Combining Unsupervised Feature Learning and Riesz Wavelets for Histopathology Image Representation: Application to Identifying Anaplastic Medulloblastoma

Abstract

Abstract. Medulloblastoma (MB) is a type of brain cancer that represent roughly 25% of all brain tumors in children. In the anaplastic medulloblastoma subtype, it is important to identify the degree of irregularity and lack of organizations of cells as this correlates to disease aggressiveness and is of clinical value when evaluating patient prognosis. This paper presents an image representation to distinguish these subtypes in histopathology slides. The approach combines learned features from (i) an unsupervised feature learning method using topographic independent component analysis that captures scale, color and translation invariances, and (ii) learned linear combinations of Riesz wavelets calculated at several orders and scales capturing the granularity of multiscale rotation-covariant information. The contribution of this work is to show that the combination of two complementary approaches for feature learning (unsupervised and supervised) improves the classification performance. Our approach outperforms the best methods in literature with statistical significance, achieving 99% accuracy over region-based data comprising 7,500 square regions from 10 patient studies diagnosed with medulloblastoma (5 anaplastic and 5 non-anaplastic).

Fusing learned representations from Riesz Filters and Deep CNN for lung tissue classification

“…For a fair comparison of all five configurations (i.e., Riesz, DL, early and late fusion, a softmax classifier with an intermediate hidden layer was trained using the same hyper-parameters. Softmax classifiers have proven to be useful when combining features from several sources in medical imaging (Otálora et al, 2015).…”

Dual discriminative local coding for tissue aging analysis

“…Depending on the focus of method design, existing studies in microscopy image classification can be categorized into two groups. The first group focuses on feature extraction, in which customized features are designed (Su et al, 2012;Sparks and Madabhushi, 2013;Peter et al, 2015;Xu et al, 2015;Jiang et al, 2015;Barker et al, 2016) or automated feature learning is conducted (Zhou et al, 2014;Otalora et al, 2015;BenTaieb et al, 2015;Wang et al, 2015). The second group focuses on the classifier design while standard and simple feature descriptors are used.…”

Histopathology Image Categorization with Discriminative Dimension Reduction of Fisher Vectors

“…The patch-level local descriptor is the concatenation of features from the two layers. The use of unsupervised feature learning is inspired by existing work [6,10], which shows that unsupervised feature learning is highly effective and can be more representative than supervised feature learning for microscopy images. We have also evaluated DBN with other numbers of layers and nodes, using only the features from the last layer, or generating local descriptors at multiple scales.…”