Segmenting Images Using Contours And Masks
9Segmenting Images Using Contoursand MasksIn this chapter“Using contours to segment a VOI” on page 308“Generating masks” on page 331“Converting VOI contours to masks” on page 350“Converting masks to VOI contours and paints” on page 351“Advanced Paint and Power Paint tools” on page 352Segmentation is the process of identifying selected regions of images asmembers of a common group. Physicians routinely segment structures inmedical images to facilitate the treatment of patients. The quantification ofimportant attributes, such as the volume of various tissue types, enablesresearchers to better understand, diagnose, monitor, and treat neurobehavioral disorders.MIPAV provides several segmentation tools that allow you to delineate avolume of interest (VOI). You can indicate a VOI by drawing a contour or bycreating a mask. You can also calculate predefined statistics on the indicated VOI.For more information, refer to the MIPAV web site: orithms/MIPAV Segmentation.html}.MIPAV User’s Guide, Volume 1, Basics30712/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o nNote: Once a VOI is segmented, you can also apply an algorithm to the volumebound by the contours. MIPAV provides a number of algorithms, such asGaussian blur, Laplacian, threshold, and watershed. These algorithms and othersare addressed in detail in volume 2 of the User’s Guide.Understanding contours and masksBefore you indicate a volume of interest, it is helpful to determine whetherto delineate the VOI by drawing a contour around a structure or to generatea mask.A contour is an array of points. If the contour is a closed polygon, the areainside defines the VOI. Contours are scalar and can be grouped to form asingle multicontoured VOI. Contours are particularly useful if you want tosave a VOI that covers a large area because the resulting file is generallysmaller than a comparable mask file.A mask is a filter that selectively includes or excludes certain values. Youcan create a mask that includes the VOI areas and excludes all other areas.Masks are particularly helpful if you use other image analysis programs thatrequire you to supply a mask. Masks can also be used to indicate a complexarea of interest. MIPAV allows you to generate binary and short image typemasks. Also, you can manually create masks using paint tools.Using contours to segment a VOIA VOI can consist of a single contour or several contoured structures thatare assigned to a group. You can automatically, manually, or interactivelydraw contours on any image that is shown in the default view. You canmodify the shape and size of a contour and trim anchor points.Once contours are drawn and modified, you can copy them to other slices inthe dataset or save them to a separate file for future use. The three overalltasks involved in using contours to segment a VOI are: Drawing contours (“Drawing contours” on page 309)MIPAV User’s Guide, Volume 1, Basics30812/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o n Modifying contours (“Modifying contours” on page 318) Grouping and ordering contours (“Grouping and ordering contours”on page 323)Drawing contoursYou can draw contours using three different methods: manual, interactive,or automatic. With the manual method, you use the mouse to draw a contour. This method provides the greatest amount of freedom: you can chooseone of MIPAV’s predefined shapes or create a freehand shape. However, themanual method can be time consuming, particularly if the structure to becontoured is intricate. With the interactive method, you must also manuallycontour the structure. However, in this case the manually drawn contourneed not be precise because you then apply an algorithm that generates anew contour based on both the manually drawn contour and the structure.With the automatic method, MIPAV generates contours as you move themouse over different structures. The automatic method is generally accurate and quick; however, it does not provide the freedom of the manualmethod.Recommendation. If you are unsure about which contour method to use, itis recommended that you try the automatic method first.C ONTOURING STRUCTURES AUTOMATICALLYIn this method, you move the mouse pointer over a structure. MIPAV firstanalyzes the intensity values and then contours what it perceives to thecontour boundary.Complete the following steps:1 Select VOI New VOI Levelset in the MIPAV window.2 Move the mouse pointer to the image.The pointer changes to the cross-hair shape. As you move the pointer,MIPAV determines the level of intensity of the pixel under the crosshair pointer and uses the results from the Levelset algorithm todetermine the probable boundary of the structure. Having determinedMIPAV User’s Guide, Volume 1, Basics30912/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o nthe probable boundary, MIPAV generates a contour (Figure 170).Continue to move the pointer until the structure you wish to outline iscontoured.3 Click the contour to apply it to the structure. See Figure 170.Figure 170. Automaticallygenerated contour.You can now do the following: Draw an additional contour Modify the contour Reassign an existing contour toa different group Order the contours Delete the contourC ONTOURING STRUCTURES MANUALLYYou can contour structures in images by selecting one of MIPAV’spredefined shapes, such as a point, straight line, 2D or 3D rectangle, 2Dellipse, interslice VOI, etc. Alternatively, you can use the polygon andpolyline tools to draw freehand shapes. For more information about VOIsavailable in MIPAV, refer to Figure 171.