Medical infrared imaging and orthostatic analysis to determine lameness in the pelvic limbs of dogs.

Subtle lameness makes it difficult to ascertain which is the affected limb. A study was conducted to investigate a change in the thermal pattern and temperature of the thermal image of the paw print in a lame pelvic limb compared to a non-lame pelvic limb of dogs confirmed by orthostatic analysis. Fourteen client owned dogs with a unilateral pelvic limb lameness and 14 healthy employee dogs were examined and the pelvic limbs radiographed. Thermal images of the paw print were taken after each dog was kept in a static position on a foam mat for 30 seconds. Average temperatures and thermographic patterns were analyzed. Analysis was performed in a static position. The asymmetry index for each stance variable and optimal cutoff point for the peak vertical force and thermal image temperatures were calculated. Image pattern analysis revealed 88% success in differentiating the lame group, and 100% in identifying the same thermal pattern in the healthy group. The mean of the peak vertical force revealed a 10.0% difference between the left and right pelvic limb in healthy dogs and a 72.4% between the lame and non-lame limb in the lame dog group. Asymmetry index analysis revealed 5% in the healthy group and 36.2% in the lame group. The optimal cutoff point for the peak vertical force to determine lameness was 41.77% (AUC = 0.93) and for MII 0.943% (AUC = 0.72). The results of this study highlight the change in the thermal pattern of the paw print in the lame pelvic limb compared to a non-lame pelvic limb in the lame group and the healthy group. Medical infrared imaging of the paw prints can be utilized to screen for the lame limb in dogs.

Medical Infrared Imaging of Normal and Dysplastic Elbows in Dogs.

OBJECTIVE: To investigate the ability of medical infrared imaging to differentiate between normal canine elbows and those with abnormal elbows (elbow dysplasia). STUDY DESIGN: Prospective cohort study. ANIMALS: Dogs with normal (n = 15) and abnormal (n = 14) elbows. METHODS: Infrared imaging was performed on all dogs and data analyzed via descriptive statistics and image pattern analysis software. Animals with elbow dysplasia had arthroscopic procedures to confirm the presence of elbow disease. RESULTS: Computer recognition pattern analysis was up to 100% correct in identifying abnormal elbows and normal elbows, with the medial images most consistent. The caudal, lateral, and cranial images correctly identified 83-100% abnormal elbows. The caudal and lateral images correctly identified 83% normal elbows. A significant difference in temperature was found between normal and abnormal elbows for the cranial full region of interest, lateral images, and each quadrant. CONCLUSION: Medical infrared imaging was able to correctly identify known abnormal and known normal elbows in dogs.

Medical infrared imaging (thermography) of type I thoracolumbar disk disease in chondrodystrophic dogs.

OBJECTIVE: To: (1) determine the success of medical infrared imaging (MII) in identifying dogs with TLIVDD, (2) compare MII localization with magnetic resonance imaging (MRI) results and surgical findings, and (3) determine if the MII pattern returns to that of normal dogs 10 weeks after decompression surgery. STUDY DESIGN: Prospective case series. ANIMALS: Chondrodystrophic dogs (n = 58) with Type I TLIVDD and 14 chondrodystrophic dogs with no evidence of TLIVDD. METHODS: Complete neurologic examination, MII, and MRI studies were performed on all dogs. Dogs with type I TLIVDD had decompressive surgery and follow-up MII was performed at 10 weeks. Pattern analysis software was used to differentiate between clinical and control dogs, and statistical analysis using anatomic regions of interest on the dorsal views were used to determine lesion location. Recheck MII results were compared with control and pre-surgical images. RESULTS: Computer recognition pattern analysis was 90% successful in differentiating normal dogs from dogs affected by TLIVDD and 97% successful in identifying the abnormal intervertebral disc space in dogs with TLIVDD. Statistical comparisons of the ROI mean temperature were unable to determine the location of the disc herniation. Recheck MII patterns did not normalize and more closely resembled the clinical group. CONCLUSIONS: MII was 90% successful differentiating between normal dogs and 97% successful in identifying the abnormal intervertebral disc space in dogs with TLIVDD. Abnormal intervertebral disc space localization using ROI mean temperature analysis was not successful. MII patterns 10 weeks after surgery do not normalize.

Differentiation of melanoma from benign mimics using the relative-color method.

