Abstract: Disclosed is a system for analysis of microscopic image data acquired from biological cells. The system includes a data processing system which is configured to read the image data and determine a plurality of vertices, wherein each of the vertices represents a location of an entity of interest within a region of interest of the image data. The data processing system generates a plurality of graphs, wherein for each of the graphs, the generation of the respective graph includes generating a plurality of edges, wherein each of the edges has two of the plurality of vertices associated therewith. For each of the graphs one or more vertex sets are identified, each of which consisting of one or more of the plurality of vertices. The data processing system further determines, for each of the graphs, a number of the identified vertex sets.

Abstract: A non-transitory computer readable medium (26) stores instructions executable by at least one electronic processor (20) to perform a method (100) of monitoring a component (10) of a medical device (1), particularly an x-ray tube. The method includes: retrieving information about the component from the medical device: deriving a wear metric indicative of wear of a portion, particularly the filament, of the component from the retrieved information; and in response to the wear metric satisfying a predetermined manual adjustment prohibition criterion, outputting an alert (30) indicating that the component of the medical device is nearing an end of its remaining useful life (RUL), and optionally that manual calibration should not be performed on the component.

Abstract: A non-transitory computer-readable medium stores instructions readable and executable by at least one electronic processor (10, 12, 14) to perform a log pattern analysis method (300) by applying a log pattern to log data undergoing analysis comprising log events which are time stamped and which are defined by values for a set of fields. The log data undergoing analysis are stored on a server (30) accessible by the at least one electronic processor via an electronic network (31).

Abstract: An apparatus (10) for navigating a hierarchical electronic questionnaire (12) includes at least one electronic processor (20) programmed to: provide (102) a user interface (UI) (27) via which: at least a portion of the hierarchical electronic questionnaire is presented on a display device (24) represented as a tree-based questionnaire map (30) with a plurality of nodes (32) connected by a plurality of branches (34), the nodes of the plurality of nodes corresponding to questions; a user input is received, via at least one user input device (22), indicative of a selection of at least one of the nodes; and the question corresponding to the selected node is displayed and a user input indicative of an answer to the question corresponding to the selected node is received via the at least one user input device; and populate (104) one or more nodes other than the selected node based on the selected node and/or the answer to the question corresponding to the selected node.

Abstract: A method (100) of automated identification of one or more malfunction areas of a set (S) of malfunction areas for a service case in which a medical device (12) is serviced includes: generating an output probability vector (40) of probabilities for the set of malfunction areas of the medical device by operations including applying at least one classifier (42, 46) to at least one of (1) text descriptions of parts ordered for the service case and/or (2) a text description of the service case; and displaying a list (56) of one or more most probable malfunction areas for the service case wherein the one or more most probable malfunction areas are the one or more most malfunction areas of the set of malfunction areas having highest probability in the output probability vector.

Abstract: A method (100) of generating a ranked list (42) of alerts (30) from files (32) of electronic devices (12) includes: applying predictive models (34) to data of the files to generate maintenance alerts for the electronic devices; assigning discrete values for a set of criteria (36) to each maintenance alert whereby the maintenance alert has a share computed as a product of the assigned discrete values; performing a credit-based queuing process (38) to assign the maintenance alerts to slots of a ranked list, wherein in the credit-based queuing process the maintenance alerts accumulate credits in accord with the shares computed for the respective maintenance alerts; and displaying, on a display device (24) operatively connected with the at least one electronic processor, the maintenance alerts as the ranked list in accordance with the assignments of the maintenance alerts to the slots of the ranked list.

Abstract: A non-transitory computer readable medium (26) stores instructions executable by at least one electronic processor (20) to perform a method (100) of detecting issues with wireless connections. The method includes: receiving Wi-Fi roaming data for wireless devices (12) connected to a wireless electronic data communication network (14) comprising a plurality of access points (APs) (16) dispersed through a facility; from the received Wi-Fi roaming data, determining single-AP disconnect events for the APs wherein a single-AP disconnect event for an AP comprises a disconnection of the AP from a wireless device followed by a reconnection of the AP with the wireless device without the wireless device connecting to any other AP during a time interval between the disconnection and the reconnection; and generating an alert (30) for any AP whose rate of single-AP disconnect events exceeds a predetermined single-AP disconnect rate alert threshold.

Abstract: Analysis of a log pattern for use in diagnosing a medical imaging device operates on log data including log events and service calls, each associated with a subset of log events within a service call time frame of a call time of the service call. Preprocessing (64) generates normalized log events (66) by removing or replacing content of the log events and linking each normalized log event with one or more service calls. Pre-analysis (68) identifies a test set of normalized log events that match a log pattern (40) and a test set of service calls (42) linked with the test set of normalized log events. The test set of service calls is analyzed (74) to identify hit service calls (46) each belonging to the test set of service calls and for which the log pattern under analysis has a hit.

Abstract: At a service device (102), a user interface (106) is provided via which a user submits an order request (117) to order a requested part (X) via the at least one user input device (103). Co-replacement information (116) for the requested part (X) is identified using a co-replacements database (114), and is displayed on the display. For example, a second part (Y) commonly co-replaced with requested part (X) may be identified and recommended for replacement with part (X); or, if two parts (X) and (Y) are ordered then the co-replacement information may be to recommend ordering only one of these parts. At a server hosting the database (114), the order request is received from a service device and the co-replacement information (116) for the requested part is generated using the co-replacements database (114), and the co-replacement information is sent to the service device.

