🔬 Moving Beyond Pixels: Advancing Multimodal Pathology Pathology AI has long relied on images alone. What happens when you add language? We combined PLUTO-4 vision embeddings with rich histological descriptions to build a joint vision-language space for disease classification, and the results are promising. 🧵 #AI #MachineLearning #Pathology #MultimodalAI #FoundationModels

These results highlight how our PLUTO-4 foundation models enhance PathAI’s AI-pathology products across digital diagnostics and translational research. We’re excited for the new capabilities PLUTO-4 will unlock for our partners and the community! 📄 Learn more in our technical report: 👉 arxiv.org/abs/2511.02826 #AI #Pathology #HealthcareAI #FoundationModels #PLUTO4

Beyond public benchmarks, PLUTO-4 shows real-world impact — 🩺 ~10 % improvement across multiple PathAI products, with strong gains in dermatopathology specimen classification. These advances bring us closer to robust, generalizable FMs for pathology applications. #Dermatology #HealthcareAI

Large-scale multi-node training is often communication-bound. We optimized ViT-G training with DDP + GPUDirect RDMA, tuning parameters (bucket_cap_mb, gradient_as_bucket_view) to saturate InfiniBand bandwidth. Result: 3× throughput improvement and near-linear scaling across 4 H200 nodes.

Self-supervised ViT training with DINOv2 is unstable at scale. Key changes that stabilized PLUTO-4 training: 🔹 Use bfloat16 → prevents overflow and NaNs in projection heads 🔹 Add register tokens → capture high-norm activations 🔹 Use large batches (≥1024) → smoother gradients #SelfSupervisedLearning #AI

Comparison of Patch-Sizes 🧩 4S (FlexiViT) lets us tune patch size per task ps-8 excels at tasks needing fine-grained features (ex: nuclear segmentation) ps-16 suits coarse pattern tasks (Gleason patterns) #FlexiViT #FoundationModels

PLUTO-4 introduces two models: 🧩 4S — a compact, high-throughput model adaptable to different tasks. Trained with FlexiViT and RoPE for configurable patch sizes and multiscale feature extraction. 💪 4G — a frontier-scale model for complex tasks and peak performance #VisionTransformers #ComputationalPathology #AI

PLUTO-4 is trained on a diverse dataset of 551,164 WSIs from 137,144 cases across 50 institutions. The dataset spans 40+ organs, 60+ diseases, and 100+ stain variants, capturing real-world variation in tissue, staining, and scanning systems.

🚀 Excited to share PLUTO-4, our new state-of-the-art foundation models for pathology! 🔬 We’re seeing SoTA performance across multiple public benchmarks (EVA and HEST) — surpassing other leading pathology foundation models. (1/6) #AI #MachineLearning #Pathology #FoundationModels #HealthcareAI

PathAI #MachineLearning engineers have recently published new #AI findings for mechanistic interpretability of PLUTO, a pathology #foundationmodel. Using sparse autoencoders (SAEs), we uncovered biologically meaningful and interpretable features. 🧵 arxiv.org/html/2407.10785v2

We sat down with VP of Product, Ben Glass, to discuss how #AI-powered #pathology is revolutionizing fibrosis quantification in #oncology and to learn more about the development of PathAI’s latest product: PathExplore™ #Fibrosis Read More: linkedin.com/pulse/discussio… #PathTwitter

PathAI is proud to announce Dr. Eric Walk’s recognition on the #PharmaVoice100 list! Learn more about our Chief Medical Officer and his award. Learn more: pathai.com/resources/pathai-… #PathTwitter #Pathology #AI #biopharma #biotech

Our Co-Founder and CEO, Andy Beck will be speaking at the MIT #AI Conference! This event brings together thought leaders and innovators to explore the transformative impact of artificial intelligence across various industries. #MITAI2024 #PathTwitter

PathAI is excited to announce a new #partnership with @Clario combining AI-powered #digitalpathology & endoscopy solutions geared towards enhancing #drugdevelopment for inflammatory bowel disease & other GI disorders. #PathTwitter #pathology Learn more: pathai.com/resources/clario-…

Thanks for meeting with us @MassEOED!

We’re halfway through #ESMO24! Stop by our booth to learn how you can leverage #AI powered #digitalpathology for oncology #drugdevelopment & #cancerresearch. 💻 See live demos of the platform by visiting us at booth 643a

🚀We launched MET Predict on AISight®! This AI-powered tool identifies NSCLC tumors w/ METex14 or MET amplification directly from H&E slides Learn more: pathai.com/resources/pathai-… MET Predict & AISight are for research use only. Not for use in diagnostic procedures. #PathTwitter

🚀PathAI Collaborates with GoldPath Labs to Elevate #DigitalPathology Capabilities with AISight® Image Management System. Read the press release here: pathai.com/resources/pathai-… #PathTwitter #pathology

Unlock the potential of the IHC Explore™ platform! Transform #Immunohistochemistry (#IHC) slide images into precise, data-driven insights for next-gen #biomarker development. Demo the AI #pathology products today info.pathai.com/pathai-demo-…. #PathTwitter

PathAI’s AISightⓇ Dx Image Management System is CE-marked for primary diagnosis in Europe! Read the full press release to learn how we’re advancing healthcare with our AI-driven digital pathology platform pathai.com/resources/pathais…