Technology Overview
Clinical Need
Clinical Solution
Segmentation Algorithm Overview
Models
Training
Summary

Morphormics' technology provides automatic segmentation of clinically important organs from CT images and other imaging modalities. MxStructure™ is a software library for autosegmentation, registration, and dose accumulation which can be incorporated into commercial partners' treatment planning systems and is in clinical use today. MxAnatomy™ is a stand-alone application built on MxStructure that can run on any Windows-based workstation or laptop.

The following paragraphs describe what Morphormics' technology can do, how it works, and why this is an advance over other segmentation approaches.

CLINICAL NEED
Three-dimensional conformal radiotherapy and intensity-modulated radiation therapy are preferred methods for treatment of prostate cancer. These treatment modalities require an accurate understanding of the three-dimensional anatomic configuration of the prostate and adjacent structures, including the bladder, rectum, seminal vesicles, urethra, and femoral heads. Accurate knowledge of the anatomic configuration, extracted from CT and other images, are critical inputs to three-dimensional treatment planning, improving the tumor-to-normal tissue dosage ratio.

The process of extracting the anatomic configuration from images is called segmentation. Conventionally, segmentation is performed by a physician or other highly skilled professional by examining many (frequently 40 or more) individual image slices and manually drawing two-dimensional contours of each relevant organ in each slice. These 2-D contours are then stitched together to produce three-dimensional representations of the relevant organs, which are used as input to treatment planning.

Such contour-based manual segmentation consumes the expensive time of skilled and experienced clinical experts and yet produces results that vary considerably across the experts. Morphormics' automatic segmentation solution yields more consistent, accurate segmentations in a fraction of the time.

CLINICAL SOLUTION
Using shape models, image intensity data, and proprietary algorithms, MxAnatomy provides segmentation results without user input. For MxAnatomy/Male Pelvis™, segmentation results are provided for the prostate, bladder, rectum, seminal vesicles, urethra, and the femoral heads/necks.

Figure 1. Axial and sagittal views of the volume identified by MxAnatomy as the prostate.

In Figure 2.
The clinician examines the resulting segmentation and decides whether to accept or to edit the segmentation produced. In standard clinical practice the radiation oncologist must approve the final results before they are used for planning. When editing is required, the clinician can use the model-based editing in 3D to make changes on multiple slices consistently and quickly, and can also use traditional 2D or 3D tools.

Figure 2. Rendering of three-dimensional organ shapes and spatial positioning.

SEGMENTATION ALGORITHM OVERVIEW
To introduce the algorithm's model-based approach, consider the knowledge that an expert human brings to bear when doing a manual segmentation. The human expert understands the organs of interest, the range of shapes each may assume under various conditions (e.g., bladder empty or full, distension of the rectum), the range of spatial relationships among the organs, the typical image intensities associated with the organs and other material (surrounding tissue, fat, urine, fecal matter, and gas) and various visible landmarks in the images. Morphormics' algorithms model this information, without which automatic methods are unlikely to be adequate compared to an expert.

MODELS
The algorithm is classified as model-based because it uses models that capture the kinds of information used by human experts. In particular, we use two kinds of models:

The shape model is defined using m-reps ("m" for "medial"), a shape representation of an object as a set of medial atoms, each of which consists of two spokes emanating from a hub in the "middle" of the object (hence, the name "medial"), as illustrated in Figure 3. M-reps have many interesting and useful mathematical properties. They are particularly suitable as a shape model for segmentation because they can capture both local variations in shape as well as more global deformations. The numbers that characterize a set of hub locations and spoke lengths and orientations completely define a shape and thus can be used as a parameterization of a particular shape. The key point is that using m-reps, any credible organ shape can be defined within the shape space by a small set of parameters, which improves processing efficiency, and solutions are largely limited to only credible variants of the organ.

Figure 3: A medial atom (left) and the implied boundary of the object, a bladder (right), defined by the m-rep.

The image intensity model constructs a set of local object-interior and object-exterior regions for each organ. For example, in Figure 4, a variety of regions are defined relative to the boundary of a prostate. For each of these regions, the image intensity model uses a representation of the region's intensity histogram to provide the algorithm with information about the variation in intensity that is expected in the region.

Figure 4: Image regions defined relative to the boundary of a prostate shape model.

Once the shape model is appropriately positioned, the regions defined by the image intensity model can be matched to the target image and the corresponding intensity data gathered. An objective function is defined based on the shape and image intensity models that measures the probability that both the shape model corresponds with what is known about the distribution of shapes in the shape space and that the intensity patterns in the image are consistent with the anatomy and how it varies. To improve the match and converge to a final segmentation, a multi-dimensional optimization algorithm is run to adjust the model parameters to maximize the objective function, i.e., to find the most probable variant of the anatomy, given the image.

TRAINING
As described above, an important role of the shape and image intensity models is to capture information that a human expert would apply when doing manual segmentation. This requires a training process to obtain information about the variations that are expected across patients, imaging devices, and within patients over time. In training, several experts manually segment the same relevant organs in the same sets of raw image sets, providing a robust sample size of patients' organs. This information is then processed to extract the probability information that characterizes the shape space for each organ and the corresponding image intensity distributions.

SUMMARY
MxAnatomy provides high-quality, automatic segmentation of organs in CT and other imaging modalities. Applications include radiation treatment planning and other clinical and research uses. MxStructure/Male Pelvis was initially released in 2010. MxStructure/Male Pelvis v1.5 was released in 2011 and is used by clinicians in the US and over 10 other countries. MxStructure/Male Pelvis v2.0 is planned for release in the first quarter of 2012. MxAnatomy for adaptive planning has been in use in research clinics since early 2010.