Abstract: An electromagnetic field quality assurance system employing an electromagnetic field generator (10) for emitting an electromagnetic field (12), and one or more quality assurance electromagnetic sensors (11, 21, 31, 41, 50) for sensing the emission of the electromagnetic field (12). The system further employs a quality assurance controller (74) for assessing a tracking quality of the electromagnetic field (12) derived from a monitoring of a sensed position of each quality assurance electromagnetic sensor (11, 21, 31, 41, 50) within a field-of-view of the electromagnetic field (12). The electromagnetic field generator (10), an ultrasound probe (20), an ultrasound stepper (30) and/or a patient table (40) may be equipped with the quality assurance electromagnetic sensor(s) (11, 21, 31, 41, 50).

Abstract: An electromagnetic (“EM”) tracking configuration system employs an EM quality assurance (“EMQA”) (30) and EM data coordination (“DC”) system (70). For the EMQA system (30), an EM sensor block (40) includes EM sensor(s) (22) positioned and oriented to represent a simulated electromagnetic tracking of interventional tool(s) inserted through electromagnetic sensor block (40) into an anatomical region. As an EM field generator (20) generates an EM field (21) encircling EM sensor(s) (22), an EMQA workstation (50) tests an EM tracking accuracy of an insertion of the interventional tool(s) through the EM sensor block (40) into the anatomical region.

Abstract: A radiology workstation (14) used to interpret a radiology examination (48) includes a display (20, 22), a user input device (24, 26, 28), and an electronic processor (12, 16). A radiology image of the radiology examination is displayed on the display. A radiology report is entered. An imaged anatomical region (54) is determined from the stored radiology examination. An examination basis medical condition is identified from the reason for examination (52). At least one additional medical condition is determined based on information on the patient retrieved from one or more medical databases (10, 44, 46) and is classified as reviewable or not reviewable based on the imaging modality (50) and the imaged anatomical region. An attention list (40) is created with items directed to the examination basis medical condition and to each reviewable additional medical condition.

Abstract: The present disclosure is directed to methods and apparatus for validating and authenticating use of machine learning models. For example, various techniques are described herein to limit the vulnerability of machine learning models to attack and/or exploitation of the model for malicious use, and for detecting when such attack/exploitation has occurred. Additionally, various embodiments described herein promote the protection of sensitive and/or valuable data, for example by ensuring only licensed use is permissible. Moreover, techniques are described for version tracking, usage tracking, permission tracking, and evolution of machine learning models.

Abstract: The present disclosure is directed to methods and apparatus for validating and authenticating use of machine learning models. For example, various techniques are described herein to limit the vulnerability of machine learning models to attack and/or exploitation of the model for malicious use, and for detecting when such attack/exploitation has occurred. Additionally, various embodiments described herein promote the protection of sensitive and/or valuable data, for example by ensuring only licensed use is permissible. Moreover, techniques are described for version tracking, usage tracking, permission tracking, and evolution of machine learning models.

Abstract: System and method for generating structured finding object (“SFO”) description recommendations. The system and method are configured to extract a plurality of first findings for a patient, assemble the first findings into a timeline for the patient, extract a plurality of second findings for a population of patients, determine a set of timelines for the population of patients, and determine conditional probabilities of findings occurring for each of the second findings in the set of timelines. Further, the system and method are configured to display the SFO description recommendations for each of the first findings in the patient's timeline based, at least in part, on the conditional probabilities for the first finding.

Abstract: A device, system, and method optimizes image acquisition workflows. The method performed at a workflow server includes receiving data associated with previous image acquisition procedures that have been performed, the image acquisition procedures having respective image orders, the image orders having respective contexts, each of the image acquisition procedures having used at least one sequence defining settings to capture an image. The method includes determining at least one metric associated with a use of a first one of the at least one sequence for a first one of the contexts. The method includes generating a rule indicative of whether the first sequence is to be included or excluded for a subsequent image acquisition procedure having the first context based on the at least one metric.

Abstract: An ultrasound imaging apparatus (10) for segmenting an anatomical object in a field of view (29) of an ultrasound acquisition unit (14) is disclosed. The ultrasound imaging apparatus comprises a data interface (32) configured to receive a two-dimensional ultrasound data (30) of the object in the field of view in an image plane from the ultrasound acquisition unit and to receive a three-dimensional segmentation model (46) as a three-dimensional representation of the object from a segmentation unit (36). An image processor (34) is configured to determine a two-dimensional segmentation model (50) on the basis of the three-dimensional segmentation model and a segmentation plane (48), wherein the segmentation plane and an image plane of the two-dimensional ultrasound data correspond to each other.

Abstract: The invention relates to an imaging apparatus (24) for imaging an introduction element (17) like a needle or a catheter for performing a brachytherapy or a biopsy. A tracking unit (3, 4) tracks the location of the introduction element within a living being (2), an imaging unit (6) like an ultrasound imaging unit generates an image showing an inner part of the living being, which includes the tracked location of the introduction element, based on the tracked location, and a display (7) displays the image. During the brachytherapy or biopsy the display can always show the introduction element, without requiring a manual control. For instance, it is not necessary that a physician manually controls the position and image plane of the imaging unit. This allows for an accurate and fast insertion of the introduction element into the living being such that a target region is reliably reached.

