Systems and methods for automated stereology using deep learning are disclosed. The systems include an update in the form of a semi-automatic approach for ground truth preparation in 3D stacks of microscopy images (disector stacks) for generating more training data. The systems also present an exemplary disector-based MIMO framework where all the planes of a 3D disector stack are analyzed as opposed to a single focus-stacked image (EDF image) per stack. The MIMO approach avoids the costly computations of 3D deep learning-based methods by using the 3D context of cells in disector stacks; and prevents stereological bias in the previous EDF-based method due to counting profiles rather than cells and under-counting overlap-ping/occluded cells. Taken together, these improvements support the view that AI-based automatic deep learning methods can accelerate the efficiency of unbiased stereology cell counts without a loss of accuracy or precision as compared to conventional manual stereology.

A processor divides a fundus region of an ultra-wide field fundus image into plural areas including at least a first area and a second area, generates first attribute information indicating an attribute of the first area and second attribute information indicating an attribute of the second area, and generates first mode instruction information to instruct display of the first area in a first mode corresponding to the first attribute information, and generates second mode instruction information to instruct display of the second area in a second mode corresponding to the second attribute information.

An image processing method according to the invention comprises: obtaining three-dimensional image data representing a three-dimensional image of a fertilized egg in a cleavage stage obtained by imaging the fertilized egg by optical coherence tomography; extracting a blastomere region corresponding to an individual blastomere in the three-dimensional image for each blastomere based on the three-dimensional image data; counting a number of the blastomere region extracted in the three-dimensional image; obtaining a volume of each blastomere region based on the three-dimensional image data; and determining a number X of the extracted blastomere regions is expressed by a following inequality:

2.sup.N<X<2.sup.N+1 (N is a natural number)

and when the inequality holds, dividing each of (2.sup.N+1−X) blastomere regions having a largest volume out of the X blastomere regions equally into two blastomere regions.

An image processing method according to the present invention includes: obtaining three-dimensional image data representing a three-dimensional image of a fertilized egg in a cleavage stage obtained by imaging the fertilized egg by optical coherence tomography; extracting a blastomere region corresponding to an individual blastomere in the three-dimensional image for each blastomere based on the three-dimensional image data; obtaining a volume of each blastomere region based on a result of the extraction and the three-dimensional image data; and obtaining an index value expressing a volume variation of the blastomeres based on a derived result of the volumes. It is possible to provide useful quantitative information in evaluating a state of the fertilized egg.

Methods, systems, and apparatuses for detecting and describing heterogeneity in a cell sample are disclosed herein. A plurality of fields of view (FOV) are generated for one or more areas of interest (AOI) within an image of the cell sample are generated. Hyperspectral or multispectral data from each FOV is organized into an image stack containing one or more z-layers, with each z-layer containing intensity data for a single marker at each pixel in the FOV. A cluster analysis is applied to the image stacks, wherein the clustering algorithm groups pixels having a similar ratio of detectable marker intensity across layers of the z-axis, thereby generating a plurality of clusters having similar expression patterns.

Methods and products for automated real-time ovarian follicular detection, monitoring and analysis are provided. The devices and methods allow for remote or local analysis, while minimizing or eliminating the need for technician review of the output images. The methods are useful in human and non-human subjects including companion animals and other animals such as endangered species.

A computer-implemented method of processing a digital dental impression includes determining one or more first digital surface regions visible from a first side of the digital dental impression along an occlusion axis and one or more second digital surface regions visible from a second side of the digital dental impression along the occlusion axis, segmenting the digital dental impression into one or more digital segments and determining the one or more digital segments as a first digital segment or a second digital segment based on the majority of digital surface regions in the one or more digital segments.

Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are commonly used to assess patients with known or suspected pathologies of the lungs and liver. In particular, identification and quantification of possibly malignant regions identified in these high-resolution images is essential for accurate and timely diagnosis. However, careful quantitative assessment of lung and liver lesions is tedious and time consuming. This disclosure describes an automated end-to-end pipeline for accurate lesion detection and segmentation.

The method for determining property feature segmentation includes: receiving a region image for a region; determining parcel data for the region; determining a final segmentation output based on the region image and parcel data using a trained segmentation module; optionally generating training data; and training a segmentation module using the training data S500.

A method of limiting processing by a 3D reconstruction system of an environment in a 3D reconstruction of an event includes dividing by the subdivision module the volume into sub-volumes; projecting from each camera each of the sub-volumes to create a set of sub-volumes masks relative to each camera; creating an imaging mask for each camera; comparing for each camera by the subdivision module the respective imaging mask to the respective sub-volume mask and extracting at least one feature from at least one imaging mask; saving by the subdivision module the at least one feature to a subspace division mask; cropping the at least one feature from the imaging frames using the subspace division mask; and processing only the at least one feature for a 3D reconstruction. The system includes cameras for recording the event in imaging frames; and a subdivision module for dividing the volume into sub-volumes.