Search

• Karyotyping is a popular method of chromosome analysis in cytogenetic laboratories to diagnose the genetic disorders. • Finding analyzable metaphase images is essential for karyotyping that needs to be done automatically and accurately. • Automation of finding analyzable metaphase images reduces the interobservor variation and speeds-up the karyotyping. • Enhancing the sensitivity and specificity of this task, has big effect on overal accuracy of karyotyping resulting to the more accurate diagnosis. • An automated high accurate metaphase finder decreases the clinical and sampling work and costs. Finding analyzable metaphase chromosome images is an essential step in karyotyping which is a common task for clinicians to diagnose cancers and genetic disorders precisely. This step is tedious and time-consuming. Hence developing automated fast and reliable methods to assist clinical technicians becomes indispensable. Previous approaches include methods with feature extraction followed by rule or quality based classifiers, component analysis, and neural networks. A two-stage automated metaphase-finding scheme, consisting of an image processing based metaphase detection stage, and a deep convolutional neural network based selection stage is proposed. The first stage detects metaphase images from 10× scan of specimen slides. The selection stage, on the other hand, selects the analyzable ones among them. The proposed scheme has a 99.33% true positive rate and 0.34% of the false positive rate of metaphase finding. This study demonstrates an effective scheme for the automated finding of analyzable metaphase images with high True positive and low False positive rates. [ABSTRACT FROM AUTHOR]

[Display omitted] • Visual expression of breast cancer with IHC allows evaluation of CerbB2 receptors. • CerbB2 mutated breast carcinomas are suitable for targeted therapy. • Breast tumors are evaluated in four different scores as 0, 1, 2, and 3. • Scoring determines the applicability of CerbB2 protein specific treatment. • Pathologists decide the scores by eye. • This is a laborious task with high inter-observer variability. • We propose cell-based image analysis techniques to determine CerbB2/HER2 scores. • This is in accordance with ASCO/CAP recommendations. • The method provides an explainable AI solution for HER2 scoring. Background and Objective: Visual expression of invasive breast cancer with immunohistochemistry (IHC) allows evaluation of CerbB2 receptors, such that CerbB2 mutated breast carcinomas are suitable for targeted therapy. Breast tumors are evaluated in four different scores as 0, 1, 2, 3 to decide if it is suitable for the CerbB2 protein specific treatment or not. Pathologists try to decide the scores by eye, which is laborious, and error-prone work with high inter-observer variability. Methods: We propose cell based image analysis termine the CerbB2/HER2 scores in breast tissue images in accordance with ASCO/CAP recommendations, automatically. The proposed ASCO/CAP recommendations compliant image analysis approach provides an explainable artificial intelligence solution for HER2 tissue scoring. Firstly, tissue images are separated into hematoxylin and diaminobenzidine color channels with color deconvolution. Cell nuclei and boundaries are segmented with a hybrid multi-level thresholding and radial line based method on hematoxylin channel. Following ASCO/CAP recommendations, cell based features representing the intensity and completeness of circumferential membrane staining are extracted with the proposed Membrane Intensity Histogram (MIH) method. Extracted features are, then, fed into a classifier, such as, k-nearest neighbours, decision trees and long-short term memory, to determine cell based HER2 scores. Individual cell scores are combined according to ASCO/CAP recommendations to obtain the final CerbB2/HER2 tissue score. Another contribution of the paper is the introduction of two publicly available image data sets on CerbB2/HER2 tissue scoring. Clinical data sets, ITU-MED-1 and ITU-MED-2, are created by digitizing IHC slides from real patients, that have ground truth CerbB2/HER2 scores. Result: The proposed automatic scoring method is tested on these clinical data sets, as well as, on a HER2 Contest data set. Performance of the proposed explainable artificial intelligence approach for HER2 tissue scoring is evaluated and compared with state-of-the-art techniques in the literature. Conclusion: Results suggest that, the proposed method is highly effective in HER2 tissue scoring on both balanced and unbalanced data sets. Significance: A hand-crafted feature extraction approach for CerbB2/HER2 scoring is proposed which provides an explainable artificial intelligence framework. The proposed HER2 scoring method can be adapted to updates in ASCO/CAP recommendations without the need for re-training and/or re-designing the model. Moreover, two publicly available data sets, namely, ITU-MED-1 and ITU-MED-2 are introduced with corresponding score labels. [ABSTRACT FROM AUTHOR]

• Myelin damage is at the heart of many neurodegenerative diseases such as MS. • Drug discovery for MS requires manual myelin counting on the microscopic images. • Myelin detection may be expedited by orders of magnitude using machine learning. • Myelin detection performances of 23 machine learning techniques were evaluated. • Boosted Trees and customized-CNN were accurate (over 98%), robust, and fast. The myelin sheath produced by glial cells insulates the axons, and supports the function of the nervous system. Myelin sheath degeneration causes neurodegenerative disorders, such as multiple sclerosis (MS). There are no therapies for MS that promote remyelination. Drug discovery frequently involves screening thousands of compounds. However, this is not feasible for remyelination drugs, since myelin quantification is a manual labor-intensive endeavor. Therefore, the development of assistive software for expedited myelin detection is instrumental for MS drug discovery by enabling high-content image-based drug screens. In this study, we developed a machine learning based expedited myelin detection approach in fluorescence microscopy images. Multi-channel three-dimensional microscopy images of a mouse stem cell-based myelination assay were labeled by experts. A spectro-spatial feature extraction method was introduced to represent local dependencies of voxels both in spatial and spectral domains. Feature extraction yielded two data set of over forty-seven thousand annotated images in total. Myelin detection performances of 23 different supervised machine learning techniques including a customized-convolutional neural network (CNN), were assessed using various train/test split ratios of the data sets. The highest accuracy values of 98.84 ± 0.09 % and 98.46 ± 0.11 % were achieved by Boosted Trees and customized-CNN, respectively. Our approach can detect myelin in a common experimental setup. Myelin extending in any orientation in 3 dimensions is segmented from 3 channel z-stack fluorescence images. Our results suggest that the proposed expedited myelin detection approach is a feasible and robust method for remyelination drug screening. [ABSTRACT FROM AUTHOR]