Breast MRI Segmentation and Ki-67 High- and Low-Expression Prediction Algorithm Based on Deep Learning

Abstract

Background and Objective. Breast cancer is a common malignant tumor that seriously threatens the health of women in my country and even around the world. The proliferation marker Ki-67 has been utilized to distinguish luminal B from luminal A tumors and is a reliable indicator of more aggressive breast cancer growth. If a reliable prediction method for breast cancer patients to avoid invasive damage can be found to predict Ki-67 before pathological examination, it will be very beneficial for doctors to formulate later treatment plans and provide more useful treatment options. Methodology. This paper proposes a tumor segmentation and prediction framework based on the combination of improved attention U-Net and SVM. The framework first improves on attention U-Net by introducing coefficients for learning multidimensional attention. Make the attention mechanism more aware of the main situation in the segmentation process. At the same time, the segmented breast MRI results and corresponding labels were input into the SVM classifier to accurately predict the expression of Ki-67. Results. The DSC, PPV, and sensitivity of our combined model are 0.94, 0.93, and 0.94, respectively, with better segmentation performance. And we compare with the segmentation frameworks of other papers and find that our combined model can make accurate segmentation of breast tumors. Conclusion. Our method can adapt to the variability of breast tumors and segment breast tumors accurately and efficiently. In the future, it can be widely used in clinical practice, so as to help the clinic better formulate a reasonable diagnosis and treatment plan for breast cancer patients.

Freehand 1.5T MR-Guided Vacuum-Assisted Breast Biopsy (MR-VABB): Contribution of Radiomics to the Differentiation of Benign and Malignant Lesions

“…When this was not possible, we selected the MRI acquisition with the highest peak of the enhanced phase (the first one of the second sequence when the highest peak was not reached at first). This method is consistent with the recent literature [ 30 , 31 ].…”

Preoperative prediction of Ki-67 status in invasive breast carcinoma using dynamic contrast-enhanced MRI, diffusion-weighted imaging and diffusion tensor imaging

“…Shen et al [41] estimated that cut off mean ADC value of 0.97 × 10 −3 mm 2 /s had 100% sensitivity in differentiating tumors with high Ki67 proliferation index from those with low Ki 67. Also Li et al [23] stated that there was inverse relationship between mean ADC value and Ki-67 status. The mean ADC value was 0.820 × 10 -3 mm 2 /s for tumors with high Ki-67 versus 0.980 × 10 -3 mm 2 /s, for tumors with low Ki-67 proliferation index (P = 0.001).…”

“…Ki-67 is the most commonly utilized immunohistochemical marker in breast cancer detection, and its expression level is related closely to tumor type, invasiveness, prognosis and effect of treatment. In clinical practice, the expression of Ki-67 in breast cancer is acquired through pathological tissue staining and immunohistochemical analysis [23]. Breast MRI provide data on not only about the morphological features of the tumor but also about the functional features of the tumor [24][25][26].…”

“…By fast progress in quantitative radiology modalities, tumor biology and genetics can be assessed in a more accurate, predictive, and cost-effective method [22]. Several previous studies investigated the relationship between quantitative MRI parameters and molecular subtypes of breast cancer [23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42]; however, there is still no evident data about cut off values between breast cancers with low Ki-67 proliferation index and those with high Ki-67 proliferation index.…”