Mustafa Al-Rubaye
@mustafaalrubaye.bsky.social
Doctoral researcher
Deep learning for medical imaging (MRI, CT, CBCT, mammography)
Focus: AI denoising & quality control
University of Oulu: https://www.oulu.fi/en/researchers/mustafa-al-rubaye
Translating AI into clinical impact
Deep learning for medical imaging (MRI, CT, CBCT, mammography)
Focus: AI denoising & quality control
University of Oulu: https://www.oulu.fi/en/researchers/mustafa-al-rubaye
Translating AI into clinical impact
🚀 New Project: Local PDF Chatbot with Llama3 and LangChain
I just built a fully offline PDF chatbot powered by Ollama, LangChain, and Llama3! 🦙 (The implementation supports other models via Ollama)
🔗 code: github.com/MustafaAl-Ru...
#AI #LLM #LangChain #Python #RAG #LocalLLM #Llama3 #DL #Ollama
I just built a fully offline PDF chatbot powered by Ollama, LangChain, and Llama3! 🦙 (The implementation supports other models via Ollama)
🔗 code: github.com/MustafaAl-Ru...
#AI #LLM #LangChain #Python #RAG #LocalLLM #Llama3 #DL #Ollama
LinkedIn
This link will take you to a page that’s not on LinkedIn
lnkd.in
July 24, 2025 at 11:05 PM
🚀 New Project: Local PDF Chatbot with Llama3 and LangChain
I just built a fully offline PDF chatbot powered by Ollama, LangChain, and Llama3! 🦙 (The implementation supports other models via Ollama)
🔗 code: github.com/MustafaAl-Ru...
#AI #LLM #LangChain #Python #RAG #LocalLLM #Llama3 #DL #Ollama
I just built a fully offline PDF chatbot powered by Ollama, LangChain, and Llama3! 🦙 (The implementation supports other models via Ollama)
🔗 code: github.com/MustafaAl-Ru...
#AI #LLM #LangChain #Python #RAG #LocalLLM #Llama3 #DL #Ollama
Reposted by Mustafa Al-Rubaye
New open access article online: Vernier microcombs for integrated optical atomic clocks.
go.nature.com/4jpVAOF
#photonics #optics
go.nature.com/4jpVAOF
#photonics #optics
May 26, 2025 at 7:22 AM
New open access article online: Vernier microcombs for integrated optical atomic clocks.
go.nature.com/4jpVAOF
#photonics #optics
go.nature.com/4jpVAOF
#photonics #optics
Reposted by Mustafa Al-Rubaye
Can you train a model for pose estimation directly on casual videos without supervision?
Turns out you can!
In our #CVPR2025 paper AnyCam, we directly train on YouTube videos and achieve SOTA results by using an uncertainty-based flow loss and monocular priors!
⬇️
Turns out you can!
In our #CVPR2025 paper AnyCam, we directly train on YouTube videos and achieve SOTA results by using an uncertainty-based flow loss and monocular priors!
⬇️
May 13, 2025 at 8:11 AM
Can you train a model for pose estimation directly on casual videos without supervision?
Turns out you can!
In our #CVPR2025 paper AnyCam, we directly train on YouTube videos and achieve SOTA results by using an uncertainty-based flow loss and monocular priors!
⬇️
Turns out you can!
In our #CVPR2025 paper AnyCam, we directly train on YouTube videos and achieve SOTA results by using an uncertainty-based flow loss and monocular priors!
⬇️
Reposted by Mustafa Al-Rubaye
Focused ultrasound cross-links functional biomaterials within deep tissues to enable on-demand in vivo printing of implants, demonstrating potential for a wide range of biomedical applications #NBThighlight www.science.org/doi/10.1126/...
Imaging-guided deep tissue in vivo sound printing
Three-dimensional printing offers promise for patient-specific implants and therapies but is often limited by the need for invasive surgical procedures. To address this, we developed an imaging-guided...
science.org
May 12, 2025 at 4:41 PM
Focused ultrasound cross-links functional biomaterials within deep tissues to enable on-demand in vivo printing of implants, demonstrating potential for a wide range of biomedical applications #NBThighlight www.science.org/doi/10.1126/...
🚀 Just open-sourced my Bachelor’s thesis project: DMQC – a deep learning pipeline for automating quality checks in mammography. Segments anatomy with U-Net/FPN + applies PGMI rules.
🔗 github.com/MustafaAl-Ru...
#AI #MedicalImaging #deeplearning #DL #unet #mammography #OpenSource
🔗 github.com/MustafaAl-Ru...
