Glossary

Aberration

The spreading of light (also called ‘wavefront distortion’) due to imperfections in the optical path or variations in refractive index at the sample, which results in images that are blurrier than the ideal diffraction-limited image we would expect were aberrations absent.

Adaptive Optics

Technology that senses distortions in the wavefront of light and cancels them, thereby suppressing optical aberrations to enhance image clarity.

Autoencoder

A deep learning architecture used to learn efficient coding of unlabeled data. An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation.

Backpropagation

The method used by neural networks to learn from its predictions. Once the prediction is done, it is compared with the ground truth through a training loss and the value of the comparison is used backwards to sequentially update the weights in the neural network, reward it when making a good prediction and punish it when making a bad prediction.

Batch

A small group of data that is processed together at the same time. For example, when training a machine learning model, a batch is a group of data that is given to the model for learning. Batches are commonly used to make the processes more efficient.

Bayesian Optimization

A strategy that allows the optimization of black-box functions such as deep neural networks. It creates a surrogate model, which is a probabilistic representation of the objective function, using only a few example points.

Binary Segmentation

A type of image segmentation where each pixel is classified into one of two categories—typically “foreground” (e.g., cell) or “background.” The output is a binary mask distinguishing objects (set to a value of 1) from their background (0).

CARE (Content-aware image restoration)

A deep learning-based method for image restoration that leverages content-specific features to enhance degraded images. See https://github.com/CSBDeep/CSBDeep for more information.

Computer Vision

A field of computer science wherein computers extract information from images. It often involves object detection within images and can involve classification of the images and/or objects.

Convolution

A mathematical process where a kernel (small matrix) slides over input data (e.g., images) to compute feature maps, highlighting patterns like edges or textures.

Convolutional Neural Networks (CNNs)

A deep learning architecture that applies convolutions to automatically learn features from images for computer vision tasks like classification and detection.

Data Augmentation

A strategy to artificially increase the diversity of a dataset prior to training by applying transformations such as rotation, flipping, or brightness adjustment. It helps improve model robustness and generalisation.

Deconvolution

A mathematical process to partially reverse the blurring effect caused by the microscope’s PSF, increasing contrast and resolution over the raw image data if performed carefully.

Domain Randomization

Using simulations or synthetic training data, domain randomization applies random and exaggerated variations to background, lighting, shapes, or textures in the synthetic dataset. This strategy helps the model learn domain-invariant features and is usually used for pretraining a neural network or to enable simulation-to-real transfer.

Effect Size

How “strong” a phenotype is, or how mathematically possible it is to distinguish a given population from the control population.

Epoch

One complete pass through the entire training dataset during the training process.

F1 Score

A classification metric that gives the harmonic mean of precision (proportion of correct true positive predictions across all predicted positive cases) and recall (proportion of true positive predictions against the total positive cases). The harmonic mean is a method to balance both metrics equally. This metric was originally designed for binary classification but can be adapted to multiclass classification by calculating the F1 score per class.

False Negatives

In a scenario where you have two classes “positive” and “negative”, you try to predict cases as one of those classes. False negatives are the cases that you incorrectly predicted as negative and were really positive.

False Positives

In a scenario where you have two classes “positive” and “negative”, you try to predict cases as one of those classes. False positives are the cases that you incorrectly predicted as positive and were really negative.

FIJI

An image processing platform that comes bundled with many plugins for scientific image analysis. See https://imagej.net/software/fiji/ for more information.

Frequency Domain

The representation of an image as a function of spatial frequency, obtained by transforming an image into the spatial domain using the Fourier transform.

Gaussian Process

A common surrogate model for optimization strategies such as Bayesian Optimization. Gaussian Processes are non-parametric a case that models a conditional probability function. In the hyperparameter search scenario, the Gaussian Process models the probability of getting an objective function value based on some hyperparameters.

Generative Adversarial Networks (GANs)

A deep learning architecture where two neural networks, a generator and a discriminator, are trained in an adversarial process, enabling the generator to create synthetic data, such as realistic images, by learning to deceive the discriminator.

Genetic Algorithms

An optimisation method inspired by the principles of natural selection and genetics. It starts with a population of solutions. These solutions are combined through a process called crossover to produce new solutions (offspring). During this process, random changes or mutations may occur to introduce diversity. After crossover and mutation, a selection step chooses the best solutions from both the parent and offspring populations to form the next generation. This cycle repeats for a set number of generations or until a predefined goal or stopping criterion is met.

Ground Truth

Accurate data against which a model can be evaluated. Ground truth data is often manually annotated. The data type itself will vary depending on the task and evaluation. e.g. instance segmentation may be compared to ground truth object counts or masks.

Hallucinations

Outputs from a model that do not have a basis in the input data and may contain false or misleading information.

Hyperparameters

The options you choose when training a machine learning model that affect the training process or the architecture of the model (e.g., learning rate, batch size, number of layers, training loss, etc.) are called hyperparameters. This term is used to differentiate them from the parameters (also known as weights) of the machine learning model.

Image Classification

A computer vision task where each image is associated with one class and the goal of this task is to correctly predict that class.

Image Restoration

The process of recovering clear, high-quality images from degraded raw data contaminated by blur, noise, or other distortions.

Instance Segmentation

A segmentation task that not only separates objects from the background but also distinguishes between individual objects of the same type (e.g., separating touching cells one by one).

