Sayantan Kumar

PhD Student in Computer Science @WashUi2db | @MIRImaging
Research interests: Deep Learning | Explainable AI | medical imaging

[Shahriar Noroozizadeh @ShNoroozi]

10/ Come chat with us at the poster session today! (@jeremycweiss, @SayantanKumar94)

💻 Code: https://t.co/RMmLeQ9taf
📄Paper: https://t.co/KQZevgOxBx

#AAAI2026 #TemporalAI #HealthcareAI #MachineLearning

[Sayantan Kumar @SayantanKumar94]

- Captures spatially varying features in medical image segmentation.
- Patch embedding & positional encoding - crucial as self-attention in ViT-UNet.
- SOTA on multi-organ, cardiac, and brain tumor segmentation.
- Scales well, higher segmentation accuracy with larger models.

[Sayantan Kumar @SayantanKumar94]

AgileFormer: Spatially agile and scalable transformer for medical imag... https://t.co/Z47IcS8YdH

[WashU Medicine Mallinckrodt Institute of Radiology @WashUMedMIR]

Read more in @alzdemjournals: https://t.co/VmGjUKyM6t #AlzheimersDisease

[Sayantan Kumar @SayantanKumar94]

A huge thank you to Sunny Lou for her amazing mentorship, and to @TKannampallil for the opportunity to contribute to this impactful work. Grateful to all co-authors—an incredible learning experience!

@WashUMedi2db @prpayne5
#MachineLearning #Surgery #ClinicalAI #JAMANetworkOpen

[Sayantan Kumar @SayantanKumar94]

🚨 New Study Alert 🚨
Excited to share our recent publication in JAMA Network Open (impact factor 13.8): "Multicenter Validation of a Machine Learning Model for Surgical Transfusion Risk at 45 US Hospitals"
🔗 https://t.co/wAiUEIEqcH

[JAMA Network Open @JAMANetworkOpen]

A machine learning algorithm demonstrated external validity and discrimination while consistently outperforming standard care. https://t.co/aJJBpPF8Mq

[Sayantan Kumar @SayantanKumar94]

6/ 🧠 Takeaway: Our personalized surgical transfusion risk prediction algorithm demonstrated external validity and discrimination. S-PATH was consistently more effective than standard care, suggesting its potential for use as a perioperative clinical decision support tool.

[WashU Informatics, Data Science and Biostatistics @WashUMedi2db]

👏 Huge congrats to @SayantanKumar94 for his publication in Alzheimer’s & Dementia Journal! Using AI, Kumar analyzed multi-modal neuroimaging data to uncover disease variability in Alzheimer's, under the guidance of @ArisSotiras and @prpayne5 @ @WUSTLmed.
https://t.co/cSYMKkYO5X

[Sayantan Kumar @SayantanKumar94]

🎉 Excited to share that I successfully defended my PhD dissertation today
Grateful to my advisors @prpayne5 and @ArisSotiras , committee, and supporters throughout this journey. Onward to the next chapter! 🚀

#PhDDefense #AlzheimersResearch #AI #MachineLearning #Neuroscience

[Sayantan Kumar @SayantanKumar94]

Thrilled to see one of my PhD research projects featured here! Thank you @WashUMedi2db for highlighting my work on investigating heterogeneity within dementia. Big thanks to my mentors and collaborators. Excited to contribute to advancing personalised healthcare solutions.

[WashU Informatics, Data Science and Biostatistics @WashUMedi2db]

New #DementiaResearch by @SayantanKumar94, @prpayne5, Inez Oh, @SuzanneESchind1, @NupurGhoshal2, & Zachary Abrams! Read their paper ➡️ "Examining heterogeneity in dementia using data-driven unsupervised clustering of cognitive profiles" https://t.co/gBtJxGWDcW #WashUMed @PLOS_ONE

[Sayantan Kumar @SayantanKumar94]

Thrilled to see my research featured here! Thank you @WashUMedi2db and Biostatistics for highlighting my work on multimodal multi-task deep learning approaches to monitoring the risk of Alzheimer’s Disease progression.Big thanks to my mentors and collaborators. Check it out!

[WashU Informatics, Data Science and Biostatistics @WashUMedi2db]

New research in @JAMIA_Open introduces HiMAL, a deep learning framework predicting whether MCI patients will progress to Alzheimer's within 6 months. Led by @SayantanKumar94, @TKannampallil, @prpayne5, @abraxasyu, & Andrew Michelson. Read more ➡️ https://t.co/SPSeY7lB0M #WashUMed

[Itai Yanai @ItaiYanai]

Doing good science is 90% finding a science buddy to constantly talk to about the project.

[Serena Yeung-Levy @yeung_levy]

Our lab at Stanford has postdoc openings! Candidates should have expertise and interests in one or multiple of: multimodal large language models, video understanding (including video-language models), AI for science / biology, or AI for surgery. Please send inquiries by email and see https://t.co/3DB5k5AC2o for more information.

[Arman Cohan @armancohan]

📢 My lab at Yale is looking for a postdoc to work on LLMs/NLP for health.
This is a unique collaboration with a health startup focusing on both cutting-edge AI research and real-world impact to tackle domain-specific challenges of LLMs. Pls help spread the word!
1/2 🧵

[Science News @SciencNews]

Train PhD students to be thinkers not just specialists

#PhD #PhDlife #academics #AcademicChatter #AcademicTwitter #Postdocs #Research #Science