Quantitative neurotoxicology: Potential role of artificial intelligence/deep learning approach

Abstract

Neurotoxicity studies are important in the preclinical stages of drug development process, because exposure to certain compounds that may enter the brain across a permeable blood brain barrier damages neurons and other supporting cells such as astrocytes. This could, in turn, lead to various neurological disorders such as Parkinson's or Huntington's disease as well as various dementias. Toxicity assessment is often done by pathologists after these exposures by qualitatively or semiquantitatively grading the severity of neurotoxicity in histopathology slides. Quantification of the extent of neurotoxicity supports qualitative histopathological analysis and provides a better understanding of the global extent of brain damage. Stereological techniques such as the utilization of an optical fractionator provide an unbiased quantification of the neuronal damage; however, the process is time‐consuming. Advent of whole slide imaging (WSI) introduced digital image analysis which made quantification of neurotoxicity automated, faster and with reduced bias, making statistical comparisons possible. Although automated to a certain level, simple digital image analysis requires manual efforts of experts which is time‐consuming and limits analysis of large datasets. Digital image analysis coupled with a deep learning artificial intelligence model provides a good alternative solution to time‐consuming stereological and simple digital analysis. Deep learning models could be trained to identify damaged or dead neurons in an automated fashion. This review has focused on and discusses studies demonstrating the role of deep learning in segmentation of brain regions, toxicity detection and quantification of degenerated neurons as well as the estimation of area/volume of degeneration.

Quantitative circular flow immunoassays with trained object recognition to detect antibodies to SARS-CoV-2 membrane glycoprotein

“…As a result, quantifications cannot be instantaneously determined and are often subjective to human error due to the ambiguity of the spot areas. The use of deep learning to help create well-defined spot areas is a solution for an accurate quantification [ 20 ]. Here, identifications of spot areas on CFIAs were performed by YOLO v4 object detection software [ 14 ].…”

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

“…273 With the introduction of whole slide imaging (WSI), different deep-learning algorithms are significantly contributing to different areas of neurotoxicological analysis like deep-learning-assisted automated brain image segmentation, detection and analysis of toxicity in different regions of the brain, etc. 273 Wang et al used a CNN model to automatically detect focal cerebral ischemia-reperfusion-injured neurons in label-free two-photon microscopic (TPM) images. 274 This model significantly improves diagnostic accuracy compared with standard histology and detects the location of the injured neuron without prior knowledge of histopathology.…”

“…274 Though this study is not directly related to druginduced toxicity, the approach could be extrapolated to neurotoxicological analysis to yield robust toxicity quantification tools that in turn shall reduce the need of using more laboratory animals to get robust results. 273,274 Drug-induced toxicity is tightly related to hepatic and cardiac adverse effects of drugs, and more than 75% of postmarketing withdrawals of drugs are due to these two causes. 275−277 These toxicities are intricately related to the disruption of the subcellular structures.…”

“…The study used 64 × 64 pixels input images to be fed into a Residual Network CNN (ResNet CNN), which reduces the spatial resolution of the input . Though this study is not directly related to drug-induced toxicity, the approach could be extrapolated to neurotoxicological analysis to yield robust toxicity quantification tools that in turn shall reduce the need of using more laboratory animals to get robust results. , …”

Assessment of Skin Toxicity in an in Vitro Reconstituted Human Epidermis Model Using Deep Learning

“…25 Finally, deep-learning methods have been suggested as a means for identifying neurotoxicity using the robust segmentation framework that has already been developed for brain imaging. 26 However, deep learning approaches have not yet been applied to preclinical skin toxicity analysis.…”