Significant Dimension Reduction of 3D Brain MRI using 3D Convolutional Autoencoders.

Content-based image retrieval (CBIR) is a technology designed to retrieve images from a database based on visual features. While the CBIR is highly desired, it has not been applied to clinical neuroradiology, because clinically relevant neuroradiological features are swamped by a huge number of noisy and unrelated voxel information. Thus, effective dimension reduction is the key to successful CBIR. We propose a novel dimensional compression method based on 3D convolutional autoencoders (3D-CAE), which was applied to the ADNI2 3D brain MRI dataset. Our method succeeded in compressing 5 million voxel information to only 150 dimensions, while preserving clinically relevant neuroradiological features. The RMSE per voxel was as low as 8.4%, suggesting a promise of our method toward the application to the CBIR.

Four-class classification of skin lesions with task decomposition strategy.

This paper proposes a new computer-aided method for the skin lesion classification applicable to both melanocytic skin lesions (MSLs) and nonmelanocytic skin lesions (NoMSLs). The computer-aided skin lesion classification has drawn attention as an aid for detection of skin cancers. Several researchers have developed methods to distinguish between melanoma and nevus, which are both categorized as MSL. However, most of these studies did not focus on NoMSLs such as basal cell carcinoma (BCC), the most common skin cancer and seborrheic keratosis (SK) despite their high incidence rates. It is preferable to deal with these NoMSLs as well as MSLs especially for the potential users who are not enough capable of diagnosing pigmented skin lesions on their own such as dermatologists in training and physicians with different expertise. We developed a new method to distinguish among melanomas, nevi, BCCs, and SKs. Our method calculates 828 candidate features grouped into three categories: color, subregion, and texture. We introduced two types of classification models: a layered model that uses a task decomposition strategy and flat models to serve as performance baselines. We tested our methods on 964 dermoscopy images: 105 melanomas, 692 nevi, 69 BCCs, and 98 SKs. The layered model outperformed the flat models, achieving detection rates of 90.48%, 82.51%, 82.61%, and 80.61% for melanomas, nevi, BCCs, and SKs, respectively. We also identified specific features effective for the classification task including irregularity of color distribution. The results show promise for enhancing the capability of the computer-aided skin lesion classification.

Age-related prevalence of dermatoscopic patterns of acral melanocytic nevi.

The objective of this study was to evaluate the relation between age and dermatoscopic features of acral nevi. We evaluated 159 dermatoscopic images of melanocytic nevi from 146 individuals filed at the Dermatoscopy Outpatient Clinic of Tokyo Women's Medical University Medical Center East between April 2006 and March 2009. All images of melanocytic lesions on acral volar skin that showed a clear-cut dermatoscopic pattern of an acral nevus at the time of initial observation were included. The dermatoscopic patterns of all images were retrospectively examined in a blinded fashion according to the standard dermatoscopic classification criteria for acral melanocytic nevi. Images were classified using 15 structural variants of the parallel furrow pattern. These variants were then re-classified into two groups; the "single" line group and "double" line group. Patients of the double line group (age, 25.5 years) were significantly younger than those of the single line group (32.4 years). There was no significant difference in the age-related predominance between the solid line patterns and dotted line patterns. There was a significant age difference between patients with nevi showing the crista dotted pattern (mean age 24.9 years) and patients with nevi without the crista dotted pattern (mean age 34.6 years). We conclude that the double line variant of the parallel furrow pattern and crista dotted pattern, which probably correspond to the congenital type acral nevus, tend to be more common in young patients.

Lesion border detection in dermoscopy images using ensembles of thresholding methods.

BACKGROUND: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. In many cases, the lesion can be roughly separated from the background skin using a thresholding method applied to the blue channel. However, no single thresholding method appears to be robust enough to successfully handle the wide variety of dermoscopy images encountered in clinical practice. METHODS: In this article, we present an automated method for detecting lesion borders in dermoscopy images using ensembles of thres holding methods. CONCLUSION: Experiments on a difficult set of 90 images demonstrate that the proposed method is robust, fast, and accurate when compared to nine state-of-the-art methods.

Automated reconstruction algorithm for identification of 3D architectures of cribriform ductal carcinoma in situ.

