Efficient and Low-Cost Skin Cancer Detection System Implementation with a Comparative Study Between Traditional and CNN-Based Models

Communication is the ultimate of man’s search for conveying his ideas, emotions, and concepts. Dance is one of the media of communication through which dancers share notion of feelings, with the spectators through gestures, i.e., mudra. Gesture recognition propagates a concept without verbal speech or listening, and in dance recognition, the notion is transferred through various dance poses and actions. This activity in a way really paves way to enhance Indian Sign Language. This study focuses to solve the mudra resemblance in Bharatanatyam through a new system developed with image processing and classification technique using histogram of oriented gradient (HOG) feature extraction techniques and support vector machine (SVM) classifier. SVM classifies the features of HOG into mudras as text labels. Popular feature vectors such as scale-invariant feature transform (SIFT), speed up robust feature (SURF), and local binary pattern (LBP) are hardened against HOG for accuracy and speediness, and this innovative proposed concept is useful for online dance learners.

Nonmelanoma skin cancer (NMSC) is the most common type of cancer that affects the Caucasian population. Approximately 80% of NMSCs are basal cell carcinoma (BCC) and 20% are squamous cell carcinoma (SCC). Actinic keratosis (AK) is a precancerous lesion that may develop into SCC. A market research survey was conducted in which dermatologists and primary care physicians (PCPs) were randomly selected from seven countries (USA, Australia, UK, Italy, France, Germany and Spain). Their knowledge of nonmelanoma skin cancer and their current clinical practice were assessed. In total, 2100 physicians took part in the survey. They had practised medicine for between 1 and 30 years and saw at least 30 patients in a typical week. The majority of dermatologists (97%) were familiar with BCC and AK, and treated each condition with a minimum of referrals. PCPs were more familiar with BCC (90%) than with AK (74%). Of the PCPs that were aware of BCC, only 31% treated the condition, and of those aware of AK, 40% treated the condition. Surgery was the most common choice of treatment for BCC. The most popular treatment choice for AK lesions was cryotherapy. Eighty to 100% of physicians reported that they discussed skin cancer prevention with their patients. A much lower number of physicians (ranging from 5 to 37%) provided educational material to patients. Overall, PCPs in the two countries that have a high incidence of NMSC (USA and Australia) were more familiar with BCC and AK and more likely to treat each condition than PCPs in Europe. All physicians rated BCC as a more serious condition than AK. Facial lesions were considered more serious than lesions on the head or trunk for both conditions. As the burden of disease and the number of patients seeking treatment for NMSC increase, dermatologists are well placed to lead educational initiatives for PCPs and provide educational material for patients. This would increase awareness of AK and BCC and could improve early diagnosis.

200 Risks and timing of future skin cancers in patients with actinic keratosis

Hardware implementation of human detection is a challenging task for embedded designs. This paper presents a real-time image-based field-programmable gate array (FPGA) implementation of human detection. Our implementation is based on the histograms of oriented gradients (HOG) feature and linear support vector machine (SVM) classifier. The novelty of this work is that we replace normalization process of HOG with a modified binarization process. Therefore, during classification process with SVM classifier, all multiplication operations are replaced by addition operations. All these modifications result in reduction of hardware resource. Experimental evaluation reveals that 293 fps can be achieved on a low-end Xilinx Spartan-3e FPGA. Moreover, a detection accuracy of 1.97% miss rate and 1% false positive rate is achieved. For further demonstration, a prototype system is developed with an OV7670 camera device. Restricted to the speed of camera, a detection rate of 30 fps is achieved.

