#deeplabcut — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #deeplabcut, aggregated by home.social.
-
Wow, I just realized that for my current #MachineLearning #ComputerVision #DeepLabCut project I have manually placed over 100.000 labels.
Of course the model is still terrible, so it feels a bit like a lot of time wasted.
-
DATE: August 14, 2026 at 06:00PM
SOURCE: PSYPOST.ORG** Research quality varies widely from fantastic to small exploratory studies. Please check research methods when conclusions are very important to you. **
-------------------------------------------------TITLE: Fluid brain circuits drive the formation of cocaine habits
URL: https://www.psypost.org/fluid-brain-circuits-drive-the-formation-of-cocaine-habits/
As animals learn to self-administer cocaine, a specific network of brain cells rapidly expands to acquire the habit and then shrinks as the behavior becomes automatic. The composition of this network constantly changes, revealing how the brain flexibly manages addictive behaviors. The study detailing these changing brain dynamics was published in bioRxiv.
Substance use disorders often begin with an initial learning period that later morphs into a deeply ingrained habit. Transitioning between these phases requires distinct mental efforts, yet the physical brain changes that support this shift remain somewhat mysterious. University of Pittsburgh researchers Linjie Jin, Xiguang Qi, and Yan Dong wanted to understand how brain networks adapt during this process.
They focused on the nucleus accumbens, a region deep in the forebrain that processes rewards, pleasure, and motivation. The main cells in this area are called medium spiny neurons. These neurons fire electrical signals in response to things like food or drugs, forming an active group called a neuronal ensemble. The researchers suspected this ensemble might change as an animal progresses from acquiring a drug habit to maintaining it.
In a small study, the researchers trained male mice to self-administer cocaine. The animals were placed in operant conditioning chambers, which are specialized testing environments where animals learn to associate a specific action with an outcome. These boxes contained two levers, with one active lever programmed to deliver the drug.
When a mouse pressed the active lever, it received an infusion of cocaine along with a flash of light and a sound cue. Over an eleven-day period, the team recorded the animals’ behavior during daily two-hour sessions. The researchers wanted to track the exact physical paths the animals took as they learned the task.
Using a machine learning algorithm called DeepLabCut to track video recordings, they mapped the coordinates of the mice as they moved around the testing chamber. During the early days of training, the mice wandered randomly before pressing the lever. By the end of the eleven days, their behavior stabilized into a highly repetitive routine. The animals developed stereotyped, circular walking patterns immediately before and after taking the drug.
Their entries and exits from the lever area followed a highly consistent path. This circular movement pattern was not seen in a control group of mice trained to seek sugar. The specific physical routine suggested that the cocaine habit was becoming an automatic behavioral response over time. The total distance the mice traveled also increased across the training days, matching a known phenomenon where repeated cocaine use sensitizes motor activity.
To see what was happening inside the brain as this habit formed, the team used a technique called in vivo calcium imaging. They injected a specialized virus into the mice’s brains that caused the medium spiny neurons to produce a fluorescent protein. This protein was designed to react to changes in internal cellular activity.
When a neuron fires an electrical signal, calcium ions flood into the cell. The engineered protein binds to this calcium and emits a tiny flash of light. A microscopic lens implanted directly into the brain captured these flashes, allowing researchers to watch individual neurons turn on and off in real time while the mice were awake and moving.
The researchers observed that a specific set of neurons reliably lit up in the five seconds immediately after a mouse pressed the cocaine lever. During the first three days of training, the sheer number of these active neurons rapidly increased. The brain seemed to recruit a massive amount of cellular resources to learn the new drug-taking rule.
As the training progressed and the physical movements of the mice became automatic routines, the size of this active network began to shrink. By the ninth and eleventh days, the number of responding neurons dropped back down to the lower levels seen on day one.
The researchers noted that the intensity of each individual neuron’s signal stayed exactly the same across the entire experiment. The brain did not dial down the volume of the cells. Instead, fewer cells were needed to execute the established habit.
This pattern of broad recruitment followed by pruning is not unique to biological brains. The authors noted that artificial neural networks learn in a similar way. During initial training, reducing the size of an artificial network impairs its performance, showing that abundant computational resources are necessary to learn a task. Once the network is trained, many connections can be stripped away without affecting the final output.
The team also tracked individual neurons over consecutive days to see if the exact same cells made up this network over time. They used imaging software to match the shape, spatial position, and activity patterns of specific neurons from one testing session to the next.
They found that the network was highly fluid. Only about one quarter of the neurons that responded to a lever press on one day would respond again two days later. Individual cells constantly dropped into and out of the active group. The overall behavioral output remained consistent, but the physical makeup of the cellular network driving it was entirely dynamic.
The experimental design involved a few limitations. The imaging process focused exclusively on male mice. The researchers noted that the heavy head-mounted microscope equipment caused less behavioral disruption in the larger males, helping them achieve a more stable response rate.
