Abstract: In some embodiments, a motion detection and correction system and/or device for tracking and compensating for patient motion during a medical imaging scan can be adapted to be integrated into a medical imaging scanner, such as an MRI scanner, or be adapted to retrofit a pre-existing medical imaging scanner. In certain embodiments, the motion detection system and/or device can comprise one or more mounting brackets and a motion correction device housing, which can further comprise one or more detector modules and a power unit. In further embodiments, the collected motion data can be further analyzed by an image processing unit of the motion tracking and/or correction system.

Abstract: In some embodiments, a motion detection and correction system and/or device for tracking and compensating for patient motion during a medical imaging scan can be adapted to be integrated into a medical imaging scanner, such as an MRI scanner, or be adapted to retrofit a pre-existing medical imaging scanner. In certain embodiments, the motion detection system and/or device can comprise one or more mounting brackets and a motion correction device housing, which can further comprise one or more detector modules and a power unit. In further embodiments, the collected motion data can be further analyzed by an image processing unit of the motion tracking and/or correction system.

Abstract: A process for determining whether tissue is precancer, in which tests discriminating between precancer and benign tissue and between precancer and normal tissue are combined, and tissue that is classified as precancer in both tests is determined to be precancer, in which neither of the tests to be combined is the most selective. Further, a process and device in which certain optimal wavelengths of glycogen, phosphate and lipid, but not protein, discriminate between normal and precancer tissues.

Abstract: A process for maintaining 3 dimensional orientation between a tissue specimen and images of the area of investigation, to register histopathologic diagnoses of multiple locations within the specimen with corresponding locations on the surface of said area of investigation.

Abstract: The present invention is an automated image analysis framework for cervical cancerous lesion detection. The present invention uses domain-specific diagnostic features in a probabilistic manner using conditional random fields. In addition, the present invention discloses a novel window-based performance assessment scheme for two-dimensional image analysis, which addresses the intrinsic problem of image misalignment. As a domain-specific anatomical feature, image regions corresponding to different tissue types are extracted from cervical images taken before and after the application of acetic acid during a clinical exam. The unique optical properties of each tissue type and the diagnostic relationships between neighboring regions are incorporated in the conditional random field model. The output provides information about both the tissue severity and the location of cancerous tissue in an image.

Abstract: The present invention is a diagnosis support system providing automated guidance to a user by automated retrieval of similar disease images and user feedback. High resolution standardized labeled and unlabeled, annotated and non-annotated images of diseased tissue in a database are clustered, preferably with expert feedback. An image retrieval application automatically computes image signatures for a query image and a representative image from each cluster, by segmenting the images into regions and extracting image features in the regions to produce feature vectors, and then comparing the feature vectors using a similarity measure. Preferably the features of the image signatures are extended beyond shape, color and texture of regions, by features specific to the disease. Optionally, the most discriminative features are used in creating the image signatures. A list of the most similar images is returned in response to a query. Keyword query is also supported.

Abstract: This invention uses LEDs and cross-polarization to produce bright, high-resolution digital images, both with and without glint (which adversely affects the clarity of standard colposcopic images), as well as streaming video at lower resolution. The invention allows for deeper layers of the tissue to be more efficiently visualized at multiple magnifications, thereby enhancing the invention's diagnostic capabilities, and it includes a focusing subsystem and a computerized data management system to archive and annotate still image data.

Abstract: The present invention discloses a method for the detection of atypical vessels in digital cervical imagery. A pre-processing stage is applied to enhance the contrast of blood vessel features compared to the surrounding tissue. Next, a segmentation stage is applied to identify regions of interest for atypical vessels using texture and gradient information. Finally, a post-processing stage (1) identifies other clinically relevant features in the cervical imager, and removes these features from the region of interest; and (2) uses color, size, and shape information to further refine the region of interest to eliminate false positives and determine a final region of interest. This automated method of atypical vessel detection is especially useful for diagnostic purposes such as cervical cancer detection.

Abstract: A process and device for detecting colon cancer by classifying and annotating clinical features in video data containing colonoscopic features by applying a probabilistic analysis to intra-frame and inter-frame relationships between colonoscopic features in spatially and temporally neighboring portions of video frames, and classifying and annotating as clinical features any of the colonoscopic features that satisfy the probabilistic analysis as clinical features. Preferably the probabilistic analysis is Hidden Markove Model analysis, and the process is carried out by a computer trained using semi supervised learning from labeled and unlabeled examples of clinical features in video containing colonoscopic features.