Ductal carcinoma in situ (DCIS) is a pre-invasive carcinoma of the breast that exhibits several distinct morphologies but the link between morphology and patient outcome is not clear. We hypothesize that different mechanisms of growth may still result in similar 2D morphologies, which may look different in 3D. To elucidate the connection between growth and 3D morphology, we reconstruct the 3D architecture of cribriform DCIS from resected patient material. We produce a fully automated algorithm that aligns, segments, and reconstructs 3D architectures from microscopy images of 2D serial sections from human specimens. The alignment algorithm is based on normalized cross correlation, the segmentation algorithm uses histogram equilization, Otsu's thresholding, and morphology techniques to segment the duct and cribra. The reconstruction method combines these images in 3D. We show that two distinct 3D architectures are indeed found in samples whose 2D histological sections are similarly identified as cribriform DCIS. These differences in architecture support the hypothesis that luminal spaces may form due to different mechanisms, either isolated cell death or merging fronds, leading to the different architectures. We find that out of 15 samples, 6 were found to have 'bubble-like' cribra, 6 were found to have 'tube-like' criba and 3 were 'unknown.' We propose that the 3D architectures found, 'bubbles' and 'tubes', account for some of the heterogeneity of the disease and may be prognostic indicators of different patient outcomes.

Three-phase general border detection method for dermoscopy images using non-uniform illumination correction.

BACKGROUND: Computer-aided diagnosis of dermoscopy images has shown great promise in developing a quantitative, objective way of classifying skin lesions. An important step in the classification process is lesion segmentation. Many studies have been successful in segmenting melanocytic skin lesions (MSLs), but few have focused on non-melanocytic skin lesions (NoMSLs), as the wide variety of lesions makes accurate segmentation difficult. METHODS: We developed an automatic segmentation program for detecting borders of skin lesions in dermoscopy images. The method consists of a pre-processing phase, general lesion segmentation phase, including illumination correction, and bright region segmentation phase. RESULTS: We tested our method on a set of 107 NoMSLs and a set of 319 MSLs. Our method achieved precision/recall scores of 84.5% and 88.5% for NoMSLs, and 93.9% and 93.8% for MSLs, in comparison with manual extractions from four or five dermatologists. CONCLUSION: The accuracy of our method was competitive or better than five recently published methods. Our new method is the first method for detecting borders of both non-melanocytic and melanocytic skin lesions.

Automated color calibration method for dermoscopy images.

Accurate color information in dermoscopy images is very important for melanoma diagnosis since inappropriate white balance or brightness in the images adversely affects the diagnostic performance. In this paper, we present an automated color calibration method for dermoscopy images of skin lesions. On a set of 319 dermoscopy images, we develop color calibration filters based on the HSV color system. We determined that the color characteristics of the peripheral part of the tumors have significant influence on the color calibration filters and confirmed that the presented filters achieved satisfactory calibration performance as evaluated by cross-validation. We also confirmed that our method successfully modifies the color distribution of a given image to make it closer to the color distribution of the training image set.

Colour and contrast enhancement for improved skin lesion segmentation.

Accurate extraction of lesion borders is a critical step in analysing dermoscopic skin lesion images. In this paper, we consider the problems of poor contrast and lack of colour calibration which are often encountered when analysing dermoscopy images. Different illumination or different devices will lead to different image colours of the same lesion and hence to difficulties in the segmentation stage. Similarly, low contrast makes accurate border detection difficult. We present an effective approach to improve the performance of lesion segmentation algorithms through a pre-processing step that enhances colour information and image contrast. We combine this enhancement stage with two different segmentation algorithms. One technique relies on analysis of the image background by iterative measurements of non-lesion pixels, while the other technique utilises co-operative neural networks for edge detection. Extensive experimental evaluation is carried out on a dataset of 100 dermoscopy images with known ground truths obtained from three expert dermatologists. The results show that both techniques are capable of providing good segmentation performance and that the colour enhancement step is indeed crucial as demonstrated by comparison with results obtained from the original RGB images.

Feasibility evaluation of a motion detection system with face images for stereotactic radiosurgery.

