Astrogliosis mapping in individual brains using multidimensional MRI

There are currently no noninvasive imaging methods available for astrogliosis mapping in the central nervous system despite its essential role in the response to injury, disease, and infection. We have developed a machine learning-based multidimensional MRI framework that provides a signature of astrogliosis, distinguishing it from normative brain at the individual level. We investigated ex vivo cortical tissue specimen derived from subjects who sustained blast induced injuries, which resulted in scar-border forming astrogliosis without being accompanied by other types of neuropathology. By performing a combined postmortem radiology and histopathology correlation study we found that astrogliosis induces microstructural changes that are robustly detected using our framework, resulting in MRI neuropathology maps that are significantly and strongly correlated with co-registered histological images of increased glial fibrillary acidic protein deposition. The demonstrated high spatial sensitivity in detecting reactive astrocytes at the individual level has great potential to significantly impact neuroimaging studies in diseases, injury, repair, and aging.

Deep Learning Algorithm for Diagnose Endoscopic and Histological Images With Ulcerative Colitis

The goal of treatment for ulcerative colitis is to achieve histological and endoscopic remission. Aiming at the problem that the observer will be affected by subjective factors in the endoscopic evaluation of ulcerative colitis and the cumbersome diagnosis process of histological images, this paper aims to develop a computer-assisted diagnosis system for real-time, objective diagnosis of endoscopic images and use the trained CNN model to predict histological images of patients with ulcerative colitis. Diagnosing endoscopic remission of ulcerative colitis, the accuracy of the CNN is 97.04% (95% CI,96.26%:97.62%). Diagnosing the severity of endoscopic inflammation in patients with ulcerative colitis, the accuracy of the CNN is 90.15% (95% CI, 89.49%:90.82%). The accuracy of predicting histological remission was 91.28%. The kappa coefficient between the CNN model and the biopsy results was 82.56%. The proposed computer-aided diagnosis system can effectively evaluate the inflammation of endoscopic images of patients with ulcerative colitis and predict the remission of histological images with high accuracy and consistency.

Fatquant: An automated image analysis tool for identification of fat cells in heterogeneous hematoxylin and eosin tissue sections.

Hematoxylin and eosin (H and E) is one of the common histological staining techniques that provides information on the tissue cytoarchitecture. Adipose (fat) cells accumulation in pancreas has been shown to impact beta cell survival and its endocrine function. The current automated tools available for fat analysis are suited for white adipose tissue which is homogeneous and easier to segment unlike heterogeneous tissues such as pancreas where fat cells continue to play critical physiopathological functions. In the current study, we present an automated fat analysis tool, Fatquant, where mathematical formula to calculate diagonal of a square drawn inside circle is utilized for identification and analysis of fat cells in heterogeneous H and E tissue sections. Using histological images of pancreas from a publicly available database, we show an area accuracy overlap of 89-93% between manual versus automated algorithm based fat cell detection.

Association between the chronology of gestation and the morphometrical skin characteristics at childbirth: a development of predictive model

ObjectiveThe structural maturation of the skin is considered a potential marker of pregnancy dating. This study investigated the correlation between the morphometrical skin characteristics with the pregnancy chronology to propose models for predicting gestational age.MethodsA cross-sectional analysis selected 35 corpses of newborns. The biopsy was performed up to 48 hours after death in the periumbilical abdomen, palm and sole regions. Pregnancy chronology was based on the obstetric ultrasound before 14 weeks. The dimensions of the skin layers, area of glands and connective fibrous tissue were measured with imaging software support. Univariate and multivariate regression models on morphometric values were used to predict gestational age.ResultsGestational age at birth ranged from 20.3 to 41.2 weeks. Seventy-one skin specimens resulted in the analysis of 1183 digital histological images. The correlation between skin thickness and gestational age was positive and strong in both regions of the body. The highest univariate correlation between gestational age and skin thickness was using the epidermal layer dimensions, in palm (r=0.867, p<0.001). The multivariate modelling with the thickness of the abdominal epidermis, the dermis and the area of the sebaceous glands adjusted had the highest correlation with gestational age (r=0.99, p<0.001).ConclusionThe thickness of the protective epidermal barrier is, in itself, a potential marker of pregnancy dating. However, sets of values obtained from skin morphometry enhanced the estimation of the gestational age. Such findings may support non-invasive image approaches to estimate pregnancy dating with various clinical applications.

