Automated detection of mouse scratching behaviour using convolutional recurrent neural network

Artificial Intelligence: A Snapshot of Its Application in Chronic Inflammatory and Autoimmune Skin Diseases

Immuno-correlated dermatological pathologies refer to skin disorders that are closely associated with immune system dysfunction or abnormal immune responses. Advancements in the field of artificial intelligence (AI) have shown promise in enhancing the diagnosis, management, and assessment of immuno-correlated dermatological pathologies. This intersection of dermatology and immunology plays a pivotal role in comprehending and addressing complex skin disorders with immune system involvement. The paper explores the knowledge known so far and the evolution and achievements of AI in diagnosis; discusses segmentation and the classification of medical images; and reviews existing challenges, in immunological-related skin diseases. From our review, the role of AI has emerged, especially in the analysis of images for both diagnostic and severity assessment purposes. Furthermore, the possibility of predicting patients' response to therapies is emerging, in order to create tailored therapies.

Development of a 3D tracking system for multiple marmosets under free-moving conditions

Assessment of social interactions and behavioral changes in nonhuman primates is useful for understanding brain function changes during life events and pathogenesis of neurological diseases. The common marmoset (Callithrix jacchus), which lives in a nuclear family like humans, is a useful model, but longitudinal automated behavioral observation of multiple animals has not been achieved. Here, we developed a Full Monitoring and Animal Identification (FulMAI) system for longitudinal detection of three-dimensional (3D) trajectories of each individual in multiple marmosets under free-moving conditions by combining video tracking, Light Detection and Ranging, and deep learning. Using this system, identification of each animal was more than 97% accurate. Location preferences and inter-individual distance could be calculated, and deep learning could detect grooming behavior. The FulMAI system allows us to analyze the natural behavior of individuals in a family over their lifetime and understand how behavior changes due to life events together with other data.

Alleviation of allergic conjunctivitis by (±)5(6)-dihydroxy-8Z,11Z,14Z,17Z-eicosatetraenoic acid in mice

Background: Allergic conjunctivitis (AC) is a common ophthalmologic disorder that causes symptoms that often reduces a patient's quality of life (QOL). We investigated the effects of the eicosapentaenoic acid metabolite (±)5(6)-dihydroxy-8Z,11Z,14Z,17Z-eicosatetraenoic acid ((±)5(6)-DiHETE) on AC using a mouse model. Methods: BALB/c mice were sensitized with two injections of short ragweed pollen in alum, challenged fifth with pollen in eyedrops. The clinical signs and tear volume were evaluated at 15 min after the final challenge. Histamine-induced ocular inflammation model was prepared by instilling histamine onto the surface of the eye. Fifteen minutes after histamine application, tear volume was measured using the Schirmer tear test. Miles assay was performed to investigate vascular permeability. To cause scratching behavior 10 μg of serotonin was injected in the cheek. Results: Repeated topical application of pollen induced conjunctivitis, accompanied by eyelid edema and tearing in mice. Pollen application typically degranulates mast cells and recruits eosinophils to the conjunctiva. Intraperitoneal administration of 300 μg/kg of (±)5(6)-DiHETE significantly inhibited pollen-induced symptoms. The administration of (±)5(6)-DiHETE also attenuated mast cell degranulation and eosinophil infiltration into the conjunctiva. To assess the effects of (±)5(6)-DiHETE on the downstream pathway of mast cell activation in AC, we used a histamine-induced ocular inflammation model. Topical application of 4 μg/eye histamine caused eyelid edema and tearing and increased vascular permeability, as indicated by Evans blue dye extravasation. Intraperitoneal administration of 300 μg/kg or topical administration of 1 μg/eye (±)5(6)-DiHETE inhibited histamine-induced manifestations. Finally, we assessed the effects of (±)5(6)-DiHETE on itching. An intradermal injection of 10 μg serotonin in the cheek caused scratching behavior in mice. Intraperitoneal administration of 300 μg/kg (±)5(6)-DiHETE significantly inhibited serotonin-induced scratching. Conclusion: Thus, (±)5(6)-DiHETE treatment broadly suppressed AC pathology and could be a novel treatment option for AC.

