Deep learning-based method for segmenting epithelial layer of tubules in histopathological images of testicular tissue.

Purpose: There is growing concern that male reproduction is affected by environmental chemicals. One way to determine the adverse effect of environmental pollutants is to use wild animals as monitors and evaluate testicular toxicity using histopathology. We propose an automated method to process histology images of testicular tissue. Approach: Testicular tissue consists of seminiferous tubules. Segmenting the epithelial layer of the seminiferous tubule is a prerequisite for developing automated methods to detect abnormalities in tissue. We suggest an encoder-decoder fully connected convolutional neural network model to segment the epithelial layer of the seminiferous tubules in histological images. The ResNet-34 is used in the feature encoder module, and the squeeze and excitation attention block is integrated into the encoding module improving the segmentation and localization of epithelium. Results: We applied the proposed method for the two-class problem, where the epithelial layer of the tubule is the target class. The F-score and Intersection over Union of the proposed method are 0.85 and 0.92. Although the proposed method is trained on a limited training set, it performs well on an independent dataset and outperforms other state-of-the-art methods. Conclusion: The pretrained ResNet-34 in the encoder and attention block suggested in the decoder result in better segmentation and generalization. The proposed method can be applied to testicular tissue images from any mammalian species and can be used as the first part of a fully automated testicular tissue processing pipeline. The dataset and codes are publicly available on GitHub.

Deep learning-based method for segmenting epithelial layer of tubules in histopathological images of testicular tissue.

Purpose: There is growing concern that male reproduction is affected by environmental chemicals. One way to determine the adverse effect of environmental pollutants is to use wild animals as monitors and evaluate testicular toxicity using histopathology. We propose an automated method to process histology images of testicular tissue. Approach: Testicular tissue consists of seminiferous tubules. Segmenting the epithelial layer of the seminiferous tubule is a prerequisite for developing automated methods to detect abnormalities in tissue. We suggest an encoder-decoder fully connected convolutional neural network model to segment the epithelial layer of the seminiferous tubules in histological images. The ResNet-34 is used in the feature encoder module, and the squeeze and excitation attention block is integrated into the encoding module improving the segmentation and localization of epithelium. Results: We applied the proposed method for the two-class problem, where the epithelial layer of the tubule is the target class. The F -score and Intersection over Union of the proposed method are 0.85 and 0.92. Although the proposed method is trained on a limited training set, it performs well on an independent dataset and outperforms other state-of-the-art methods. Conclusion: The pretrained ResNet-34 in the encoder and attention block suggested in the decoder result in better segmentation and generalization. The proposed method can be applied to testicular tissue images from any mammalian species and can be used as the first part of a fully automated testicular tissue processing pipeline. The dataset and codes are publicly available on GitHub.

Erratum: Publisher's note: Deep learning-based method for segmenting epithelial layer of tubules in histopathological images of testicular tissue.

[This corrects the article DOI: 10.1117/1.JMI.10.3.037501.].

Basic Exploratory Study of Bisphenol A (BPA) Dietary Administration to Istrian Pramenka Rams and Male Toxicity Investigation.

Bisphenol A (BPA), an endocrine-disrupting chemical and environmental pollutant, has been reported by many researchers to induce male reproductive toxicity in different experimental models. In this study, we investigated whether long-term exposure for two months to 25 µg/kg body weight (low dose) of BPA affects spermatogenesis or sperm quality in young Istrian Pramenka rams exposed via diet. We evaluated body and testicular weights, histopathology of testes and epididymides, and sperm analyses, and compared these parameters between the group of treated rams and the control group of rams. Although there were some differences between the two groups, these differences were not large or statistically significant. The only statistically significant difference was the lower epithelial height of seminiferous tubules in treated rams, compared to control rams. In addition to assessing toxicity, BPA concentrations in the blood plasma of treated rams were determined after the first administration, and the toxicokinetic parameters of total BPA were calculated. In this study, no major signs of altered reproduction in rams were detected.

Age and seasonal variation in testis and baculum morphology in East Greenland polar bears (Ursus maritimus) in relation to high concentrations of persistent organic pollutants.

Persistent organic pollutants (POPs) are found in high concentrations in the Artic. Polar bears (Ursus maritimus) are one of the most exposed mammals in the Arctic and are thereby vulnerable to reproductive disruption. The aim of this study was to investigate male polar bear reproduction based on a detailed evaluation of testis histology and to assess possible effects of environmental chemicals on male polar bear reproduction. Reproductive groups that were identified based on histology were as follows: actively reproductive (REP), non-reproductive either with degenerated testes (DEG), undeveloped seminiferous tubules (UND), or morphology in-transition (INT). Categorization into these groups was supported by significant differences in testis and baculum measurements among REP, DEG, and UND, as well as differences in the area and diameter of seminiferous tubules among REP, DEG, and UND. These results show that it is possible to identify the reproductive stage in polar bears even if capture date and or age is lacking. Based on testis morphology we suggest that adult male polar bears from East Greenland have active spermatogenesis in February to June, and inactive degenerated testes in August to January. January to February was the main period of reproductive transition, characterised by a shift between inactive and active spermatogenesis. Baculum and testis size measurements decreased significantly with increasing concentrations of the chlordane metabolite oxychlordane, suggesting a potential impact on male reproductive success. Half of the investigated polar bears in REP group displayed signs of disorganization of the spermatogenesis which might be a sign of disrupted reproduction. However, no correlations with levels of the investigated POPs were detected. Reproductive organ measurements in polar bears differed significantly between REP and DEG groups, which cannot be explained by age, and therefore should be considered when investigating the effect of POPs on male reproduction.

