A review on breast cancer pathological image processing
Shubham S Bagade
Breast cancer is the most frequent type of cancer. Breast pathological image processing has become an essential tool for the early detection of breast cancer. Using medical image processing to help doctors discover probable breast cancer as early as possible has long been a hot issue in medical image diagnostics. This work systematically elaborates on a breast cancer recognition technique based on image processing from four perspectives: breast cancer detection, picture segmentation, image registration, and image fusion. The achievements and application scope of supervised learning, unsupervised learning, deep learning, CNN, and so on in breast cancer examination is expounded. The prospect of unsupervised learning and transfer learning for breast cancer diagnosis has been prospected. Finally, the privacy protection of breast cancer patients is put forward. The accomplishments and application breadth of supervised learning, unsupervised learning, deep learning, CNN, and other methods in breast cancer examination are discussed. Unsupervised learning and transfer learning have been considered for breast cancer detection. Finally, breast cancer sufferers' private rights are advocated for. Pseudocolor display uses an image as a baseline and superimposes the image's grey and contrast characteristics to be fused with the benchmark image. The tomographic presentation technique may simultaneously show the merged three-dimensional data in cross-sectional, coronal, and sagittal pictures, making it easier for the observer to diagnose. The three-dimensional presentation approach, specifically three-dimensional reconstruction, involves displaying the merged breast data in the form of three-dimensional pictures, which allow for a more intuitive observation of the lesions' spatial anatomical location. The back projection was the first approach to 3D reconstruction. There are two popular reconstruction approaches at the moment: filtered back projection and convolution back projection. Three-dimensional images have a high information capacity, and future three-dimensional image fusion technologies will focus on image fusion research. New image fusion approaches are developing as a result of the advancement of multidisciplinary research. Image fusion research will concentrate on wavelet transform, nonlinear registration based on finite element analysis, and artificial intelligence technologies in breast image fusion.