Abstract
BackgroundInterest in artificial intelligence-driven analysis of medical images has seen a steep increase in recent years. Thus, our paper aims to promote and facilitate the use of this state-of-the-art technology to fellow researchers and clinicians. New methodWe present custom deep learning models generated in DeePathology™ STUDIO without the need for background knowledge in deep learning and computer science underlined by practical suggestions. ResultsWe describe the general workflow in this commercially available software and present three real-world examples how to detect microglia on IBA1-stained mouse brain sections including their differences, validation results and analysis of a sample slide. Comparison with existing methodsDeep-learning assisted analysis of histological images is faster than classical analysis methods, and offers a wide variety of detection possibilities that are not available using methods based on staining intensity. ConclusionsReduced researcher bias, increased speed and extended possibilities make deep-learning assisted analysis of histological images superior to traditional analysis methods for histological images.
Highlights
Evaluation of histological sections is a core practise in clinical and research routine
The detected objects will appear more and more round
The different average object size is a consequence of the selected target objects and their size, with somas being smaller than microglia including their ramifications, which are in turn smaller than clusters consisting of several microglia cells (Fig. 5)
Summary
Evaluation of histological sections is a core practise in clinical and research routine. Interest in deep learning-assisted his tological analysis has spiked from around 20–50 publications per year (1975–2015) to 300–600 (2018–2020).. Interest in deep learning-assisted his tological analysis has spiked from around 20–50 publications per year (1975–2015) to 300–600 (2018–2020).1 This reflects, among other factors, changes in availability and technological advances (i.e. faster computers) that make deep learning more accessible (Shen et al, 2017). Deep learning has clear advantages over conventional methods It can save 90% of analysis time (Bascunana et al, 2021) and improves detection sensitivity (Klein et al, 2020). In this follow-up report, we provide a comprehensive guide on how to successfully develop custom models, using the versatile Objects mode of STUDIO. We demonstrate the vast possi bilities of deep learning models by comparing three different models developed with the same staining and tissue type
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have