0000000000164872
AUTHOR
Pekka Ruusuvuori
Quantitative Analysis of Dynamic Association in Live Biological Fluorescent Samples
Determining vesicle localization and association in live microscopy may be challenging due to non-simultaneous imaging of rapidly moving objects with two excitation channels. Besides errors due to movement of objects, imaging may also introduce shifting between the image channels, and traditional colocalization methods cannot handle such situations. Our approach to quantifying the association between tagged proteins is to use an object-based method where the exact match of object locations is not assumed. Point-pattern matching provides a measure of correspondence between two point-sets under various changes between the sets. Thus, it can be used for robust quantitative analysis of vesicle …
H&E Multi-Laboratory Staining Variance Exploration with Machine Learning
In diagnostic histopathology, hematoxylin and eosin (H&E) staining is a critical process that highlights salient histological features. Staining results vary between laboratories regardless of the histopathological task, although the method does not change. This variance can impair the accuracy of algorithms and histopathologists’ time-to-insight. Investigating this variance can help calibrate stain normalization tasks to reverse this negative potential. With machine learning, this study evaluated the staining variance between different laboratories on three tissue types. We received H&E-stained slides from 66 different laboratories. Each slide contained kidney, skin, and colon tissue sampl…
Echovirus 1 internalization negatively regulates epidermal growth factor receptor downregulation
We have demonstrated previously that the human picornavirus Echovirus 1 (EV1) triggers an infectious internalization pathway that follows closely, but seems to stay separate, from the epidermal growth factor receptor (EGFR) pathway triggered by epidermal growth factor (EGF). Here, we confirmed by using live and confocal microscopy that EGFR and EV1 vesicles are following intimately each other but are distinct entities with different degradation kinetics. We show here that despite being sorted to different pathways and located in distinct endosomes, EV1 inhibits EGFR downregulation. Simultaneous treatment with EV1 and EGF led to an accumulation of EGFR in cytoplasmic endosomes, which was evi…
Application independent greedy particle tracking method for 3D fluorescence microscopy image series
Single-particle tracking is computationally a challenging problem, and usually solved with local methods. Local methods suffer from defects in the image data or in the detection of particles, such as temporal disappearing of particles. A particle tracking method has to provide a solution also to real disappearing and appearing of particles as a result of merging and splitting. Here, we present an efficient, greedy algorithm as a solution to the particle tracking problem. This improved local method is application independent, as it has high configurability of the function used to solve particle correspondence. To demonstrate the accuracy of the method, we apply it to real microscopy image da…
Domain-specific transfer learning in the automated scoring of tumor-stroma ratio from histopathological images of colorectal cancer
Tumor-stroma ratio (TSR) is a prognostic factor for many types of solid tumors. In this study, we propose a method for automated estimation of TSR from histopathological images of colorectal cancer. The method is based on convolutional neural networks which were trained to classify colorectal cancer tissue in hematoxylin-eosin stained samples into three classes: stroma, tumor and other. The models were trained using a data set that consists of 1343 whole slide images. Three different training setups were applied with a transfer learning approach using domain-specific data i.e. an external colorectal cancer histopathological data set. The three most accurate models were chosen as a classifie…