016/j.xcrm.2024.101719.

Spatial and geometric learning for classification of breast tumors from multi-center ultrasound images: a hybrid learning approach.

Ru J, Zhu Z, Shi J BMC Med Imaging. 2024; 24(1):133.

PMID: 38840240 PMC: 11155188. DOI: 10.1186/s12880-024-01307-3.

Evaluating Magnetic Seed Localization in Targeted Axillary Dissection for Node-Positive Early Breast Cancer Patients Receiving Neoadjuvant Systemic Therapy: A Comprehensive Review and Pooled Analysis.

Alamoodi M, Wazir U, Sakr R, Venkataraman J, Mokbel K, Mokbel K J Clin Med. 2024; 13(10).

PMID: 38792449 PMC: 11122577. DOI: 10.3390/jcm13102908.

References

Nazari S, Mukherjee P . An overview of mammographic density and its association with breast cancer. Breast Cancer. 2018; 25(3):259-267. PMC: 5906528. DOI: 10.1007/s12282-018-0857-5. View

Qiao M, Suo S, Cheng F, Hua J, Xue D, Guo Y . Three-dimensional breast tumor segmentation on DCE-MRI with a multilabel attention-guided joint-phase-learning network. Comput Med Imaging Graph. 2021; 90:101909. DOI: 10.1016/j.compmedimag.2021.101909. View

Wang S, Sun K, Wang L, Qu L, Yan F, Wang Q . Breast Tumor Segmentation in DCE-MRI With Tumor Sensitive Synthesis. IEEE Trans Neural Netw Learn Syst. 2021; 34(8):4990-5001. DOI: 10.1109/TNNLS.2021.3129781. View

Guo J, Li B . The Application of Medical Artificial Intelligence Technology in Rural Areas of Developing Countries. Health Equity. 2018; 2(1):174-181. PMC: 6110188. DOI: 10.1089/heq.2018.0037. View

Siegel R, Miller K, Fuchs H, Jemal A . Cancer statistics, 2022. CA Cancer J Clin. 2022; 72(1):7-33. DOI: 10.3322/caac.21708. View

Zhang Y, Chen J, Lin Y, Chan S, Zhou J, Chow D . Prediction of breast cancer molecular subtypes on DCE-MRI using convolutional neural network with transfer learning between two centers. Eur Radiol. 2020; 31(4):2559-2567. PMC: 8547260. DOI: 10.1007/s00330-020-07274-x. View

Yankeelov T, Lepage M, Chakravarthy A, Broome E, Niermann K, Kelley M . Integration of quantitative DCE-MRI and ADC mapping to monitor treatment response in human breast cancer: initial results. Magn Reson Imaging. 2007; 25(1):1-13. PMC: 2634832. DOI: 10.1016/j.mri.2006.09.006. View

van Griethuysen J, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V . Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017; 77(21):e104-e107. PMC: 5672828. DOI: 10.1158/0008-5472.CAN-17-0339. View

Chan H, Samala R, Hadjiiski L . CAD and AI for breast cancer-recent development and challenges. Br J Radiol. 2019; 93(1108):20190580. PMC: 7362917. DOI: 10.1259/bjr.20190580. View

10.

Morrow M, Waters J, Morris E . MRI for breast cancer screening, diagnosis, and treatment. Lancet. 2011; 378(9805):1804-11. DOI: 10.1016/S0140-6736(11)61350-0. View

11.

Ginsburg O, Yip C, Brooks A, Cabanes A, Caleffi M, Dunstan Yataco J . Breast cancer early detection: A phased approach to implementation. Cancer. 2020; 126 Suppl 10:2379-2393. PMC: 7237065. DOI: 10.1002/cncr.32887. View

12.

Calnan M . The health belief model and participation in programmes for the early detection of breast cancer: a comparative analysis. Soc Sci Med. 1984; 19(8):823-30. DOI: 10.1016/0277-9536(84)90399-x. View

13.

Zhang J, Saha A, Zhu Z, Mazurowski M . Hierarchical Convolutional Neural Networks for Segmentation of Breast Tumors in MRI With Application to Radiogenomics. IEEE Trans Med Imaging. 2018; 38(2):435-447. DOI: 10.1109/TMI.2018.2865671. View

14.

Ma W, Ji Y, Qi L, Guo X, Jian X, Liu P . Breast cancer Ki67 expression prediction by DCE-MRI radiomics features. Clin Radiol. 2018; 73(10):909.e1-909.e5. DOI: 10.1016/j.crad.2018.05.027. View

15.

Sudre C, Li W, Vercauteren T, Ourselin S, Cardoso M . Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2017). 2021; 2017:240-248. PMC: 7610921. DOI: 10.1007/978-3-319-67558-9_28. View

16.

Granzier R, van Nijnatten T, Woodruff H, Smidt M, Lobbes M . Exploring breast cancer response prediction to neoadjuvant systemic therapy using MRI-based radiomics: A systematic review. Eur J Radiol. 2019; 121:108736. DOI: 10.1016/j.ejrad.2019.108736. View

17.

Yoon H, Kim Y, Chung J, Kim B . Predicting neo-adjuvant chemotherapy response and progression-free survival of locally advanced breast cancer using textural features of intratumoral heterogeneity on F-18 FDG PET/CT and diffusion-weighted MR imaging. Breast J. 2018; 25(3):373-380. DOI: 10.1111/tbj.13032. View

18.

Zheng Y, Baloch S, Englander S, Schnall M, Shen D . Segmentation and classification of breast tumor using dynamic contrast-enhanced MR images. Med Image Comput Comput Assist Interv. 2007; 10(Pt 2):393-401. PMC: 2840387. DOI: 10.1007/978-3-540-75759-7_48. View

19.

Fan M, Yuan W, Zhao W, Xu M, Wang S, Gao X . Joint Prediction of Breast Cancer Histological Grade and Ki-67 Expression Level Based on DCE-MRI and DWI Radiomics. IEEE J Biomed Health Inform. 2019; 24(6):1632-1642. DOI: 10.1109/JBHI.2019.2956351. View

20.

Chammings F, Ueno Y, Ferre R, Kao E, Jannot A, Chong J . Features from Computerized Texture Analysis of Breast Cancers at Pretreatment MR Imaging Are Associated with Response to Neoadjuvant Chemotherapy. Radiology. 2017; 286(2):412-420. DOI: 10.1148/radiol.2017170143. View