#AI #MedicalImaging #deeplearning #DL #unet #mammography #OpenSource
GitHub - MustafaAl-Rubaye/DMQC: Deep Mammography Quality Control
Deep Mammography Quality Control. Contribute to MustafaAl-Rubaye/DMQC development by creating an account on GitHub.
github.com
May 12, 2025 at 3:42 PM
🚀 Just open-sourced my Bachelor’s thesis project: DMQC – a deep learning pipeline for automating quality checks in mammography. Segments anatomy with U-Net/FPN + applies PGMI rules.
🔗 github.com/MustafaAl-Ru...
#AI #MedicalImaging #deeplearning #DL #unet #mammography #OpenSource
🔗 github.com/MustafaAl-Ru...
#AI #MedicalImaging #deeplearning #DL #unet #mammography #OpenSource
Excited to share our new preprint:
“Deep learning-based classification of lumbar T2-weighted MRIs to subjects with and without low back pain symptoms”
www.researchsquare.com/article/rs-6...
#AIinHealthcare #DeepLearning #SpineMRI #MedicalImaging
“Deep learning-based classification of lumbar T2-weighted MRIs to subjects with and without low back pain symptoms”
www.researchsquare.com/article/rs-6...
#AIinHealthcare #DeepLearning #SpineMRI #MedicalImaging
Deep learning-based classification of lumbar T2-weighted MRIs to subjects with and without low back pain symptoms
Background:Low back pain (LBP) is a prevalent condition, with most individuals experiencing it at some point. Magnetic resonance imaging (MRI) is the primary imaging modality for LBP diagnostics, enab...
www.researchsquare.com
May 7, 2025 at 10:14 AM
Excited to share our new preprint:
“Deep learning-based classification of lumbar T2-weighted MRIs to subjects with and without low back pain symptoms”
www.researchsquare.com/article/rs-6...
#AIinHealthcare #DeepLearning #SpineMRI #MedicalImaging
“Deep learning-based classification of lumbar T2-weighted MRIs to subjects with and without low back pain symptoms”
www.researchsquare.com/article/rs-6...
#AIinHealthcare #DeepLearning #SpineMRI #MedicalImaging
AI Value Creators playbook and it’s free on #IBM
Lessons from IBM leaders on turning AI into business value.
• Real stories
• Strategic insights
• Actionable steps
Worth a read if you care about building with AI, not just talking about it.
Free PDF: lnkd.in/gsUzs39n
#free #book #DL #AI #ML
Lessons from IBM leaders on turning AI into business value.
• Real stories
• Strategic insights
• Actionable steps
Worth a read if you care about building with AI, not just talking about it.
Free PDF: lnkd.in/gsUzs39n
#free #book #DL #AI #ML
IBM Registration form
AI Value Creators: Beyond the Generative AI Mindset, IBM account registration
lnkd.in
May 5, 2025 at 12:06 PM
Reposted by Mustafa Al-Rubaye
Find your support bubble, says Emily Dowdeswell, in her blog post for doctoral students on completing your PhD - for all the #EmergingResearchers out there #EduSci https://blog.eera-ecer.de/phd-during-covid-19/
5 really helpful tips for completing your PhD - EERA Blog
We asked PhD student Emily Dowdeswell for her top tips for students currently starting their doctoral journey
blog.eera-ecer.de
April 21, 2025 at 6:31 AM
Find your support bubble, says Emily Dowdeswell, in her blog post for doctoral students on completing your PhD - for all the #EmergingResearchers out there #EduSci https://blog.eera-ecer.de/phd-during-covid-19/
Mammography QC with AI
Trained a DL model to segment breast, pectoral, nipple & skin-foldings for automatic quality control in screening.
0.90 Dice for key structures.
Helps reduce unnecessary recalls.
oulurepo.oulu.fi/handle/10024/18084
#AI #Mammography #MedicalImaging
#DeepLearning #DL #ML
Trained a DL model to segment breast, pectoral, nipple & skin-foldings for automatic quality control in screening.
0.90 Dice for key structures.
Helps reduce unnecessary recalls.
oulurepo.oulu.fi/handle/10024/18084
#AI #Mammography #MedicalImaging
#DeepLearning #DL #ML
Automatic quality assessment in mammography screening : a deep learning based segmentation method
oulurepo.oulu.fi
April 14, 2025 at 8:12 PM
Mammography QC with AI
Trained a DL model to segment breast, pectoral, nipple & skin-foldings for automatic quality control in screening.
0.90 Dice for key structures.
Helps reduce unnecessary recalls.
oulurepo.oulu.fi/handle/10024/18084
#AI #Mammography #MedicalImaging
#DeepLearning #DL #ML
Trained a DL model to segment breast, pectoral, nipple & skin-foldings for automatic quality control in screening.
0.90 Dice for key structures.
Helps reduce unnecessary recalls.
oulurepo.oulu.fi/handle/10024/18084
#AI #Mammography #MedicalImaging
#DeepLearning #DL #ML