Lesion Pixels Research Articles

StripeRust-Pocket: A Mobile-Based Deep Learning Application for Efficient Disease Severity Assessment of Wheat Stripe Rust.

Wheat stripe rust poses a marked threat to global wheat production. Accurate and effective disease severity assessments are crucial for disease resistance breeding and timely management of field diseases. In this study, we propose a practical solution using mobile-based deep learning and model-assisted labeling. StripeRust-Pocket, a user-friendly mobile application developed based on deep learning models, accurately quantifies disease severity in wheat stripe rust leaf images, even under complex backgrounds. Additionally, StripeRust-Pocket facilitates image acquisition, result storage, organization, and sharing. The underlying model employed by StripeRust-Pocket, called StripeRustNet, is a balanced lightweight 2-stage model. The first stage utilizes MobileNetV2-DeepLabV3+ for leaf segmentation, followed by ResNet50-DeepLabV3+ in the second stage for lesion segmentation. Disease severity is estimated by calculating the ratio of the lesion pixel area to the leaf pixel area. StripeRustNet achieves 98.65% mean intersection over union (MIoU) for leaf segmentation and 86.08% MIoU for lesion segmentation. Validation using an additional 100 field images demonstrated a mean correlation of over 0.964 with 3 expert visual scores. To address the challenges in manual labeling, we introduce a 2-stage labeling pipeline that combines model-assisted labeling, manual correction, and spatial complementarity. We apply this pipeline to our self-collected dataset, reducing the annotation time from 20 min to 3 min per image. Our method provides an efficient and practical solution for wheat stripe rust severity assessments, empowering wheat breeders and pathologists to implement timely disease management. It also demonstrates how to address the "last mile" challenge of applying computer vision technology to plant phenomics.

Determining the Presence and Size of Shoulder Lesions in Sows Using Computer Vision.

Shoulder sores predominantly arise in breeding sows and often result in untimely culling. Reported prevalence rates vary significantly, spanning between 5% and 50% depending upon the type of crate flooring inside a farm, the animal's body condition, or an existing injury that causes lameness. These lesions represent not only a welfare concern but also have an economic impact due to the labor needed for treatment and medication. The objective of this study was to evaluate the use of computer vision techniques in detecting and determining the size of shoulder lesions. A Microsoft Kinect V2 camera captured the top-down depth and RGB images of sows in farrowing crates. The RGB images were collected at a resolution of 1920 × 1080. To ensure the best view of the lesions, images were selected with sows lying on their right and left sides with all legs extended. A total of 824 RGB images from 70 sows with lesions at various stages of development were identified and annotated. Three deep learning-based object detection models, YOLOv5, YOLOv8, and Faster-RCNN, pre-trained with the COCO and ImageNet datasets, were implemented to localize the lesion area. YOLOv5 was the best predictor as it was able to detect lesions with an mAP@0.5 of 0.92. To estimate the lesion area, lesion pixel segmentation was carried out on the localized region using traditional image processing techniques like Otsu's binarization and adaptive thresholding alongside DL-based segmentation models based on U-Net architecture. In conclusion, this study demonstrates the potential of computer vision techniques in effectively detecting and assessing the size of shoulder lesions in breeding sows, providing a promising avenue for improving sow welfare and reducing economic losses.

Towards robust registration of heterogeneous multispectral UAV imagery: A two-stage approach for cotton leaf lesion grading