Reduced and stable feature sets selection with random forest for neurons segmentation in histological images of macaque brain

In preclinical research, histology images are produced using powerful optical microscopes to digitize entire sections at cell scale. Quantification of stained tissue relies on machine learning driven segmentation. However, such methods require multiple additional information, or features, which are increasing the quantity of data to process. As a result, the quantity of features to deal with represents a drawback to process large series or massive histological images rapidly in a robust manner. Existing feature selection methods can reduce the amount of required information but the selected subsets lack reproducibility. We propose a novel methodology operating on high performance computing (HPC) infrastructures and aiming at finding small and stable sets of features for fast and robust segmentation of high-resolution histological images. This selection has two steps: (1) selection at features families scale (an intermediate pool of features, between spaces and individual features) and (2) feature selection performed on pre-selected features families. We show that the selected sets of features are stables for two different neuron staining. In order to test different configurations, one of these dataset is a mono-subject dataset and the other is a multi-subjects dataset to test different configurations. Furthermore, the feature selection results in a significant reduction of computation time and memory cost. This methodology will allow exhaustive histological studies at a high-resolution scale on HPC infrastructures for both preclinical and clinical research.

Potential of Optical Frequency Domain Imaging for Differentiation Between Early and Advanced Coronary Atherosclerosis

Purpose Optical frequency domain imaging (OFDI) is widely used to characterize lipidic-atherosclerotic plaques, shown as signal-poor regions with diffuse borders, in clinical setting. Given that lipid components are common to both fibroatheroma (FA) and pathological intimal thickening (PIT), it is unclear whether OFDI can be used to accurately distinguish between FA and PIT. This study evaluated the differences in OFDI findings between FA and PIT in comparison with histopathology. Methods A total of 631 histological cross-sections from 14 autopsy hearts were analyzed for the comparison between OFDI and histological images. Of those, 190 (30%) sections were diagnosed with PIT and 120 (19%) with FA. All OFDI images were matched with histology and the OFDI signal attenuation rate was calculated from an exponential. The lipid length was measured longitudinally, and the lipid arc was measured with a protractor centered in the center of the lumen. Results There was no significant difference in the OFDI signal attenuation rate between FA and PIT (3.09 ± 1.04 versus 2.79 ± 1.20, p = 0.13). However, the lipid length was significantly longer and the maximum lipid arc was significantly larger in FA than in PIT (7.5 [4.3–10.3] mm versus 4.3 [2.7–5.8] mm, p < 0.0001, and 125 [101–174]° versus 96 [74–131]°, p < 0.0001, respectively). Conclusions OFDI may be capable of discriminating advanced lipid plaques from early stage atherosclerosis based on the longitudinal and circumferential extent of signal-poor region.

Jointly Optimized Spatial Histogram UNET Architecture (JOSHUA) for Adipose Tissue Segmentation

Objective: We quantify adipose tissue deposition at surgical sites as a function of biomaterial implantation. Impact Statement: To our knowledge, this study is the first investigation to apply convolutional neural network (CNN) models to identify and segment adipose tissue in histological images from silk fibroin biomaterial implants. Introduction: When designing biomaterials for the treatment of various soft tissue injuries and diseases, one must consider the extent of adipose tissue deposition. In this work, we implant silk fibroin biomaterials in a rodent subcutaneous injury model. Current strategies for quantifying adipose tissue after biomaterial implantation are often tedious and prone to human bias during analysis. Methods: We used CNN models with novel spatial histogram layer(s) that can more accurately identify and segment regions of adipose tissue in hematoxylin and eosin (H&E) and Masson's Trichrome stained images, allowing for determination of the optimal biomaterial formulation. We compared the method, Jointly Optimized Spatial Histogram UNET Architecture (JOSHUA), to the baseline UNET model and an extension of the baseline model, Attention UNET, as well as to versions of the models with a supplemental "attention"-inspired mechanism (JOSHUA+ and UNET+). Results: The inclusion of histogram layer(s) in our models shows improved performance through qualitative and quantitative evaluation. Conclusion: Our results demonstrate that the proposed methods, JOSHUA and JOSHUA+, are highly beneficial for adipose tissue identification and localization. The new histological dataset and code for our experiments are publicly available.