Real-time abnormal cell detection using a deformable snake model

Radiomics Evaluation of Histological Heterogeneity Using Multiscale Textures Derived From 3D Wavelet Transformation of Multispectral Images

Purpose

Colorectal cancer (CRC) is markedly heterogeneous and develops progressively toward malignancy through several stages which include stroma (ST), benign hyperplasia (BH), intraepithelial neoplasia (IN) or precursor cancerous lesion, and carcinoma (CA). Identification of the malignancy stage of CRC pathology tissues (PT) allows the most appropriate therapeutic intervention.

Methods

This study investigates multiscale texture features extracted from CRC pathology sections using 3D wavelet transform (3D-WT) filter. Multiscale features were extracted from digital whole slide images of 39 patients that were segmented in a pre-processing step using an active contour model. The capacity for multiscale texture to compare and classify between PTs was investigated using ANOVA significance test and random forest classifier models, respectively.

Results

12 significant features derived from the multiscale texture (i.e., variance, entropy, and energy) were found to discriminate between CRC grades at a significance value of p < 0.01 after correction. Combining multiscale texture features lead to a better predictive capacity compared to prediction models based on individual scale features with an average (±SD) classification accuracy of 93.33 (±3.52)%, sensitivity of 88.33 (± 4.12)%, and specificity of 96.89 (± 3.88)%. Entropy was found to be the best classifier feature across all the PT grades with an average of the area under the curve (AUC) value of 91.17, 94.21, 97.70, 100% for ST, BH, IN, and CA, respectively.

Conclusion

Our results suggest that multiscale texture features based on 3D-WT are sensitive enough to discriminate between CRC grades with the entropy feature, the best predictor of pathology grade.

An on-chip imaging droplet-sorting system: a real-time shape recognition method to screen target cells in droplets with single cell resolution

A microfluidic on-chip imaging cell sorter has several advantages over conventional cell sorting methods, especially to identify cells with complex morphologies such as clusters. One of the remaining problems is how to efficiently discriminate targets at the species level without labelling. Hence, we developed a label-free microfluidic droplet-sorting system based on image recognition of cells in droplets. To test the applicability of this method, a mixture of two plankton species with different morphologies (Dunaliella tertiolecta and Phaeodactylum tricornutum) were successfully identified and discriminated at a rate of 10 Hz. We also examined the ability to detect the number of objects encapsulated in a droplet. Single cell droplets sorted into collection channels showed 91 ± 4.5% and 90 ± 3.8% accuracy for D. tertiolecta and P. tricornutum, respectively. Because we used image recognition to confirm single cell droplets, we achieved highly accurate single cell sorting. The results indicate that the integrated method of droplet imaging cell sorting can provide a complementary sorting approach capable of isolating single target cells from a mixture of cells with high accuracy without any staining.

Algorithm for the precise detection of single and cluster cells in microfluidic applications

Recent advances in imaging flow cytometry and microfluidic applications have led to the development of suitable mathematical algorithms capable of detecting and identifying targeted cells in images. In contrast to currently existing algorithms, we herein proposed the identification and reconstruction of cell edges based on original approaches that overcome frequent detection limitations such as halos, noise, and droplet boundaries in microfluidic applications. Reconstructed cells are then discriminated between single cells and clusters of round-shaped cells, and cell information such as the area and location of a cell in an image is output. Using this method, 76% of cells detected in an image had an error <5% of the cell area size and 41% of the image had an error <1% of the cell area size (n = 1,000). The method developed in the present study is the first image processing algorithm designed to be flexible in use (i.e. independent of the size of an image, using a microfluidic droplet system or not, and able to recognize cell clusters in an image) and provides the scientific community with a very accurate imaging algorithm in the field of microfluidic applications. © 2016 International Society for Advancement of Cytometry.