Skip to main content

Introduction to AI Concepts

This page summarizes key AI and machine learning concepts that power Neolens. Understanding these terms will help you interpret the platform's behavior, outputs, and limitations.


Glossary of Core Concepts

Anomaly Detection
Automatically identifying data points or regions that deviate from expected patterns in medical images.

Artificial Intelligence (AI)
A broad field of computer science focused on creating systems capable of tasks that typically require human intelligence.

Attention Mechanisms
Model components that help focus on the most relevant parts of an image or input.

Bias and Fairness
The study of whether a model performs consistently across different patient populations and imaging contexts.

Classification
Assigning categories or labels to images or regions (e.g., benign vs malignant).

Computer Vision
The field of AI focused on enabling machines to interpret and process visual information from images or videos.

Convolutional Neural Network (CNN)
A deep learning architecture commonly used for image analysis tasks like detection, segmentation, and classification.

Deep Learning
A type of machine learning that uses layered neural networks to analyze data, especially useful for images and signals.

Explainability
The degree to which the internal mechanics of an AI model can be interpreted by humans.

Image Segmentation
Dividing an image into meaningful parts or regions, such as organs or anomalies.

Machine Learning (ML)
A subset of AI where algorithms learn from data to improve performance without explicit programming.

Multimodal Learning
Combining multiple data types (e.g., imaging + text) to enhance diagnostic accuracy.

NLP (Natural Language Processing)
A branch of AI used to understand and generate human language—used in Neolens to generate reports or interpret clinical notes.

Object Detection
Locating and identifying specific features or abnormalities in an image (e.g., nodules, lesions).

Uncertainty Estimation
Quantifying how confident the model is in its predictions—critical for clinical risk management.


tip

Need a refresher while reading the API docs? Return here anytime to revisit key terms.