Low-dose exposure to Bisphenol A during development has limited effects on male reproduction in midpubertal and aging Fischer 344 rats.

Low doses of Bisphenol A (BPA) during development may affect reproduction. In this study, Fischer 344 rats were exposed to 0.5 or 50 µg BPA/kg bw/day via drinking water from gestational day 3.5 to postnatal day 22. Anogenital distance, organ weight, histopathology of reproductive organs, hormone analysis and sperm morphology were evaluated in male offspring. In this study no major effects of BPA on male reproduction in midpubertal (postnatal day 35) or adult (12-month-old) rats were revealed, apart from a higher prevalence of mild inflammatory cell infiltrate in cauda epididymis in adult rats exposed to 50 µg BPA/kg bw/day. No BPA-related effects on sexual development were seen but care should be taken when evaluating histopathology in midpuberty testis due to large morphological variation. Results from the present study show no major signs of altered male reproduction in rats exposed to low doses of BPA during gestation and lactation.

New computerized staging method to analyze mink testicular tissue in environmental research.

Histopathology of testicular tissue is considered to be the most sensitive tool to detect adverse effects on male reproduction. When assessing tissue damage, seminiferous epithelium needs to be classified into different stages to detect certain cell damages; but stage identification is a demanding task. The authors present a method to identify the 12 stages in mink testicular tissue. The staging system uses Gata-4 immunohistochemistry to visualize acrosome development and proved to be both intraobserver-reproducible and interobserver-reproducible with a substantial agreement of 83.6% (kappa = 0.81) and 70.5% (kappa = 0.67), respectively. To further advance and objectify this method, they present a computerized staging system that identifies these 12 stages. This program has an agreement of 52.8% (kappa 0.47) with the consensus staging by 2 investigators. The authors propose a pooling of the stages into 5 groups based on morphology, stage transition, and toxicologically important endpoints. The computerized program then reached a substantial agreement of 76.7% (kappa = 0.69). The computerized staging tool uses local ternary patterns to describe the texture of the tubules and a support vector machine classifier to learn which textures correspond to which stages. The results have the potential to modernize the tedious staging process required in toxicological evaluation of testicular tissue, especially if combined with whole-slide imaging and automated tubular segmentation. Environ Toxicol Chem 2017;36:156-164. © 2016 The Authors. Environmental Toxicology and Chemistry Published by Wiley Periodicals, Inc. on behalf of SETAC.

Precision Automation of Cell Type Classification and Sub-Cellular Fluorescence Quantification from Laser Scanning Confocal Images.

While novel whole-plant phenotyping technologies have been successfully implemented into functional genomics and breeding programs, the potential of automated phenotyping with cellular resolution is largely unexploited. Laser scanning confocal microscopy has the potential to close this gap by providing spatially highly resolved images containing anatomic as well as chemical information on a subcellular basis. However, in the absence of automated methods, the assessment of the spatial patterns and abundance of fluorescent markers with subcellular resolution is still largely qualitative and time-consuming. Recent advances in image acquisition and analysis, coupled with improvements in microprocessor performance, have brought such automated methods within reach, so that information from thousands of cells per image for hundreds of images may be derived in an experimentally convenient time-frame. Here, we present a MATLAB-based analytical pipeline to (1) segment radial plant organs into individual cells, (2) classify cells into cell type categories based upon Random Forest classification, (3) divide each cell into sub-regions, and (4) quantify fluorescence intensity to a subcellular degree of precision for a separate fluorescence channel. In this research advance, we demonstrate the precision of this analytical process for the relatively complex tissues of Arabidopsis hypocotyls at various stages of development. High speed and robustness make our approach suitable for phenotyping of large collections of stem-like material and other tissue types.

Effect of pre-fixation delay and freezing on mink testicular endpoints for environmental research.

There is growing interest in using wild animals to monitor the real-life cocktail effect of environmental chemicals on male reproduction. However, practical difficulties, such as long distances to the laboratory, generally prolong the time between euthanisation and specimen handling. For instance, tissue fixation is often performed on frozen material or on material where deterioration has started, which may affect tissue morphology. This study examined the effect of pre-fixation delay and freezing on mink testicular endpoints in order to determine robust endpoints in suboptimally handled specimens. Sexually mature farmed mink (n=30) selected at culling were divided into six groups and subjected to different time intervals between euthanisation and fixation or freezing: 0 hours (fixed immediately post mortem), 6 hours, 18 hours, 30 hours, 42 hours, or frozen 6 hours post mortem and thawed overnight. Unaffected endpoints when pre-fixation storage was extended to 30 hours included: area and diameter of the seminiferous tubules, length and weight of the testes, and acrosomes marked with Gata-4. Epithelial height, Sertoli cells marked with Gata-4 and cell morphology were affected endpoints after 6 hours of storage. Freezing the tissue prior to fixation severely altered cell morphology and reduced testicular weight, tubular diameter and area. Morphological changes seen after 6 hours included shredded germ cells and excess cytoplasm in seminiferous tubular lumen, chromatin rearrangements and increased germ cell death. Extended delay before fixation and freezing affected many endpoints in the mink testicular tissue. Some of these endpoints may mimic chemically induced effects, which is important to consider when evaluating specimens from wild animals for environmental toxicity.