Deep learning classification of liver lesions from contrast-enhanced ultrasound images (CEUS) to improve diagnostic confidence.
Designed and trained neural networks for automated classification of liver lesion types from noisy, low-contrast CEUS imagery a modality that requires specialized preprocessing and domain-specific augmentation.
Stack
Challenge
Bracco Suisse needed to improve diagnostic confidence in contrast-enhanced ultrasound examinations by automatically classifying liver lesion types from noisy, low-contrast CEUS images where temporal contrast dynamics and image artifacts make standard classification approaches unreliable.
Approach
Designed custom neural network architectures for CEUS image processing, implementing domain-specific augmentation strategies that account for ultrasound artifacts, contrast agent dynamics, and temporal perfusion patterns. Built a preprocessing pipeline tailored to the unique characteristics of contrast-enhanced ultrasound data.
Results
- ●Multi-class lesion classification
- ●CEUS-specific preprocessing pipeline
- ●Domain-adapted augmentation strategies
How Frema Labs applies this for you
If you work with a noisy imaging modality, we build the domain-specific preprocessing and classification pipelines that off-the-shelf models miss.
More case studies
Other engagements across luxury manufacturing, life sciences, finance, and applied research.
- RichemontAesthetical Quality Control for Luxury ManufacturingComputer Vision · Luxury ManufacturingIndustrial-grade computer vision system for aesthetical defect detection in luxury watchmaking and jewelry.Read case study
- KeringSupply Chain Replenishment OptimizationSupply-Chain ML · Luxury RetailDynamic warehouse replenishment using statistical modeling and reinforcement learning for a major luxury retailer.Read case study
- Academic ResearchProtein Functional ClassificationApplied ML Research · BioinformaticsComparative deep learning study classifying proteins into 18 functional categories.Read case study
- Academic ResearchEmbryo Survival Prediction from Time-Lapse VideoComputer Vision Research · Life SciencesDeep learning pipeline predicting developmental viability from time-lapse video analysis.Read case study
- Academic ResearchReal-Time Stock Market PredictionStreaming Data & ML · FintechDistributed ML pipeline for real-time stock prediction using big data infrastructure.Read case study
- Academic ResearchParkinson's Detection via Gait AnalysisExplainable ML · Digital HealthExplainable AI for early-stage Parkinson's disease detection through gait sensor data.Read case study
Working on a similar problem?
Let's talk about how production-grade ML can move your roadmap forward.