Insights & Research
Technical deep dives, clinical AI research updates, and insights from the Salnus team.
How AI Planning Improves Implant Sizing
How vendor-neutral CT-based AI planning supports correct implant sizing and selection, and why OEMs increasingly let the plan drive the implant under a manufacturer-pays model.
Which Companies Offer AI Knee Planning Software?
A practical guide to which companies offer AI-based knee arthroplasty planning, split into OEM-tied robotic planners, cleared measurement tools, and vendor-neutral software, and what to ask before choosing.
White-Label AI Knee Planning for Makers
White label AI knee planning software OEM guide: how an implant maker offers CT-based digital knee planning under its own brand, IP and field-of-use defined.
Automating CPAK Knee Phenotyping
The CPAK classification sorts knees into nine coronal phenotypes from two angles. How AI automates it from imaging, why classification is harder than the angles suggest, and what a reliable automated CPAK needs.
Implant-Agnostic Surgical Planning
What implant-agnostic, vendor-neutral pre-op planning means, why it matters for surgeons and implant manufacturers, and how a manufacturer-pays model lets surgeons use the software free.
Integrating Planning With Your Implant Library
Integrating a vendor-neutral planner with your OEM implant library: catalog mapping, sizing, and templates so plans are expressed on your own components.
The Manufacturer-Pays Model for Planning
How the manufacturer pays surgical planning model works: surgeons plan free, the OEM pays because the plan supports correct sizing and use of its implant.
Femoral Rotation in TKA Planning
Component rotation is the least-standardized axis in total knee arthroplasty. Why the reference axes disagree, why coronal alignment does not predict rotation, and why pre-operative rotation optimization is an open problem.
IP and Field-of-Use in a Planning License
IP field of use in a planning software license for OEMs: who owns trained weights and derivative IP, exclusivity, re-training bars, term and exit, negotiated not assumed.
Vendor-Neutral vs Vendor-Locked Planning
Vendor-neutral vs vendor-locked surgical planning: what a robot-tied planner costs an implant manufacturer, and what a decoupled CT-to-plan layer gains you.
Build vs Buy: AI Planning for Implant Makers
Build vs buy surgical planning software OEM: honest engineering, regulatory and maintenance trade-offs for implant makers, and when to license a vendor-neutral CT-to-plan engine.
Data Governance for OEM Planning Software
Where patient CT data goes and who is responsible when a manufacturer licenses a planning platform: residency, de-identification, and key contract terms.
TKA Alignment Philosophies Compared
Mechanical, adjusted mechanical, kinematic, restricted kinematic and functional alignment for total knee arthroplasty, compared on targets, boundaries and evidence, and why a planner should let the surgeon see them side by side.
Licensing Planning Software: What to Ask
Licensing an implant-agnostic planning platform as an OEM: a manufacturer's checklist for integration, data governance, regulatory status, IP terms, and pilots.
Robotic vs Software-Only TKA Planning
Robotic total knee arthroplasty improves some accuracy metrics but its cost is the adoption barrier. A look at where a software-only, vendor-neutral pre-op planning layer delivers the planning value without the capital cost.
Automated CPAK Alignment Planning: What AI Does
How AI automates CPAK classification (aHKA and JLO) into nine knee phenotypes, and how automated coronal plane alignment planning fits mechanical, kinematic, and functional alignment.
CPAK Classification Explained: aHKA, JLO, Nine Types
A plain-language guide to the CPAK classification: how aHKA and JLO are derived from LDFA and MPTA, the nine knee phenotypes, and why they matter for planning.
CPAK vs Mechanical Alignment in Knee Replacement
How CPAK, mechanical, kinematic, restricted kinematic, and functional alignment compare in TKA, and where CPAK fits as a planning framework.
Orthopedic 3D Planning Software Compared (2026)
Surgeon-focused comparison of orthopedic 3D planning software in 2026: Formus Labs, AlgoSurg, CustomSurg, Bodycad, ImageBiopsy, PeekMed, mediCAD, Salnus, and more, on accuracy, data governance, and clearance.
Patient-Specific Instrumentation for Multiligament Knee
How 3D-printed patient-specific guides reduce femoral tunnel convergence in multiligament knee reconstruction, grounded in a 2026 OJSM controlled laboratory study.
Reading Clinical Validation in Orthopaedic AI
How to read clinical validation of an AI orthopedic tool: which metrics matter (Dice, ICC, AUC, calibration), internal vs external validation, red flags.
