Research progress of artificial intelligence measurement technology for three-dimensional volume of breast cancer based on dynamic contrast-enhanced magnetic resonance imaging

Share this content in WeChat

• Review •

XU Jingyao LIU Xiaomin ZHANG Xinfeng GUO Wei WANG Fei LI Xiangsheng

XU J Y, LIU X M, ZHANG X F, et al. Research progress of artificial intelligence measurement technology for three-dimensional volume of breast cancer based on dynamic contrast-enhanced magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2023, 14(9): 148-153. DOI:10.12015/issn.1674-8034.2023.09.027.

Abstract

[Abstract] As one of the important imaging methods for breast diseases, MRI is of great significance in the early detection of breast cancer and prediction of outcome. At present, the assessment of breast cancer tumor size is mainly based on the information of tumor diameter and morphology contained in two-dimensional images, which has certain limitations and low reproducibility, and the prediction accuracy needs to be further improved. Based on dynamic contrast enhanced MRI measurement of tumor volume and other three-dimensional information can provide an important basis for determining the course of breast cancer and evaluating the efficacy of neoadjuvant chemotherapy. However, the measurement of 3D information of breast cancer tumors relies on the experience of the physicians and takes a long time. To improve the measurement accuracy and reduce the time cost, artificial intelligence technology has a promising research prospect in the field of breast MRI. In view of this, we compared the research and applications of artificial intelligence, especially deep learning techniques, in automated breast cancer tumor volume measurement, mainly in the areas of image segmentation, morphological 3D reconstruction, visualization and volume measurement. This paper provides precise material for clinicians to gain insight into how AI techniques can help in automated and high-precision measurement of breast tumors, and provides ideas for information technology personnel to understand how AI techniques can be applied to breast tumor measurement.

[Keywords] breast cancer；breast tumor volume；deep learning；image segmentation；3D reconstruction techniques；magnetic resonance imaging

Contributor Information

XU Jingyao¹ LIU Xiaomin¹ ZHANG Xinfeng¹ GUO Wei² WANG Fei² LI Xiangsheng^2*

¹ Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China

² Department of Medical Imaging, Air Force Medical Center, People Military Army, Beijing 100142, China

Corresponding author: Li XS, E-mail: lxsheng500@163.com

Conflicts of interest None.

Publication Information

Received 2023-03-08

Accepted 2023-07-27

DOI: 10.12015/issn.1674-8034.2023.09.027

Text

References

[1]

International Agency for Research on Cancer. Latest global cancer data: Cancer burden rises to 19.3 million new cases and 10.0 million cancer deaths in 2020[EB/OL]. (2020-12-16). [2023-03-07]. https://www.iarc.fr/fr/news-events/latest-global-cancer-data-cancer-burden-rises-to-19-3-million-new-cases-and-10-0-million-cancer-deaths-in-2020.

[2]

OKCU O, ÖZTÜRK S D, ÖZTÜRK Ç, et al. Tumor-infiltrating lymphocytes (TILs)/volume and prognosis: the value of TILs for survival in HER2 and TN breast cancer patients treated with chemotherapy[J/OL]. Ann Diagn Pathol, 2022, 58: 151930 [2023-03-07]. https://pubmed.ncbi.nlm.nih.gov/35245821/. DOI: 10.1016/j.anndiagpath.2022.151930.

[3]

LIU X J, LUO C X, YANG Y M. Application value of contrast-enhanced ultrasonography in the diagnosis of benign and malignant breast tumors[J]. J Dali Univ, 2022, 7(8): 71-74. DOI: 10.3969/j.issn.2096-2266.2022.08.015.

[4]

GENG R X, YAN G Q, WU J, et al. Automatic stitching method of ultrasound panorama of mammary gland in ABUS[J]. Electron Meas Technol, 2021, 44(1): 98-102. DOI: 10.19651/j.cnki.emt.2005305.

[5]

ZHANG L J, LI L H, FENG G Q, et al. Advances in CT techniques in vascular calcification[J/OL]. Front Cardiovasc Med, 2021, 8: 716822 [2023-03-07]. https://pubmed.ncbi.nlm.nih.gov/34660718/. DOI: 10.3389/fcvm.2021.716822.

[6]

GENG W, CHEN Q H, LI H M, et al. Research on the correlation of radiation dosage and image quality in digital DR mammography with different exposure modes[J]. J Med Imag, 2021, 31(8): 1423-1425.

