No abstract

Accurate detection and classification of breast cancer is a critical task in medical imaging due to the complexity of breast tissues. Due to automatic feature extraction ability, deep learning methods have been successfully applied in different areas, especially in the field of medical imaging. In this study, a novel patchbased deep learning method called Pa-DBN-BC is proposed to detect and classify breast cancer on histopathology images using the Deep Belief Network (DBN). Features are extracted through an unsupervised pre-training and supervised fine-tuning phase. The network automatically extracts features from image patches. Logistic regression is used to classify the patches from histopathology images. The features extracted from the patches are fed to the model as input and the model presents the result as a probability matrix as either a positive sample (cancer) or a negative sample (background). The proposed model is trained and tested on the whole slide histopathology image dataset having images from four different data cohorts and achieved an accuracy of 86%. Consequently, the proposed method is better than the traditional ones, as it automatically learns the best possible features and experimental results show that the model outperformed the previously proposed deep learning methods.

The liver segmentation in CT scan images is a significant step toward the development of a quantitative biomarker for computer-aided diagnosis. In this paper, we propose an automatic feature learning algorithm based on the deep belief network (DBN) for liver segmentation. The proposed method was based on training by a DBN for unsupervised pretraining and supervised fine tuning. The whole method of pretraining and fine tuning is known as DBN-DNN. In traditional machine learning algorithms, the pixelby-pixel learning is a time-consuming task; therefore, we use blocks as a basic unit for feature learning to identify the liver, which saves memory and computational time. An automatic active contour method is applied to refine the liver in post-processing. The experiments on test images show that the proposed algorithm obtained satisfactory results on healthy and pathological liver CT images. Our algorithm achieved 94.80% Dice similarity coefficient on mixed (healthy and pathological) images while 91.83% on pathological liver images, which is better than those of the state-of-the-art methods. INDEX TERMS Liver segmentation, deep learning, deep belief network, restricted Boltzmann machine.

CT vertebral segmentation plays an essential role in various clinical applications, such as computer-assisted surgical interventions, assessment of spinal abnormalities, and vertebral compression fractures. Automatic CT vertebral segmentation is challenging due to the overlapping shadows of thoracoabdominal structures such as the lungs, bony structures such as the ribs, and other issues such as ambiguous object borders, complicated spine architecture, patient variability, and fluctuations in image contrast. Deep learning is an emerging technique for disease diagnosis in the medical field. This study proposes a patch-based deep learning approach to extract the discriminative features from unlabeled data using a stacked sparse autoencoder (SSAE). 2D slices from a CT volume are divided into overlapping patches fed into the model for training. A random under sampling (RUS)-module is applied to balance the training data by selecting a subset of the majority class. SSAE uses pixel intensities alone to learn high-level features to recognize distinctive features from image patches. Each image is subjected to a sliding window operation to express image patches using autoencoder high-level features, which are then fed into a sigmoid layer to classify whether each patch is a vertebra or not. We validate our approach on three diverse publicly available datasets: VerSe, CSI-Seg, and the Lumbar CT dataset. Our proposed method outperformed other models after configuration optimization by achieving 89.9% in precision, 90.2% in recall, 98.9% in accuracy, 90.4% in F-score, 82.6% in intersection over union (IoU), and 90.2% in Dice coefficient (DC). The results of this study demonstrate that our model’s performance consistency using a variety of validation strategies is flexible, fast, and generalizable, making it suited for clinical application.