Label Type Label Definition 2D Image 3D Volume Video CLASSIFICATION (non objectType) Classification SEGMENTATION CommonLabelProps LENGTH MeasureLength ANGLE MeasureAngle POINT Landmark Landmark3D POLYLINE Polyline POLYGON Polygon ELLIPSE Ellipse BBOX BoundingBox CUBOID Cuboid class redbrick.types.task.Point2D[source] 2D pixel point. The Point2D coordinates are normalized in relation to the dimensions of the image, meaning they are scaled down to a range between 0 and 1. To convert these normalized points back to their original scale on the image, you “un-normalize” them by multiplying by the image’s dimensions. This operation typically results in a floating-point number. RedBrick AI enhances the precision of annotations on its canvas by supporting a resolution higher than that of the underlying image. This capability facilitates sub-pixel annotation accuracy. However, if sub-pixel precision is not necessary for your application, you can simplify the process by rounding the un-normalized coordinates to the nearest whole number. This adjustment converts the precise floating-point values back to standard pixel coordinates, making them easier to work with for general purposes. Important The origin point (0,0) from which these coordinates are measured is at the top left of the image. However, for mammography and DBT the origin is the top right of the image. xNorm: float X co-ordinate normalized by the width of the image. yNorm: float Y co-ordinate normalized by the height of the image. class redbrick.types.task.VoxelPoint[source] Represents a three-dimensional point in image-space, where i, j, and k are columns, rows, and k is the slice number. i: int j: int k: int class redbrick.types.task.WorldPoint[source] Represents a three-dimensional point in physical space/world co-ordinates. The world co-ordinates are calculated using redbrick.types.task.VoxelPoint and the DICOM Image Plane Module. x: float y: float z: float class redbrick.types.task.MeasurementStats[source] Measurement statistics for annotations. average: float Average pixel/voxel intensity within the annotation. In CT, this is the average HU value. area: float Area contained within the annotation in mm^2. volume: float Volume contained within the annotation in mm^3 minimum: float Minimum intensity value within the annotation. maximum: float Maximum intensity value within the annotation. class redbrick.types.task.VideoMetaData[source] Contains annotation information along the third axis. Frames for video, and slices for 3D volumes. Warning redbrick.types.task.VideoMetaData has a misleading name. It contains information for both videos, and 3D volumes. Hint Watch this video for a detailed explaination of all the attributes of this object. seriesItemIndex: int The index of the file in series “items” list that this annotation is present on. seriesFrameIndex: int Frame index of the annotation for nifti and dicom multipart files. frameIndex: int The frame number (for video) or slice index (for 3D volumes) the annotation is present on. trackId: str Each distinct object has a unique trackId. Two annotations on different frameIndex’s with the same trackId’s represent the same distinct object. keyFrame: bool If True, this annotation is user-defined. If False, this annotation is interpolated. endTrack: bool If True, this annotation is the last annotation of a specific track defined by trackId. redbrick.types.task.Attributes Attributes for Taxonomy objects. Attributes can be boolean, textfields, select’s or multi-select’s. alias of Dict[str, Union[str, bool, List[str]]] class redbrick.types.task.CommonLabelProps[source] Full version of redbrick.types.task.Series.segmentMap. category: Union[int, str, List[str]] Taxonomy object category. attributes: Dict[str, Union[str, bool, List[str]]] Associated taxonomy object attributes. mask: Union[str, List[str]] Filepath to segmentation file for this annotation. overlappingGroups: List[int] Overlapping instances that this label is part of (when without_masks is set). group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.InstanceClassification[source] Instance level classifications for frame-by-frame (video) or slice-by-slice (volume) classifications.. fileIndex: int For video this is the frameIndex, for DICOM volumes this is the sliceIndex. fileName: str The file name represented by frameIndex. group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.Classification[source] Study or series classification. attributes: Dict[str, Union[str, bool, List[str]]] group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.Polyline[source] Open polylines, not supported in 3D images. points: List[Point2D] category: Union[int, str, List[str]] attributes: Dict[str, Union[str, bool, List[str]]] video: VideoMetaData group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.Polygon[source] Closed polygons, not