Spot Detection Methods in Fluorescence Microscopy Imaging: A Review

Abstract

Fluorescence microscopy imaging has become one of the essential tools used by biologists to visualize and study intracellular particles within a cell. Studying these particles is a long-term research effort in the field of microscopy image analysis, consisting of discovering the relationship between the dynamics of particles and their functions. However, biologists are faced with challenges such as the counting and tracking of these intracellular particles. To overcome the issues faced by biologists, tools which can extract the location and motion of these particles are essential. One of the most important steps in these analyses is to accurately detect particle positions in an image, termed spot detection. The detection of spots in microscopy imaging is seen as a critical step for further quantitative analysis. However, the evaluation of these microscopic images is mainly conducted manually, with automated methods becoming popular. This work presents some advances in fluorescence microscopy image analysis, focusing on the detection methods needed for quantifying the location of these spots. We review several existing detection methods in microscopy imaging, along with existing synthetic benchmark datasets and evaluation metrics.

A bird’s-eye view of deep learning in bioimage analysis

“…Here, too, traditional approaches have made way for deep learning in numerous applications, with two-stage region-proposal CNN-based (R-CNN) and unified you-only-look-once (YOLO) approaches and variants being most popular [207] , [208] , [209] . In contrast with traditional object detection methods, which have found broad application in bioimage analysis for spotting intracellular particles [16] , [18] , [210] , [211] , cell nuclei [17] , [26] , and cellular events such as mitosis [212] , [213] , [214] , deep learning approaches for these tasks have been explored since only recently. First results are promising [196] , [215] , [216] , [217] , [218] ( Fig.…”

“…Automated bioimage analysis typically requires executing an intricate series of operations, which may involve image restoration [10] , [11] , [12] and registration [13] , [14] , [15] , object detection [16] , [17] , [18] , segmentation [17] , [19] , [20] , and tracking [21] , [22] , [23] , as well as downstream image or object classification [24] , [25] , [26] , quantification [27] , [28] , [29] , and visualization [30] , [31] , [32] . As attested by the just cited reviews and evaluations, a plethora of methods and tools have been developed for this purpose in the first half a century of computational bioimage analysis, based on what may now be considered traditional image processing and computer vision paradigms.…”

SPECHT: Self-tuning Plausibility Based Object Detection Enables Quantification of Conflict in Heterogeneous Multi-scale Microscopy

“…When the intensity profile of the fluorescence diverges from a generalised normal distribution, our object detection will increasingly fail and split objects into parts; a different detection method is then warranted [40]. The Mahalanobis distance can be uninformative in high-dimensional space due to the 'curse' of dimensionality, however, this is only the case if the increase in dimensions is due to non-discriminatory features [41].…”

Validation and tuning of in situ transcriptomics image processing workflows with crowdsourced annotations

“…Studies typically use synthetic images to evaluate or test the performance of any spot detector because ground truth does not inherently exist for real images. [ 17 ] The typical way of generating ground truth datasets for real images is having an expert inspect the images and annotate the valid spot locations by hand. [ 17 ] In cases where manual annotation of a large in situ transcriptomics image dataset by an expert is unfeasible, it is necessary to have alternative sources of ground truth.…”