Concerns about public health have been heightened by the rapid spread of monkeypox to more than 90 countries. To contain the spread, AI assisted diagnosis system can play an important role. In this study, different deep CNN models with multiple machine learning classifiers are investigated for monkeypox disease diagnosis using skin images. For this, bottleneck features of three CNN models i.e. AlexNet, GoogleNet and Vgg16Net are exploited with multiple machine learning classifiers such as SVM, KNN, Naïve Bayes, Decision Tree and Random Forest. Results shows that with Vgg16Net features, Naïve Bayes classifier gives highest accuracy of 91.11%.

In the medical field, due to their economic and clinical benefits, there is a growing interest in minimally invasive surgeries and microscopic surgeries. These types of surgeries are often recorded during operations, and these recordings have become a key resource for education, patient disease analysis, surgical error analysis, and surgical skill assessment. However, manual searching in this collection of long-term surgical videos is an extremely labor-intensive and long-term task, requiring an effective content-based video analysis system. In this regard, previous methods for surgical video retrieval are based on handcrafted features which do not represent the video effectively. On the other hand, deep learning-based solutions were found to be effective in both surgical image and video analysis, where CNN-, LSTM- and CNN-LSTM-based methods were proposed in most surgical video analysis tasks. In this paper, we propose a hybrid spatiotemporal embedding method to enhance spatiotemporal representations using an adaptive fusion layer on top of the LSTM and temporal causal convolutional modules. To learn surgical video representations, we propose exploring the supervised contrastive learning approach to leverage label information in addition to augmented versions. By validating our approach to a video retrieval task on two datasets, Surgical Actions 160 and Cataract-101, we significantly improve on previous results in terms of mean average precision, 30.012 ± 1.778 vs. 22.54 ± 1.557 for Surgical Actions 160 and 81.134 ± 1.28 vs. 33.18 ± 1.311 for Cataract-101. We also validate the proposed method’s suitability for surgical phase recognition task using the benchmark Cholec80 surgical dataset, where our approach outperforms (with 90.2% accuracy) the state of the art.

Content based image retrieval (CBIR) is the problem of retrieving similar images from a database to a given query by use of its visual information only. It has been a hot topic for years. Current CBIR methods rely on the fact that the database consists of large inter-class variance but in real scenario a user for example wants to retrieve same sub-category images to the query, in that case inter-class variance is quite small. Retrieving similar images from database of small inter-class variance is quite difficult from that of large inter-class variance. Convolutional neural networks (CNN) has shown tremendous results in image tasks such as classification, detection, retrieval, segmentation and more. In this paper we proposed a framework for content based fine-grained image retrieval (CB-FGIR) by using CNN. Oxford flower-17 dataset is used to test the proposed framework. Five splits of the dataset is used to evaluate the CB-FGIR framework and achieves superior retrieval results than other handcrafted and state of art methods Keywords— CNN, Retrieval, CB-FGIR, Deep learning.

Videos are recorded and uploaded daily to the sites like YouTube, Facebook etc. from devices such as mobile phones and digital cameras with less or without metadata (semantic tags) associated with it. This makes extremely difficult to retrieve similar videos based on this metadata without using content based semantic search. Content based video retrieval is problem of retrieving most similar videos to a given query video and has wide range of applications such as video browsing, content filtering, video indexing, etc. Traditional video level features based on key frame level hand engineered features which does not exploit rich dynamics present in the video. In this paper we propose a fast content based video retrieval framework using compact spatio-temporal features learned by deep learning. Specifically, deep CNN along with LSTM is deploy to learn spatio-temporal representations of video. For fast retrieval, binary code is generated by hashing learning component in the framework. For fast and effective learning of hash code proposed framework is trained in two stages. First stage learns the video dynamics and in second stage compact code is learn using learned video’s temporal variation from the first stage. UCF101 dataset is used to test the proposed method and results compared by other hashing methods. Results show that our approach is able to improve the performance over existing methods.

Medicine has seen a rapid increase in the number of minimally invasive surgeries that benefit patients in various ways due to economic and clinical factors. In most hospitals such surgeries are often recorded and stored. The use of these recordings includes many potential applications like for medical education, patient disease analysis, surgical error analysis and skill assessment, etc. However, manual search in this database of long-term videos is exceptionally laborious and time-consuming. Therefore, there is a critical need for an efficient and effective content-based video search system for surgical videos. On the other hand, recent progress in deep learning showed the convolutional neural network (CNN) as an effective feature representation learning model. In this paper, we exploit the multiple CNNs for feature representation and proposed a multi feature fusion based approach for Content based Surgical Video Retrieval. To validate our approach we choose Surgical Actions 160 dataset, where the results demonstrate the effectiveness of feature fusion and outperforms the other state-of-the-arts.