The study also did not distinguish between different subtypes of medium spiny neurons. The nucleus accumbens contains cells with distinct receptors that respond differently to the chemical messenger dopamine. Some neurons possess D1 receptors, while others possess D2 receptors. These different subtypes are thought to play distinct and sometimes opposing roles in reward processing and movement.
The five-second window following a lever press includes the physical act of pressing, the onset of a cue light, and the physical sensation of the drug entering the bloodstream. The identified network of neurons is likely a composite of several smaller groups processing each of these separate stimuli. Tracking a larger number of individual cells in future experiments could help separate these overlapping signals.
The ever-changing nature of this cellular network challenges traditional ideas about how habits are stored in the brain. A fluid membership might allow the brain to constantly update learned information while maintaining a steady behavioral output. The flexibility of these cells ensures that the addiction remains firmly rooted even as individual neurons tag out.
The study, “Refinement of Nucleus Accumbens Neuronal Dynamics During Cocaine Self-Administration Training,” was authored by Linjie Jin, Xiguang Qi, Jianwei Liu, William J. Wright, Terra A. Schall, King-Lun Li, Bo Zeng, Charles Wang, Lirong Wang, and Yan Dong.
URL: https://www.psypost.org/fluid-brain-circuits-drive-the-formation-of-cocaine-habits/
-------------------------------------------------
Private, vetted email list for mental health professionals: https://www.clinicians-exchange.org
Unofficial Psychology Today Xitter to toot feed at Psych Today Unofficial Bot @PTUnofficialBot
-------------------------------------------------
#psychology #counseling #socialwork #psychotherapy @psychotherapist @psychotherapists @psychology @socialpsych @socialwork @psychiatry #mentalhealth #psychiatry #healthcare #depression #psychotherapist #cocainehabits #nucleusaccumbens #neuralnetworks #habitscience #calciumimaging #neuronensemble #addictionresearch #deepLabCut #drugselfadministration #neuroscience研究
-
Since it remains unclear whether my current #PostDoc contract will be prolonged in January, I am starting to look for a new #AcademicJob!
My expertise are #ecology, #ethology, #AnimalBehavior, with a focus on #olfaction in #mammals.
I had a stint in #NeuroEthology, but that wasn't quite my cup of tea, and I am currently working in #AnimalWelfare for husbandry animals (think cows, pigs etc).
I have done field work (wild rodents), lab work (very controlled behavioral assays), and pure data analysis.
I do everything in #rstats, so my standard analysis tools are GLM/GLMM, but I'm currently learning how to properly use Generalized Additive Models, as they seem like the natural next step.
I've also dabbled in #python in order to work with #DeepLabCut and #moseq, so the last few years I spent mostly with #ComputerVision, #DeepLearning, and extracting data from videos.
As that requires heavy GPU calculations, I've done most on my work on institutional and/or national #HPC, and then crunched the masses of resulting data in #rstatsI'm looking for a job in the #EU, preferably anywhere north of Germany, but let's be honest, I'll go wherever there is a job.
My website is a bit outdated, but https://tsievert.com/
Please boost for visibility!
#AnimalBehaviour #FediJobs #FediHire #GetFediHired #LookingForJob
-
I spent the day manually labeling frames for #DeepLabCut ( #MachineLearning model to track #animals in videos).
Incredibly mind-numbing, but hopefully my new model will be good enough to work through the terabytes of videos.
If the model can actually track up to 18 piglets, that would be amazing!
#AcademicChatter #AnimalBehavior #AnimalBehaviour -
From @nvladimus : "We have opened the #mesoSPIM official User Forum" at https://forum.image.sc/tag/mesospim alongside #Fiji #ImageJ #ilastik #BiaPy #napari #DeepLabCut and many other open source softwares for bioimage informatics.
-
@choldgraf visited the #deeplabcut team @TrackingActions 's lab, EPFL, in early August to learn how they used open-source tools to share work. Learn how a @mystmarkdown mini-hackathon facilitated learning and accelerated contributions to the project https://2i2c.org/blog/2024/deeplabcut-myst-hackathon/ 📖
-
Seen on the #NeuroMethods slack:
Any suggestions for algorithms to track pupil in mice? (Not #DeepLabCut )
-
Good morning #ISOT2024!
Today's the last poster session of the meeting @[email protected], so come and stop by to chat.I'll try to be around during most breaks!
If you're interested in #DeepLabCut (or #MoSeq), definitely come and chat!
-
I have added a hands-on #tutorial to the Assessing Animal Behavior lecture. The tutorial covers the GUI-based use of #DeepLabCut 💻, a software package for markerless pose estimation of animals 🐭🔍 It’s aimed at #neuroscience students with no or little programming knowledge. Feel free to share it with your students and colleagues ☺️
🌍 https://www.fabriziomusacchio.com/teaching/teaching_assessing_animal_behavior/05_deeplabcut
#Ethology #MachineLearning #behaviourscience #BehavioralScience #animalbehavior
-
New this week @Nature, Mackenzie and Alexander Mathis (@TrackingActions) were still early in their careers when their #DeepLabCut software created a sensation. Now they’re using it to support other young scientists. 🧪 https://www.nature.com/articles/d41586-024-01474-x
-
Anyone here working on #PoseEstimation #animalbehavior #neuroethology ?