Data repurposing from digital home cage monitoring enlightens new perspectives on mouse motor behaviour and reduction principle

In this longitudinal study we compare between and within-strain variation in the home-cage spatial preference of three widely used and commercially available mice strains-C57BL/6NCrl, BALB/cAnNCrl and CRL:CD1(ICR)-starting from the first hour post cage-change until the next cage-change, for three consecutive intervals, to further profile the circadian home-cage behavioural phenotypes. Cage-change can be a stressful moment in the life of laboratory mice, since animals are disturbed during the sleeping hours and must then rapidly re-adapt to a pristine environment, leading to disruptions in normal motor patterns. The novelty of this study resides in characterizing new strain-specific biological phenomena, such as activity along the cage walls and frontality, using the vast data reserves generated by previous experimental data, thus introducing the potential and exploring the applicability of data repurposing to enhance Reduction principle when running in vivo studies. Our results, entirely obtained without the use of new animals, demonstrate that also when referring to space preference within the cage, C57BL/6NCrl has a high variability in the behavioural phenotypes from pre-puberty until early adulthood compared to BALB/cAnNCrl, which is confirmed to be socially disaggregated, and CRL:CD1(ICR) which is conversely highly active and socially aggregated. Our data also suggest that a strain-oriented approach is needed when defining frequency of cage-change as well as maximum allowed animal density, which should be revised, ideally under the EU regulatory framework as well, according to the physiological peculiarities of the strains, and always avoiding the "one size fits all" approach.

Marker-less tracking system for multiple mice using Mask R-CNN

Although the appropriate evaluation of mouse behavior is crucial in pharmacological research, most current methods focus on single mouse behavior under light conditions, owing to the limitations of human observation and experimental tools. In this study, we aimed to develop a novel marker-less tracking method for multiple mice with top-view videos using deep-learning-based techniques. The following stepwise method was introduced: (i) detection of mouse contours, (ii) assignment of identifiers (IDs) to each mouse, and (iii) correction of mis-predictions. The behavior of C57BL/6 mice was recorded in an open-field arena, and the mouse contours were manually annotated for hundreds of frame images. Then, we trained the mask regional convolutional neural network (Mask R-CNN) with all annotated images. The mouse contours predicted by the trained model in each frame were assigned to IDs by calculating the similarities of every mouse pair between frames. After assigning IDs, correction steps were applied to remove the predictive errors semi-automatically. The established method could accurately predict two to four mice for first-look videos recorded under light conditions. The method could also be applied to videos recorded under dark conditions, extending our ability to accurately observe and analyze the sociality of nocturnal mice. This technology would enable a new approach to understand mouse sociality and advance the pharmacological research.

Generalized resistance to pruritogen-induced scratching in the C3H/HeJ strain

Previously the effect of the pruritogens, such as histamine and chloroquine, was tested in 11 inbred mouse strains, and this study aimed to identify resistant and sensitive strains, consistent with the observation that underlies the large variability in human populations. In the present study, we used the low responder C3H/HeJ (C3H) and the more sensitive C57BL/6J (C57) strain to find out if resistance and sensitivity to develop pruritus is restricted to only histamine and chloroquine or extends to other known pruritogens as well. We tested five additional commonly known pruritogens. We established dose-response relationships by injecting four concentrations of the pruritogens in the range of 0.3, 1, 3, and ten-fold in the nuchal fold. Then we assessed the scratching behavior for 30 min after injection with an automated custom-designed device based on the bilateral implantation of mini-magnets in the hind paws and on single cages placed within a magnetic coil. We found that the resistance to pruritogens is a general phenotype of the C3H strain and extends to all pruritogens tested, including not only histamine and chloroquine, but also endothelin, trypsin, 5-HT (serotonin), the short peptide SLIGRL, and Lysophosphatidic acid (LPA). C57 was more sensitive to all pruritogens and, in contrast to C3H, dose-response relationships were evident for some of the pruritogens. In general, comparable peak scratch responses were observed for the 0.3-fold concentrations of the pruritogens in C57 whereas C3H required at least the ten-fold concentration and still displayed only between 5 and 33% of the scratch responses observed in C57 for the respective pruritogen. The general resistance to pruritogens and the low level of scratching behavior found in the C3H strain is an interesting trait and represents a model for the study of the heritability of itch. It is accompanied in C3H with a higher sensitivity in assays of nociception.