Non-melanoma skin cancer (NMSC) is generally considered to be a worldwide epidemic. Current estimates predict that between 0.9 and 1.2 million new cases will be diagnosed each year in the United States of America (USA), which is one-third of all cancers diagnosed (1). In Australia, the incidence of NMSC continues to rise and it now affects at least 1% to 2% of the population annually (1, 2). NMSC tends to affect Caucasians particularly in areas exposed to sunlight, such as the head, neck and back of the hands. There is an increased risk with fair skin, blue eyes and a history of repeated sunburns (1). There are two main forms of NMSC, basal cell carcinoma (BCC) and squamous cell carcinoma (SCC), which account for 80% and 16% respectively (1). The majority of BCCs present as two varieties. Nodular BCC (nBCC) appears mostly on the head and neck and accounts for approximately 60% of all BCCs (3). Most of the remainder are superficial BCC (sBCC), which occur on the trunk and extremities (4, 5). Standard treatments for BCCs include excision, curettage and electrodesiccation, and cryosurgery (6). Other forms of treatment such as Mohs micrographic surgery, intralesional interferon (7) and radiotherapy, may be used depending on the nature, site and size of the tumor (6). Actinic keratosis (AK) is considered by some to be the earliest clinically recognizable manifestation of SCC in situ (8, 9). The risk of progression of AK to invasive SCC has been reported as ranging from 0.25 to 20% within 10 – 25 years (8, 10, 11). Sun avoidance measures and sunscreen protection are the first steps in the therapy of AK. The conventional approaches for treating AKs include cryotherapy, electrodesiccation and curettage, excision, CO2 laser therapy, 5-fluorouracil (5-FU), chemical peels and photodynamic therapy (12). Recently, topical immunotherapy in the form of imiquimod 5% cream has demonstrated efficacy for the treatment of BCC and AK. Imiquimod, an immune response modifier, has demonstrated in pre-clinical studies to have both antiviral and antitumor activity in vivo (13). It is currently recommended for the treatment of external genital warts induced by human papillomavirus (14 – 16). This paper reviews the evidence of the safety and efficacy of imiquimod for the treatment of BCC and AK. IMIQUIMOD FOR THE TREATMENT OF BASAL CELL CARCINOMA

This study investigated the effect of a new approach, the support vector machine, as a classifier tool to identify the weeds in corn fields at early growth stage. Image segmentation was done by transforming original color images to gray level images according to the statistical values of red, green, blue components. The Gray Level Co-occurrence Matrix (GLCM) and statistical properties of the histogram from the gray level images were further used to obtain the texture features of the weeds and corn seedlings. These texture features were used in the classification procedure. Principle component analysis was used to select the texture features according to their better contributions to reduce space dimensions. A Support Vector Machine (SVM) classifier was employed to recognize the weeds and the corn seedlings. The results indicated that the SVM classifiers with different feature selections could identify successfully weed-corn with a higher accuracy ranged from 92.31 to 100%. A comparison study of the recognition capabilities of SVM and back-propagation (BP) neural-network classifier using the same data set was conducted. It was found that the SVM classifier provided the best recognition performance with an accuracy of 100%, which exceeded the accuracy of 80% given by the BP classifier. Key words: Corn seedling, weeds, texture, support vector machine, recognize.

Background: A use of conventional 12-lead electrocardiographic (ECG) criteria and machine learning for the ECG parameters to identify the presence of left ventricular hypertrophy (LVH) is estimated 20%-30% in the general population. We developed an ECG system with simple anthropometric data using machine learning to increase the sensitivity in screening for LVH. Methods: In a large sample of 2,196 males, aged 17-45 years, the support vector machine (SVM) classifier with linear kernel is used as the machine learning method for 31 characteristics including age, body height, and body weight in addition to 28 ECG parameters such as axes, intervals and voltages to link the output of LVH. The diagnosis of LVH is based on the echocardiographic criteria for young adult males as 116 g/m 2 (left ventricular mass (LVM)/body surface area) or 49 g/m 2.7 (LVM/body height 2.7 ). The samples are divided into a training/validation set and a test set. By applying the synthetic minority over-sampling technique (SMOTE) in pre-processing of training data, the imbalance in sample size between the Non-LVH and LVH cases can be solved. Results: For the test set with 440 cases, average accuracy, specificity, sensitivity, precision and F 1 score are 76.1%, 75.1%, 92.6%, 19.5% and 32.3%, respectively. The AUCs of ROC and PR curves are 0.871 and 0.272, respectively. To compare with the Cornell and Sokolow-Lyon voltage criteria as shown in Fig.1, all data of the 2,196 young males are also tested in the model. With the specificity of 73.3%, our SVM technique provides much better sensitivity 86.7% compared to 3.3% and 52.7% for the Cornell and Sokolow-Lyon voltage criteria, respectively. The body height and body weight are the most important factors among the 31 features in our SVM model. Conclusions: We provide a novel screening tool using simple anthropometrics and several ECG data to identify LVH in young adults and improves much in sensitivity as compared with the conventional ECG criteria or using machine learning for ECG data alone to identify LVH.