You may be interested in the free and open-source Python 🐍 package I’m currently working on, together with @adamltyson @bd_peri and others.
It’s called movement, and it’s made for analysing the pose tracks produced by pose estimation frameworks, like #DeepLabCut and #SLEAP.
Website: https://movement.neuroinformatics.dev
GitHub: https://github.com/neuroinformatics-unit/movementIt’s still in early development 🏗️ but we appreciate feedback/feature requests.
Check out the detailed thread on our team’s mastodon account: @neuroinformatics
-
Well, it's time again: I'm officially looking for a new #PostDoc
Please share far and wide!
My expertise lies in behavioral ecology, focused on mammalian chemical communication. I've also been exploring #DeepLabCut & #MoSeq for automated behavior analysis.
For more info about my research & background, visit my newly revamped website https://tsievert.com/
Shout-out to my friend Ramin at websplash GmbH for the fantastic redesign! -
We recently made our lab's handbook for #DeepLabCut public!
It's not finished yet and quite rough on the edges, but you can watch us (well, me) struggle in the process of trying to establish #DeepLabCut in our lab.The handbook also includes #HowTo.s and scripts to run everything on a HPC cluster.
Long-term aim is to also include guides and scripts for #KeypointMoseq.
Check it out at https://github.com/LassanceLab/DLC_handbook
-
@egonw Thanks a lot for the advice! I guess my license needs to follow the original #DeepLabCut license, right? In this case GNU Lesser General Public License v3.0.
And thanks for reminding me about the CITATION.cff, I'll get right on it. -
I need some feedback from more experienced #OpenData #OpenScience folks.
My lab is trying to be as open as possible, so we just published our progress making a #DeepLabCut model (including all annotated frames).
Please let me know if the README is missing anything crucial or if I missed any other best practices.
https://github.com/LassanceLab/primary_DeepLabCut_model -
@kevinbolding Good question, but I'm not 100% sure myself.
I'm new to the neuro world, so bear with me.
We are trying to identify which receptors, pathways, and brain areas are activated upon contact with the odor.
This is then combined with behavioral observations using #DeepLabCut
At least that's the plan. We've encountered a bunch of (administrative) roadblocks, so I can't really give a more sophisticated answer. -
@TrackingActions Would you be interested in additional data for the #SuperAnimal TopViewMouse-5k model?
We're just getting started with #DeepLabCut and will work on two Peromyscus species (plus wild Mus musculus and maybe Apodemus) -
Just in case you thought #ImageAnalysis was all about cells
https://forum.image.sc/t/is-facial-recognition-of-racoons-possible-with-deeplabcut/76826/2?u=dnmason
-
Does anybody have experience with #DeepLabCut and a workflow including #GoogleCollab?
I'm looking at the documentation and feeling a bit lost.Super extra plus points if you have used a pre-trained #ModelZoo and annotated extra frames for better performance.
@ecologies #AnimalBehavior #AnimalBehaviour #ComputerVision @academicchatter -
Have you discovered the image processing forum yet? https://forum.image.sc
Featuring tutorials, requests for guidance, help, discussion of new features and documentation for open source software #FijiSc #ImageJ #CellProfiler #DeepLabCut #Icy #ilastik #napari #QuPath #scikitimage #StarDist and many more.
-
Any #DLC #DeepLabCut users moved across to Mastodon yet? #MachineLearning or #behaviour #behavior are a bit too broad for me
-
Using the amazing #DeepLabCut we were able to track every movement of all relevant anatomical landmarks of the mouse in 3D, without even marking the joints beforehand (with an accuracy of nearly 100%).
We determined considerable changes in e.g., footfall patterns, angular variations, reduced movement of the joints, as well as changes in protraction and retraction with none, partial recovery or full recovery
-
Have you discovered the image processing forum yet? https://forum.image.sc
Featuring tutorials, requests for guidance, help, discussion of new features and documentation for open source software #FijiSc #ImageJ #CellProfiler #DeepLabCut #Icy #ilastik #napari #QuPath #scikitimage #StarDist and many more.
#java #python #kotlin #groovy -
#nvidia #deeplabcut #b3d
I was making a test to show that we could use audio2face + deeplabcut to drive our animations.I had just 1h to do this, so it is far from perfect.
On first loop its only audio2face, on second loop is audio2face and deeplabcut.
Carlos Barreto
-
Hello everyone.
Today I was doing some tests on Deeplabcut Live (https://github.com/DeepLabCut/DeepLabCut-live)This package let you run the created model done in #deeplabcut (https://github.com/DeepLabCut/DeepLabCut) to do some prediction on new footage.
Very interesting..
Carlos Barreto
-
Back on tests, creating a face model, and using the model to create the face mocap in blender
BTW. Its amazing the work done by @DeepLabCut . you should check it
http://www.mackenziemathislab.org/deeplabcut
Carlos Barreto