Abstract: The present invention is an automated image analysis framework for cervical cancerous lesion detection. The present invention uses domain-specific diagnostic features in a probabilistic manner using conditional random fields. In addition, the present invention discloses a novel window-based performance assessment scheme for two-dimensional image analysis, which addresses the intrinsic problem of image misalignment. As a domain-specific anatomical feature, image regions corresponding to different tissue types are extracted from cervical images taken before and after the application of acetic acid during a clinical exam. The unique optical properties of each tissue type and the diagnostic relationships between neighboring regions are incorporated in the conditional random field model. The output provides information about both the tissue severity and the location of cancerous tissue in an image.

Abstract: The present invention discloses methods and systems for improved focusing of imaging systems for the acquisition of high-quality focused tissue image data. A light emitter (L) aims a focusing light beam (FLB) towards an object of interest (O) so that the focusing light beam (FLB) is at an angle relative to the optical axis (OA) of the imager (I). If the object of interest (O) is out of focus, the focusing light spot (FLS) will appear above or below the focal point in the image (I). The pixel difference between the center of the focusing light spot (FLS) and the focal point indicates the range adjustment value. The range between the imager (I) and the object of interest (O) can then be adjusted according to the range adjustment value using a lookup table or calculations.

Abstract: A process for determining whether tissue is precancer, in which tests discriminating between precancer and benign tissue and between precancer and normal tissue are combined, and tissue that is classified as precancer in both tests is determined to be precancer, in which neither of the tests to be combined is the most selective. Further, a process and device in which certain optimal wavelengths of glycogen, phosphate and lipid, but not protein, discriminate between normal and precancer tissues.

Abstract: A process for maintaining 3 dimensional orientation between a tissue specimen and images of the area of investigation, to register histopathologic diagnoses of multiple locations within the specimen with corresponding locations on the surface of said area of investigation, by marking at least two fiduciary lines on the area of investigation; acquiring a fiduciary image of the tissue with the fiduciary lines; excising the tissue to form a tissue specimen; inserting at least two parallel needles through said specimen; acquiring a specimen image of the specimen with inserted needles over an alignment grid; fixing the specimen by immersing the specimen; acquiring a fixed image of the fixed specimen with the inserted needles over the alignment grid; forming a paraffin mold containing the fixed specimen and inserted needles; injecting different colored inks through the needles while withdrawing them from the fixed specimen, so that different colored needle tracks are formed in the specimen; sectioning the specimen

Abstract: This invention uses LEDs and cross-polarization to produce bright, high-resolution digital images, both with and without glint (which adversely affects the clarity of standard colposcopic images), as well as streaming video at lower resolution. The invention allows for deeper layers of the tissue to be more efficiently visualized at multiple magnifications, thereby enhancing the invention's diagnostic capabilities, and it includes a focusing subsystem and a computerized data management system to archive and annotate still image data.

Abstract: The present invention discloses methods and systems for improved focusing of imaging systems for the acquisition of high-quality focused tissue image data. A light emitter (L) aims a focusing light beam (FLB) towards an object of interest (O) so that the focusing light beam (FLB) is at an angle relative to the optical axis (OA) of the imager (I). If the object of interest (O) is out of focus, the focusing light spot (FLS) will appear above or below the focal point in the image (I). The pixel difference between the center of the focusing light spot (FLS) and the focal point indicates the range adjustment value. The range between the imager (I) and the object of interest (O) can then be adjusted according to the range adjustment value using a lookup table or calculations.

Abstract: The present invention discloses a method for the detection of atypical vessels in digital cervical imagery. A pre-processing stage is applied to enhance the contrast of blood vessel features compared to the surrounding tissue. Next, a segmentation stage is applied to identify regions of interest for atypical vessels using texture and gradient information. Finally, a post-processing stage (1) identifies other clinically relevant features in the cervical imager, and removes these features from the region of interest; and (2) uses color, size, and shape information to further refine the region of interest to eliminate false positives and determine a final region of interest. This automated method of atypical vessel detection is especially useful for diagnostic purposes such as cervical cancer detection.

Abstract: The image registration systems and methods according to this invention register reflectance and fluorescence hyperspectral imagery and provide the spatial image transformation between the reflectance and fluorescence hyperspectral imagery. A reflectance image is embedded into the fluorescence hyperspectral imagery and thereby resolves the resemblance problem of reflectance and fluorescence hyperspectral imagery. The reflectance image is embedded into the fluorescence hyperspectral imagery using (1) light from a narrow-band source embedded in Ultraviolet (UV) excitation light, (2) second order diffracted light, and/or (3) Ultraviolet (UV) excitation light reflectance. Resembling reflectance images are calculated from the reflectance hyperspectral imagery and the embedded reflectance image in the fluorescence hyperspectral imagery. The two respective reflectance images are pre-processed to maximize the resemblance between them.