Skip to content

The Art of Balancing: Accuracy in Image Analysis

Dortmund, 20th December 2023

Centuries ago, the invention of the microscope opened a window to a tiny, previously invisible world. Since then, it is not only the quality of images that has changed dramatically, but also the way in which we interpret them. Instead of just optically revealing the depths of the smallest structures, we can now translate biological processes into precise figures using modern image analysis methods. But for this translation to succeed, all researchers must first ask themselves the same questions: What do we want to measure? How precise do these measurements need to be so that we can interpret them in a meaningful way?

Modern microscopes generate enormous amounts of data. A light sheet fluorescence microscope at ISAS, for example, produces an average of well over 500 high-resolution images per sample. Handling this amount of data and then efficiently analysing it requires innovative approaches to data analysis. Specialised software or image analysis methods find use here, with the increasing help of artificial intelligence (AI). However, there is no such thing as a universally applicable approach to image analysis. "Just as there is no 'one size fits all' microscope, different research projects require customised image analysis workflows or software tailored to the specific requirements", explains Dr Jianxu Chen. He leads the AMBIOM – Analysis of Microscopic BIOMedical Images junior research group at ISAS, which is working on these types of AI-based biomedical image analysis algorithms.

Die Abbildung zeigt eine Wage und symbolisiert das Gleichgewicht zwischen Analyse und Genauigkeit bei der Validierung von biomedizinischen Aufnahmen.

The checklist is about the balance between analysis and accuracy. This image was created by Dr Jianxu Chen (AMBIOM) on December 13, 2023, using ChatGPT, model "DALL-E". See end of page for details including prompt.

© ChatGPT

A checklist to validate bioimage analysis results

When analysing images, the challenge is to ensure that the findings obtained are not only quantitatively or statistically accurate, but also biologically meaningful to the research question. "To achieve this, researchers should fine-tune the experimental design, the details of the microscopic imaging and the target metrics of the image analysis from the start", advises Chen. Together with Dr Susanne Rafelski and Dr Matheus Viana from the Allen Institute for Cell Science in the US, he recently published some key considerations for researchers in the journal Nature Methods (see info box). Researchers can utilise them as a type of checklist when considering how to analyse their image data.

  • Basics

      • Should the measurements be relative or absolute?

      • Which measurements or variables are required?

      • Do you want to do Segmentation, deep learning prediction or do you have a specific quantification goal?

  • Boundaries

      • What experimental factors need to be considered?

      • Which microscope types and settings are suitable?

      • What are the limits of resolution?

  • Validation

      • Relative or absolute validation?

      • Is the goal a one-off or a robust, scalable result?

      • Should the accuracy apply to the entire image or specific features?

      • Qualitative or quantitative error bars?

  • Time and Effort

      • Time and effort

      • What is the best approach for the analysis?

      • How much time and effort should the analysis cost?

Just how good is good enough?

A key step on the way to a biologically valid image analysis is the question of validation, meaning how accurate and precise the measurements should be. "It is important that the validation is application-oriented and geared towards the specific objectives of the research", emphasises Chen. In practice, this means that researchers need to consider beforehand how accurate their measurements should be and how many errors they can tolerate. For example, if they want to measure cell parts like the nucleus or mitochondria, they could ask themselves the question: Do the exact volumes of the organelles matter, or is it more about comparing different volumes? In the latter case, the exact volume may not play a major role, but for the comparison, however, the computer programmes used must perform all the more consistently in different situations.  

Portrait von Dr.  Jianxu Chen.

Dr Jianxu Chen

© ISAS / Hannes Woidich

Constant adaptation – with the help of AI

However, not even the best image recognition algorithms always work equally well if, for example, the shape of the organelles changes just slightly. Researchers therefore have to regularly check and validate their measurements, adjust individual parameters or, at worst, even use a completely different programme. "If such adjustments are not taken into account, this can lead to fundamental misinterpretations of the biological results", warns Chen. To him, one solution is deep learning, a form of machine learning that can automatically extract patterns and features from large amounts of data. His research group has already developed a plug-in based on deep learning for the segmentation (see infobox) of immune cells. In the future, deep learning could help researchers to automatically recognise drops in performance in their image analysis algorithms during validation.

Segmentation

In biomedical research, it can be helpful to recognise and differentiate between different structures such as cells in an image. This process is called segmentation. For a long time, it was common practice to go through the images individually and annotate (assign) them by hand. However, as data volumes and image sizes increase, researchers are increasingly turning to deep learning-based programmes. These are not only significantly faster, but also much more objective and accurate. Nevertheless, manual annotations often still serve as a training basis for these deep learning algorithms. Compared to models trained with biological ground truth, models trained with manual annotations have an error rate of over 30 per cent (see Sonneck 2023). By biological ground truth, AI experts mean the optimal approach to objective reality, which is difficult to determine with a single analysis. Instead of using manual annotations, experts determine the biological ground truth using experimental computer-aided analyses.