In stereotactic radiosurgery we can irradiate a targeted volume precisely with a narrow high-energy x-ray beam, and thus the motion of a targeted area may cause side effects to normal organs. This paper describes our motion detection system with three USB cameras. To reduce the effect of change in illuminance in a tracking area we used an infrared light and USB cameras that were sensitive to the infrared light. The motion detection of a patient was performed by tracking his/her ears and nose with three USB cameras, where pattern matching between a predefined template image for each view and acquired images was done by an exhaustive search method with a general-purpose computing on a graphics processing unit (GPGPU). The results of the experiments showed that the measurement accuracy of our system was less than 0.7 mm, amounting to less than half of that of our previous system.

Robust video-oculography for non-invasive autonomic nerve quantification.

A relationship between autonomic nerves activity and depression or Alzheimer's disease has been reported. The quantification of autonomic nerves is expected to serve as a tool for quantifying the of severity of the disease or for early detection. Video-oculography is known as a non-invasive and reliable procedure of measurement of pupil response and is used in clinical practice. However, measuring the transition of pupil areas accurately is often difficult due to eyelid overlap, effects of blinking, eyelashes etc. Current video-oculography only performs thresholding to split pupil area and backgrounds and therefore sometimes has difficult in measuring accurate transitions of pupil reflex. In this study, we developed a robust and accurate method to measure the transition of pupil size. The proposed method introduces an interpolation process using an active contour model and ellipse estimation with selection of reliable contour points and attains robust measurement of pupil area against the abovementioned difficulties. We confirmed our method achieved an extraction accuracy of 98.3 % in precision and 98.9% in recall in average on the tested a total of 8,518 image frames from 30 movies.

Development of a novel border detection method for melanocytic and non-melanocytic dermoscopy images.

Computer aided diagnosis of dermoscopy images has shown great promise in developing a quantitative, objective way of classifying skin lesions. An important step in the classification process is the lesion segmentation. Many papers have been successful at segmenting melanocytic skin lesions (MSLs) but few have focused on non-melanocytic skin lesions (NoMSLs), since the wide variety of lesions makes accurate segmentation difficult. We developed an automatic segmentation program for the border detection of skin lesions. We tested our method on a set of 107 non-melanocytic lesions and on a set of 319 melanocytic lesions. Our method achieved precision/recall scores of 84.5% and 88.5% for NoMSLs, achieving higher scores than two previously published methods. Our method also achieved precision/recall scores of 93.9% and 93.8% for MSLs which was competitive or better than the two other methods. Therefore, we conclude that our approach is an accurate segmentation method for both melanocytic and non-melanocytic lesions.

Classification of melanocytic skin lesions from non-melanocytic lesions.

In this paper, we present a classification method of dermoscopy images between melanocytic skin lesions (MSLs) and non-melanocytic skin lesions (NoMSLs). The motivation of this research is to develop a pre-processor of an automated melanoma screening system. Since NoMSLs have a wide variety of shapes and their border is often ambiguous, we developed a new tumor area extraction algorithm to account for these difficulties. We confirmed that this algorithm is capable of handling different dermoscopy images not only those of NoMSLs but also MSLs as well. We determined the tumor area from the image using this new algorithm, calculated a total 428 features from each image, and built a linear classifier. We found only two image features, "the skewness of bright region in the tumor along its major axis" and "the difference between the average intensity in the peripheral part of the tumor and that in the normal skin area using the blue channel" were very efficient at classifying NoMSLs and MSLs. The detection accuracy of MSLs by our classifier using only the above mentioned image feature has a sensitivity of 98.0% and a specificity of 86.6% in a set of 107 non-melanocytic and 548 melanocytic dermoscopy images using a cross-validation test.

Skin lesion segmentation using an improved snake model.

Accurate identification of lesion borders is an important task in the analysis of dermoscopy images since the extraction of skin lesion borders provides important cues for accurate diagnosis. Snakes have been used for segmenting a variety of medical imagery including dermoscopy, however, due to the compromise of internal and external energy forces they can lead to under- or over-segmentation problems. In this paper, we introduce a mean shift based gradient vector flow (GVF) snake algorithm that drives the internal/external energies towards the correct direction. The proposed segmentation method incorporates a mean shift operation within the standard GVF cost function. Experimental results on a large set of diverse dermoscopy images demonstrate that the presented method accurately determines skin lesion borders in dermoscopy images.

An improved objective evaluation measure for border detection in dermoscopy images.