ABSTRACTOil palm trees are important economic crops in tropical areas. Accurate knowledge of the number of oil palm trees in a plantation area is important to predict the yield of palm oil, manage the growing situation of the palm trees and maximise their productivity. In this study, we propose a novel automatic method for detection and enumeration of individual oil palm trees using images from unmanned aerial vehicles (UAVs). This method required three major steps. First, images from UAVs were classified as vegetation or non-vegetation by the support vector machine (SVM) classifier. Second, a feature descriptor based on the histogram of oriented gradient (HOG) was designed for palm trees and used to extract features for machine learning. Finally, a SVM classifier was trained and optimised using the HOG features from positive (i.e., oil palm trees) and negative samples (i.e., objects other than oil palm trees). The trained classifier was then applied to detect individual oil palm trees using adaptive moving windows that allowed it to also return the crown size of each oil palm tree. The method was trained at one site and validated independently at four other sites with different situations. The overall accuracy of palm tree detection was 99.21% at the training site and 99.39%, 99.06%, 99.90% and 94.63% at the four validation sites; the last one was for the most challenging site, in which palm trees were mixed with other trees. These tests confirm the effectiveness of the proposed method. The simplicity and great efficiency of the proposed method allow it to support oil palm tree counting for large areas using imagery from UAVs.

A case study on computer-aided diagnosis of nonerosive reflux disease using deep learning techniques

The medical sciences are facing a major problem with the auto-detection of disease due to the fast growth in population density. Intelligent systems assist medical professionals in early disease detection and also help to provide consistent treatment that reduces the mortality rate. Skin cancer is considered to be the deadliest and most severe kind of cancer. Medical professionals utilize dermoscopy images to make a manual diagnosis of skin cancer. This method is labor-intensive and time-consuming and demands a considerable level of expertise. Automated detection methods are necessary for the early detection of skin cancer. The occurrence of hair and air bubbles in dermoscopic images affects the diagnosis of skin cancer. This research aims to classify eight different types of skin cancer, namely actinic keratosis (AKs), dermatofibroma (DFa), melanoma (MELa), basal cell carcinoma (BCCa), squamous cell carcinoma (SCCa), melanocytic nevus (MNi), vascular lesion (VASn), and benign keratosis (BKs). In this study, we propose SNC_Net, which integrates features derived from dermoscopic images through deep learning (DL) models and handcrafted (HC) feature extraction methods with the aim of improving the performance of the classifier. A convolutional neural network (CNN) is employed for classification. Dermoscopy images from the publicly accessible ISIC 2019 dataset for skin cancer detection is utilized to train and validate the model. The performance of the proposed model is compared with four baseline models, namely EfficientNetB0 (B1), MobileNetV2 (B2), DenseNet-121 (B3), and ResNet-101 (B4), and six state-of-the-art (SOTA) classifiers. With an accuracy of 97.81%, a precision of 98.31%, a recall of 97.89%, and an F1 score of 98.10%, the proposed model outperformed the SOTA classifiers as well as the four baseline models. Moreover, an Ablation study is also performed on the proposed method to validate its performance. The proposed method therefore assists dermatologists and other medical professionals in early skin cancer detection.