Abstract: A method (100) for transferring at least a portion of a log file to a service center server (16) includes: analyzing the log file to generate notifications (38) of maintenance issues and sending the notifications to the service center server and, for each notification, defining a part of the log associated to the notification; partitioning the log file into parts (40, 42), including the parts associated to the notifications and at least one part corresponding to the remainder of the log file; assigning costs (44) and values (46) to the parts; determining an order of the parts based on the assigned costs and the assigned values for the parts; and transferring the parts to the service center server in the determined order.

Abstract: A method (100) of generating a machine-learned (ML) decision tree classifier (12) includes: iteratively adding child nodes to nodes of the ML decision tree classifier by: selecting a plurality of features from the set of features; creating one or more boundaries (34) in a plane (30) defined by the selected plurality of features, the one or more boundaries partitioning the plane into regions (36) that split the training data associated to the node into at least two subsets of training data, the one or more boundaries being created based on the class labels of the training data associated to the node; for each subset of training data, adding to the node a child node having associated training data consisting of the subset of training data; and defining a classification rule for the node using the created one or more boundaries in the plane.

Abstract: A non-transitory computer readable medium (107, 127) stores instructions executable by at least one electronic processor (101, 113) to perform a method (200, 300) of generating a recommendation engine for recommending actions during performance of a fault-finding task. The method comprises: converting a collection of historical fault-finding process sequences (140) into a fault-finding tree (130) having nodes (132), action edges (135) and outcome edges (137) connecting the nodes. The action edges are labeled with actions of the historical fault-finding process sequences and the outcome edges are labeled with outcomes of the historical fault-finding process sequences. The nodes include terminal nodes (133) labeled with root causes or solutions identified by the historical fault-finding process sequences. A visualization (142) of the fault-finding tree is provided on a user interface (UI) (120) on a service device (102) operable by a field service engineer (FSE).

Abstract: A non-transitory computer readable medium stores instructions executable by at least one electronic processor to perform a method of tracking patient movement through a medical facility. The method includes: receiving wireless roaming data for a wireless patient device associated to a patient from a wireless electronic data communication network comprising a plurality of access points (APs) dispersed through the medical facility; from the received wireless roaming data, determining a connection history for the wireless patient device indicating the AP connected with the wireless patient device as a function of time; and generating a visualization of the connection history for the wireless patient device.

Abstract: A wireless network comprises access points (APs) implementing roaming by way of handover of wireless devices between APs. Handover events over an analysis time interval are extracted from a wireless network log of the wireless network. Each handover event comprises a source AP from which a wireless device disconnects and a destination AP to which the wireless device connects. At least one handover frequency (HF) network topology graph is constructed fro the analysis time interval from the extracted handover events. The graph has nodes representing at least a subset of the APs of the extracted handover events and edges connecting pairs of nodes with each edge having a weight representing a count or frequency of handover events between the APs represented by the pair of nodes connected by the edge. A network diagnostic or visualization task is performed using the HF network topology graph.

Abstract: An apparatus (10) for navigating a hierarchical electronic questionnaire (12) includes at least one electronic processor (20) programmed to: provide (102) a user interface (UI) (27) via which: at least a portion of the hierarchical electronic questionnaire is presented on a display device (24) represented as a tree-based questionnaire map (30) with a plurality of nodes (32) connected by a plurality of branches (34), the nodes of the plurality of nodes corresponding to questions; a user input is received, via at least one user input device (22), indicative of a selection of at least one of the nodes; and the question corresponding to the selected node is displayed and a user input indicative of an answer to the question corresponding to the selected node is received via the at least one user input device; and populate (104) one or more nodes other than the selected node based on the selected node and/or the answer to the question corresponding to the selected node.

Abstract: Aspects and embodiments relate to a method and apparatus configured to perform that method. The method relates to generating an indication of relevance associated with a selected biological phenomenon indicative of condition of an immune system of a patient, that selected biological phenomenon being associated with response of a patient to a chosen therapy. The method comprises steps of: determining one or more measurable input parameters characteristic of the patient and associated with the biological phenomenon; mapping the one or more input parameters to a contribution to a score associated with the selected biological phenomenon; and combining the mapped contributions across the one or more input parameters to calculate the score associated with the selected biological phenomenon.

Abstract: In an electronic data processing method, a first column and a second column of at least one table are identified which have a one-to-one or one-to-many relationship with fewer than a threshold number of violations of the one-to-one or one-to-many relationship. On a display, possible data errors in the at least one table corresponding to the violations of the one-to-one or one-to-many relationship are indicated. The identifying of the violations may include generating a weighted bipartite graph representing the first and second columns, and detecting the violations using the bipartite graph. The method may further include displaying, on the display, a user interface whereby a user accepts or rejects each indicated violation of the one-to-one or one-to-many relationship.

Abstract: A non-transitory computer readable medium (107, 127) stores instructions readable and executable by at least one electronic processor (101, 113) operatively connected with a display (105) and at least one user input device (103) to perform a device service support method (200).

Abstract: A wireless network comprises access points (APs) implementing roaming by way of handover of wireless devices between APs. Handover events over an analysis time interval are extracted from a wireless network log of the wireless network. Each handover event comprises a source AP from which a wireless device disconnects and a destination AP to which the wireless device handover events. The graph has nodes representing at least a subset of the APs of the extracted handover events and edges connecting pairs of nodes with each edge having a weight representing a count or frequency of handover events between the APs represented by the pair of nodes connected by the edge. A network diagnostic or visualization task is performed using the HF network topology graph.

Abstract: A non-transitory computer readable medium (107, 127) stores instructions readable and executable by at least one electronic processor (101, 113) to perform a suspect device configuration detection method (200).