BACKGROUND: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Owing to the difficulty and subjectivity of human interpretation, dermoscopy image analysis has become an important research area. One of the most important steps in dermoscopy image analysis is the automated detection of lesion borders. Although numerous methods have been developed for the detection of lesion borders, very few studies were comprehensive in the evaluation of their results. METHODS: In this paper, we evaluate five recent border detection methods on a set of 90 dermoscopy images using three sets of dermatologist-drawn borders as the ground truth. In contrast to previous work, we utilize an objective measure, the normalized probabilistic rand index, which takes into account the variations in the ground-truth images. CONCLUSION: The results demonstrate that the differences between four of the evaluated border detection methods are in fact smaller than those predicted by the commonly used exclusive-OR measure.

Approximate lesion localization in dermoscopy images.

BACKGROUND: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Because of the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. METHODS: In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms. RESULTS: The method is tested on a set of 428 dermoscopy images. The localization error is quantified by a metric that uses dermatologist-determined borders as the ground truth. CONCLUSION: The results demonstrate that the method presented here achieves both fast and accurate localization of lesions in dermoscopy images.

Lesion border detection in dermoscopy images.

BACKGROUND: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, computerized analysis of dermoscopy images has become an important research area. One of the most important steps in dermoscopy image analysis is the automated detection of lesion borders. METHODS: In this article, we present a systematic overview of the recent border detection methods in the literature paying particular attention to computational issues and evaluation aspects. CONCLUSION: Common problems with the existing approaches include the acquisition, size, and diagnostic distribution of the test image set, the evaluation of the results, and the inadequate description of the employed methods. Border determination by dermatologists appears to depend upon higher-level knowledge, therefore it is likely that the incorporation of domain knowledge in automated methods will enable them to perform better, especially in sets of images with a variety of diagnoses.

Application of support vector machine classifiers to preoperative risk stratification with myocardial perfusion scintigraphy.

BACKGROUND: Myocardial perfusion single-photon emission computed tomography (SPECT) has been used for risk stratification before non-cardiac surgery. However, few authors have used mathematical models for evaluating the likelihood of perioperative cardiac events. METHODS AND RESULTS: This retrospective cohort study collected data of 1,351 patients referred for SPECT before non-cardiac surgery. We generated binary classifiers using support vector machine (SVM) and conventional linear models for predicting perioperative cardiac events. We used clinical and surgical risk, and SPECT findings as input data, and the occurrence of all and hard cardiac events as output data. The area under the receiver-operating characteristic curve (AUC) was calculated for assessing the prediction accuracy. The AUC values were 0.884 and 0.748 in the SVM and linear models, respectively in predicting all cardiac events with clinical and surgical risk, and SPECT variables. The values were 0.861 (SVM) and 0.677 (linear) when not using SPECT data as input. In hard events, the AUC values were 0.892 (SVM) and 0.864 (linear) with SPECT, and 0.867 (SVM) and 0.768 (linear) without SPECT. CONCLUSION: The SVM was superior to the linear model in risk stratification. We also found an incremental prognostic value of SPECT results over information about clinical and surgical risk.

Automatic detection of blue-white veil and related structures in dermoscopy images.

Dermoscopy is a non-invasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. One of the most important features for the diagnosis of melanoma in dermoscopy images is the blue-white veil (irregular, structureless areas of confluent blue pigmentation with an overlying white "ground-glass" film). In this article, we present a machine learning approach to the detection of blue-white veil and related structures in dermoscopy images. The method involves contextual pixel classification using a decision tree classifier. The percentage of blue-white areas detected in a lesion combined with a simple shape descriptor yielded a sensitivity of 69.35% and a specificity of 89.97% on a set of 545 dermoscopy images. The sensitivity rises to 78.20% for detection of blue veil in those cases where it is a primary feature for melanoma recognition.

An improved Internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm.

In this paper, we present an Internet-based melanoma screening system. Our web server is accessible from all over the world and performs the following procedures when a remote user uploads a dermoscopy image: separates the tumor area from the surrounding skin using highly accurate dermatologist-like tumor area extraction algorithm, calculates a total of 428 features for the characterization of the tumor, classifies the tumor as melanoma or nevus using a neural network classifier, and presents the diagnosis. Our system achieves a sensitivity of 85.9% and a specificity of 86.0% on a set of 1258 dermoscopy images using cross-validation.