#Lunit
Lunit Partners with Saudi Arabia's Health Ministry for AI Imaging Solutions Deployment#Saudi_Arabia#Riyadh#Lunit_AI#National_Guard
Lunit Partners with Saudi Arabia's Health Ministry for AI Imaging Solutions Deployment
Lunit is set to enhance cancer diagnostics in Saudi Arabia by supplying AI-powered imaging solutions to the Ministry of National Guard Health Affairs.
third-news.com
November 9, 2026 at 2:26 PM
November 7, 2026 at 10:02 AM
Lunit Showcases Advanced AI Pathology Research on Ovarian and Bladder Cancers at SITC 2026#South_Korea#Seoul#Cancer_Research#Lunit#AI_Pathology
Lunit Showcases Advanced AI Pathology Research on Ovarian and Bladder Cancers at SITC 2026
At SITC 2026, Lunit highlights groundbreaking AI research on ovarian and bladder cancers, revealing critical insights into treatment responses and immune features.
third-news.com
November 4, 2026 at 2:58 PM
“Je vais révéler un petit secret” : Alexia Laroche-Joubert, ce lien qui l’unit à Ambre, gagnante de la dernière saison de la Star Academy

#Marfeel_Connexes #Trend #ActuPeople

https://justpaste.in/frenchstardaily/je-vais-reveler-un-petit-secret-alexia-laroche-joubert-ce-lien-qui-lunit-…
“Je vais révéler un petit secret” : Alexia Laroche-Joubert, ce lien qui l’unit à Ambre, gagnante de la dernière saison de la Star Academy
justpaste.in
November 4, 2026 at 3:00 PM
The companies are testing the use of Lunit's Scope IO platform in support of Summit Therapeutics' cancer drug ivonescimab.
Lunit, Summit Therapeutics to Explore Use of AI Pathology Platform for Cancer Drug Programs
Lunit, Summit Therapeutics to Explore Use of AI Pathology Platform for Cancer Drug Programs
ebx.sh
October 27, 2026 at 10:15 PM
The companies are testing the use of Lunit's Scope IO platform in support of Summit Therapeutics' cancer drug ivonescimab.
Lunit, Summit Therapeutics to Explore Use of AI Pathology Platform for Cancer Drug Programs
Lunit, Summit Therapeutics to Explore Use of AI Pathology Platform for Cancer Drug Programs
ebx.sh
October 26, 2026 at 3:26 PM
Lunit and Summit Therapeutics Collaborate on AI for Tumor Microenvironment Insights in Immuno-Oncology#South_Korea#Seoul#Ivonescimab#Summit_Therapeutics#Lunit_Inc
Lunit and Summit Therapeutics Collaborate on AI for Tumor Microenvironment Insights in Immuno-Oncology
Lunit Inc. and Summit Therapeutics have partnered to leverage AI technology in analyzing tumor microenvironments, enhancing immuno-oncology development efforts.
third-news.com
October 24, 2026 at 1:28 AM
🎬 Jailer 2 made Rs 14.50 cr on Day 9.
💊 VRTX shared slides at ASN Kidney Week 2026.
🤝 Lunit and Summit partner on SCOPE IO AI.
📉 Singapore and Indonesia IPOs cool off in 2026.
October 24, 2026 at 4:26 AM
$SMMT Oct 23, 2026: Summit and Lunit signed a research agreement to apply Lunit SCOPE IO, an AI pathology platform, to H&E whole-slide images in ivonescimab programs, aiming at biomarker discovery and patient selection. No clinical data...

https://www.merlintrader.com/summit-therapeutics-stock-hub/
Summit Therapeutics ($SMMT): November 14 PDUFA, HARMONi
Summit Therapeutics ($SMMT): the November 14, 2026 PDUFA, a HARMONi overall-survival miss, the FDA's OS requirement and a pending $2B AstraZeneca deal.
www.merlintrader.com
October 24, 2026 at 6:19 AM
#SMMT Summit Therapeutics and Lunit Announce Agreement to Apply AI-powered SCOPE IO Platform for Tumor Microenvironment Analys…