– Point VOI– Interslice PolylineFigure 171. VOIs available in MIPAVMIPAV User’s Guide, Volume 1, Basics31012/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o n– Line VOI– Protractor tool– Rectangular VOI– Ellipse VOI– Polygon/Polyline VOI– Levelset VOIFigure 171. VOIs available in MIPAV (continued)MIPAV User’s Guide, Volume 1, Basics31112/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o n– Live wire VOI– 3D rectangular VOIFigure 171. VOIs available in MIPAV (continued)This section explains how to draw the following: Point VOIsVOIs with a straight line2D rectangular VOIs3D rectangular VOIsEllipsoidal VOIsPolyline (segmented line) and closed polygon VOIsTip: Before you begin, decide whether you want to draw more than one of thesame contour in succession. If you do, hold down the Shift key as you select thecontour button and draw the contours.To draw point VOIs– Draw Point VOI1 Click the Draw Point VOI button, in the MIPAV window.2 Move the pointer to the image.3 Click the area where you want the point to appear. A numbered pointappears on the image.Note: For some algorithms, the sequence in which you draw the points isimportant (refer to Volume 2 of the User’s Guide).MIPAV User’s Guide, Volume 1, Basics31212/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o nTo create VOIs with a straight line– Draw Line VOI1 Click the Draw line VOI icon.2 Click the area on the image where you want the line to begin.3 Drag the pointer to the place where you want the line to end. As youdrag the pointer, the line lengthens.4 Release the mouse button. The line VOI appears on the image in red.To create 2D rectangular VOIs– Draw Rectangular VOI1 Click the Draw Rectangle VOI icon.2 Click the area on the image where you want a corner of the rectangle toappear.3 Drag the pointer. As you drag the pointer, the rectangle changes in size.4 Release the mouse button when the rectangle is the desired size.Note: When you create a 2D rectangular VOI, the rectangles appear on only oneslice in the dataset.To create 3D rectangular VOIs– Draw 3D Rectangular VOI1 Click the 3D rectangular VOI icon.2 Click the area on the image where you want a corner of the rectangle toappear.3 Drag the pointer. As you drag the pointer, the rectangle changes in size.4 Release the mouse button when the rectangle is the desired size.Note: Unlike 2D rectangular VOIs, 3D rectangular VOIs appear on all slices inthe dataset.MIPAV User’s Guide, Volume 1, Basics31312/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o nTo create ellipsoidal VOIs– Draw Ellipsoid VOI1 Click the Draw Ellipse VOI icon.2 Click the area of the image where you want an edge of the ellipse toappear.3 Drag the pointer. As you drag the pointer, the ellipse changes in size.4 Release the mouse button when the ellipse is the desired size(Figure 171).To create polyline (segmented line) VOIs or closedpolygon VOIs– Draw Polygon/Polyline VOI1 Click the Draw Polygon/Polyline VOI icon.2 Click the area of the image where the polyline VOI should begin.3 Decide whether to draw either a straight or freehand line segment. Doone of the following: To draw a straight line segment Make sure that you have released the mouse button. Move thepointer to the place where you want the segment to end. A straightline, which extends from the starting place to your pointer tip,appears. Click the mouse button to anchor the line segment. To draw a freehand line segment Drag the mouse button and move the pointer to the place on theimage where you want the segment to end. A line, which matchesyour mouse movements, extends from the starting place to yourpointer tip. Click the mouse button to anchor the line segment.4 Repeat drawing straight line segments or freehand lines until you finishdrawing all of the segments needed to contour the structure.5 Decide whether to create a polyline VOI or a closed polygon VOI: Polyline VOI: Go to the next step.MIPAV User’s Guide, Volume 1, Basics31412/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o n Closed polygon VOI: Click the first anchor point to connect the lastline segment to the first, thus forming a closed polygon. Then go to thenext step.6 Click the Default icon, to return the pointer to the default mode.7 Double-click the mouse button to complete the polyline VOI.Tip: Depending on which is more comfortable, you can switch betweendrawing straight line segments or drawing freehand lines at any time.Tip: To draw multiple VOI, hold Shift while pressing the corresponding VOIicon.C ONTOURING STRUCTURES INTERACTIVELYIn the interactive method, you first manually draw a contour that provides ageneral indication of the location and shape of the structure. You then selectan algorithm that analyzes the manually drawn contour and generates anew one that more closely outlines the structure.To use the interactive method to contour structures,complete the following steps:1 Draw a contour using one of the manual methods detailed in“Contouring structures manually” on page 310. The contour need not beprecise, but it should indicate the general location and shape of