BACKGROUND: Previous studies have successfully classified 86% of malignant melanomas using a relative-color segmentation method, by feature extraction from photographic images in the automatic identification of skin tumors. These studies were extended by applying the relative-color method to dermoscopic images of melanoma grouped with melanoma in situ and clark nevus lesions in dermoscopic images allow more control over lighting variations, which contribute to lesion misclassification. Dermoscopic images then enable a more detailed examination of the structure of skin lesions, provide much more structural detail within lesions, and contain visual information that cannot be seen in photographic images. This present work extends the previous studies by applying relative-color feature extraction to dermoscopic images to differentiate among melanoma, seborrheic keratoses and Reed/Spitz nevi. OBJECTIVE: To develop a method for automatically differentiating among malignant melanoma, seborrheic keratoses and Reed/Spitz nevi, using digitized, color, dermoscopic images. METHODS: Images underwent preprocessing, tumor segmentation, feature extraction and tumor classification. The relative-color method was used in the segmentation stage. Classification was accomplished by taking the inner products of model tumor feature vectors with test-image tumor vectors followed by the nearest-neighbor classification method. RESULTS: The classification rates of melanoma, seborrheic keratoses and Reed/Spitz nevi images mixed together, were 60%, 58.3% and 80%, respectively. Classification of melanoma and Reed/Spitz nevi mixed, were 70% and 90%, respectively. Classification rates were the best when melanoma was being differentiated from seborrheic keratoses. These rates were 100% and 88.9%, respectively. CONCLUSION: Dermoscopic rather than photographic images were preprocessed, using a hair-removal technique. They were then converted to relative-color images, which were segmented using the principal components transform and median split, followed by morphological filtering. After processing, the multi-dimensional tumor feature space described herein was used to differentiate the tumors. The high success rates for differentiating seborrheic keratoses from melanoma show that the use of dermoscopic images has a strong promise in enabling prescreening, as well as automated assistance and significant improvement in tumor diagnosis in clinics.

Thermal imaging of normal and cranial cruciate ligament-deficient stifles in dogs.

OBJECTIVE: To investigate the capability of thermography for differentiation between normal stifles and those with cranial cruciate ligament (CCL) rupture in dogs, initially with a full hair coat and 1 hour after clipping the hair coat. STUDY DESIGN: Prospective study. ANIMALS: Labrador Retrievers (n=6) with normal stifle joints (controls) and adult dogs (n=10) with CCL rupture. METHODS: Thermography was performed before, and 60 minutes after, clipping the hair coat from the pelvic limb. Stifle images were classified as normal or abnormal, then subclassified as clipped and unclipped hair coat. CCL deficiency was confirmed at surgery and thermographic images subsequently classified as abnormal before analysis with image processing software. RESULTS: Using image recognition analysis, differentiation between normal and CCL-deficient stifles in both clipped and unclipped dogs was 85% successful on cranial images, medial, caudal, and lateral images were between 75% and 85% successful. Although there were significant increases in skin temperature after clipping in both groups (P<.0002-.0001), there were no significant temperature differences between normal and CCL-deficient stifles when the entire stifle was examined. CONCLUSION: Thermography was successful in differentiating naturally occurring CCL-deficient stifles in dogs, with a success rate of 75-85%. Clipping is not necessary for successful thermographic evaluation of the canine stifle. CLINICAL RELEVANCE: Thermography may be a useful imaging modality for diagnosis of CCL deficiency in dogs when CCL rupture is suspected but stifle laxity is not evident.

Skin lesion classification using relative color features.

BACKGROUND/PURPOSE: Clinically, it is difficult to differentiate the early stage of malignant melanoma and certain benign skin lesions due to similarity in appearance. Our research uses image analysis of clinical skin images and relative color-based pattern recognition techniques to enhance the images and improve differentiation of these lesions. METHODS: First, the relative color images were created from digitized photographic images. Then, they were segmented into objects and morphologically filtered. Next, the relative color features were extracted from the objects to form two different feature spaces; a lesion feature space and an object feature space. The two feature spaces serve as two data models to be analyzed to determine the best features. Finally, we used a statistical analysis model of relative color features, which better classifies the various types of skin lesions. RESULTS/CONCLUSIONS: The best features found for differentiation of melanoma and benign skin lesions from this study are area, mean in the red and blue bands, standard deviation in the red and green bands, skewness in the green band, and entropy in the red band. With the relative color feature algorithm developed, the best results were obtained with a multi-layer perceptron neural network model. This showed an overall classification success of 79%, with 70% of the benign lesions successfully classified, and 86% of malignant melanoma successfully classified.

Melanoma and seborrheic keratosis differentiation using texture features.

PURPOSE: To explore texture features in two-dimensional images to differentiate seborrheic keratosis from melanoma. METHODS: A systematic approach to consistent classification of skin tumors is described. Texture features, based on the second-order histogram, were used to identify the features or a combination of features that could consistently differentiate a malignant skin tumor (melanoma) from a benign one (seborrheic keratosis). Two hundred and seventy-one skin tumor images were separated into training and test sets for accuracy and consistency. Automatic induction was applied to generate classification rules. Data analysis and modeling tools were used to gain further insight into the feature space. RESULT AND CONCLUSIONS: In all, 85-90% of seborrheic keratosis images were correctly differentiated from the malignant skin tumors. The features correlation_average, correlation_range, texture_energy_average and texture_energy_range were found to be the most important features in differentiating seborrheic keratosis from melanoma. Over-all, the seborrheic keratosis images were better identified by the texture features than the melanoma images.