https://www.stocktitan.net/news/SMMT/summit-therapeutics-and-lunit-announce-agreement-to-apply-ai-powered-j3n91jgvbu28.html?utm_source=stocktitan-bluesky&utm_medium=social
Summit Therapeutics and Lunit Announce Agreement to Apply AI-powered SCOPE IO Platform for Tumor Microenvironment Analysis in Immuno-Oncology Development
Summit Therapeutics (SMMT) entered a research agreement with Lunit to evaluate AI-powered pathology analysis for its ivonescimab development programs.The research will apply Lunit SCOPE IO to whole-slide tissue images stained with hematoxylin and eosin, a routine tissue stain. It will characterize the tumor microenvironment—the cells and structures surrounding a tumor. The companies aim to explore how this analysis could support biomarker discovery, patient grouping or selection, and understanding of responses to ivonescimab, an investigational antibody targeting PD-1 and VEGF.The companies expect insights that may inform future research and clinical development planning. No clinical outcome data accompany the agreement. Lunit SCOPE products are for research use only, not diagnostic procedures or decisions.
www.stocktitan.net
October 23, 2026 at 8:37 PM
Lunit Unveils Groundbreaking AI Pathology Studies at ESMO 2026 in Madrid#South_Korea#Seoul#Lunit#AI_Pathology#ESMO
Lunit Unveils Groundbreaking AI Pathology Studies at ESMO 2026 in Madrid
Lunit presents five innovative pathology studies at ESMO 2026, showcasing AI's impact on cancer diagnostics and precision oncology across multiple cancer types.
third-news.com
October 20, 2026 at 1:56 PM
Compact models for patient-level histopathology MIL: baselines and controlled evaluation
For now, I found a few compact models and implementation examples that might be relevant: * * * ## Short answers to the three questions **1. Compact encoders and frozen features versus fine-tuning.** I would keep the project’s existing compact CNN or ViT as a reference and compare it with at least one released, pathology-pretrained small encoder. Three concrete ViT-S/16 candidates are Kaiko ViT-S, Lunit DINO ViT-S, and DistillPath-KS16-HOpt0. The first two offer different pathology-pretraining references; the third is a small student initialized from Kaiko and subsequently distilled from a larger pathology teacher. None is necessarily best for an unseen patient-level task. **Frozen crop embeddings followed by a small patient-level MIL head** are a particularly interpretable and inexpensive first comparison. End-to-end or partial fine-tuning can be a separate branch if the frozen representation appears limiting. **2. Variable crop counts and heterogeneous tissue.** Start with **mean pooling and attention-based MIL** using identical cached embeddings and an explicit crop budget. The classic attention-based deep MIL paper provides a simple learnable set aggregator. Vary the number of crops per patient and repeat crop sampling with different seeds; this often tells you more than immediately adding a complex head. Max/top-k or class-aware selection are conditional alternatives when evidence is sparse. If a patient has several identifiable slides, compare flat crop-to-patient pooling with slide-first aggregation rather than assuming either hierarchy is universally better. **3. Controls that separate methodological gains.** Hold **encoder and crop IDs fixed** when comparing aggregation methods; hold **MIL head, splits, crop budget, and evaluation protocol fixed** when comparing encoders. A released distilled checkpoint versus its released initialization is a practical comparison of _weights as distributed_ , not a clean causal estimate of a distillation loss: the distilled student also had additional training data and compute. To study the distillation objective itself, compare the same student initialized the same way under suitably matched training conditions, with and without the teacher signal. Report patient-level macro-F1 and class recall beside crop counts and costs, rather than treating parameter count alone as a compute control. The earlier reply already suggests frozen pathology features and one-factor-at-a-time comparisons. To complement it, I have included specific weights, implementation references, conditional choices, and a bounded T4 engineering check. None requires access to unpublished methods or private results. In a short **Colab Tesla T4 feature-extraction test** , all three public ViT-S checkpoints loaded through `timm` and yielded **384-dimensional pooled crop embeddings**. This checks compatibility and a limited cost reference, **not** patient macro-F1, clinical utility, or a distillation gain. The tested scope appears below. ## A practical low-compute route 1. **Keep the existing patient/source split.** Maintain an unambiguous mapping among patient, label, crop, tissue-source group, and slide ID if one exists. With patient labels, keep the patient as the prediction and evaluation unit even if feature files are stored by slide. 2. **Cache frozen embeddings** for the existing compact model and one or two pathology-pretrained candidates. Use identical source crops and patient membership but each checkpoint’s prescribed preprocessing. Record revisions and transforms. 3. **Compare mean pooling with a small attention head** on those same features. This avoids rerunning the encoder and tests aggregation against a simple permutation-invariant baseline. 4. **Change the crop budget, not everything at once.** Test a few feasible per-patient caps, repeat subsampling, and report patient macro-F1, per-class recalls, and variability. If results are stable at a small cap, that itself helps the efficiency objective. 5. **Spend additional compute only where the results point.** If encoder choice dominates, investigate fine-tuning or a better student. If crop sampling or aggregation dominates, focus there. If the objective or teacher signal is the claimed contribution, preserve the simple baselines and add matched training controls. ## Checks worth making before interpreting any gains * **Compare predictions at the patient level.** If multiple slides belong to one patient, a split that is disjoint only by slide does not guarantee patient independence. Your post already identifies patient/source separation; the important point is to preserve it through feature extraction, MIL training, and reporting. * **Define the crop policy.** “32 crops” could mean exactly 32 sampled, at most 32, or all available up to 32. A patient with fewer than 32 images needs an explicit policy; duplicating crops is not equivalent to keeping the smaller bag. * **Keep crop identities stable across encoders.** Compare the _same underlying images_ with each checkpoint’s intended resize/normalization; forcing identical transforms is a separate ablation. * **State which feature tensor enters MIL.** For these tested ViT-S weights, `model(x)` with `num_classes=0` gives `[B, 384]`; `forward_features(x)` gives `[B, 197, 384]`. Feeding tokens instead of one pooled vector per crop changes both the model and its compute. See the official timm feature-extraction guide. * **Separate training convenience from inference cost.** A feature cache saves repeated encoder work during head training, but an unseen patient’s images still require preprocessing and encoding. Teacher computation for distillation is a third, separate cost. The expanded sections provide details and references for the branches that turn out to matter. Compact pathology encoders, feature extraction, and a small T4 check (click for more details) Variable crop counts, heterogeneous tissue, and patient-level MIL (click for more details) Controlled experiments: which conclusion does each comparison support? (click for more details) Compute accounting: cached training versus a new patient's inference (click for more details) Code and paper references organized by the question they answer (click for more details) Reproducibility, conditional risks, and what remains unknown (click for more details)
discuss.huggingface.co
October 21, 2026 at 10:04 AM
Lunit's Scope suite of pathology image-analysis tools will be integrated into Discovery's tissue analysis workflows.
Lunit, Discovery Life Sciences Partner on AI-Powered Pathology Services
Lunit, Discovery Life Sciences Partner on AI-Powered Pathology Services
ebx.sh
October 13, 2026 at 12:05 AM
Lunit and Discovery Life Sciences Join Forces for AI-Enhanced Tissue Analysis in Biopharma#South_Korea#Seoul#Lunit#AI_Pathology#Discovery_Life_Sciences
Lunit and Discovery Life Sciences Join Forces for AI-Enhanced Tissue Analysis in Biopharma
Lunit and Discovery Life Sciences collaborate to advance AI-driven tissue analysis for biopharmaceutical research, improving biomarker insights and drug development.
third-news.com
October 12, 2026 at 1:26 PM
【乳がん検診のAI、ストックホルム全域へ】
マンモグラフィーをAIが2人目の読影者として見る仕組みが広がる。全面導入後は年20万〜25万件を支援する見込み。先行施設では、がんの検出が15%増え、読影時間は36%以上短くなった。
一施設の運用から、地域の二重読影に組み込む段階へ進んだ事例です。
prevono.net/world/3306/
乳がん検診、AIを「2人目の読影」に活用 スウェーデン・ストックホルム全域へ導入拡大
乳がん検診で撮影するマンモグラフィーをAIが解析し、医師の判定を支援する仕組みが、スウェーデンのストックホルム地域全体に広がる。AI開発企業のルニット(Lunit)が2026年9月に発表した。
prevono.net
October 5, 2026 at 10:22 PM
“A European health system [will] replace radiologist second reads with AI at three Stockholm hospitals