thestructure you want to delineate.2 Select the contour. White anchor points appear on the contour outline.3 Select one of the following in the MIPAV window: VOI Evolve Boundary 2D Active Contour. This algorithmdetermines the structure's boundary more quickly than the 2DSpline Active Contour algorithm. It is also more sensitive to noisepresent in the image. MIPAV applies a gradient magnitude filter todetermine the structure's boundary. When complete, the MIPAVgenerated contour appears around the structure. VOI Evolve Boundary 2D Active GVF. The Evolve BoundaryMIPAV User’s Guide, Volume 1, Basics31512/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o ndialog box uses a special type of active contours, or snakes to findthe object boundaries. GVF or the gradient vector flow snake, whichis used to calculate VOI boundaries, begins with the calculation of aGVF field of forces by applying generalized diffusion equations toboth components of the gradient of an image edge map. Here, GVFfields, are dense vector fields derived from images by minimizing acertain energy functional in a variational framework. The minimization is achieved by solving a pair of decoupled linear partial differential equations that diffuses the gradient vectors of a gray-level orbinary edge map computed from the image. See also Figure 172. VOI Evolve Boundary 2D Spline active contour. This algorithmdetermines the structure's boundary less quickly than the ActiveContour algorithm, however it is less sensitive to noise. Thisalgorithm fits a spline to the data. When complete, the MIPAVgenerated contour appears around the structure. VOI Evolve Boundary 2D Spline GVF. This is the combinationof the GVF force with the B-spline snake. B-spline snakes haveseveral characteristics which make them well suitable for describingVOI boundary as well as snake evolution: the B-spline implicitlyincorporates contour smoothness and avoids the ad hoc tension andrigidity parameters of the traditional GVF snake and also fewersample points are required to implement contour evolution for theB-spline.ABFigure 172. An initial VOI (A) and VOI after applying the EvolveBoundary Active Contour algorithm with the default parameters (B)MIPAV User’s Guide, Volume 1, Basics31612/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o nE VOLVE B OUNDARY DIALOG BOX OPTIONSScale of theGaussianA large Gaussian scale slowsthe snake and causes it toconform to large scalestructure. A small Gaussianscale causes the snake toconform to the small scalestructure, which is thereforemore sensitive to noise.Evolve BoundarySingle Slice – applies thealgorithm only on a currentimage slice.Propagate to adjacent slices –propagates boundaries toadjacent slices.Note that the algorithm usedfor 3D images version is a 2.5Ddimensional algorithm wherethe resultant contour in a sliceis projected into the adjacentslice and is used as an initialization to the evolution in the newslice.Replace original contour – ifchecked, replaces the originalVOI.MaximumIterationsGVF field iterations – enter a desired number of GVF iterations here.Evolve iterations – enter a max number of iterations needed to generate anew VOI boundary.Display GVF image; if this box is checked, the GVF image appears in a newimage frame.ParametersGVFk is a positive constant controlling the smoothness of the resulting VOI.Smoothness corresponds to the balance between internal and externalforces. The internal force constrains the snake to be smooth while theexternal guides the snake to seek desirable image properties, such asedges.Slice by slice processing – if checked, this activates evolving boundary sliceby slice.Figure 173. The Evolve Boundary dialog boxMIPAV User’s Guide, Volume 1, Basics31712/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o nCell TrackingCell Tracking – if checked, this box activates the cell tracking algorithm;Expected Cell Radius (in pixels) – a user-defined cell radiusSize Constraint and Shape Constraint factors are contributed towards theshape and size of the snake in order to make it circular with a user-definedcell radius.Implicit Resampling Constraint factor minimizes the number of points alongthe snake curve, thus they maintain an equal distance.Cell Dilation – if checked, allows dilationCell dilation factor is multiple of the cell radiusInitial Cell Velocity in pixels (X,Y)OKApplies the parameters that you specified.CloseDisregards any changes that you made in this dialog box and closes thedialog box.HelpDisplays online help for this dialog box.Figure 173. The Evolve Boundary dialog box (continued)Modifying contoursOnce contours are drawn, you can reposition, resize, or reshape them. Youcan also trim anchor points.R EPOSITIONING CONTOURSYou can reposition a single contour or a group of contours. Follow theinstructions below.To reposition a single contourSelect the contour and drag it to the new location.To reposition a group of contours1 Hold down the Shift key as you click one of the contours in the group.All of the other contours in the group are also selected.2 Continue to hold down the Shift key as you drag the contour group tothe new location.MIPAV User’s Guide, Volume 1, Basics31812/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o nR ESIZING CONTOURSYou cannot collectively resize a group that consists of multiple contours;each contour