The future of image analysis is interdisciplinary

But Chen and his colleagues are not just interested in finding better ways to analyse images. They are keen to ensure that their methods can be understood and applied in both biology and computer technology. "We need more interdisciplinary collaboration between researchers in the lab and AI experts, preferably early on in each of their training", Chen urges. For those who cannot wait to get started, but do not have a computer vision soecialist nearby, Chen recommends online learning materials such as The Bioimage Guide or Resources via the German Network for Bioinformatics Infrastructure – de.NBI. There is also a forum at the online platform Github for specific questions. “Collaboration is the only way that quantitative microscopy image analysis can really evolve”, Chen concludes.

The MSCoreSys associated junior research group AMBIOM – Analysis of Microscopic BiOMedical Images is funded by the Federal Ministry of Education and Research (Bundesministerium für Bildung und Forschung, BMBF) under the funding reference 161L0272.

About the illustration: Prompt = „I am creating a picture illustration for my article with name “The Art of Balancing: Accuracy in Image Analysis”. It is a press article about how to do bioimage analysis validation. Could you help make an illustration, as normal as possible, and as simple as possible?” ChatGPT only provides the following information about the image: „Here is the illustration representing the concept of „The Art of Balancing: Accuracy in Image Analysis” for your article. It features a balance scale with a magnifying glass on one side and a checkmark on the other, symbolizing the equilibrium between analysis and accuracy in bioimage validation.”

(Cheyenne Peters)

Share

Further articles

30th April 2025

Humboldt Fellow Prof Dr Xiaowei Xu started at ISAS in March

Prof Dr Xiaowei Xu from the Chinese Guangdong Cardiovascular Institute is researching the clinical application of artificial intelligence (AI) in the context of cardiovascular diseases. For 18 months in total, he will be researching various AI methods for analysing cell images as a Humboldt Fellow at ISAS.

Prof Dr Xiaowei Xu in front of the ISAS city building.
22nd April 2025

Valuable Connections: Dr Mohammad Ibrahim AlWahsh

Dr Mohammad Ibrahim AlWahsh worked as a research assistant at ISAS during his doctorate. He is now Vice Dean of the Faculty of Pharmacy and Assistant Professor of Toxicological Pathology at Al-Zaytoonah University in Jordan. In the Kompakt series ‘Valuable Connections,’ he reports on his time at ISAS and his ongoing network with the institute.

Mohammad Alwahsh.
9th April 2025

Bacteria & Sweets: Schoolgirls Examine their Breath at the Girls’ Day

On Girls' Day 2025, twelve schoolgirls got to know the work of researchers and technical assistants at the institute. They investigated the cause of and fight against inflammation, went on the hunt for bacteria and used ion mobility spectrometry to analyze the aromatic substances of various sweets in their breath.

Luisa Speicher erklärt drei Mädchen den Vortexmischer.
27th March 2025

Valuable Connections: Dr Jianxu Chen

Dr Jianxu Chen leads the junior research group AMBIOM - Analysis of Microscopic BIOMedical Images at ISAS since 2021. He previously worked at the Allen Institute for Cell Science in Seattle, USA. In the ISAS -Kompakt series ‘Valuable Connections’, the computer scientist reports on his move to health research and to Germany.

Portrait von Dr.  Jianxu Chen.
12th March 2025

Two-step Analysis is a Thing of the Past Thanks to Innovative Mass Spectrometry

Fast and accurate mass spectrometric detection of non-polar substances such as cholesterol together with polar substances? And in just one analysis run? This is made possible by a new combination method that unites two ionization sources in one setup.

Daniel Foest steht im Labor und hält ein Papier mit einer Leberprobe, die er am Massenspektrometer untersucht.
26th February 2025

What are you doing at ISAS, Leon?

What do marshmallows and chocolate have to do with cell analysis? Leon is finding out the answer during his school internship at ISAS. For ISAS Kompakt, the 15-year-old talks about what else he is learning during his time at the institute.

Leon hält Marshmallows, Schokolade und die Hardware für sein Projekt zur Bilderkennung.
14th February 2025

Valentines’ Day: Perfect Couples in the Lab

On Valentine's Day, the editors of ISAS Kompakt wanted to know what makes our researchers' hearts beat faster. The examples from the laboratories of the Bioimaging and NMR Metabolomics research groups show that special bonds do not only exist in love, but also in science.

Porträt von Dr. Themistoklis Venianakis.
4th February 2025

Valuable Connections: Adrian Sebuliba

Adrian Sebuliba joined the ISAS junior research group AMBIOM in 2023 as a software engineer. Previously, he worked for a digital commerce platform for the chemical industry in Uganda. In the ISAS Kompakt series ‘Valuable Connections’, he reports on his move into health research, among other things.

Portrait of Adrian Sebuliba.
28th January 2025

A Small But Very Important Step

Susmita Ghosh joined the Biofluorescence research group at ISAS in October 2021. The PhD student has now received the first funding of her career for her pilot project “Dissecting the neutrophil-tumor cell interactome using SILAC-labelling”.

Portrait Susmita Ghosh.