Abstract: A region of interest (ROI) segmentation system (10) includes a display device (20), a gaze-tracking device (28), a gaze point collector (32), a boundary identifier(36), and a region identifier (38). The display device (20) displays an image (14). The gaze-tracking device (28) generates gaze points relative to the displayed image (14). The gaze point collector (32) selects gaze points from the generated gaze points (30) corresponding to a region of interest (ROI) (25) of the displayed image (14). The boundary identifier (36) estimates a boundary (70) based on the selected gaze points (54, 60). The region identifier (38) segments the ROI (25) based on the estimated boundary (70).

Abstract: The present invention relates to a device, system and method for quality assessment of medical images. The device comprises an image input configured to obtain a medical image acquired according to an imaging guideline, a database access unit configured to access a database storing reference images for a plurality of imaging guidelines and for obtaining a reference image based on the imaging guideline used for acquisition of the obtained medical image, an analysis unit configured to analyze the obtained medical image in view of the obtained reference image and/or the used imaging guideline to generate quality information representing the quality of the obtained medical image, and a quality output configured to output the generated quality information.

Abstract: This invention relates generally to medical imaging and, in particular, to a method and system for reconstructing a model path through a branched tubular organ. Novel methodologies and systems segment and define accurate endoluminal surfaces in airway trees, including small peripheral bronchi. An automatic algorithm is described that searches the entire lung volume for airway branches and poses airway-tree segmentation as a global graph-theoretic optimization problem. A suite of interactive segmentation tools for cleaning and extending critical areas of the automatically segmented result is disclosed. A model path is reconstructed through the airway tree.

Abstract: A therapy system and method treats an internal target of a patient (16). A treatment plan (36) is received to treat the internal target. The treatment plan (36) includes a plurality of treatment fractions including correspondences (38) between the internal target and an external body surface based on a pre-procedural planning image (14) and pre-procedural tracking data (20). Before selected treatment fractions of the plurality of treatment fractions, a pre-fraction planning image (50) of the target is received, tracking data (20, 52) of the external body surface of the patient (16) is received, and the correspondences (38) between the internal target and the external body surface are updated based on the received pre-fraction planning image (50) and the received tracking data (20, 52). Therapy is delivered to the patient (16) in accordance with the treatment plan (36) and using the updated correspondences (38).

Abstract: A surgical tool set for treating a collapsed lung condition employs a trocar (20), and a nested cannula including a pleural port tube (30) and a fluid suction tube (50). In operation, the trocar (20) is nested within the pleural port tube (30), and utilized to puncture a port into a pleural cavity (10) of the patient while securing the pleural port tube (30) within the port. Subsequent to removing the trocar (20) from the pleural port tube (30), a fluid suction tube (50) is advanced with a fixed orientation through the secured pleural port tube (30) in a direction of a pleural cavity (10) target location (15) and air is suctioned from the pleural air space through one or more perforated holes into the fluid suction tube (50). The fluid suction tube (50) may have a target orientation section (42) or an additional target orientation tube (40) may be used to fix the orientation of the fluid suction tube (50) relative to the pleural port tube (30).

Abstract: A planning tool, system and method include a processor (114) and memory (116) coupled to the processor which stores a planning module (144). A user interface (120) is coupled to the processor and configured to permit a user to select a path through a pathway system (148). The planning module is configured to upload one or more slices of an image volume (111) corresponding to a user-controlled cursor point (108) guided using the user interface such that as the path is navigated the one or more slices are updated in accordance with a depth of the cursor point in the path.

Abstract: A method, system, and program product are provided for user-steered, on-the fly path planning in an image-guided endoscopic procedure, comprising: presenting, on a display, a 2D sectional image showing a region of interest from a preoperative CT scan; defining a control point on the 2D sectional image within a patient's body lumen responsive to a first user input; centering the control point; adjusting a viewing angle about the control point to show a longitudinal section of the body lumen responsive to a second user input; identifying a second point on a planned path within the body lumen responsive to a third user input; extending a planned path connecting the control point and the second point; redefining the second point as a new control point; and repeating the presenting adjusting, identifying, extending, and the redefining steps until the planned path reaches a procedure starting point within the patient's body.

Abstract: A surgical navigation system employs an endoscope (30) and an imaging unit (80). The endoscope (30) include an electromagnetic tracker (40) within a working channel of endoscope (30) for generating electromagnetic sensing signals indicative of one or more poses of the endoscope (30) within an anatomical region, and an endoscopic camera (50) within an imaging channel of the endoscope (30) for generating endoscopic images of the anatomical region. The imaging unit (80) executes an intraoperative calibration of the electromagnetic tracker (40) and the endoscopic camera (50) as a function of an image registration between the preoperative scan image of a calibration site within the anatomical region and one or more endoscopic images of the calibration site within the anatomical region.

Abstract: This invention relates generally to medical imaging and, in particular, to a method and system for reconstructing a model path through a branched tubular organ. Novel methodologies and systems segment and define accurate endoluminal surfaces in airway trees, including small peripheral bronchi. An automatic algorithm is described that searches the entire lung volume for airway branches and poses airway-tree segmentation as a global graph-theoretic optimization problem. A suite of interactive segmentation tools for cleaning and extending critical areas of the automatically segmented result is disclosed. A model path is reconstructed through the airway tree.