Semantic segmentation is an important imaging analysis method enabling the identification of tissue structures. Histological image segmentation is particularly challenging, having large structural information while providing only limited training data. Additionally, labeling these structures to generate training data is time consuming. Here, we demonstrate the feasibility of a semantic segmentation using U-Net with a novel sparse labeling technique. The basic U-Net architecture was extended by attention gates, residual and recurrent links, and dropout regularization. To overcome the high class imbalance, which is intrinsic to histological data, under- and oversampling and data augmentation were used. In an ablation study, various architectures were evaluated, and the best performing model was identified. This model contains attention gates, residual links, and a dropout regularization of 0.125. The segmented images show accurate delineations of the vascular structures (with a precision of 0.9088 and an AUC-ROC score of 0.9717), and the segmentation algorithm is robust to images containing staining variations and damaged tissue. These results demonstrate the feasibility of sparse labeling in combination with the modified U-Net architecture.
4 November 2024 in Journal of Materials Chemistry B
The transformative power of support vector regression in optimizing magnetic nanoparticle synthesis intricate relationships between process parameters and particle size, enabling the production of particles with tailored properties.
For reliable in silico or in vitro investigations in, for example, biosensing and drug delivery applications, accurate models of tumor vascular networks down to the capillary size are essential. Compared to images acquired with conventional medical imaging techniques, digitalized histological tumor slices have a higher resolution, enabling the delineation of capillaries. Volume rendering procedures can then be used to generate a 3D model. However, the preparation of such slices leads to misalignments in relative slice orientation between consecutive slices. Thus, image registration algorithms are necessary to re-align the slices. Here, we present an algorithm for the registration and reconstruction of a vascular network from histologic slices applied to 169 tumor slices. The registration includes two steps. First, consecutive images are incrementally pre-aligned using feature- and area-based transformations. Second, using the previous transformations, parallel registration for all images is enabled. Combining intensity- and color-based thresholds along with heuristic analysis, vascular structures are segmented. A 3D interpolation technique is used for volume rendering. This results in a 3D vascular network with approximately 400–450 vessels with diameters down to 25–30 µm. A delineation of vessel structures with close distance was limited in areas of high structural density. Improvement can be achieved by using images with higher resolution and or machine learning techniques.
This study explores the size of magnetic nanoparticles (MNP) for applications in Magnetic Resonance Imaging (MRI) and Magnetic Particle Imaging (MPI). Emphasizing the critical role of MNP size on their response to alternating magnetic fields, the study unveils a regression model to optimize MNP synthesis towards tailored sizes of MNP. With a limited and broadly distributed data set at hand, the feasibility of building an accurate predictive model based on Support Vector Machines is shown. Integrating such a model into a continuous synthesis setup establishes a feedback loop, enabling real-time control and adaptation of synthesis parameters.