must be resized individually. Except for point VOIs, you canresize any contour shape. For lines, only the length can be changed; thewidth cannot. To resize lines, go to ‘‘To resize contours’’.Before you can resize them, all contour shapes except lines must besurrounded by a bounding box. See also the following section ‘‘To turn thebounding box on’’.To turn the bounding box on1 Do either of the following: Select the contour and then select VOI Properties in the MIPAVwindow. Right-click the contour. A menu appears. Select Properties.The VOI Statistics dialog box opens. See also Figure 196 on page 361.2 Select Show contour bounding box.3 Change, if you want, any of the other information in the dialog box.4 Click Apply.5 Click Cancel to close the dialog box.To turn the bounding box off1 Do one of the following: Right-click the contour. Select Properties from the pop-up menu. Left-click the contour. Select Properties from the VOI menu in theMIPAV window.The VOI Statistics dialog box appears. See also Figure 174.2 Clear Show Contour Bounding Box.3 Click Apply.4 Click Cancel to close the window.MIPAV User’s Guide, Volume 1, Basics31912/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o nTo resize contours1 Select the contour. The bounding box appears (Figure 174) around theshape. (For rectangle contours, the bounding box and rectangle legsmay overlap.)2 Click Cancel to close the window.Figure 174.A VOI bounding box and the VOI Properties dialog box3 Do one of the following: To resize lines: Click an edge or corner of the shape. Drag until theshape is the desired size. To size other shapes: Click one of the bounding box handles. Dragthe handle until the shape is the desired size.4 Choose whether to continue showing the bounding box.Note: If you want to reposition or add an anchor point, turn the bounding boxoption off.MIPAV User’s Guide, Volume 1, Basics32012/2/08
MIPAV User’s Guide, Volume 1, BasicsM I P A VM e d i c a l I m a g e P r o c e s s i n g, A n a l y s i s, & V i s u a l i z a t i o nR ESHAPING A CONTOURYou reshape the contour by adding or repositioning anchor points.Instructions for adding and repositioning anchor points follow.To add anchor points1 Click the contour to select it. The anchor points become visible.2 Click the place where you want to add the new anchor point. The newanchor point appears.To reposition anchor pointsYou can reposition a single anchor point at a time. If you need to redraw aportion of the contour, MIPAV allows you to reposition several contiguousanchor points with one motion of the mouse.1 Select the contour. The anchor points become visible.2 Position the pointer over the anchor point or points that you want toreposition. The pointer changes to the shape of a ha
Tip: Before you begin, decide whether you want to draw more than one of the same contour in succession. If you do, hold down the Shift key as you select the contour button and draw the contours. To draw point VOIs – Draw Point VOI 1 Click the Draw Point VOI butt
Following the Lines: Where the land slopes steeply, contours are close together, and in flat areas the contours are far apart. If 2 contours touch cliff Contours lines can never cross Where contours cross ravines and stream valleys
Observation Checklist: Phonological Awareness Content Observed ( ) Discriminating words or sounds Rhyming Blending syllables Blending phonemes Isolating initial sounds Isolating medial sounds Isolating final sounds Segmenting words in sentences Segmenting syllables in words Segmenting phonemes in words
The easyCBM Phoneme Segmenting assessment was designed to exclusively measure phoneme segmenting across 20 forms within a grade. A preliminary examination of the CCSS indicated that only some components
However, traditional edge-based active contour models have been applicable to only relatively simple images whose sub-regions are uniform without internal edges. Here in this paper we attempt to brief the taxonomy and current state of the art in Image segmentation and usage of Active Contours. Keywords : Active Contours, Snakes, Level Sets.
generate DTMs using data extracted from contours. The existence of large volumes of hardcopy topographic maps provides a source of primary input in the form of contours which can be digitised and used for DTM generation purposes. In other words, the generation of DTMs from contours is emphasised because this is the major source of DTMs
Active Contours: A Brief Review Serdar Kemal Balcı and Burak Acar A . EE 570 Image Processing – Term Project 2 model [6] by introducing an additional edge strength term. Aubert et al. [10] showed that geometric active contours unify the curve evolution framework with classical energy
related weather information in the Enroute area Vertically Integrated Liquid (VIL) Mosaic (1km resolution) VIL Forecast Contours (Std. Mode) VIL 2-hr. Forecast VIL Forecast Contours (Winter Mode) Echo Tops Mosaic (1 km resolution) Echo Tops Forecast Contours Echo Tops 2-hr. Forecast
English Language Arts: Grade 3 READING Guiding Principle: Students read a wide range of fiction, nonfiction, classic, and contemporary works, to build an understanding of texts, of themselves, and of the cultures of the United States and the world; to acquire new information; to respond to the needs and demands of society and the workplace .
