Photoacoustic Image Classification and Segmentation of Breast Cancer: A Feasibility Study

Abstract

Nowadays, breast cancer has increasingly threatened the health of human, especially females. However, breast cancer is still hard to detect in the early stage, and the diagnostic procedure can be timeconsuming with abundant expertise needed. In this paper, we explored the deep learning algorithms in emerging photoacoustic tomography for breast cancer diagnostics. Specifically, we used a pre-processing algorithm to enhance the quality and uniformity of input breast cancer images and a transfer learning method to achieve better classification performance. Besides, by comparing the area under the curve, sensitivity, and specificity of support vector machine with AlexNet and GoogLeNet, it can be concluded that the combination of deep learning and photoacoustic imaging has the potential to achieve important impact on clinical diagnostics. Finally, according to the breast imaging reporting and data-system levels, we divided breast cancer images into six grades and designed a segmentation software for identifying the six grades of breast cancer. Then, we tested based on MAMMOGRAPHYC IMAGES DATABASE FROM LAPIMO EESC/USP (Laboratory of Analysis and Processing of Medical and Dental Images) to verify the accuracy of our segmentation method, which showed a satisfactory result. INDEX TERMS Photoacoustic imaging, deep learning, breast cancer diagnosis, image classification and segmentation.

Deep learning in photoacoustic imaging: a review

“…Common methods include random pixel shifting, rotation, cropping, warping, vertical and horizontal flipping, and adding noise. 70 , 72 …”

“…It is a commonly used technique, in which the network is pretrained on public/simulated data before being retrained on a more relevant, high-quality data set with limited size. 70 , 112 …”

“…In 2018, Zhang et al. 70 applied AlexNet and GoogLeNet to classify breast cancer on stimulated PACT data. They achieved accuracies of 87.69% and 91.18% using AlexNet and GoogLeNet, respectively.…”

A generative adversarial network for artifact removal in photoacoustic computed tomography with a linear-array transducer

“…Deep learning (DL) has been increasingly applied in enhancing PACT performance, including localizing wavefronts, 17 improving LED-based PAT, 18 and assisting cancer detection. 19–21 DL has also been extensively explored for PACT artifact removal. For example, several groups have reported the use of UNet and other deep convolutional neural networks (CNNs) to address the limited-view and sparse-sampling issues as postprocessing correction, 22–24 direct reconstruction, 25 and model-based learning.…”

Photoacoustic image-guided interventions

“…Applications of PAI in cancers include early detection, identifying the stages and metastasis, treatment planning and evaluation. 6–12 PAI is revealed to be successful in the diagnosis of breast, 13–19 prostate, 20–26 thyroid, 27–31 melanoma, 32–36 and ovarian 37–41 cancers. In stroke, PAI is utilized for imaging and understanding mechanical thrombolysis, 42 vessel segmentation, 43 and other vessel injuries that are caused by stroke in the brain.…”