Since its initial adoption in 2023, use of Lunit AI progressed from clinical evaluation to routine breast cancer screening, and has supported around 200,000 breast exams over the last three years”
Health system will use AI instead of radiologists for breast imaging 2nd reads
The implementation will span three hospitals in Sweden’s Stockholm Region, supporting between 200,000 and 250,000 breast imaging exams annually.
radiologybusiness.com
September 30, 2026 at 3:43 AM
Lunit's Innovative AI Mammography Solution Expands in Stockholm Region for Breast Cancer Screening#Sweden#Stockholm#Lunit#Breast_Cancer#AI_Screening
Lunit's Innovative AI Mammography Solution Expands in Stockholm Region for Breast Cancer Screening
Lunit expands its AI-powered mammography solution across Stockholm, improving breast cancer screening and diagnostics in the region. Discover the impact.
third-news.com
September 28, 2026 at 1:16 PM
When AI Pathology Meets Spatial Genomics, Cancer Drug Selection Gets Smarter by OncoFrontier

#CancerFax

medium.com/@OncoFrontie...
When AI Pathology Meets Spatial Genomics, Cancer Drug Selection Gets Smarter
Inside the Lunit and 10x Genomics collaboration turning routine biopsy slides into predictive biomarkers for ADCs and immunotherapy
medium.com
September 14, 2026 at 12:29 PM
Lunit Collaborates with 10x Genomics to Leap Forward in Oncology Research Using AI and Spatial Biology#South_Korea#Seoul#oncology#Lunit #10x_Genomics
Lunit Collaborates with 10x Genomics to Leap Forward in Oncology Research Using AI and Spatial Biology
Lunit has joined forces with 10x Genomics to enhance oncology research by integrating AI pathology analysis with spatial biology studies, promising breakthroughs in cancer treatment.
third-news.com
September 10, 2026 at 1:29 PM