Acrylamide is a commonly used industrial chemical that is known to be neurotoxic to mammals. However, its developmental toxicity is rarely assessed in mammalian models because of the cost and complexity involved. We used zebrafish to assess the neurotoxicity, developmental and behavioral toxicity of acrylamide. At 6 h post fertilization, zebrafish embryos were exposed to four concentrations of acrylamide (10, 30, 100, or 300 mg/L) in a medium for 114 h. Acrylamide caused developmental toxicity characterized by yolk retention, scoliosis, swim bladder deficiency, and curvature of the body. Acrylamide also impaired locomotor activity, which was measured as swimming speed and distance traveled. In addition, treatment with 100 mg/L acrylamide shortened the width of the brain and spinal cord, indicating neuronal toxicity. In summary, acrylamide induces developmental toxicity and neurotoxicity in zebrafish. This can be used to study acrylamide neurotoxicity in a rapid and cost-efficient manner.

Drug-induced liver injury (DILI) presents significant diagnostic challenges, and recently artificial intelligence-based deep learning technology has been used to predict various hepatic findings. In this study, we trained a set of Mask R-CNN-based deep algorithms to learn and quantify typical toxicant induced-histopathological lesions, portal area, and connective tissue in Sprague Dawley rats. We compared a set of single-finding models (SFMs) and a combined multiple-finding model (MFM) for their ability to simultaneously detect, classify, and quantify multiple hepatic findings on rat liver slide images. All of the SFMs yielded mean average precision (mAP) values above 85%, suggesting that the models had been successfully established. The MFM showed better performance than the SFMs, with a total mAP value of 92.46%. We compared the model predictions for slide images with ground-truth annotations generated by an accredited pathologist. For the MFM, the overall and individual finding predictions were highly correlated with the annotated areas, with R-squared values of 0.852, 0.952, 0.999, 0.990, and 0.958 being obtained for portal area, infiltration, necrosis, vacuolation, and connective tissue (including fibrosis), respectively. Our results indicate that the proposed MFM could be a useful tool for detecting and predicting multiple hepatic findings in basic non-clinical study settings.

Although drug-induced liver injury (DILI) is a major target of the pharmaceutical industry, we currently lack an efficient model for evaluating liver toxicity in the early stage of its development. Recent progress in artificial intelligence-based deep learning technology promises to improve the accuracy and robustness of current toxicity prediction models. Mask region-based CNN (Mask R-CNN) is a detection-based segmentation model that has been used for developing algorithms. In the present study, we applied a Mask R-CNN algorithm to detect and predict acute hepatic injury lesions induced by acetaminophen (APAP) in Sprague-Dawley rats. To accomplish this, we trained, validated, and tested the model for various hepatic lesions, including necrosis, inflammation, infiltration, and portal triad. We confirmed the model performance at the whole-slide image (WSI) level. The training, validating, and testing processes, which were performed using tile images, yielded an overall model accuracy of 96.44%. For confirmation, we compared the model’s predictions for 25 WSIs at 20× magnification with annotated lesion areas determined by an accredited toxicologic pathologist. In individual WSIs, the expert-annotated lesion areas of necrosis, inflammation, and infiltration tended to be comparable with the values predicted by the algorithm. The overall predictions showed a high correlation with the annotated area. The R square values were 0.9953, 0.9610, and 0.9445 for necrosis, inflammation plus infiltration, and portal triad, respectively. The present study shows that the Mask R-CNN algorithm is a useful tool for detecting and predicting hepatic lesions in non-clinical studies. This new algorithm might be widely useful for predicting liver lesions in non-clinical and clinical settings.

Polyhexamethyleneguanidine phosphate (PHMG-P) is one of the causative agents of humidifier disinfectant-induced lung injury. Direct exposure of the lungs to PHMG-P causes interstitial pneumonia with fibrosis. Epidemiological studies showed that patients with humidifier disinfectant-associated lung injuries have suffered from restrictive lung function five years after the onset of the lung injuries. We investigated whether lung damage was sustained after repeated exposure to PHMG-P followed by a long-term recovery and evaluated the adverse effects of PHMG-P on mice lungs. Mice were intranasally instilled with 0.3 mg/kg PHMG-P six times at two weeks intervals, followed by a recovery period of 292 days. Histopathological examination of the lungs showed the infiltration of inflammatory cells, the accumulation of extracellular matrix in the lung parenchyma, proteinaceous substances in the alveoli and bronchiolar–alveolar hyperplasia. From RNA-seq, the gene expression levels associated with the inflammatory response, leukocyte chemotaxis and fibrosis were significantly upregulated, whereas genes associated with epithelial/endothelial cells development, angiogenesis and smooth muscle contraction were markedly decreased. These results imply that persistent inflammation and fibrotic changes caused by repeated exposure to PHMG-P led to the downregulation of muscle and vascular development and lung dysfunction. Most importantly, this pathological structural remodeling induced by PHMG-P was not reversed even after long-term recovery.

Deep learning has recently become one of the most popular methods of image analysis. In non-clinical studies, several tissue slides are generated to investigate the toxicity of a test compound. These are converted into digital image data using a slide scanner, which is then studied by researchers to investigate abnormalities, and the deep learning method has been started to adopt in this study. However, comparative studies evaluating different deep learning algorithms for analyzing abnormal lesions are scarce. In this study, we applied three algorithms, SSD, Mask R-CNN, and DeepLabV3⁺, to detect hepatic necrosis in slide images and determine the best deep learning algorithm for analyzing abnormal lesions. We trained each algorithm on 5750 images and 5835 annotations of hepatic necrosis including validation and test, augmented with 500 image tiles of 448 × 448 pixels. Precision, recall, and accuracy were calculated for each algorithm based on the prediction results of 60 test images of 2688 × 2688 pixels. The two segmentation algorithms, DeepLabV3⁺ and Mask R-CNN, showed over 90% of accuracy (0.94 and 0.92, respectively), whereas SSD, an object detection algorithm, showed lower accuracy. The trained DeepLabV3⁺ outperformed all others in recall while also successfully separating hepatic necrosis from other features in the test images. It is important to localize and separate the abnormal lesion of interest from other features to investigate it on a slide level. Therefore, we suggest that segmentation algorithms are more appropriate than object detection algorithms for use in the pathological analysis of images in non-clinical studies.

Artificial intelligence (AI)-based analysis has recently been adopted in the examination of histological slides via the digitization of glass slides using a digital scanner. In this study, we examined the effect of varying the staining color tone and magnification level of a dataset on the result of AI model prediction in hematoxylin and eosin stained whole slide images (WSIs). The WSIs of liver tissues with fibrosis were used as an example, and three different datasets (N20, B20, and B10) were prepared with different color tones and magnifications. Using these datasets, we built five models trained Mask R-CNN algorithm by a single or mixed dataset of N20, B20, and B10. We evaluated their model performance using the test dataset of three datasets. It was found that the models that were trained with mixed datasets (models B20/N20 and B10/B20), which consist of different color tones or magnifications, performed better than the single dataset trained models. Consequently, superior performance of the mixed models was obtained from the actual prediction results of the test images. We suggest that training the algorithm with various staining color tones and multi-scaled image datasets would be more optimized for consistent remarkable performance in predicting pathological lesions of interest.