Evaluation of Response Rate to Chemotherapy in Patients with Breast Cancer using DWI and ADC Sequences of MRI Images by Machine Learning Modeling

Pazoki, Z; Tahmasebi, Z

Evaluation of Response Rate to Chemotherapy in Patients with Breast Cancer using DWI and ADC Sequences of MRI Images by Machine Learning Modeling

Authors

Z Pazoki ¹

Z Tahmasebi ²

¹ Biomedical Engineering, Islamic Azad University of Medical Sciences, Tehran, Iran

² Department of Nursing, Borujen School of Nursing, Shahrekord University of Medical Sciences

Abstract

Introduction & Objective: Currently, chemotherapy is considered as one of the standard and important treatments for patients with breast cancer. Locally advanced BCs must receive Neo - adjuvant chemotherapy before surgery. With the advancement of MRI techniques such as DWI sequence, the effects of chemotherapy such as cell apoptosis and necrosis can be investigated. However, ADC images more accurately show the diffusion and movement of water molecules as well as, distinguish between cancerous tissue and normal tissue, thereby investigating the response to treatment. However, the limitations of these techniques have restricted roles and minimal use. With the advent of artificial intelligence and machine learning, besides clinical studies, it is possible to identify more reliable and accurate methods by examining and modeling with the help of imaging data. Therefore, this study aimed to investigate different indices extracted from DWI sequences and draw ADC maps with the help of different algorithms using machine learning to determine the response rate to chemotherapy in patients with breast cancer Materials & Methods: In this study, imaging data related to breast cancer patients were first extracted from the ACRIN website of the American Imaging Society and with the help of different algorithms including decision tree, K-nearest neighbors, logistic regression, support vector machines, linear support vector machines, and random forest. Different indices of DWI images and drawing ADC maps calculated a reliable index to estimate the response to treatment in different stages of chemotherapy (including T0, T1, T2, T3). Results: In this study, the information of 8 patients was collected from the ACRIN site. Then, different indices of DWI images were analyzed with the help of machine learning. The results showed that in the b-value equal to 1000, and with the help of apparent diffusion coefficient (D), ADC maps were drawn and it was shown that an increase in the diffusion coefficient D can indicate a positive response to chemotherapy. The data of 3 patients who responded completely to the treatment were analyzed with different algorithms and indicators and it was shown that the increase of D in ADC images can be seen in all stages of chemotherapy, even before the apparent changes in the images are identified, so it can determine the response rate to treatment. Conclusions: The results of this study showed that the use of D value in ADC images can reliably and with high accuracy determine the response rate to chemotherapy.

Keywords

Breast Cancer

Machine Learning

Apparent Diffusion Coefficient

Diffusion of Water Molecules

Response to Treatment

1. Kulkarni A, Kelkar DA, Parikh N, Shashidhara LS, Koppiker CB, Kulkarni M. Meta-analysis of prevalence of triple-negative breast cancer and its clinical features at incidence in Indian patients with breast cancer. JCO global oncology. 2020 Jul; 6: 1052-62.

2. Barroso-Sousa R, Jain E, Cohen O, Kim D,
Buendia-Buendia J, Winer E, Lin N, Tolaney SM, Wagle N. Prevalence and mutational determinants of high tumor mutation burden in breast cancer. Annals of Oncology. 2020 Mar 1; 31(3): 387-94.

3. Burguin A, Diorio C, Durocher F. Breast cancer treatments: updates and new challenges. Journal of personalized medicine. 2021 Aug 19; 11(8): 808.

4. Yuen S, Monzawa S, Yanai S, Matsumoto H, Yata Y, Ichinose Y, Deai T, Hashimoto T, Tashiro T, Yamagami K. The association between MRI findings and breast cancer subtypes: focused on the combination patterns on diffusion-weighted and
T2-weighted images. Breast Cancer. 2020 Sep; 27: 1029-37.

5. Iima M, Honda M, Sigmund EE, Ohno Kishimoto A, Kataoka M, Togashi K. Diffusion MRI of the breast: Current status and future directions. Journal of Magnetic Resonance Imaging. 2020 Jul; 52(1):
70-90.

6. Meyer HJ, Wienke A, Surov A. Diffusion-weighted imaging of different breast cancer molecular subtypes: a systematic review and meta-analysis. Breast Care. 2022 Feb 17; 17(1): 47-54.