Machine learning and deep learning frameworks for the automated analysis of pain and opioid withdrawal behaviors

The automation of behavioral tracking and analysis in preclinical research can serve to advance the rate of research outcomes, increase experimental scalability, and challenge the scientific reproducibility crisis. Recent advances in the efficiency, accuracy, and accessibility of deep learning (DL) and machine learning (ML) frameworks are enabling this automation. As the ongoing opioid epidemic continues to worsen alongside increasing rates of chronic pain, there are ever-growing needs to understand opioid use disorders (OUDs) and identify non-opioid therapeutic options for pain. In this review, we examine how these related needs can be advanced by the development and validation of DL and ML resources for automated pain and withdrawal behavioral tracking. We aim to emphasize the utility of these tools for automated behavioral analysis, and we argue that currently developed models should be deployed to address novel questions in the fields of pain and OUD research.

Automated scratching detection system for black mouse using deep learning

The evaluation of scratching behavior is important in experimental animals because there is significant interest in elucidating mechanisms and developing medications for itching. The scratching behavior is classically quantified by human observation, but it is labor-intensive and has low throughput. We previously established an automated scratching detection method using a convolutional recurrent neural network (CRNN). The established CRNN model was trained by white mice (BALB/c), and it could predict their scratching bouts and duration. However, its performance in black mice (C57BL/6) is insufficient. Here, we established a model for black mice to increase prediction accuracy. Scratching behavior in black mice was elicited by serotonin administration, and their behavior was recorded using a video camera. The videos were carefully observed, and each frame was manually labeled as scratching or other behavior. The CRNN model was trained using the labels and predicted the first-look videos. In addition, posterior filters were set to remove unlikely short predictions. The newly trained CRNN could sufficiently detect scratching behavior in black mice (sensitivity, 98.1%; positive predictive rate, 94.0%). Thus, our established CRNN and posterior filter successfully predicted the scratching behavior in black mice, highlighting that our workflow can be useful, regardless of the mouse strain.

Automated Grooming Detection of Mouse by Three-Dimensional Convolutional Neural Network

Grooming is a common behavior for animals to care for their fur, maintain hygiene, and regulate body temperature. Since various factors, including stressors and genetic mutations, affect grooming quantitatively and qualitatively, the assessment of grooming is important to understand the status of experimental animals. However, current grooming detection methods are time-consuming, laborious, and require specialized equipment. In addition, they generally cannot discriminate grooming microstructures such as face washing and body licking. In this study, we aimed to develop an automated grooming detection method that can distinguish facial grooming from body grooming by image analysis using artificial intelligence. Mouse behavior was recorded using a standard hand camera. We carefully observed videos and labeled each time point as facial grooming, body grooming, and not grooming. We constructed a three-dimensional convolutional neural network (3D-CNN) and trained it using the labeled images. Since the output of the trained 3D-CNN included unlikely short grooming bouts and interruptions, we set posterior filters to remove them. The performance of the trained 3D-CNN and filters was evaluated using a first-look dataset that was not used for training. The sensitivity of facial and body grooming detection reached 81.3% and 91.9%, respectively. The positive predictive rates of facial and body grooming detection were 83.5% and 88.5%, respectively. The number of grooming bouts predicted by our method was highly correlated with human observations (face: r = 0.93, body: r = 0.98). These results highlight that our method has sufficient ability to distinguish facial grooming and body grooming in mice.

Dissecting the precise nature of itch-evoked scratching

Itch is a discrete and irritating sensation tightly coupled to a drive to scratch. Acute scratching developed evolutionarily as an adaptive defense against skin irritants, pathogens, or parasites. In contrast, the itch-scratch cycle in chronic itch is harmful, inducing escalating itch and skin damage. Clinically and preclinically, scratching incidence is currently evaluated as a unidimensional motor parameter and believed to reflect itch severity. We propose that scratching, when appreciated as a complex, multidimensional motor behavior, will yield greater insight into the nature of itch and the organization of neural circuits driving repetitive motor patterns. We outline the limitations of standard measurements of scratching in rodent models and present new approaches to observe and quantify itch-evoked scratching. We argue that accurate quantitative measurements of scratching are critical for dissecting the molecular, cellular, and circuit mechanisms underlying itch and for preclinical development of therapeutic interventions for acute and chronic itch disorders.