Multiple source images acquired from diverse sensors mounted on unmanned aerial vehicles (UAVs) offer valuable complementary information for ground vegetation analysis. However, accurately aligning heterogeneous UAV images poses challenges due to differences in geometry, intensity, and noise resulting from varying imaging principles. This paper presents a two-stage registration method aimed at fusing visible RGB and multispectral images for cotton leaf lesion grading. The coarse alignment stage utilizes Scale Invariant Feature Transform (SIFT), while the refined alignment stage employs a novel correlation coefficient-based template matching. The proposed method first employs the EfficientDet network to detect infected cotton leaves with lesions in RGB images. Subsequently, lesion leaves in multiple spectral imagery (red, green, red edge, and near-infrared bands) are located using the perspective transformation matrix derived from SIFT and the coordinates of lesion leaves in RGB images. Refined registration between RGB and multispectral imagery is achieved through template matching with the new correlation coefficient. The registered reflectance data from the different spectral bands and RGB components are utilized to classify pixels in each infected leaf into lesion, healthy, and soil parts. The lesion grade is determined based on the ratio of lesion pixels to the total corresponding leaf area. Experimental results, compared with manual assessment, demonstrate a lesion leaves detection model with a mAP@0.5 of 91.01% and a leaf lesion grading accuracy of 92.01%. These results validate the suitability of the proposed method for UAV RGB and multispectral image registration, enabling automated cotton leaf lesion grading.

Research of segmentation recognition of small disease spots on apple leaves based on hybrid loss function and CBAM.

Identification technology of apple diseases is of great significance in improving production efficiency and quality. This paper has used apple Alternaria blotch and brown spot disease leaves as the research object and proposes a disease spot segmentation and disease identification method based on DFL-UNet+CBAM to address the problems of low recognition accuracy and poor performance of small spot segmentation in apple leaf disease recognition. The goal of this paper is to accurately prevent and control apple diseases, avoid fruit quality degradation and yield reduction, and reduce the resulting economic losses. DFL-UNet+CBAM model has employed a hybrid loss function of Dice Loss and Focal Loss as the loss function and added CBAM attention mechanism to both effective feature layers extracted by the backbone network and the results of the first upsampling, enhancing the model to rescale the inter-feature weighting relationships, enhance the channel features of leaf disease spots and suppressing the channel features of healthy parts of the leaf, and improving the network's ability to extract disease features while also increasing model robustness. In general, after training, the average loss rate of the improved model decreases from 0.063 to 0.008 under the premise of ensuring the accuracy of image segmentation. The smaller the loss value is, the better the model is. In the lesion segmentation and disease identification test, MIoU was 91.07%, MPA was 95.58%, F1 Score was 95.16%, MIoU index increased by 1.96%, predicted disease area and actual disease area overlap increased, MPA increased by 1.06%, predicted category correctness increased, F1 Score increased by 1.14%, the number of correctly identified lesion pixels increased, and the segmentation result was more accurate. Specifically, compared to the original U-Net model, the segmentation of Alternaria blotch disease, the MIoU value increased by 4.41%, the MPA value increased by 4.13%, the Precision increased by 1.49%, the Recall increased by 4.13%, and the F1 Score increased by 2.81%; in the segmentation of brown spots, MIoU values increased by 1.18%, MPA values by 0.6%, Precision by 0.78%, Recall by 0.6%, and F1 Score by 0.69%. The spot diameter of the Alternaria blotch disease is 0.2-0.3cm in the early stage, 0.5-0.6cm in the middle and late stages, and the spot diameter of the brown spot disease is 0.3-3cm. Obviously, brown spot spots are larger than Alternaria blotch spots. The segmentation performance of smaller disease spots has increased more noticeably, according to the quantitative analysis results, proving that the model's capacity to segment smaller disease spots has greatly improved. The findings demonstrate that for the detection of apple leaf diseases, the method suggested in this research has a greater recognition accuracy and better segmentation performance. The model in this paper can obtain more sophisticated semantic information in comparison to the traditional U-Net, further enhance the recognition accuracy and segmentation performance of apple leaf spots, and address the issues of low accuracy and low efficiency of conventional disease recognition methods as well as the challenging convergence of conventional deep convolutional networks.