7. Hottat NA, Badr DA, Lecomte S, Besse-Hammer T, Jani JC, Cannie MM. Value of diffusion-weighted MRI in predicting early response to neoadjuvant chemotherapy of breast cancer: Comparison between ROI-ADC and whole-lesion-ADC measurements. European radiology. 2022 Jun; 32(6): 4067-78.

8. Ha SM, Chang JM, Lee SH, Kim ES, Kim SY, Cho N, Moon WK. Diffusion-weighted MRI at 3.0 T for detection of occult disease in the contralateral breast in women with newly diagnosed breast cancer.
Breast Cancer Research and Treatment. 2020 Jul; 182: 283-97.

9. Sammut SJ, Crispin-Ortuzar M, Chin SF,
Provenzano E, Bardwell HA, Ma W, Cope W, Dariush A, Dawson SJ, Abraham JE, Dunn J.
Multi-omic machine learning predictor of breast cancer therapy response. Nature. 2022 Jan 27; 601(7894): 623-9.

10. Giess CS, Poole PS, Chikarmane SA, Sippo DA, Birdwell RL. Screening breast MRI in patients previously treated for breast cancer: diagnostic yield for cancer and abnormal interpretation rate. Academic radiology. 2015 Nov 1; 22(11): 1331-7.

11. Partridge SC, Zhang Z, Newitt DC, Gibbs JE, Chenevert TL, Rosen MA, Bolan PJ, Marques HS, Romanoff J, Cimino L, Joe BN. Diffusion-weighted MRI findings predict pathologic response in neoadjuvant treatment of breast cancer: the ACRIN 6698 multicenter trial. Radiology. 2018 Dec; 289(3): 618-27.

12. Amornsiripanitch N, Bickelhaupt S, Shin HJ, Dang M, Rahbar H, Pinker K, Partridge SC.
Diffusion-weighted MRI for unenhanced
breast cancer screening. Radiology. 2019 Dec; 293(3): 504-20.

13. Hottat NA, Badr DA, Lecomte S, Besse-Hammer T, Jani JC, Cannie MM. Value of diffusion-weighted MRI in predicting early response to
neoadjuvant chemotherapy of breast cancer: Comparison between ROI-ADC and
whole-lesion-ADC measurements. European radiology. 2022 Jun; 32(6): 4067-78.

14. Rotili A, Trimboli RM, Penco S, Pesapane F, Tantrige P, Cassano E, Sardanelli F. Double reading of diffusion-weighted magnetic resonance imaging for breast cancer detection. Breast cancer research and treatment. 2020 Feb; 180: 111-20.

15. Avendano D, Marino MA, Leithner D,
Thakur S, Bernard-Davila B, Martinez DF,
Helbich TH, Morris EA, Jochelson MS, Baltzer PA, Clauser P. Limited role of DWI with apparent diffusion coefficient mapping in breast lesions presenting as non-mass enhancement on dynamic contrast-enhanced MRI. Breast Cancer Research. 2019 Dec; 21: 1-0.

16. Pinker K, Moy L, Sutton EJ, Mann RM, Weber M, Thakur SB, Jochelson MS, Bago-Horvath Z, Morris EA, Baltzer PA, Helbich TH. Diffusion-weighted imaging with apparent diffusion coefficient
mapping for breast cancer detection as a stand-alone parameter: comparison with dynamic
contrast-enhanced and multiparametric magnetic resonance imaging. Investigative radiology. 2018 Oct 1; 53(10): 587-95.

17. Surov A, Meyer HJ, Wienke A. Can apparent diffusion coefficient (ADC) distinguish breast
cancer from benign breast findings? A meta-analysis based on 13 847 lesions. BMC cancer. 2019
Dec; 19: 1-4.

18. Ding JR, Wang DN, Pan JL. Apparent
diffusion coefficient value of diffusion-weighted imaging for differential diagnosis of ductal carcinoma in situ and infiltrating ductal carcinoma. Journal of cancer research and therapeutics. 2016 Apr 1; 12(2): 744-50.

19. Islam MM, Haque MR, Iqbal H, Hasan MM, Hasan M, Kabir MN. Breast cancer prediction: a comparative study using machine
learning techniques. SN Computer Science. 2020 Sep; 1: 1-4.

20. Yue W, Wang Z, Chen H, Payne A, Liu X.
Machine learning with applications in
breast cancer diagnosis and prognosis. Designs.
2018 May 9; 2(2): 13.

21. Le Bihan D, Breton E, Lallemand D, Aubin ML, Vignaud J, Laval-Jeantet M. Separation of diffusion and perfusion in intravoxel incoherent motion MR imaging. Radiology. 1988 Aug; 168(2): 497-505.