[7]

LI Z Q, LIANG S. The value of MRI, CT and mammography in the diagnosis of breast diseases[J]. Guide China Med, 2020, 18(11): 50-51. DOI: 10.15912/j.cnki.gocm.2020.11.021.

[8]

KADRY S, DAMAŠEVIČIUS R, TANIAR D, et al. Extraction of tumour in breast MRI using joint thresholding and segmentation-A study[C]//2021 Seventh International conference on Bio Signals, Images, and Instrumentation (ICBSII). March 25-27, 2021, Chennai, India. IEEE, 2021: 1-5. DOI: 10.1109/ICBSII51839.2021.9445152.

[9]

MARTIN M S, FROUIN F, MALHAIRE C, et al. Decrypting the information captured by MRI-radiomic features in predicting the response to neoadjuvant chemotherapy in breast cancer[J/OL]. Annu Int Conf IEEE Eng Med Biol Soc, 2022, 2022: 3227-3230 [2023-03-07]. https://pubmed.ncbi.nlm.nih.gov/36085726/. DOI: 10.1109/embc48229.2022.9871844.

[10]

HOU P, QI Y L. Automatic region segmentation method of breast tumor based on deep neural network[J]. J Biomed Eng Res, 2021, 40(3): 241-245. DOI: 10.19529/j.cnki.1672-6278.2021.03.03.

[11]

SUN Y J. Comparison of the application value of multi-slice spiral CT and X-ray molybdenum target in the diagnosis of breast masses[J]. Clin Med, 2021, 41(6): 93-94. DOI: 10.19528/j.issn.1003-3548.2021.06.036.

[12]

ZHAO X, YUAN L, ZHANG C, et al. Quantitative value of DCE-MRI perfusion parameters in distinguishing benign and malignant breast lesions[J]. J Clin Radiol, 2022, 41(5): 834-838. DOI: 10.13437/j.cnki.jcr.2022.05.014.

[13]

WU S, LIN L, DOU Q, et al. Deep learning for automated contouring of primary tumor volumes by MRI for nasopharyngeal carcinoma[J]. Int J Med Radiol, 2019, 42(4): 488. DOI: 10.19300/j.2019.r0609.

[14]

BINTI INDERA PUTERA S H, DZULKIFLI M R BIN, SIDEK N B, et al. Simulation of three-dimensional images and estimation of lung volumes from two-dimensional MRI and CT images[C]//2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE). October 21-22, 2022, Penang, Malaysia. IEEE, 2022: 81-86. DOI: 10.1109/ICCSCE54767.2022.9935628.

[15]

BASHER A, KIM B C, LEE K H, et al. Automatic localization and discrete volume measurements of hippocampi from MRI data using a convolutional neural network[C]//IEEE Access. May 13, 2020, IEEE, 2020: 91725-91739.

[16]

MA Y Z, CHEN W, WU Z W, et al. Development and application of medical image analysis technology[J]. Med J Chin People's Armed Police Force, 2017, 28(10): 1060-1062. DOI: 10.14010/j.cnki.wjyx.2017.10.027.

[17]

MUTLU F, ÇETINEL G, GÜL S. A fully-automated computer-aided breast lesion detection and classification system[J/OL]. Biomed Signal Process Contr, 2020, 62: 102157 [2023-03-07]. https://doi.org/10.1016/j.bspc.2020.102157. DOI: 10.1016/j.bspc.2020.102157.

[18]

JAGLAN P, DASS R, DUHAN M. Escalate the efficacy of breast tumor detection through magnetic resonance imaging: a framework[J]. Int J Inf Tecnol, 2020, 12(3): 879-887. DOI: 10.1007/s41870-019-00393-9.

[19]

GAVRILESCU M. Representation of partially-occluded structures in regular point clouds from 3D scanner data using vision-based modulation[C]//2017 E-Health and Bioengineering Conference (EHB). June 22-24, 2017, Sinaia, Romania. IEEE, 2017: 539-542. DOI: 10.1109/EHB.2017.7995480.

[20]

TWELLMANN T, LICHTE O, NATTKEMPER T W. An adaptive tissue characterization network for model-free visualization of dynamic contrast-enhanced magnetic resonance image data[J]. IEEE Trans Med Imaging, 2005, 24(10): 1256-1266. DOI: 10.1109/TMI.2005.854517.

[21]

SRIDHAR B. A quality representation of tumor in breast using hybrid model watershed transform and Markov random fields[C]//2020 International Conference on Computer Communication and Informatics (ICCCI). January 22-24, 2020, Coimbatore, India. IEEE, 2020: 1-5. DOI: 10.1109/ICCCI48352.2020.9104154.