HAF-Net: A Fully Convolutional Segmentation Network Based on Hybrid Attention for Skin Lesion Segmentation

Skin cancer has become one of the leading causes of life threatening, and accurate segmentation of lesion regions from dermoscopic images is an effective aid to diagnosis. The lack of obvious lesion features and the large variations in the shape of lesion areas lead to the inability of many convolutional neural networks (CNNs) to accurately identify lesion pixels. In this paper, we propose a fully convolutional segmentation network based on hybrid attention (HAF-Net) for skin lesion segmentation. The model integrates the residual-dense block (RDB) in the encoding stage to improve the efficiency of feature extraction. Furthermore, channel attention block (CAB) and position attention block (PAB) are embedded at the end of the encoding stage, and the semantic relevance of the same class of features is integrated by hybrid attention to highlight the feature representation. In addition, we use channel separable convolution to reduce the number of parameters of the model. Test results on the publicly available skin lesion datasets ISIC 2016 and ISIC 2017 illustrate the superiority of the proposed model.

Data augmentation based on multiple oversampling fusion for medical image segmentation

A high-performance medical image segmentation model based on deep learning depends on the availability of large amounts of annotated training data. However, it is not trivial to obtain sufficient annotated medical images. Generally, the small size of most tissue lesions, e.g., pulmonary nodules and liver tumours, could worsen the class imbalance problem in medical image segmentation. In this study, we propose a multidimensional data augmentation method combining affine transform and random oversampling. The training data is first expanded by affine transformation combined with random oversampling to improve the prior data distribution of small objects and the diversity of samples. Secondly, class weight balancing is used to avoid having biased networks since the number of background pixels is much higher than the lesion pixels. The class imbalance problem is solved by utilizing weighted cross-entropy loss function during the training of the CNN model. The LUNA16 and LiTS17 datasets were introduced to evaluate the performance of our works, where four deep neural network models, Mask-RCNN, U-Net, SegNet and DeepLabv3+, were adopted for small tissue lesion segmentation in CT images. In addition, the small tissue segmentation performance of the four different deep learning architectures on both datasets could be greatly improved by incorporating the data augmentation strategy. The best pixelwise segmentation performance for both pulmonary nodules and liver tumours was obtained by the Mask-RCNN model, with DSC values of 0.829 and 0.879, respectively, which were similar to those of state-of-the-art methods.

Two new methods for severity assessment of wheat stripe rust caused by Puccinia striiformis f. sp. tritici.

Accurate severity assessment of wheat stripe rust caused by Puccinia striiformis f. sp. tritici is of great significance for phenotypic determination, prediction, and control of the disease. To achieve accurate severity assessment of the disease based on the actual percentages of lesion areas in the areas of the corresponding whole diseased leaves, two new methods were proposed for severity assessment of the disease. In the Adobe Photoshop 2022 software, the acquired images of single diseased leaves of each severity class of the disease were manually segmented, and the numbers of the leaf region pixels and lesion pixels of each diseased leaf were obtained by pixel statistics. After calculation of the actual percentages of lesion areas in the areas of the corresponding whole diseased leaves based on the obtained pixel numbers, the training sets and testing sets were constructed for each severity class by using the system sampling method with two sampling ratios of 4:1 and 3:2. Then the mean and standard deviation of the actual percentages of lesion areas contained in each training set were calculated, respectively. For each sampling ratio, two methods, one based on the midpoint value of the means of the actual percentages of lesion areas corresponding to two adjacent severity classes and the other based on the distribution range of most of the actual percentages of lesion areas, were used to determine the midpoint-of-two-adjacent-means-based actual percentage reference range and the 90%, 95%, and 99% reference ranges of the actual percentages of lesion areas for each severity class. According to the determined reference ranges, the severity of each diseased leaf in the training sets and testing sets was assessed. The results showed that high assessment accuracies (not lower than 85%) for the training sets and testing sets were achieved, demonstrating that the proposed methods could be used to conduct severity assessment of wheat stripe rust based on the actual percentages of lesion areas. This study provides a reference for accurate severity assessments of plant diseases.

