Evaluation of reproducible cryogel preparation based on automated image analysis using deep learning

Abstract

Cryogels represent a class of porous sponge‐like materials possessing unique properties including high‐fidelity reproduction of tissue structure and maximized permeability. Their architecture is mainly based on an interconnected network of macropores that provides sufficient stability while allowing the movement of substances through the material. In most cryogel applications, the pore size is very important, especially when the material is used as a 3D scaffold for tissue culture, applied as a filter, or utilized as a membrane. In this study, poly(dimethylacrylamide‐co‐2‐hydroxyethyl methacrylate) cryogels have been prepared by two preparation methods to investigate the reproducibility of homogeneous pore structures and pore sizes. Automated image analysis algorithms were developed to rapidly evaluate cryogel pore sizes based on scanning electron microscopy (SEM) images. The quantification approach contained a unique combination of classical and deep learning–based algorithms. To validate the accuracy of the two models, we compared the results obtained from automated SEM image analysis with those from manual pore size determinations and mercury intrusion porosimetry (MIP) measurements. Effect sizes were calculated to compare the results from manual and automated pore size measurements for the cryogel reproducibility series. 81% of the values obtained revealed only trivial differences, which strongly suggests that automated image analysis can reliably substitute the manual evaluation of cryogel pore sizes. The use of an adapted reactor setup yielded cryogels with heterogeneous morphologies in the absence of recognizable pore structures. With the conventional cryogel preparation using plastic syringes, the obtained cryogels represented highly reproducible morphologies and pore sizes in the range between 17 and 22 μm. Calculated effect sizes within the cryogel replicate series revealed only trivial differences between the obtained pore sizes in 83.5% or 99.4% of the data (classical approach and deep learning‐based approach, respectively).

Hydrophilic cryogels as potential 3D cell culture materials: Synthesis and characterization of 2‐(methacrylamido) glucopyranose‐based polymer scaffolds

“…SEM images of freeze‐dried cryogel samples indicated the presence of smaller pores compared to the respective CLSM images of hydrated and swollen cryogels suggesting a shrinkage of pores during the freeze‐drying process, as exemplary shown for CGPOx1‐26 which revealed a 2.8 times decrease of the median pore size in the dried state (Figure S4). For the determination of the pore sizes, we utilized an already established automated SEM image analysis platform which allows a fast and efficient evaluation of SEM images 46 . No clear correlation between cryogel pore sizes and the type of cross‐linker or the sugar content was observed (Figure 5).…”

“…Only the median values were considered as reliable measures to compare the pore size variation among the cryogel series. The establishment and creation of the algorithmic approach was described in an earlier work 46 . In brief, electron microscopy images were analyzed in TIFF 8‐bit format, using a workflow written in JIPipe 59 .…”

“…For the determination of the pore sizes, we utilized an already established automated SEM image analysis platform which allows a fast and efficient evaluation of SEM images. 46 No clear correlation between cryogel pore sizes and the type of cross-linker or the sugar content was observed (Figure 5). The pore sizes varied between 18.5 and 23.0 μm, considering the median values.…”

“…The establishment and creation of the algorithmic approach was described in an earlier work. 46 In brief, electron microscopy images were analyzed in TIFF 8-bit format, using a workflow written in JIPipe. 59 The analysis produced intensity-based and morphometric measures of the pores; the latter was also utilized to compare the automated framework of analysis with the manual measurements of the pores.…”

Cryogels Based on Poly(2-oxazoline)s through Development of Bi- and Trifunctional Cross-Linkers Incorporating End Groups with Adjustable Stability

“…However, their potential has rarely been exploited with respect to cryogels. To the best of our knowledge, only one POx containing cryogel has been reported, 40 which is mainly based on N,N-dimethylacrylamide and only contains 14 mol % of poly(2-ethyl-2-oxazoline) diacrylate (PEtOxDA). Cryogels prepared from solely cross-linkers are rare, although PEGDA has been applied for that purpose.…”