JP-2022530039-A5 -

Dates

Publication Date

20230501

Application Date

20200423

Description

While the present invention has been illustrated and described in detail with respect to certain preferred embodiments, those skilled in the art will understand that various forms and details can be modified without departing from the spirit and scope of the invention as defined by the appended claims. The present invention provides, for example, the following items: (Item 1) A method for lesion marking and quantitative analysis of nuclear medicine images in human subjects, (a) A step of accessing a set of bone scan images of a human subject using the processor of a computing device, wherein the set of bone scan images is obtained after administration of a drug to the human subject; (b) The processor automatically segments each image in the bone scan image set to identify one or more skeletal regions of interest, each corresponding to a specific anatomical region of the human skeleton, thereby obtaining a set of annotated images, wherein the one or more skeletal regions of interest are (i) A femoral region corresponding to a portion of the femur of the human subject, wherein the portion of the femur is a femoral region encompassing at least three-quarters of the femur along the length of the femur, and (ii) A humeral region corresponding to a portion of the humerus of the human subject, wherein the portion of the humerus is a humeral region that encompasses at least three-quarters of the humerus along its length, A step including at least one of the following, (c) The step of automatically detecting an initial set of one or more hotspots by the processor, each hotspot corresponding to a high-intensity area in the set of annotated images, the automatic detection comprising identifying the one or more hotspots using the intensity of pixels in the set of annotated images and using one or more region-dependent thresholds, the one or more region-dependent thresholds comprising one or more values associated with the femoral region and/or the humeral region to provide enhanced hotspot detection sensitivity in the femoral region and/or the humeral region to compensate for reduced drug uptake in the region, (d) For each hotspot in the initial set of hotspots, the processor extracts a set of hotspot features associated with the hotspot; (e) For each hotspot in the initial set of hotspots, the processor calculates a transition probability value corresponding to the likelihood that the hotspot will represent a transition, based on the set of hotspot features associated with the hotspot; (f) A method comprising the step of causing the processor to render a graphic representation of at least a portion of the initial set of hotspots for display in a graphical user interface (GUI). (Item 2) Step (b) is, A step of comparing each member of the bone scan image set with a corresponding atlas image from the atlas image set, wherein each atlas image includes one or more identifications of the one or more skeletal regions of interest, and the skeletal regions of interest include the femoral region and/or the humeral region. The method according to item 1, comprising the step of aligning the corresponding atlas image with the image in the bone scan image set, such that the identification of one or more skeletal regions of interest in the atlas image is applied to the image in the bone scan image set. (Item 3) The method of item 2, wherein each atlas image includes the identification of (i) the femoral region including at least a portion of the knee region of the human subject, and/or (ii) the humeral region including at least a portion of the elbow region of the human subject, and for each image in the set of bone scan images, the alignment of the corresponding atlas image to the bone scan image includes using the identified knee region and/or the identified elbow region as landmarks in the image. (Item 4) The method according to any one of the above items, wherein the location of at least one detected hotspot from the initial set of hotspots corresponds to a physical location in or on the femur that is located more than three-quarters of the distance along the femur from the end of the femur facing the buttocks of the human subject to the end of the femur facing the knee of the human subject. (Item 5) The method according to any one of the above items, wherein the location of at least one detected hotspot from the initial set of hotspots corresponds to a physical location in or on the humerus, which is located more than three-quarters of the distance along the humerus from the shoulder end of the humerus facing the elbow end of the human subject. (Item 6) Step (c) is The processor performs the steps of identifying healthy tissue regions within the bone scan image set in which it is determined that no hotspots are present, The processor performs the steps of calculating a normalization coefficient such that the product of the normalization coefficient and the average intensity of the identified healthy tissue area is a predetermin