Melanoma identification and classification model based on fine-tuned convolutional neural network.

Background: Breakthroughs in skin cancer diagnostics have resulted from recent image recognition and Artificial Intelligence (AI) technology advancements. There has been growing recognition that skin cancer can be lethal to humans. For instance, melanoma is the most unpredictable and terrible form of skin cancer. Materials and Methodology: This paper aims to support Internet of Medical Things (IoMT) applications by developing a robust image classification model for the early detection of melanoma, a deadly skin cancer. It presents a novel approach to melanoma detection using a Convolutional Neural Network (CNN)-based method that employs image classification techniques based on Deep Learning (DL). We analyze dermatoscopic images from publicly available datasets, including DermIS, DermQuest, DermIS&Quest, and ISIC2019. Our model applies convolutional and pooling layers to extract meaningful features, followed by fully connected layers for classification. Results: The proposed CNN model achieves high accuracy demonstrates the model's effectiveness in distinguishing between malignant and benign skin lesions. We developed deep features and used transfer learning to improve the categorization accuracy of medical images. Soft-max classification layer and support vector machine have been used to assess the classification performance of deep features. The proposed model's efficacy is rigorously evaluated using benchmark datasets: DermIS, DermQuest, and ISIC2019, having 621, 1233, and 25000 images, respectively. Its performance is compared to current best practices showing an average of 5% improved detection accuracy in DermIS, 6% improvement in DermQuest, and 0.81% in ISIC2019 datasets. Conclusion: Our study showcases the potential of CNN in melanoma detection, contributing to early diagnosis and improved patient outcomes. The developed model proves its capability to aid dermatologists in accurate decision-making, paving the way for enhanced skin cancer diagnosis.

Discrimination of methicillin-resistant and methicillin-susceptible Staphylococcus aureus using near-infrared spectroscopy based on support vector machine method / 解放军医学杂志

Objective To explore the feasibility of distinguishing between methicillin-resistant S. aureus (MRSA) and methicillin-susceptible Staphylococcus aureus (MSSA) using near-infrared spectroscopy and the Support Vector Machine analysis method. Methods The concentration standard curve of the MRSA and MSSA was prepared. The bacteria were amplified and prepared into the same concentration according to the concentration formula. Near-infrared spectroscopy data of the MRSA and MSSA were collected and pretreated with first derivative, smoothing, normalization and baseline correction. After the pretreatment, the correlation analysis of the two kinds of bacteria was executed. The spectral data of bacteria with the wavelength from 900 to 2200 nm were analyzed by principal components. According to the results of cumulative contribution rate, the first three principal components were extracted and used as the input vector to establish Support Vector Machine models in three classifiers (linear, polynomial and RBF) and then a comparison of the three models was performed. Results The correlation coefficient of the pretreatment spectral curve of MRSA and MSSA was as high as 1.000. The training and test accuracies of the models were all over 95% after using the principal component analysis and Support Vector Machine models in three classifiers (linear, polynomial and RBF). The RBF classifier had the highest accuracy, and the result was 99.72%±0.21% for training accuracy and 99.47%±0.00% for the test accuracy. Conclusion Near-infrared spectroscopy and the Support Vector Machine analysis method has a high ability to discriminate between MSSA and MRSA.

Hierarchical Classification of ECG Beat Using Higher Order Statistics and Hermite Model / 대한의료정보학회지

OBJECTIVE: The heartbeat classification of the electrocardiogram is important in cardiac disease diagnosis. For detecting QRS complex, conventional detection algorithmhave been designed to detect P, QRS, Twave, first. However, the detection of the P and T wave is difficult because their amplitudes are relatively low, and occasionally they are included in noise. Furthermore the conventionalmulticlass classificationmethodmay have skewed results to themajority class, because of unbalanced data distribution. METHODS: The Hermite model of the higher order statistics is good characterization methods for recognizing morphological QRS complex. We applied three morphological feature extraction methods for detecting QRS complex: higher-order statistics, Hermite basis functions andHermitemodel of the higher order statistics.Hierarchical scheme tackle the unbalanced data distribution problem. We also employed a hierarchical classification method using support vector machines. RESULTS:We compared classification methods with feature extraction methods. As a result, our mean values of sensitivity for hierarchical classification method (75.47%, 76.16% and 81.21%) give better performance than the conventionalmulticlass classificationmethod (46.16%). In addition, theHermitemodel of the higher order statistics gave the best results compared to the higher order statistics and the Hermite basis functions in the hierarchical classification method. CONCLUSION: This research suggests that the Hermite model of the higher order statistics is feasible for heartbeat feature extraction. The hierarchical classification is also feasible for heartbeat classification tasks that have the unbalanced data distribution.