Automated Detection of Laryngeal Carcinoma in Laryngoscopic Images from a Multicenter Database using a Convolutional Neural Network

OBJECTIVE Little is known about the efficacy of using artificial intelligence to identify laryngeal carcinoma from images of vocal lesions taken in different hospitals with multiple laryngoscope systems. This multicenter study was aimed to establish an artificial intelligence system and provide a reliable auxiliary tool to screen for laryngeal carcinoma. Study Design: Multicentre case-control study Setting: Six tertiary care centers Participants: The laryngoscopy images were collected from 2179 patients with vocal lesions. Outcome Measures: An automatic detection system of laryngeal carcinoma was established based on Faster R-CNN, which was used to distinguish vocal malignant and benign lesions in 2179 laryngoscopy images acquired from 6 hospitals with 5 types of laryngoscopy systems. Pathology was the gold standard to identify malignant and benign vocal lesions. Results: Among 89 cases of the malignant group, the classifier was able to evaluate the laryngeal carcinoma in 66 patients (74.16%, sensitivity), while the classifier was able to assess the benign laryngeal lesion in 503 cases among 640 cases of the benign group (78.59%, specificity). Furthermore, the CNN-based classifier achieved an overall accuracy of 78.05% with a 95.63% negative prediction for the testing dataset. Conclusion: This automatic diagnostic system has the potential to assist clinical laryngeal carcinoma diagnosis, which may improve and standardize the diagnostic capacity of endoscopists using different laryngoscopes.

Automatic Detection of Osteosarcoma Based on Integrated Features and Feature Selection Using Binary Arithmetic Optimization Algorithm

Osteosarcoma is one of the most common malignant bone tumor mostly found in children and teenagers. Manual detection of osteosarcoma requires expertise and is a labour-intensive process. If detected on time, the mortality rate can be reduced. With the advent of new technologies, automatic detection systems are used to analyse and classify images obtained from different sources. Here, we propose an automatic detection system Integrated Features-Feature Selection Model for Classification (IF-FSM-C) that detect osteosarcoma from the high-resolution whole slide images (WSIs). The novelty of the proposed approach is the use of integrated features obtained by fusion of features extracted using traditional handcrafted feature extraction techniques and deep learning models. It is quite possible that the integrated features may contain some redundant and irrelevant features which may unnecessarily increases the computation time and leads to wastage of resources. To avoid this, we perform feature selection (FS) before giving the integrated features to the classifier. To perform feature selection, we propose two binary variants of recently proposed Arithmetic Optimization Algorithm (AOA) known as BAOA-S and BAOA-V. The selected features are given to a classifier that classifies the WSIs into Viable tumor (VT), Non-viable tumor (NVT) and non-tumor (NT). Experiments are performed and the results prove the superiority of the proposed IF-FSM-C that uses integrated features and feature selection in classifying WSIs as compared to the classifiers which use handcrafted or deep learning features alone as well as state-of-the-art methods for osteosarcoma detection.

Estrus Detection Methods in Dairy Animals- Advances and the Prospects: A Review

Fertility over the past few decades is of serious concern in the dairy industry. Fertility of a dairy herd is determined by composite factors, which in turn depends upon effective management strategies. The reproductive potential of the animals need to be exploited to its maximum to achieve optimum production in a herd. The single most important factor that limits the establishment of pregnancy and survival of the embryo in dairy cattle and buffaloes and thereby reproductive efficiency of a herd is proper estrus detection, Pedometer or activity meter is a motion switches devices within which steps followed by animals are recorded. Activity meters can be attached to the neck or leg of cows and they may be read by a receiver and processed by computer in a milking parlour. By implementing automatic detection system, heat detection rates can be improved, for improving reproductive efficiency. The activity monitoring techniques can also be used to detect the silent ovulation which is helpful for improving efficiency and accuracy of estrus.

Application of deep learning in automatic detection of technical and tactical indicators of table tennis

A DCNN-LSTM (Deep Convolutional Neural Network-Long Short Term Memory) model is proposed to recognize and track table tennis’s real-time trajectory in complex environments, aiming to help the audiences understand competition details and provide a reference for training enthusiasts using computers. Real-time motion features are extracted via deep reinforcement networks. DCNN tracks the recognized objects, and the LSTM algorithm predicts the ball’s trajectory. The model is tested on a self-built video dataset and existing systems and compared with other algorithms to verify its effectiveness. Finally, an overall tactical detection system is built to measure ball rotation and predict ball trajectory. Results demonstrate that in feature extraction, the Deep Deterministic Policy Gradient (DDPG) algorithm has the best performance, with a maximum accuracy rate of 89% and a minimum mean square error of 0.2475. The accuracy of target tracking effect and trajectory prediction is as high as 90%. Compared with traditional methods, the performance of the DCNN-LSTM model based on deep learning is improved by 23.17%. The implemented automatic detection system of table tennis tactical indicators can deal with the problems of table tennis tracking and rotation measurement. It can provide a theoretical foundation and practical value for related research in real-time dynamic detection of balls.