Attention-optimized DeepLab V3 + for automatic estimation of cucumber disease severity

BackgroundAutomatic and accurate estimation of disease severity is critical for disease management and yield loss prediction. Conventional disease severity estimation is performed using images with simple backgrounds, which is limited in practical applications. Thus, there is an urgent need to develop a method for estimating the disease severity of plants based on leaf images captured in field conditions, which is very challenging since the intensity of sunlight is constantly changing, and the image background is complicated.ResultsThis study developed a simple and accurate image-based disease severity estimation method using an optimized neural network. A hybrid attention and transfer learning optimized semantic segmentation model was proposed to obtain the disease segmentation map. The severity was calculated by the ratio of lesion pixels to leaf pixels. The proposed method was validated using cucumber downy mildew, and powdery mildew leaves collected under natural conditions. The results showed that hybrid attention with the interaction of spatial attention and channel attention can extract fine lesion and leaf features, and transfer learning can further improve the segmentation accuracy of the model. The proposed method can accurately segment healthy leaves and lesions (MIoU = 81.23%, FWIoU = 91.89%). In addition, the severity of cucumber leaf disease was accurately estimated (R2 = 0.9578, RMSE = 1.1385). Moreover, the proposed model was compared with six different backbones and four semantic segmentation models. The results show that the proposed model outperforms the compared models under complex conditions, and can refine lesion segmentation and accurately estimate the disease severity.ConclusionsThe proposed method was an efficient tool for disease severity estimation in field conditions. This study can facilitate the implementation of artificial intelligence for rapid disease severity estimation and control in agriculture.

Automated Computer-Aided Diagnosis of Diabetic Retinopathy Based on Segmentation and Classification using K-nearest neighbor algorithm in retinal images

Abstract Diabetic retinopathy (DR) is an eye oddity where the human retina is afflicted because of the ever-increasing quantity of insulin in the blood. It leads to the loss of sight. Preliminary diagnosis of DR assists to improve to inhibit future injury. Proper DR screening has been recognized as an economical way to accumulate health services. Automated retinal analysis become known as the most significant screening approach for primitive DR diagnosis, which leads to diminishing the workload related to manual screening and also, cost-effective and less time-consuming efforts. In the proposed work, the preprocessing, removal of applicant lesion pixels, and formulation of feature set have been examined which is fully appropriate for the classification task. In preprocessing approach, the framework removes the unwanted pixels, eliminates the optic disc, and extraction of the blood vessels from the retinal images. Morphological operations are applied to extract the boundaries of the blood vessels and then 2D discrete wavelet decomposition is applied to estimate the horizontal, vertical and diagonal coefficients. The candidate lesion pixels i.e. dark and bright DR pixels are detected using an adaptive threshold that uses local statistical, geometrical, and location-based characteristics of the background image. The extracted feature set is processed using a K-nearest neighbor (KNN) classifier with 80% of training data and 20% of testing data to diagnose the severity level of the disease. The proposed scheme is evaluated by the DIARETDB1 benchmark dataset with the performance parameters, i.e. 95% of accuracy, 92.6% of sensitivity and 87.56% specificity achieved with less computation time required.

An Expanded MLP Neural Network for Fast Angiodysplasia Lesions Segmentation in Capsule Endoscopy Images

In this paper, an expanded multilayer perceptron (EMLP) neural network is proposed to automatically segment angiodysplasia regions in wireless capsule endoscopy (WCE) images The main idea is to minimize the distance between the input image and the corresponding binary ground truth, i.e., the mask image. After the training phase, when a test image is given to the network, the lesion pixels will be close to “one” and the other pixels will be close to “zero” and finally, the lesion area can be segmented using thresholding. Since angiodysplasia lesions appear in images with different spectrums of red color, the classical MLP neural network cannot be trained with a wide range of red color, hence leads to undesirable network accuracy. To solve this problem, we proposed an EMLP neural network for image segmentation. In the EMLP neural network, neurons are divided into several groups, each of which is for learning a spectrum of the lesion. The EMLP is able to learn a wider range of red colors. The proposed method is able to segment WCE images containing angiodysplasia faster than the existing methods. Our investigation shows that our method also outperforms existing methods in terms of segmentation scores.

Cystic (including atypical) and solid breast lesion classification using the different features of quantitative ultrasound parametric images.

