Deep Integrated Pipeline of Segmentation Leading to Classification for Automated Detection of Breast Cancer from Breast Ultrasound Images

Breast cancer has become a symbol of tremendous concern in the modern world, as it is one of the major causes of cancer mortality worldwide. In this concern, many people are frequently screening for breast cancer in order to be identified early and avert mortality from the disease by receiving treatment. Breast Ultrasonography Images are frequently utilized by doctors to diagnose breast cancer at an early stage. However, the complex artifacts and heavily noised Breast Ultrasonography Images make detecting Breast Cancer a tough challenge. Furthermore, the ever-increasing number of patients being screened for Breast Cancer necessitates the use of automated Computer Aided Technology for high accuracy diagnosis at a cheap cost and in a short period of time. The current progress of Artificial Intelligence (AI) in the fields of Medical Image Analysis and Health Care is a boon to humanity. In this study, we have proposed a compact integrated automated pipelining framework which integrates ultrasonography image preprocessing with Simple Linear Iterative Clustering (SLIC) to tackle the complex artifact of Breast Ultrasonography Images complementing semantic segmentation with Modified U-Net leading to Breast Tumor classification with robust feature extraction using a transfer learning approach with pretrained VGG 16 model and densely connected neural network architecture. The proposed automated pipeline can be effectively implemented to assist medical practitioners in making more accurate and timely diagnoses of breast cancer.

Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation

Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, convolutional neural network (CNN) has established itself as a powerful model in segmentation and classification by demonstrating excellent performances. The use of a graphical model such as a conditional random field (CRF) contributes further in capturing contextual information and thus improving the segmentation performance. In this paper, we propose a method to segment hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF. We use multiple spectral cubes to learn deep features using CNN, and then formulate deep CRF with CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between patches consisting of three-dimensional data cubes. Effective piecewise training is applied in order to avoid the computationally expensive iterative CRF inference. Furthermore, we introduce a deep deconvolution network that improves the segmentation masks. We also introduce a new dataset and experimented our proposed method on it along with several widely adopted benchmark datasets to evaluate the effectiveness of our method. By comparing our results with those from several state-of-the-art models, we show the promising potential of our method.