Classification and Assessment of Hand Arthritis Stage using Support Vector Machine.

Arthritis is one of the most common health problems affecting people around the world. The goal of the work presented work is to classify and categorizing hand arthritis stages for patients, who may be developing or have developed hand arthritis, using machine learning. Stage classification was done using finger border detection, developed curvature analysis, principal components analysis, support vector machine and K-nearest neighbor algorithms. The outcome of this work showed that the proposed method can classify subject finger proximal interphalangeal joints (PIP) and distal interphalangeal joints (DIP) into stage classes with promising accuracy, especially for binary classification.

Automatic detection and severity measurement of eczema using image processing.

Chronic skin diseases like eczema may lead to severe health and financial consequences for patients if not detected and controlled early. Early measurement of disease severity, combined with a recommendation for skin protection and use of appropriate medication can prevent the disease from worsening. Current diagnosis can be costly and time-consuming. In this paper, an automatic eczema detection and severity measurement model are presented using modern image processing and computer algorithm. The system can successfully detect regions of eczema and classify the identified region as mild or severe based on image color and texture feature. Then the model automatically measures skin parameters used in the most common assessment tool called "Eczema Area and Severity Index (EASI)," by computing eczema affected area score, eczema intensity score, and body region score of eczema allowing both patients and physicians to accurately assess the affected skin.

Automated image analysis of digital colposcopy for the detection of cervical neoplasia.

Digital colposcopy is a promising technology for the detection of cervical intraepithelial neoplasia. Automated analysis of colposcopic images could provide an inexpensive alternative to existing screening tools. Our goal is to develop a diagnostic tool that can automatically identify neoplastic tissue from digital images. A multispectral digital colposcope (MDC) is used to acquire reflectance images of the cervix with white light before and after acetic-acid application in 29 patients. A diagnostic image analysis tool is developed to identify neoplasia in the digital images. The digital image analysis is performed in two steps. First, similar optical patterns are clustered together. Second, classification algorithms are used to determine the probability that these regions contain neoplastic tissue. The classification results of each patient's images are assessed relative to the gold standard of histopathology. Acetic acid induces changes in the intensity of reflected light as well as the ratio of green to red reflected light. These changes are used to differentiate high-grade squamous intraepithelial (HGSIL) and cancerous lesions from normal or low-grade squamous intraepithelial (LGSIL) tissue. We report diagnostic performance with a sensitivity of 79% and a specificity of 88%. We show that diagnostically useful digital images of the cervix can be obtained using a simple and inexpensive device, and that automated image analysis algorithms show a potential to identify histologically neoplastic tissue areas.

Methodology of a real-time quality control for the multispectral digital colposcope (MDC).

BACKGROUND: The diagnostic ability of algorithms developed for the Multispectral Digital Colposcope (MDC) is highly dependent on the quality of the image. The field of objective medical image quality analysis has great potential but has not been well exploited. Various researchers have reported different measures of image quality but with an existence of a reference image. The quality of an image can be attributed to several sources of errors, a few of which would be inclusion of presence of extraneous components, improper illumination, or an image out of focus. This can be due to motion artifact or the region of interest out of the focal plane. METHODS: With spectroscopic measurements, assessment of data quality has been used by our group in the past to avoid hardware errors at the time of acquisition. We are currently developing algorithms that will help identify hardware and acquisition errors to the clinician in under a few seconds. RESULTS: Minimizing these errors not only provides quality images for a diagnostic algorithm, but reduces the necessity for complex and time intensive post-processing software for enhancing the images. CONCLUSION: We propose a no reference image quality system specifically designed for MDC that can be modified to similar spectroscopic imaging applications.

Results of a pilot study of multispectral digital colposcopy for the in vivo detection of cervical intraepithelial neoplasia.