The amount of ultrasound (US) breast examinations continues to grow rapidly because of the wider endorsement of breast cancer screening programs. Cysts are the most commonly diagnosed breast lesions. Atypical breast cysts can be a serious differentiation problem in the US. Our goal was to develop noninvasive automated US grayscale image analysis for the cystic and solid breast lesion differentiation based on mathematical image post-processing. We used a set of 217 ultrasound images of proven 107 cystic (including 53 atypical) and 110 solid lesions. Empirical statistical and morphological models of the lesions were used to obtain features. The AUC indicator and Student's t test were used to assess the quality of the individual features. The Pearson correlation matrix was used to calculate the correlation between various features. The LASSO and stepwise regression methods were used to determine the most significant features. Finally, the lesion classification was carried out by the various methods. The use of LASSO regression for the feature selection made it possible to select the most significant features for classification. The sensitivity increased from 87.1% to 89.2% and the specificity-from 92.2 to 94.8%. After the correlation matrix construction, it was found that features with a high value of the correlation coefficient (0.72; 0.75) can also be used to improve the quality of the classification. The construction of the empirical model of the lesion pixels brightness behavior can provide parameters that are important for the correct classification of ultrasound images. The optimal set of features with the maximum discriminant characteristics may not be consistent with the correlation of features and the value of the AUC index. Features with a low AUC index (in our case 0.72) can also be important for improving the quality of the classification.

A new approach to learning and recognizing leaf diseases from individual lesions using convolutional neural networks

Leaf disease recognition using image processing and deep learning techniques is currently a vibrant research area. Most studies have focused on recognizing diseases from images of whole leaves. This approach limits the resulting models’ ability to estimate leaf disease severity or identify multiple anomalies occurring on the same leaf. Recent studies have demonstrated that classifying leaf diseases based on individual lesions greatly enhances disease recognition accuracy. In those studies, however, the lesions were laboriously cropped by hand. This study proposes a semi-automatic algorithm that facilitates the fast and efficient preparation of datasets of individual lesions and leaf image pixel maps to overcome this problem. These datasets were then used to train and test lesion classifier and semantic segmentation Convolutional Neural Network (CNN) models, respectively. We report that GoogLeNet’s disease recognition accuracy improved by more than 15% when diseases were recognized from lesion images compared to when disease recognition was done using images of whole leaves. A CNN model which performs semantic segmentation of both the leaf and lesions in one pass is also proposed in this paper. The proposedKijaniNetmodel achieved state-of-the-art segmentation performance in terms of mean Intersection over Union (mIoU) score of 0.8448 and 0.6257 for the leaf and lesion pixel classes, respectively. In terms of mean boundary F1 score, theKijaniNetmodel attained 0.8241 and 0.7855 for the two pixel classes, respectively. Lastly, a fully automatic algorithm for leaf disease recognition from individual lesions is proposed. The algorithm employs the semantic segmentation network cascaded to a GoogLeNet classifier for lesion-wise disease recognition. The proposed fully automatic algorithm outperforms competing methods in terms of its superior segmentation and classification performance despite being trained on a small dataset.

Automatic Skin Lesion Segmentation—A Novel Approach of Lesion Filling through Pixel Path

Lesion segmentation is a vital step in a melanoma recognition system. Many algorithms were developed for the efficient skin lesion segmentation. Most of them fails to realize a perfect segmentation. This paper proposes a novel, fully automatic system, for the lesion segmentation in dermatograms. The proposed approach executes in two steps. Selection of root seed is the first step. All the lesion pixels in the dermatogram are identified during the second step. Traversal through a predefined lesion pixel path ensures the reachability of all lesion pixels irrespective of the possible lesion discontinuity. The proposed algorithm is tested with two publically available dataset, PH2 and images of ISBI2016 challenge. Out of the six evaluation parameters, the proposed method shows the best values for specificity, accuracy, Hammuode distance and XOR. This confirms the merit of the proposal with respect to existing popular methods.

