Texture Descriptors Ensembles Enable Image-Based Classification of Maturation of Human Stem Cell-Derived Retinal Pigmented Epithelium

Abstract

AimsA fast, non-invasive and observer-independent method to analyze the homogeneity and maturity of human pluripotent stem cell (hPSC) derived retinal pigment epithelial (RPE) cells is warranted to assess the suitability of hPSC-RPE cells for implantation or in vitro use. The aim of this work was to develop and validate methods to create ensembles of state-of-the-art texture descriptors and to provide a robust classification tool to separate three different maturation stages of RPE cells by using phase contrast microscopy images. The same methods were also validated on a wide variety of biological image classification problems, such as histological or virus image classification.MethodsFor image classification we used different texture descriptors, descriptor ensembles and preprocessing techniques. Also, three new methods were tested. The first approach was an ensemble of preprocessing methods, to create an additional set of images. The second was the region-based approach, where saliency detection and wavelet decomposition divide each image in two different regions, from which features were extracted through different descriptors. The third method was an ensemble of Binarized Statistical Image Features, based on different sizes and thresholds. A Support Vector Machine (SVM) was trained for each descriptor histogram and the set of SVMs combined by sum rule. The accuracy of the computer vision tool was verified in classifying the hPSC-RPE cell maturation level.Dataset and ResultsThe RPE dataset contains 1862 subwindows from 195 phase contrast images. The final descriptor ensemble outperformed the most recent stand-alone texture descriptors, obtaining, for the RPE dataset, an area under ROC curve (AUC) of 86.49% with the 10-fold cross validation and 91.98% with the leave-one-image-out protocol. The generality of the three proposed approaches was ascertained with 10 more biological image datasets, obtaining an average AUC greater than 97%.ConclusionsHere we showed that the developed ensembles of texture descriptors are able to classify the RPE cell maturation stage. Moreover, we proved that preprocessing and region-based decomposition improves many descriptors’ accuracy in biological dataset classification. Finally, we built the first public dataset of stem cell-derived RPE cells, which is publicly available to the scientific community for classification studies. The proposed tool is available at https://www.dei.unipd.it/node/2357 and the RPE dataset at http://www.biomeditech.fi/data/RPE_dataset/. Both are available at https://figshare.com/s/d6fb591f1beb4f8efa6f.

Experiments of Image Classification Using Dissimilarity Spaces Built with Siamese Networks

“…The testing protocol is three-fold cross-validation with data separated at the patient level to ensure that the frames from the same class were classified based on the features characteristic of each class and not on features linked to the individual patient (e.g., vocal fold anatomy). RPE [ 44 ]: This is a data set that contains 195 images for the classification of maturation of human stem cell-derived retinal pigmented epithelium. The images were divided into sixteen subwindows, each of which was assigned to one of four classes: (1) Fusifors (216 images of nuclei and separated cells that are fuse shaped), (2) Epithelioid (547 images of relatively packed cells and nuclei that are globular in shape), (3) Cobblestone (949 images of well-defined cell contours and cell walls that are tightly packed, homogeneous cytoplasm, and hexagonal in shape), and (4) Mixed (150 images containing two or more instances of the other three classes).…”

“…To accomplish this goal, the new system is built with a large set of eight different CNN architectures selected for the twin classifiers, with four new CNN architectures presented here. Heterogeneous auto-similarities of characteristics (HASC) [ 42 ] features are extracted from the aforementioned bird [ 39 ] and cat [ 40 , 41 ] data sets as well as on a medical data set for classifying narrow-band imaging (NBI) endoscopic videos [ 43 ] and a data set of images for the classification of the maturation of human stem cell-derived retinal pigmented epithelium [ 44 ]. In the training phase, a clustering algorithm is employed to select a set of relevant samples to be used as the prototypes of the training samples.…”

“…RPE [44]: This is a data set that contains 195 images for the classification of maturation of human stem cell-derived retinal pigmented epithelium. The images were divided into sixteen subwindows, each of which was assigned to one of four classes:…”

Quantitative pigment extraction analysis for human pluripotent stem cell derived retinal pigment epithelial cells

“…The other aim was to evaluate if the pigment-extraction protocol could verify pigmentation values gained with the optical pigmentation analysis. The pigmentation analysis from the hESC-RPEs has previously been done with image analysis from the bright field micrographs (9,19,20) or by quantitating the extracted melanin (3) but comparison has not been previously done. Here our results demonstrated that optical pigmentation values and melanin values were clearly correlating.…”

Bird and whale species identification using sound images

“…The filters used in this approach are built by maximising the statistical independence of the filter responses on a set of sub‐windows extracted from natural images by independent component analysis. To increase the performance of this descriptor, an ensemble, as in [33], is built by varying the parameters of the approach: the filter size (size ∈ {3, 5, 7, 9, 11}); and the threshold used for binarising (th ∈ {−9, −6, −3, 0, 3, 6, 9}). In total, the ensemble is built with 35 SVMs combined by sum rule, with each SVM trained using a different feature vector extracted with a possible ( size , th ) combination of the parameters of BSIF.…”