[22]

ZHANG L, GU C H, FU H C, et al. Application of improved watershed algorithm in X-ray breast cancer image segmentation[J]. Electron World, 2021, (21): 33-34. DOI: 10.19353/j.cnki.dzsj.2021.21.015.

[23]

CONTE L, TAFURI B, PORTALURI M, et al. Breast cancer mass detection in DCE-MRI using deep-learning features followed by discrimination of infiltrative vs. In situ carcinoma through a machine-learning approach[J]. Appl Sci, 2020, 10(17): 6109. DOI: 10.3390/app10176109.

[24]

SHRIVASTAVA N, BHARTI J. Breast tumor detection and classification based on density[J]. Multimed Tools Appl, 2020, 79(35/36): 26467-26487. DOI: 10.1007/s11042-020-09220-x.

[25]

AL-FARIS A Q, NGAH U K, ISA N A M, et al. Breast MRI tumour segmentation using modified automatic seeded region growing based on particle swarm optimization image clustering[C]//SNÁŠEL V, KRÖMER P, KÖPPEN M, et al. Soft Computing in Industrial Applications. Cham: Springer, 2014: 49-60. DOI: 10.1007/978-3-319-00930-8_5

[26]

ABASPOOR M, MESHGINI S, REZAII T Y, et al. A novel method for detecting breast cancer location based on growing GA-FCM approach[C]//2019 9th International Conference on Computer and Knowledge Engineering (ICCKE). October 24-25, 2019, Mashhad, Iran. IEEE, 2020: 238-242. DOI: 10.1109/ICCKE48569.2019.8964904.

[27]

JAGLAN P, DASS R, DUHAN M. Escalate the efficacy of breast tumor detection through magnetic resonance imaging: a framework[J]. Int J Inf Technol, 2020, 12(3): 879-887. DOI: 10.1007/s41870-019-00393-9.

[28]

WANG C M, HUANG C L, YANG S C. 3D shape-weighted level set method for breast MRI 3D tumor segmentation[J]. J Healthc Eng, 2018, 2018: 7097498 [2023-03-07]. https://pubmed.ncbi.nlm.nih.gov/30008992/. DOI: 10.1155/2018/7097498.

[29]

NADKARNI S, NORONHA K. A review on multiparametric magnetic resonance imaging for the detection of breast cancer[C]//2020 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT). July 2-4, 2020, Bangalore, India. IEEE, 2020: 1-5. DOI: 10.1109/CONECCT50063.2020.9198362.

[30]

PATIL S M, TONG L, WANG M D. Generating region of interests for invasive breast cancer in histopathological whole-slide-image[C]//2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC). July 13-17, 2020, Madrid, Spain. IEEE, 2020: 723-728. DOI: 10.1109/COMPSAC48688.2020.0-174.

[31]

WANG J X, FU L J, YIN P B, et al. Medical image segmentation based on CNN and transformer[J]. Comput Syst Appl, 2023, 32(4): 141-148. DOI: 10.15888/j.cnki.csa.009010.

[32]

WANG S, SUN K, WANG L, et al. Breast tumor segmentation in DCE-MRI with tumor sensitive synthesis[J]. IEEE Trans Neural Netw Learn Syst, 2023, 34(8): 4990-5001. DOI: 10.1109/TNNLS.2021.3129781.

[33]

ZHANG J, SAHA A, ZHU Z, et al. Hierarchical convolutional neural networks for segmentation of breast tumors in MRI with application to radiogenomics[J]. IEEE Trans Med Imaging, 2019, 38(2): 435-447. DOI: 10.1109/TMI.2018.2865671.

[34]

QIAO M Y, SUO S T, CHENG F, et al. Three-dimensional breast tumor segmentation on DCE-MRI with a multilabel attention-guided joint-phase-learning network[J/OL]. Comput Med Imaging Graph, 2021, 90: 101909 [2023-03-07]. https://pubmed.ncbi.nlm.nih.gov/33845432/. DOI: 10.1016/j.compmedimag.2021.101909.

[35]

ZHOU J, LUO L Y, DOU Q, et al. Weakly supervised 3D deep learning for breast cancer classification and localization of the lesions in MR images[J]. J Magn Reson Imaging, 2019, 50(4): 1144-1151. DOI: 10.1002/jmri.26721.