A Novel Selective Encryption Method Based on Skin Lesion Detection

Due to the semitrusted cloud, privacy protection of medical images in medical imaging clouds has become a precondition. For the privacy of patients and the security of medical images in the cloud, this paper proposes a selective encryption based on DNA sequence and chaotic maps for skin lesion image. Initially, we design a transition region-based level set evolution functional which is merged into a variational level set expression with two extra energy functionals, to segment skin lesion image. Once skin lesion detection has been performed, the detected skin lesion pixels are encrypted by employing chaotic systems and DNA sequences. We apply 2D-LASM and 1D-LSS to produce the pseudorandom sequences and use the hash function of the plaintext image to calculate the secret keys of the encryption system. Results demonstrate that the proposed segmentation method is particularly suitable for the detection of skin lesion images with strong noise and complex background. Meanwhile, security analysis also reveals that this selective encryption has a large security key space and high sensitivity to the plaintext image and the secret key.

Directional Vector-Based Skin Lesion Segmentation — A Novel Approach to Skin Segmentation

Efficient skin lesion segmentation algorithms are required for computer aided diagnosis of skin cancer. Several algorithms were proposed for skin lesion segmentation. The existing algorithms are short of achieving ideal performance. In this paper, a novel semi-automatic segmentation algorithm is proposed. The fare concept of the proposed is 8-directional search based on threshold for lesion pixel, starting from a user provided seed point. The proposed approach is tested on 200 images from PH2 and 900 images from ISBI 2016 datasets. In comparison to a chosen set of algorithms, the proposed approach gives high accuracy and specificity values. A significant advantage of the proposed method is the ability to deal with discontinuities in the lesion.

A discrete polar Stockwell transform for enhanced characterization of tissue structure using MRI.

The purpose of this study was to present an effective algorithm for computing the discrete polar Stockwell transform (PST), investigate its unique multiscale and multi-orientation features, and explore potentially new applications including denoising and tissue segmentation. We investigated PST responses using both synthetic and MR images. Moreover, we compared the features of PST with both Gabor and Morlet wavelet transforms, and compared the PST with two wavelet approaches for denoising using MRI. Using a synthetic image, we also tested the edge effect of PST through signal-padding. Then, we constructed a partially supervised classifier using radial, marginal PST spectra of T2-weighted MRI, acquired from postmortem brains with multiple sclerosis. The classification involved three histology-verified tissue types: normal appearing white matter (NAWM), lesion, or other, along with 5-fold cross-validation. The PST generated a series of images with varying orientations or rotation-invariant scales. Radial frequencies highlighted image structures of different size, and angular frequencies enhanced structures by orientation. Signal-padding helped suppress boundary artifacts but required attention to incidental artifacts. In comparison, the Gabor transform produced more redundant images and the wavelet spectra appeared less spatially smooth than the PST. In addition, the PST demonstrated lower root-mean-square errors than other transforms in denoising and achieved a 93% accuracy for NAWM pixels (296/317), and 88% accuracy for lesion pixels (165/188) in MRI segmentation. The PST is a unique local spectral density-assessing tool which is sensitive to both structure orientations and scales. This may facilitate multiple new applications including advanced characterization of tissue structure in standard MRI.

Plant disease leaf image segmentation based on superpixel clustering and EM algorithm

Plant disease leaf image segmentation plays an important role in the plant disease detection through leaf symptoms. A novel segmentation method of plant disease leaf image is proposed based on a hybrid clustering. The whole color leaf image is firstly divided into a number of compact and nearly uniform superpixels by superpixel clustering, which can provide useful clustering cues to guide image segmentation to accelerate the convergence speed of the expectation maximization (EM) algorithm, and then, the lesion pixels are quickly and accurately segmented from each superpixel by EM algorithm. The experimental results and the comparison results with similar approaches demonstrate that the proposed method is effective and has high practical value for plant disease detection.

Segmentation of acne lesion using fuzzy C-means technique with intelligent selection of the desired cluster.

