Background: Numerous studies have attempted to apply artificial intelligence (AI) in the dermatological field, mainly on the classification and segmentation of various dermatoses. However, researches under real clinical settings are scarce.Objectives: This study was aimed to construct a novel framework based on deep learning trained by a dataset that represented the real clinical environment in a tertiary class hospital in China, for better adaptation of the AI application in clinical practice among Asian patients.Methods: Our dataset was composed of 13,603 dermatologist-labeled dermoscopic images, containing 14 categories of diseases, namely lichen planus (LP), rosacea (Rosa), viral warts (VW), acne vulgaris (AV), keloid and hypertrophic scar (KAHS), eczema and dermatitis (EAD), dermatofibroma (DF), seborrheic dermatitis (SD), seborrheic keratosis (SK), melanocytic nevus (MN), hemangioma (Hem), psoriasis (Pso), port wine stain (PWS), and basal cell carcinoma (BCC). In this study, we applied Google's EfficientNet-b4 with pre-trained weights on ImageNet as the backbone of our CNN architecture. The final fully-connected classification layer was replaced with 14 output neurons. We added seven auxiliary classifiers to each of the intermediate layer groups. The modified model was retrained with our dataset and implemented using Pytorch. We constructed saliency maps to visualize our network's attention area of input images for its prediction. To explore the visual characteristics of different clinical classes, we also examined the internal image features learned by the proposed framework using t-SNE (t-distributed Stochastic Neighbor Embedding).Results: Test results showed that the proposed framework achieved a high level of classification performance with an overall accuracy of 0.948, a sensitivity of 0.934 and a specificity of 0.950. We also compared the performance of our algorithm with three most widely used CNN models which showed our model outperformed existing models with the highest area under curve (AUC) of 0.985. We further compared this model with 280 board-certificated dermatologists, and results showed a comparable performance level in an 8-class diagnostic task.Conclusions: The proposed framework retrained by the dataset that represented the real clinical environment in our department could accurately classify most common dermatoses that we encountered during outpatient practice including infectious and inflammatory dermatoses, benign and malignant cutaneous tumors.

No abstract

In this paper, we explore the spectrum inference to achieve the spectrum occupancy in advance through analyzing the historical spectrum. We have conceived an offline-online cooperative framework. Specifically, the hyperparameters can be achieved on an offline way, which will be used for online prediction. Moreover, based on the accuracy of online spectrum inference, the hyperparameters can be further optimized relying on specifically designed grid search and K-fold cross-validation combined method in an iterative manner. We present a long short-term memory (LSTM) aided spectrum occupancy prediction method, relying on adaptive threshold quantization aided data preprocessing (ATQ-DP). To be specific, first, the captured spectrum data may be quantized by the adaptive thresholds in order to lesson the influence of noise imposed on them, where the thresholds are obtained by kernel density estimation (KDE) method. Then, LSTM will be activated to perform spectrum prediction based on the quantized data, thus, future spectrum occupancy can be inferred in advance. Additionally, performance evaluations show that the accuracy of spectrum inference is always better than that of the LSTM aided spectrum inference relying on the traditional fixed threshold quantization aided data preprocessing (FTQ-DP), where the FTQ-DP is used for comparison purposes.INDEX TERMS Adaptive threshold quantization, spectrum prediction, long short-term memory (LSTM).

No abstract

No abstract