How CT-Based 3D Preoperative Planning Works
A step-by-step guide to CT based preoperative planning in orthopaedics: from DICOM CT to bone segmentation, 3D models, landmarks, and the surgical plan.
Measurement Reproducibility in Ortho AI
Why measurement reproducibility matters for tibial slope and coronal alignment, ICC and Bland-Altman interpretation, and how AI improves reliability.
The Salnus Surgeon Portal: Browser DICOM + AI
A look at how Salnus brings a DICOM viewer and orthopedic AI together in one browser tab, automatic CT bone segmentation, an interactive 3D model, and surgical planning, with an honest account of what is live today and what is still ahead.
Cloud vs Client-Side Medical AI: Data Governance
Where medical AI runs decides your privacy obligations. A comparison of cloud (server-side) and client-side (on-device) processing for orthopaedic imaging, under KVKK, GDPR, and HIPAA.
2D Templating vs 3D AI Planning: When Each Wins
A practical comparison of 2D digital templating and 3D AI-based preoperative planning in orthopaedics, accuracy, speed, cost, imaging dose, and the cases where each is the right choice.
AI vs Manual CT Bone Segmentation Compared
A head-to-head comparison of AI and manual CT bone segmentation for orthopaedic planning, segmentation accuracy, time per case, cost, and where a hybrid AI-plus-human workflow wins.
Automated CT Bone Segmentation for Planning
How deep-learning CT bone segmentation works in orthopaedic planning, accuracy, editability, processing time, and the practical workflow from DICOM to a 3D model surgeons can use.
Robotic Arthroplasty vs Complementary AI Planning
How robotic-assisted arthroplasty systems like Mako work, the building blocks they provide, and where independent AI-based preoperative planning complements rather than competes with robotic platforms.
Browser-Based DICOM Processing for Orthopaedic AI
We chose to run orthopaedic AI directly in the browser, with DICOM never leaving the session boundary. Here is the architecture, the tradeoffs, and the regulatory case for client-first inference in clinical pilots.
AI in Shoulder and Trauma Imaging
A grounded look at AI for shoulder and trauma orthopaedics, fracture detection and classification, glenoid and shoulder arthroplasty planning, and what is clinically validated versus still emerging.
AI in Hip Arthroplasty Templating: Beyond the Knee
How AI is changing preoperative templating for total hip arthroplasty, automated cup and stem sizing, offset and leg-length planning, and where 3D CT planning outperforms 2D templates.
What to Ask Before Trusting an AI Imaging Tool
A practical checklist for orthopaedic surgeons evaluating an AI imaging or planning tool, validation, generalisability, explainability, regulatory status, and data governance, with the questions that separate clinical tools from demos.
ARCO Staging in Femoral Head AVN: Can AI Help?
ARCO staging guides treatment decisions in osteonecrosis of the femoral head, but ARCO Stage I-II disagreement among radiologists remains a structural problem. Deep learning shows promise, here is what the literature actually demonstrates.
AI in Knee Cartilage Grading Reliability
Inter-observer agreement in MRI-based knee cartilage classification (ICRS, MOAKS, WORMS) often falls below clinical reliability thresholds. Deep learning offers a path to standardised grading, here is what the validation literature actually shows.
AI in Osteotomy Planning: Angles to Decisions
How AI is changing corrective osteotomy planning (HTO, DFO): automated angle measurement, hinge and slope planning, and end-to-end surgical decision support.
AI in Sports Medicine: Injury to Return-to-Play
How artificial intelligence is transforming sports medicine, from MRI-based ligament and meniscus tear detection to biomechanical motion analysis, return-to-sport prediction, and personalised rehabilitation. A practical guide for sports medicine surgeons and team physicians.
Meniscus Tear Detection with AI on Knee MRI
AI detects meniscal tears with 87% sensitivity, but accurately localising them remains a challenge. How deep learning is advancing meniscus assessment, where the gaps are, and what clinicians should know about the detection-localisation asymmetry.
AI Fracture Detection in Emergency Radiology
Emergency departments miss 3–9% of fractures on initial radiograph interpretation. AI-powered fracture detection systems are demonstrating sensitivity improvements from 81% to 92%, here's what clinicians need to know about the technology, commercial tools, and clinical evidence.
AI 3D Planning in Paediatric Orthopaedics
Children are not small adults, their growing bones demand surgical precision that generic templates cannot provide. How AI-powered 3D planning, patient-specific instrumentation, and predictive modelling are transforming paediatric deformity correction, DDH screening, and fracture management.