Abstract: A radiology viewer includes at least one electronic processor (10, 20), at least one display (12), and at least one user input device (14, 16, 18). The display shows at least a portion of a radiology image (30) in an image window (40), and at least a portion of a radiology report (32) in a report window (42). A selection is received of an anatomical feature shown in the image window, and a corresponding passage of the radiology report is identified and highlighted in the report window. A selection is received of a passage of the radiology report shown in the report window, and a corresponding anatomical feature of the at least one radiology image is identified and highlighted in the image window. The highlighting operations use image anatomical feature tags and report clinical concept tags generated using a medical ontology (56) and an anatomical atlas (62).

Abstract: The present disclosure pertains to computer-assisted search of image slices. In some embodiments, an image slice having a detected finding (and representing a cross section of at least a portion of an individual) may be determined. A search space may be reduce to a subset of image slices respectively representing a cross section corresponding to the cross section represented by the determined image slice. The search space reduction may comprise filtering a set of image slices based on the cross section represented by the determined image slice. Image slice information related to the determined image slice and related one or more image slices (of the image slices subset) may be obtained based on the search space reduction. A determination of whether indications of the detected finding exist in the image slices (of the image slices subset) may be effectuated based on the image slice information.

Abstract: A system (100) includes an end point prediction engine (150) that predicts an end point (302) using a machine learning model (132) and one or more clinical report objects (152) for a patient, wherein the machine learning model inputs the one or more clinical report objects and outputs the predicted end point according to phrases or n-grams in the one or more clinical report objects. An end point visualization interface (160) visualizes the predicted end point (302) using a scorecard (162) or a timeline (164). An end point modeling engine (130) generates the machine learning model from training data that includes validated end points (122) and clinical report objects (116).

Abstract: A system for tracking an instrument including an intraoperative transducer array configured to generate signals from array positions to generate real-time images of an area of interest. The instrument can be a penetrating instrument having a sensor mounted at a position of interest and being responsive to the signals from the array positions. A signal processing module can be provided and configured to determine a position and orientation of the instrument in accordance with the signals and to classify media of the position of interest based upon a response of the sensor to the signals from the array positions. An overlay module can be provided and configured to generate an overlay image registered to the real-time images to identify a position of the position of interest and provide feedback on the media in which the position of interest is positioned. A display can be provided and configured to provide visual feedback of the overlay image on the real-time images.

Abstract: A system (100) includes a parser engine (120), a context inferring engine (130), and an action selection engine (140). The parser engine (120) detects a recommendation in a received clinical report (112) for a patient. The context inferring engine (130) extracts and normalizes recommendation elements in the detected recommendation. The action selection engine (140) generates a patient actionable clinical report (142) based on the received clinical report and the extracted and normalized recommendation elements.

Abstract: An image interpretation workstation includes a display (12), user input devices (14, 16, 18), an electronic processor (20, 22), and a non-transitory storage medium storing instructions readable and executable by the electronic processor. An image interpretation environment (31) is implemented by instructions (30) which display medical images on the at least one display, manipulate the displayed medical images, generate finding objects, and construct of an image examination findings report (40). Finding object detection instructions (32) monitor the image interpretation environment to detect generation of a finding object or user selection of a finding object. Patient record retrieval instructions (34) identify and retrieve patient information relevant to a finding object (40) detected by the finding object detection instructions from at least one electronic patient record (24, 25, 26).

Abstract: A device, system, and method optimizes usage of prior studies. The method performed by an optimization server includes receiving a request for relevant prior studies for a patient from a practitioner device utilized by a medical professional, the request including a current study for the patient, the relevant prior studies being relevant to the current study. The method includes determining the relevant prior studies from prior studies of the patient based on a personalized model, the personalized model associated with the medical professional, the personalized model indicating a relevance score of the relevant prior studies to the current study. The method includes transmitting the relevant prior studies to the practitioner device.

Abstract: A radiology workstation (10) includes a computer (12) connected to access radiology studies stored in an radiology studies archive (20) with at least one processor (22) programmed to operate the computer to: provide a user interface (24) for performing readings of radiology studies including: displaying images on a display (14) of a current radiology study being read; receiving user inputs via one or more user input devices (16) and operating on the user inputs to manipulate the display of images and to open and view past radiology studies during the reading and to receive a radiology report summarizing the reading and store the radiology report in the radiology studies archive; and recording a activity log of user inputs received via the one or more user input devices during readings of radiology studies.

Abstract: A report-entry workstation (10) includes a computer with a display (14, 16), one or more user input devices (20, 22, 24), and at least one processor (1) programmed to operate the computer to perform operations.

Abstract: The invention relates to an assisting apparatus for assisting in performing brachytherapy. The position of an introduction element (17) like a catheter is tracked particularly by using electromagnetic tracking, while a group of seeds is introduced into a living object (2). This provides a rough knowledge about the position of the seeds within the object. An ultrasound image showing the group is generated depending on the tracked position of the introduction element and, thus, depending on the rough knowledge about the position of the seeds, in order to optimize the ultrasound visualization with respect to showing the introduced seeds. Based on this optimized ultrasound visualization the position of a seed of the group is determined, thereby allowing for an improved determination of seed positions and correspondingly for an improved brachytherapy performed based on the determined positions.

Abstract: A radiology workstation (10) includes a computer (12) connected to receive a stack of radiology images of a portion of a radiology examination subject. The computer includes at least one display component (14) and at least one user input component (16). The computer includes at least one processor (22) programmed to: display selected radiology images of the stack of radiology images on the at least one display component; receive entry of a current radiology report via the at least one user input component and displaying the entered radiology report on the at least one display component; identify a radiology finding by at least one of (i) automated analysis of the stack of radiology images and (ii) detecting textual description of the radiology finding in the radiology report; identify or extract at least one key image from the stack of radiology images depicting the radiology finding; and embed or link the at least one key image with the radiology report.