Segmentation is the basic and important step for digital image analysis and understanding. Segmentation of acne lesions in the visual spectrum of light is very challenging due to factors such as varying skin tones due to ethnicity, camera calibration and the lighting conditions. In this approach the color image is transformed into various color spaces. The image is decomposed into the specified number of homogeneous regions based on the similarity of color using fuzzy C-means clustering technique. Features are extracted for each cluster and average values of these features are calculated. A new objective function is defined that selects the cluster holding the lesion pixels based on the average value of cluster features. In this study segmentation results are generated in four color spaces (RGB, rgb, YIQ, I1I2I3) and two individual color components (I3, Q). The number of clusters is varied from 2 to 6. The experiment was carried out on fifty images of acne patients. The performance of the proposed technique is measured in terms of the three mostly used metrics; sensitivity, specificity, and accuracy. Best results were obtained for Q and I3 color components of YIQ and I1I2I3 color spaces with the number of clusters equal to three. These color components show robustness against non-uniform illumination and maximize the gap between the lesion and skin color.

A perceptually oriented method for contrast enhancement and segmentation of dermoscopy images

Dermoscopy images often suffer from low contrast caused by different light conditions, which reduces the accuracy of lesion border detection. Accordingly for lesion recognition, automatic melanoma border detection (MBD) is an initial as well as crucial task. In this article, a novel perceptually oriented approach for MBD is presented by combing region and edge-based segmentation techniques. The MBD system for color contrast and segmentation improvement consists of four main steps: first, the RGB dermoscopy image is transformed to CIE L*a*b* color space, lesion contrast is then enhanced by adjusting and mapping the intensity values of the lesion pixels in the specified range using the three channels of CIE L*a*b*, a hill-climbing algorithm is used later to detect region-of-interest (ROI) map in a perceptually oriented color space using color channels (L*,a*,b*) and finally, an adaptive thresholding is applied to determine the optimal lesion border. Manually drawn borders obtained from an experienced dermatologist are utilized as a ground truth for performance evaluation. The proposed MBD method is tested on a total of 100 dermoscopy images. A comparative study with three state-of-the-art color and texture-based segmentation techniques (JSeg, dermatologists-like tumor area extraction: DTEA and region-based active contours: RAC), is also conducted to show the effectiveness of our MBD method using measures of true positive rate (TPR), false positive rate (FPR), and error probability (EP). Among different algorithms, our MBD algorithm achieved TPR of 94.25%, FPR of 3.56%, and EP of 4%. The proposed MBD approach is highly accurate to detect the lesion border area. The MBD software and sample of dermoscopy images can be downloaded at http://cs.ntu.edu.pk/research.php.

Quantitative Assessment of Lesion Detection Accuracy, Resolution, and Reconstruction Algorithms in Neutron Stimulated Emission Computed Tomography

We present a quantitative analysis of the image quality obtained using filtered back-projection (FBP) with Ram-Lak filtering and maximum likelihood-expectation maximization (ML-EM)-with no post-reconstruction filtering in either case-in neutron stimulated emission computed tomography (NSECT) imaging using Monte Carlo simulations in the context of clinically relevant models of liver iron overload. The ratios of pixel intensities for several regions of interest and lesion shape detection using an active-contours segmentation algorithm are assessed for accuracy across different scanning configurations and reconstruction algorithms. The modulation transfer functions (MTFs) are also computed for the cases under study and are applied to determine a minimum detectable lesion spacing as a form of sensitivity analysis. The accuracy of NSECT imaging in measuring relative tissue concentration is presented for simulated clinical liver cases. When using the 15th iteration, ML-EM provides at least 25% better resolution than FBP and proves to be highly robust under low-signal high-noise conditions prevalent in NSECT. However, FBP gives more accurate lesion pixel intensity ratios and size estimates in some cases; due to advantages provided by both reconstruction algorithms, it is worth exploring the development of an algorithm that is a hybrid of the two. We also show that NSECT imaging can be used to accurately detect 3-cm lesions in backgrounds that are a significant fraction (one-quarter) of the concentration of the lesion, down to a 4-cm spacing between lesions.