Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images

Abstract

Automated nuclear detection is a critical step for a number of computer assisted pathology related image analysis algorithms such as for automated grading of breast cancer tissue specimens. The Nottingham Histologic Score system is highly correlated with the shape and appearance of breast cancer nuclei in histopathological images. However, automated nucleus detection is complicated by (1) the large number of nuclei and the size of high resolution digitized pathology images, and (2) the variability in size, shape, appearance, and texture of the individual nuclei. Recently there has been interest in the application of “Deep Learning” strategies for classification and analysis of big image data. Histopathology, given its size and complexity, represents an excellent use case for application of deep learning strategies. In this paper, a Stacked Sparse Autoencoder (SSAE), an instance of a deep learning strategy, is presented for efficient nuclei detection on high-resolution histopathological images of breast cancer. The SSAE learns high-level features from just pixel intensities alone in order to identify distinguishing features of nuclei. A sliding window operation is applied to each image in order to represent image patches via high-level features obtained via the auto-encoder, which are then subsequently fed to a classifier which categorizes each image patch as nuclear or non-nuclear. Across a cohort of 500 histopathological images (2200 × 2200) and approximately 3500 manually segmented individual nuclei serving as the groundtruth, SSAE was shown to have an improved F-measure 84.49% and an average area under Precision-Recall curve (AveP) 78.83%. The SSAE approach also out-performed 9 other state of the art nuclear detection strategies.

Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images

“…SC-CNN can be trained to predict the probability of a pixel being the center of a nucleus. As opposed to other approaches [7], [8] that do not enforce the pixels close to the center of a nucleus to have a higher probability value than those further away, the predicted probability values produced by SC-CNN are topologically constrained such that high probability values are concentrated in the vicinity of the center of nuclei. For classification, we introduce neighboring ensemble predictor (NEP) to be used in conjunction with a standard softmax CNN.…”

Building Energy Consumption Prediction: An Extreme Deep Learning Approach

“…The autoencoder will be invalid for dimension reduction and key feature extraction if the number of hidden nodes is the same or greater than the number of input nodes, that is, L ≥ n. To solve this problem, sparsity constraints are imposed on the hidden layer to obtain the representative features and to learn useful structures from the input data [36][37][38][39]. This allows for sparse representations of inputs and is useful for pre-training in many tasks.…”

“…We minimize the following loss function, which imposes a sparsity constraint on the reconstruction error to obtain the optimal parameters of the sparsity autoencoder [36][37][38][39]:…”

“…is the average activation of the jth hidden node with respect to the training set, and KL(ρ ρ j ) is the Kullback-Leibler divergence, which is also called the relative entropy and is defined as follows [36][37][38][39]:…”

Automatic Feature Extraction for Breast Density Segmentation and Classification

“…Later, features are extracted from the images using mathematical calculations [7]. The features extracted can be statistical, textural, and structural [8] [9]. These features are later classified using the classification algorithm called support vector machine (SVM) which helps in gaining high accuracy of cancer prediction.…”