Frequent analysis and updating the condition of traffic signs and mile markers are among the most important aspects of a highway asset management system. Today's practices mainly involve manual data collection and analysis, which have to be done for millions of miles of roads and the practice needs to be repeated regularly. While significant progress has been made on improving the data collection practice by leveraging video streams collected from car-mounted cameras, the analysis has primarily remained a manual and labor-intensive process. Automating the analysis from the collected videos is also challenging due to the interclass variability of traffic signs, expected changes in illumination, occlusion, sign position, and orientation. To address these challenges, this paper presents and evaluates the performance of three computer vision algorithms for detection and classification of traffic signs in presence of cluttered backgrounds and static and dynamic occlusions. The task particularly focuses on (1) extracting two-dimensional (2D) candidate windows from already collected video streams that potentially contain traffic signs–without making any prior assumption about their locations; (2) detecting the presence of signs in these 2D candidate windows; and (3) classifying them into warning, regulatory, stop, and yield sign categories based on their shape and color. For validation, a new comprehensive benchmark data set of over 11,000 annotated U.S. traffic sign images with a large range of pose, scale, background, illumination, and occlusion variation is introduced. Experimental results show an average accuracy of 76.20%, 89.31%, and 94.83% for the methods of (1) Haar-like features with Cascade classifiers, (2) histograms of oriented gradients (HOG) with multiple one-versus-all support vector machine (SVM) classifiers, and (3) HOG+C with the SVM classifiers, a variant of the second method with histograms of colors concatenated to HOG. The experimental results demonstrate the potential of leveraging joint representation of texture and color in HOG+C together with SVM discriminative classifiers as a viable solution for creating up-to-date and complete inventories of traffic signs for U.S. roadways.

Human action recognition from 2D videos is a demanding area due to its broad applications. Many methods have been proposed by the researchers for recognizing human actions. The improved accuracy in identifying human actions is desirable. This paper presents an improved method of human action recognition using support vector machine (SVM) classifier. This paper proposes a novel feature descriptor constructed by fusing the various investigated features. The handcrafted features such as scale invariant feature transform (SIFT) features, speed up robust features (SURF), histogram of oriented gradient (HOG) features and local binary pattern (LBP) features are obtained on online 2D action videos. The proposed method is tested on different action datasets having both static and dynamically varying backgrounds. The proposed method achieves shows best recognition rates on both static and dynamically varying backgrounds. The datasets considered for the experimentation are KTH, Weizmann, UCF101, UCF sports actions, MSR action and HMDB51.The performance of the proposed feature fusion model with SVM classifier is compared with the individual features with SVM. The fusion method showed best results. The efficiency of the classifier is also tested by comparing with the other state of the art classifiers such as k-nearest neighbors (KNN), artificial neural network (ANN) and Adaboost classifier. The method achieved an average of 94.41% recognition rate.

To compare the diagnostic imaging ability of three different optical coherence tomography (OCT) devices in non-melanoma skin cancer (NMSC). Thirty actinic keratoses (AKs) and 27 basal cell carcinomas (BCCs) of 29 patients were examined with three different OCT devices, VivoSight® , Callisto® and Skintell® . Complete data sets were available for 16 BCCs and 10 AKs of 18 patients. All OCT devices were able to discriminate BCCs and AKs significantly from perilesional normal skin due to lower signal intensities as well as a thicker stratum corneum and epidermis in AKs. A significant decrease in the signal intensity and thickness of all skin layers was noted with Skintell® in contrast to VivoSight® and Callisto® . OCT comparisons revealed only slight differences between VivoSight® and Callisto® . Regarding BCC tumor thickness VivoSight® and Callisto® correlated well, histology did not correlate with the three OCT devices, whereas Skintell® showed no correlation with VivoSight® , Callisto® or histology. All tested OCT devices could identify BCCs and AKs objectively through standardized measurement of signal intensity and skin layer thickness. Due to their technical specifications (resolution, penetration depth), each of the OCT systems offers additional and special information on NMSC.

A machine learning approach for skin disease detection and classification using image segmentation

In order to improve the performance of Support Vector Machine (SVM) classifier for imbalanced data, this paper proposes dynamic cost-sensitive SVM classifier based on chaos particle swarm optimization (CPDC_SVM). Firstly, this paper introduces dynamic cost-sensitive thought to SVM classifier, and gives the method for structuring dynamic cost and cost-sensitive SVM model. Secondly, we propose the evaluation methodology performance for classifier, and adopts decimal base to code the particles. At last, chaos thought is introduced in particle swarm optimization algorithm, and the Algorithm of the dynamic cost-sensitive SVM classifier is given, which improves convergent speed and accuracy of particle swarm optimization, and can optimize dynamic cost-sensitive SVM well, so CPDC_SVM adds effectively the convergence speed and accuracy for the particle swarm optimization algorithm. Experimental results show CPDC_SVM has higher precision than traditional SVM classifier, and dynamic cost and chaos particle swarm optimization can improve the performance for classifier.