supported in 3D images. points: List[Point2D] category: Union[int, str, List[str]] attributes: Dict[str, Union[str, bool, List[str]]] stats: MeasurementStats video: VideoMetaData group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.Cuboid[source] 3D bounding boxes for 3D images. point1: VoxelPoint Top left diagonal corner. point2: VoxelPoint Bottom right diagonal corner. absolutePoint1: WorldPoint absolutePoint2: WorldPoint category: Union[int, str, List[str]] attributes: Dict[str, Union[str, bool, List[str]]] stats: MeasurementStats group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.BoundingBox[source] 2D bounding box for 2D images, or slice by slice annotation in 3D images. Hint See the following diagram to understand the coordinate system. pointTopLeft: Point2D Coordinates of the top left of the bounding box. wNorm: float Width of the bounding box, normalized by image width. hNorm: float Height of the bounding box, normalized by the image height. category: Union[int, str, List[str]] attributes: Dict[str, Union[str, bool, List[str]]] stats: MeasurementStats video: VideoMetaData group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.Ellipse[source] Ellipse annotation. Hint See this ellipse diagram to understand the coordinate system. Please read the redbrick.types.task.Point2D documentation to understand how normalization works & the origin of the coordinate system. Warning For DICOM images of a certain type, ellipse annotations might be flipped i.e., rotating the ellipse clockwise would result in counter-clockwise rotation. If you encounter these cases, reach out to our support for instructions on how to handle this support@redbrickai.com. pointCenter: Point2D The normalized center of the ellipse. xRadiusNorm: float The x axis of the ellipse, normalized with by the image width. Adjusting for rotationRad, the x-axis of the ellipse aligns with the x-axis of the image. yRadiusNorm: float The y axis of the ellipse, normalized with by the image width. Adjusting for rotationRad, the y-axis of the ellipse aligns with the y-axis of the image. rotationRad: float The rotation of the ellipse measured clockwise as the angle between the y-axis of the ellipse and y-axis of the image. category: Union[int, str, List[str]] attributes: Dict[str, Union[str, bool, List[str]]] stats: MeasurementStats video: VideoMetaData group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.MeasureAngle[source] Angle measurement label. An angle measurement is defined by three points, where vertex is the middle point between point1 and point2. The angle between the two vectors <point1, vertex> and <point2, vertex> defines the angle measurement. Hint See this angle diagram to understand the coordinate system. type: Literal['angle'] point1: VoxelPoint vertex: VoxelPoint point2: VoxelPoint absolutePoint1: WorldPoint absoluteVertex: WorldPoint absolutePoint2: WorldPoint normal: List[float] Measurements can be made on oblique planes. normal defines the normal unit vector to the slice on which the annotation was made. For annotations made on non-oblique planes, the normal will be [0,0,1]. The measurement is fully defined even without normal, however, for completeness see this angle diagram for it’s definition. angle: float Measurement angle in degrees. category: Union[int, str, List[str]] attributes: Dict[str, Union[str, bool, List[str]]] group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.MeasureLength[source] Length measurement label. A length measurement is defined by two points, and the length measurement is the distance between the two points. type: Literal['length'] point1: VoxelPoint point2: VoxelPoint absolutePoint1: WorldPoint absolutePoint2: WorldPoint normal: List[float] Measurements can be made on oblique planes. normal defines the normal unit vector to the slice on which the annotation was made. For annotations made on non-oblique planes, the normal will be [0,0,1]. The measurement is fully defined even without normal, however, for completeness see this length diagram for it’s definition. length: float The value of the measurement in millimeters. category: Union[int, str, List[str]] attributes: Dict[str, Union[str, bool, List[str]]] group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.Landmark3D[source] 3D landmark for 3D data. point: VoxelPoint category: Union[int, str, List[str]] attributes: Dict[str, Union[str, bool, List[str]]] group: str Linked label group id. readOnly: bool Read only status class redbrick.types.task.Landmark[source] 2D landmark for 2D data. point: Point2D category: Union[int, str, List[str]] attributes: Dict[str, Union[str, bool, List[str]]] video: VideoMetaData group: str Linked label group id. readOnly: bool Read only status NextTaxonomy formatPreviousFormats Copyright © 2023, RedBrick AI Made with Sphinx and @pradyunsg’s Furo On this page Read the Docs