Evaluating the Margins of Breast Cancer Tumors by Using Digital Breast Tomosynthesis with Deep Learning: A Preliminary Assessment

Abstract

Background: The assessment information of tumor margins is extremely important for the success of the breast cancer surgery and whether the patient undergoes a second operation. However, conducting surgical margin assessments is a time-consuming task that requires pathology-related skills and equipment, and often cannot be provided in a timely manner. To address this challenge, digital breast tomosynthesis technology was utilized to generate detailed cross-sectional images of the breast tissue and integrate deep learning algorithms for image segmentation, achieving an assessment of tumor margins during surgery.

Methods: this study utilized post-operative tissue samples from 46 patients who underwent breast-conserving treatment, and generated image sets using digital breast tomosynthesis for the training and evaluation of deep learning models.

Results: Deep learning algorithms effectively identifying the tumor area. They achieved a Mean Intersection over Union (MIoU) of 0.91, global accuracy of 99%, weighted IoU of 44%, precision of 98%, recall of 83%, F1 score of 89%, and dice coefficient of 93% on the training dataset; for the testing dataset, MIoU was at 83%, global accuracy at 97%, weighted IoU at 38%, precision at 87%, recall rate at 69%, F1 score at 76%, dice coefficient at 86%.

Conclusions: The initial evaluation suggests that the deep learning-based image segmentation method is highly accurate in measuring breast tumor margins. This helps provide information related to tumor margins during surgery, and by using different datasets, this research method can also be applied to the surgical margin assessment of various types of tumors.

Keywords: breast cancer; cancer surgery; deep learning; surgical precision.

Figure 1

The overall workflow of this study.

Figure 2

Images of the same tumor tissue presented on different sectional planes. This example dataset contains a total of 50 images. (a) The 1st slice, (b) the 7th slice, (c) the 14th slice, (d) the 21st slice, (e) the 28th slice, (f) the 35th slice.

Figure 3

Masking of the tumor boundary. The column marked as “true_image” consists of original DBT images that display the internal characteristics of breast tissue. The column labeled as “true_mask” consists of corresponding mask images generated based on tumor areas manually annotated by experts.

Figure 4

Unet3+ algorithm framework. The direction of the dashed arrows indicates how Unet3+ integrates feature maps of different sizes at each encoder layer through skip connections.

Figure 5

The process of patient inclusion and exclusion in this study.

Figure 6

Algorithm Unet3+ with true image, true mask, ground truth + predict & prediction mask.

Figure 7

The performance comparisons based on (a) MIoU score and (b) dice score.

Figure 8

Schematic diagram of the deformation effects on slices at different positions in the DBT image sequence. This example sequence consists of 50 images. (a) Slice 1, (b) slice 17, (c) slice 32, (d) slice 47.