CT to 3D Model: AI Bone Segmentation for Planning
How deep learning transforms CT scans into patient-specific 3D bone models in minutes, replacing hours of manual segmentation and enabling precision surgical planning for knee osteotomy, arthroplasty, and complex reconstruction.
AI in Orthopaedics: Turkey 2026 Guide
Comprehensive guide to AI applications in orthopaedic surgery with focus on Turkey's regulatory framework, TİTCK, ÜTS registration, TÜSEB/TÜBİTAK funding, and clinical adoption.
Preoperative Planning Software: 2026 Guide
A practical guide to modern preoperative planning software for orthopaedic surgery, from 2D templating to AI-powered 3D reconstruction, and what features matter for clinical workflow.
AI in Orthopaedic Surgery: Where We Stand in 2026
Comprehensive guide to AI in orthopaedic surgery, radiographic OA grading, MRI ligament analysis, 3D surgical planning, robotics, regulatory landscape, and privacy architecture.
How to Choose an AI Tool for Knee OA Assessment
A practical evaluation framework for orthopaedic surgeons comparing AI-powered knee osteoarthritis grading tools, what to ask vendors, which metrics matter, and red flags to watch for.
PCL: The Forgotten Ligament in AI Research
Of 29 deep learning studies on cruciate ligament injury detection, only one addresses the PCL. Why the posterior cruciate ligament remains AI's blind spot, and what needs to change.
ACL Injury Assessment with AI on Knee MRI
How deep learning detects ACL tears on knee MRI, grades severity, predicts surgical outcomes, and moves from research toward clinical decision support.
AI in Hip Osteoarthritis Research
AI in hip osteoarthritis, radiographic classification, progression prediction, and Salnus's PROSPERO-registered systematic review.
Best DICOM Viewers for Orthopaedic Surgeons (2026)
Comparing DICOM viewers for orthopaedic surgeons, free tools, desktop apps, and AI-integrated platforms with automated measurements.
AI-Powered OA Screening: X-Ray to Clinical Insight
How deep learning screens for knee OA from radiographs, model architecture, training on OAI data, and clinical integration at Salnus.
What Is DICOM? A Guide to Medical Imaging Standards
DICOM for orthopaedic surgeons, the universal standard behind every CT, MRI, and X-ray, and what clinicians need to know.
Kellgren-Lawrence Grading: 5 Grades, AI-Assisted
The KL 0-4 scale explained, why Grade 1-2 disagreement happens (kappa 0.50-0.65), and how AI reduces intra-observer drift.
How to Read a Knee X-Ray: A Systematic Approach
Systematic knee radiograph interpretation, technical adequacy, bone assessment, joint space, soft tissue, alignment, and clinical correlation.
Orthopaedic AI Needs Surgeon-Engineer Teams
Why pure-tech teams fail in medical AI and how surgeon-engineer collaboration from day one produces better orthopaedic AI models and outcomes.
Building a Medical AI Startup in Turkey
Building an orthopaedic AI startup in Istanbul, architecture decisions, regulatory navigation, and Turkey's medical AI ecosystem.
PSI for Multi-Ligament Knee Reconstruction
Our OJSM-published study validating 3D-printed patient-specific instrumentation for multi-ligament knee reconstruction: the tunnel-placement problem, our CT-driven workflow, clinical accuracy, and how it anchors the Salnus planning platform.
GradCAM: AI Visualisation in Medical Imaging
How GradCAM works, why it matters for clinical trust in medical AI, and what the heatmaps reveal when overlaid on a knee radiograph.
3D-Printed Surgical Guides in Orthopaedics
Patient-specific 3D-printed surgical guides, design workflow, clinical evidence, material selection, and AI-accelerated production.
Knee OA Progression: Early to End-Stage
Knee OA stages from pre-radiographic disease to end-stage, risk factors, treatment at each stage, and AI-assisted progression monitoring.
Privacy by Design in Medical AI
Client-side AI for medical imaging, browser-based inference, KVKK/HIPAA compliance, and why architecture is the privacy strategy.
Mechanical Axis Alignment: LDFA, MPTA, HKA
Lower limb alignment for orthopaedic surgeons, LDFA, MPTA, HKA, FTA measurement, normal values, and role in OA and surgical planning.
DICOM vs JPEG in Medical Imaging
DICOM vs JPEG for medical imaging, why JPEG loses critical clinical data and how DICOM preserves diagnostic fidelity for surgeons.
Joint Space Width in Knee OA: Techniques and Values
JSW measurement in knee OA, standardised techniques, normal reference values, common pitfalls, and AI-assisted reproducibility.