“Interpreting” noise to remove image artifacts
Digital images consist of tiny elements named pixels, which are characterised by a fixed position, colour, and brightness within the picture. Random variation of pixel brightness and colour is defined as image noise. Denoising – the process whereby noise is removed from an image – is essential to retain the details of an image as far as possible.
Machine learning methods based on artificial neural networks that enable a computer to learn from observational data are widely used for image denoising and artefact removal. However, network training can often be difficult due to the lack of appropriate reference images, thus limiting the applicability of these denoising methods.
Florian Jug and his team at the Human Technopole Computational Biology Centre, found a way to circumvent this problem by developing a new denoising tool for microscopy images based on an unsupervised method that can be trained using noisy images only. The project was carried out in collaboration with researchers from Google and the results of the study are published at the International Conference on Learning Representations (ICRL) 2022, a top-tier venue for machine learning research.
Leveraging on a denoising method that they had previously published (DivNoising, or DN), the team now describe Hierarchical DivNoising (HDN), an unsupervised diversity denoising tool that is still easy to train and gives best results among competing methods. The researchers tested HDN on twelve publicly available denoising datasets, including natural (photographic) images, various microscopy datasets, and hand-written characters, and found that it outperformed existing unsupervised methods, and could, at times, even outperform supervised approaches while not requiring hard to obtain paired training data.
Furthermore, HDN was additionally capable of generating different sensible “interpretations” of noisy images. This possibility is unique to DN and HDN and will – according to Florian Jug – “change the way microscopists will assess the inherent uncertainty in noisy image data. HDN gives a very intuitive way to understand how much you can trust your data”.
Finally, the researchers showed how a trained HDN network can be used to remove imaging artefacts from microscopy images, far beyond the possibilities of other denoising methods.
In summary, Jug and co-workers designed a neural network-based method for unsupervised noise and artefact removal that can interpret noisy image data, thus paving the way to novel and innovative applications in microscopy and biomedical imaging.
Share:
You could also like:
-
Italy at the centre of the Genome of Europe project
The Human Technopole, ELIXIR Italia, the national node of the European life sciences research infrastructure coordinated by the National Research Council (CNR), and the Centro Cardiologico Monzino, as the Italian coordinating centre, have been selected as the Italian partners of Genome of Europe (GoE), the largest EU-funded genomic project, whose ultimate goal is to make […]
-
Human Technopole wins 2024 Oscar di Bilancio
On Friday 13 December, at Palazzo Mezzanotte in Milan, the Human Technopole Foundation’s ‘Integrated Report 2023’ received the Oscar di Bilancio in the social enterprises and non-profit organisations category. The award was presented to President Gianmario Verona, Elena Trovesi, Head of Administration, as well as the project leaders Giovanni Selmi, Head of Finance, and Alessandro […]
-
Mosaic Organoids to Study the Brains of Multiple Patients Simultaneously
An international team of scientists from Human Technopole and the University of Milan has developed and validated an innovative approach to studying human brain development across multiple individuals simultaneously using single organoids—laboratory models that replicate key cellular processes of human neurodevelopment. The research paves the way for in vitro population studies. Additionally, the scientists have developed a novel computational method to more accurately quantify the genetic identity of individual cells profiled from multiple individuals concurrently. The findings have been published in Nature Methods.
-
Cancer stem cell morphology predicts glioblastoma growth and resistance
Human Technopole researchers have identified adducin-γ (ADD3) as a crucial regulator of glioblastoma cancer stem cell morphology and intercellular bridges between tumour cells. These connections facilitate communication and allow tumour cells to share resources, evade chemotherapy, and survive in challenging conditions. The study has been funded by AIRC and the findings are published in Life Science Alliance.
-
Colorectal Cancer: ML Enhances Cetuximab Response Predictions
An international collaborative study led by Human Technopole, Candiolo Cancer Institute IRCCS in Turin, the University of Turin, and the Wellcome Sanger Institute in Cambridge (UK) has identified new factors associated with therapeutic response in colorectal cancer. The research has led to the development of a machine-learning model capable of accurately predicting the effects of cetuximab, a drug in clinical use, on different colorectal tumour subtypes. Funded by the AIRC Foundation, the study paves the way to identifying molecular features that could serve as biomarkers for predicting treatment response in patients with this type of cancer.