[36]

AYATOLLAHI F, SHOKOUHI S B, MANN R M, et al. Automatic breast lesion detection in ultrafast DCE-MRI using deep learning[J]. Med Phys, 2021, 48(10): 5897-5907. DOI: 10.1002/mp.15156.

[37]

LU W H, WANG Z, HE Y Q, et al. Breast cancer detection based on merging four modes MRI using convolutional neural networks[C]//ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). May 12-17, 2019, Brighton, UK. IEEE, 2019: 1035-1039. DOI: 10.1109/ICASSP.2019.8683149.

[38]

KRAVCOVA L A, KOSTRUBOVA I I. Construction of isometric outlines of surfaces using their superimposed orthogonal projections[J/OL]. IOP Conf Ser: Earth Environ Sci, 2021, 751(1): 012064 [2023-03-07]. https://iopscience.iop.org/article/10.1088/1755-1315/751/1/012064. DOI: 10.1088/1755-1315/751/1/012064.

[39]

GUO Y H. Research and discussion on key technologies of medical image information visualization[J]. Electron Compon Inf Technol, 2021, 5(5): 216-218. DOI: 10.19772/j.cnki.2096-4455.2021.5.096.

[40]

LORENSEN W E, CLINE H E. Marching cubes: a high resolution 3d surface construction algorithm[J]. Comput Graph ACM, 1987, 21(4): 163-169.

[41]

GNONNOU C, SMAOUI N. Segmentation and 3D reconstruction of MRI images for breast cancer detection[C]//International Image Processing, Applications and Systems Conference. November 5-7, 2014, Sfax, Tunisia. IEEE, 2015: 1-6. DOI: 10.1109/IPAS.2014.7043316.

[42]

ZHU Y M. A study on breast mass segmentation and three-dimensional reconstruction[D]. Hangzhou: Hangzhou Dianzi University, 2013. DOI: 10.7666/d.D318753.

[43]

ALLISON B, YE X J, JANAN F. Breast3D: an augmented reality system for breast CT and MRI[C]//2020 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR). December 14-18, 2020, Utrecht, Netherlands. IEEE, 2021: 247-251. DOI: 10.1109/AIVR50618.2020.00052.

[44]

LIU Y Q, YIN D, ZHANG J J. Breast tumor MRI segmentation and 3D reconstruction based on ray casting method[J]. Beijing Biomed Eng, 2016, 35(4): 374-380. DOI: 10.3969/j.issn.1002-3208.2016.04.07.

[45]

WESTERMANN R, ERTL T. A multiscale approach to integrated volume segmentation and rendering[J/OL]. Comput Graph Forum, 2008, 16: C117-C127 [2023-03-07]. https://onlinelibrary.wiley.com/doi/10.1111/1467-8659.16.3conferenceissue.13. DOI: 10.1111/1467-8659.16.3conferenceissue.13.

[46]

WILHELMS J, VAN GELDER A. A coherent projection approach for direct volume rendering[C]//Proceedings of the 18th annual conference on Computer graphics and interactive techniques-SIGGRAPH '91. Not Known. New York: ACM Press, 1991. DOI: 10.1145/122718.122758.

[47]

SHAO Z H, WANG W, LIU W Y, et al. Value of multiparametric MRI sequences in evaluating the index lesion volume of prostate cancer[J]. J Tongji Univ Med Sci, 2021, 42(2): 214-219, 225. DOI: 10.12289/j.issn.1008-0392.20362.

[48]

ZHU L F, QIAN Y F, LI L L. Application of tumor/breast volume ratio measured by magnetic resonance imaging in surgical treatment of breast cancer[J]. Oncoradiology, 2019, 28(3): 165-169. DOI: 10.19732/j.cnki.2096-6210.2019.03.008.

[49]

HECKEL F, MEINE H, MOLTZ J H, et al. Segmentation-based partial volume correction for volume estimation of solid lesions in CT[J]. IEEE Trans Med Imaging, 2014, 33(2): 462-480. DOI: 10.1109/TMI.2013.2287374.

[50]

MOFTAH H M, GHALI N I, HASSANIEN A E, et al. Volume identification and estimation of MRI brain tumor[C]//2012 12th International Conference on Hybrid Intelligent Systems (HIS). December 4-7, 2012, Pune, India. IEEE, 2013: 120-124. DOI: 10.1109/HIS.2012.6421320.

PREV Summary of mammography of breast MRI and progress in its prognostic application

NEXT Research progress of MRI radiomics in the evaluation of curative effect of hepatocellular carcinoma

LINK

Tel & Fax: +8610-67113815 E-mail: editor@cjmri.cn