A machine-vision-based frailty index for mice

Hession, Leinani; Sabnis, Gautam; Churchill, Gary A.; Kumar, Vivek

doi:10.1038/s43587-022-00266-0

Cited by 18 publications

(21 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grooming was classified using a action detection network as previously described [35]. Spinal mobility metrics and rearing were derived using the pose estimation data as previously described [54]. Freezing behavior was heuristically derived by taking the average speed of the nose, base of head, and base of tail points at each frame, and finding periods of at least 3 seconds where the average speed of the mouse was less than 0.09 pixels/sec.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A high-throughput machine vision-based univariate scale for pain and analgesia in mice

Sabnis

Hession

Kim

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Treatment of acute and chronic pain represent a widespread clinical challenge with poor therapeutic options. While rodents are an invaluable model to study pain, scoring nociceptive responses in clinically relevant paradigms and at high-throughput remains an unmet challenge. Therefore, there is a need for automated, high-throughput methods that sensitively and accurately assess pain and analgesia. Such objective and scalable technologies will enable the discovery of novel analgesics and yield mechanistic insights into the neural and genetic mechanisms of pain. Here, we adopt the open field arena to build a univariate scale for the formalin injection model of inflammatory pain by using a machine learning approach that incorporates 82 behavioral features. This tool outperforms traditional measures of licking and shaking in detection of formalin dose, and was validated using 4 diverse mouse strains. We also detected previously unreported differences in formalin induced nocifensive behaviors that were strain and sex specific. This model also reliably identifies morphine induced antinociception. This novel, sensitive, and inexpensive tool provides a method for quantifying voluntary nociceptive responses to facilitate genetic mapping and analgesic compound screening in a high throughput manner.

show abstract

Section: Methodsmentioning

confidence: 99%

“…We took the averages and inter-quartile ranges for all measures. We previously developed methods for looking at the bend of the spine throughout the video [54]. Briefly, we track the pose coordinates of three points on the mouse at each frame: the back of the head (A), the middle of the back (B), and the base of the tail (C).…”

Section: Pose Estimation and Gaitmentioning

confidence: 99%

A high-throughput machine vision-based univariate scale for pain and analgesia in mice

Sabnis

Hession

Kim

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Parks et al, 2011). The convenience of the open-field paradigm for analysis of multiple traits has motivated the development of mouse FI versions that rely mostly (Whitehead et al, 2013) or entirely (Hession et al, 2021) on analytics of data from that assay. In addition to improved consistency/reliability, these cases greatly ease the practical application of FI by consolidating data collection to a single, low-labor assay.…”

Section: Introductionmentioning

confidence: 99%

A home-cage, video monitoring-based mouse frailty index detects age-associated morbidity in the absence of handler-induced stress

Ruby

Ylagan

Francesco

et al. 2022

Preprint

View full text Add to dashboard Cite

Frailty indexes provide quantitative measurements of non-specific health decline and are particularly useful as longitudinal monitors of pre-mortal morbidity in aging studies. For mouse studies, frailty assessments can be taken non-invasively, but they require handling and direct observation that is labor-intensive to the scientist and stress-inducing to the animal. Here, we implement, evaluate, and provide a digital frailty index composed entirely of computational analyses of home-cage video and compare it to manually obtained frailty scores in genetically diverse mice. We show that the frailty scores assigned by our digital index correlate with both manually obtained frailty scores and chronological age. Thus, we provide a tool for frailty assessment that reduces stress to the animal and can be collected consistently, at scale, without substantial labor cost.

show abstract

“…Parameters derived from the open-field assay ( 18 ), for which behavior is often analyzed using computer vision ( 19 ), are often included in traditional frailty assessments (eg, ( 9 )). The convenience of the open-field paradigm for analysis of multiple traits has motivated the development of mouse FI versions that rely entirely on data from that assay ( 20 ). In addition to improved reliability, these cases greatly ease the practical application of FI by consolidating data collection to a single, low-labor assay.…”

mentioning

confidence: 99%

“…The FIs described above invariantly include parameters known to be modified by handling-related stress: posture, response to stimuli, exploratory behavior, and blood chemistry among them ( 26–28 ). The recent development of an ML-based FI in the context of an open-field environment ( 20 ) represents a major advance in this regard, greatly minimizing the handling of animals—though still monitoring the mice in a stressful, brightly lit environment ( 29 ). The development of systems capable of continuously monitoring mice in their home-cage environment ( 30 , 31 ) provides an avenue to increase throughput and refine longitudinal aging studies while minimizing handling-related stress as confounders of frailty assessment.…”

mentioning

confidence: 99%

An Automated, Home-Cage, Video Monitoring-based Mouse Frailty Index Detects Age-associated Morbidity in C57BL/6 and Diversity Outbred Mice

Ruby

Francesco

Ylagan

et al. 2023

The Journals of Gerontology: Series A

View full text Add to dashboard Cite

Frailty indexes provide quantitative measurements of non-specific health decline and are particularly useful as longitudinal monitors of morbidity in aging studies. For mouse studies, frailty assessments can be taken non-invasively, but they require handling and direct observation that is labor-intensive to the scientist and stress-inducing to the animal. Here, we implement, evaluate, and provide a refined digital frailty index composed entirely of computational analyses of home-cage video and compare it to manually obtained frailty scores in both C57BL and genetically heterogeneous Diversity Outbred mice. We show that the frailty scores assigned by our digital index correlate with both manually obtained frailty scores and chronological age. Thus, we provide an automated tool for frailty assessment that can be collected reproducibly, at scale, without substantial labor cost.

show abstract

A machine-vision-based frailty index for mice

Cited by 18 publications

References 63 publications

A high-throughput machine vision-based univariate scale for pain and analgesia in mice

A high-throughput machine vision-based univariate scale for pain and analgesia in mice

A home-cage, video monitoring-based mouse frailty index detects age-associated morbidity in the absence of handler-induced stress

An Automated, Home-Cage, Video Monitoring-based Mouse Frailty Index Detects Age-associated Morbidity in C57BL/6 and Diversity Outbred Mice

Contact Info

Product

Resources

About