IoU

“Intersection over Union”. A segmentation metric that calculates the difference between the area of overlap between two segmentation masks divided by the area of union.

Manual Annotation

The process of manually labeling specific structures or objects in an image using drawing tools. Typically done in software like Fiji or Napari, this step is essential for creating ground truth data to train or evaluate machine learning models.

Metadata

Any data that provides additional information about other data. In bioimaging, examples include information about sample preparation, the imaging instrument, and image acquisition parameters.

N2N (Noise2Noise)

A supervised denoising method that trains a neural network on pairs of independently noisy images of the same scene, requiring no clean reference data but needing paired noisy inputs. See https://github.com/NVlabs/noise2noise for more information.

N2S (Noise2Self)

A self-supervised denoising method that trains a neural network assuming statistically independent noise across the image, requiring only single noisy images without paired clean data. See https://github.com/czbiohub-sf/noise2self for more information.

N2V (Noise2Void)

A self-supervised denoising method that trains a neural network to predict pixel values from noisy images by masking input pixels, requiring only single noisy images without paired clean data. See https://github.com/juglab/n2v for more information.

Nonlinear Problem

A mathematical problem where the governing equations or operations are nonlinear, meaning outputs are not linearly proportional to inputs.

Object Detection

A computer vision task that identifies and locates individual objects within an image, typically by drawing bounding boxes around them. It provides both the category (what) and position (where) of each object.

Panoptic Segmentation

A computer vision technique that is a combination of semantic segmentation and instance segmentation. It separates an image into regions while also detecting individual object instances within those regions.

Pixel Classifiers

Machine learning models that classify each pixel in an image based on features such as intensity, texture, or local neighborhood. Commonly used in traditional workflows for segmentation or classification tasks.

Point Spread Function (PSF)

A mathematical function that describes how an imaging system blurs a point source.

Quality Control Metric

Any metric that can be used to evaluate quality. It will vary depending on the task and data type. It can be binary (e.g. an image doesn’t have debris) or continuous (e.g. annotated object centroids are within 5 pixels of the ground truth centroids).

RCAN (residual channel attention network)

A deep learning-based method using residual learning and channel attention to improve image restoration tasks. See https://github.com/AiviaCommunity/3D-RCAN for more information.

ReLU

An activation function common in deep learning that outputs the input directly if it is positive, and outputs zero otherwise; this characteristic helps introduce non-linearity into the model and mitigate the vanishing gradient problem.

Self-supervised learning

A deep learning method where models generate their own supervisory signals from unlabeled data, often by using pretext tasks, to learn useful representations that can be applied to various downstream tasks.

Semantic Segmentation

A form of segmentation where each pixel in an image is assigned to a class (e.g., nucleus, cytoplasm, background), but it does not distinguish between separate instances of the same class.

Sigmoid Function

An activation function common in deep learning that non-linearly maps real inputs to outputs between 0 and 1, being most sensitive to changes in inputs around zero and increasingly compressing extreme positive or negative inputs as they approach 1 or 0 respectively; this characteristic enables it to model probabilities for binary classification and introduce smooth non-linearity.

Spatial Domain

The representation of an image as a function of spatial coordinates.

Star-convex Polygon

A geometric shape used in segmentation algorithms like StarDist. Imagine drawing straight lines (rays) from the centre of an object out toward its edges—if you can see the edge from the centre in all directions, the object is considered star-convex. This method works well for blob-like structures such as nuclei, because their general shape can be captured by measuring how far each ray travels from the centre to the boundary.

Supervised learning

A deep learning method where models learn from labeled data (input-output pairs), enabling them to learn a mapping function for making predictions or decisions on unseen inputs.

Training Data

Data used to train an algorithm to make predictions.

Transfer Learning

A deep learning technique that reuses a model pre-trained on one task as the starting point for a new, related task, leveraging its learned knowledge to improve performance or reduce training requirements. In practice, part of a pretrained neural network (usually the initial layers, responsible for feature extraction) is frozen and reused in a new model. These frozen layers, with the knowledge from a previous dataset, are combined with untrained layers tailored for a specific bioimaging task. During training, only the new layers will be updated, allowing the model to adapt to the new task with limited data.

Transformer Models

A deep learning architecture based on the multi-head attention mechanism; specifically referring to the ‘vision transformer’ architecture. A vision transformer (ViT) is a transformer designed for computer vision. A ViT decomposes an input image into a series of patches (rather than text into tokens), serializes each patch into a vector, and maps it to a smaller dimension with a single matrix multiplication. These vector embeddings are then processed by a transformer encoder as if they were token embeddings.

True Negatives

In a scenario where you have two classes “positive” and “negative”, you try to predict cases as one of those classes. True positives are the cases that you predicted as negative and were really negative.

True Positives

In a scenario where you have two classes “positive” and “negative”, you try to predict cases as one of those classes. True positives are the cases that you predicted as positive and were really positive.

Virtual Machine

On a physical computer, you install an operating system (e.g., Windows or Ubuntu) that you interact with. A virtual machine is a program that simulates a complete computer with its own operating system. This lets you run a “computer inside your computer” (e.g., using Linux inside Windows or the other way around). As this simulated computer is separate from your physical one, it adds an extra layer of security, because unless the user specifically allows it, the virtual machine cannot access or connect to your real computer.

Zernike Modes

A set of orthogonal polynomials used to describe and correct wavefront aberrations in optical systems.