OBJECTIVE: Fluorescence spectroscopy is a promising technology for the detection of cervical squamous intraepithelial precancers and cancers. To date, many investigators have focused on point spectroscopy as an adjunct to diagnostic colposcopy. A device that visualizes the whole field of the cervix is needed for screening. To that end, we have developed a multispectral digital colposcope that works through the colposcope to image with white light, UV excitation at 345 nm, and blue light at 440 nm excitation. Here, we report the pilot study that precedes a Phase I trial. METHODS: The MDC system is composed of a light source, a colposcope, and a video rate color CCD camera with a frame grabber and takes approximately less than 1 min to make images of the cervix. Patients were measured at baseline and after acetic acid placement with white light, 345 nm excitation, and 440 nm excitation from the xenon arc lamp. The white light is in the visible spectrum, 345 nm excitation is in the UV spectrum and is not visible, and 440 nm excitation is blue light in the visible spectrum. White light generates a pink image of the cervix. 345 nm excitation, the UV light, excites fluorophores to emit a blue image. 440 nm excitation, the blue light, excites fluorophores to emit a green image. The patients underwent a loop excision procedure and the histopathology was inked and cut into 12 sections by the study pathologists. The histopathologic slides were scanned and the images were then reconstructed into maps. A diagnostic algorithm was calculated. The data were preprocessed, transformed, and analyzed by the K-means clustering method. Disease maps were generated using the algorithm and classifier and compared to white light colposcopy and the blue and green images obtained at 345 and 440 nm. RESULTS: Forty-six patients were measured at four clinical sites. Images were made of the cervix with white light, 345 nm excitation, and 440 nm excitation and are presented in the figures. As the study went on, images improved with improvements in the instrument. The white light and fluorescence images are presented with crudely constructed histopathologic maps and algorithmic maps. At 345 nm excitation, the UV light, histologically confirmed CIN appears darker blue; while at 440 nm excitation, the blue light, histologically confirmed CIN appears lighter green. CONCLUSIONS: This pilot study shows that MDC images can be matched to both histopathologic and algorithmic maps. The device and the algorithm are evolving but show promise. A Phase I trial is planned.

Optical technologies for cervical neoplasia: update of an NCI program project grant.

Cervical cancer is the second most common cancer in women worldwide and the leading cause of cancer mortality in women in developing countries. In the United States, over $6 billion is spent annually in the evaluation and treatment of low-grade lesions, many of which do not develop into full-blown cancer. In developing countries, however, the chief concern is that cervical cancer goes undetected because of the cost of testing and the lack of resources and trained personnel to screen and diagnose the disease. The goal of the National Cancer Institute Program Project Grant CA82710 is to assess the emerging technologies of fluorescence and reflectance spectroscopy and quantitative cytology and histopathology for the diagnosis of cervical neoplasia. All of these technologies should decrease mortality, morbidity, and the cost of treating cervical cancer.

Multispectral digital microscopy for in vivo monitoring of oral neoplasia in the hamster cheek pouch model of carcinogenesis.

In this study we use a multi-spectral digital microscope (MDM) to measure multi-spectral auto-fluorescence and reflectance images of the hamster cheek pouch model of DMBA (dimethylbenz[alpha]anthracene)- induced oral carcinogenesis. The multi-spectral images are analyzed both in the RGB (red, green, blue) color space as well as in the YCbCr (luminance, chromatic minus blue, chromatic minus red) color space. Mean image intensity, standard deviation, skewness, and kurtosis are selected as features to design a classification algorithm to discriminate normal mucosa from neoplastic tissue. The best diagnostic performance is achieved using features extracted from the YCbCr space, indicating the importance of chromatic information for classification. A sensitivity of 96% and a specificity of 84% were achieved in separating normal from abnormal cheek pouch lesions. The results of this study suggest that a simple and inexpensive MDM has the potential to provide a cost-effective and accurate alternative to standard white light endoscopy.

Multispectral digital colposcopy for in vivo detection of cervical cancer.

We present a multispectral digital colposcope (MDC) to measure multispectral autofluorescence and reflectance images of the cervix by using an inexpensive color CCD camera. The diagnostic ability of the MDC was evaluated by application of MDC spectral response to fluorescence and reflectance spectra measured from a large clinical trial. High diagnostic performance was achieved by use of only two excitation wavelengths: 330 and 440 nm. Good quality autofluorescence images of the human cervix were acquired in vivo with the MDC. Automated diagnostic algorithms correctly identified CIN (cervical intraepithelial neoplasia) lesions from MDC fluorescence images. The MDC has the potential to provide a costeffective alternative to standard colposcopy and better direction of biopsies.