Search

Content-based image retrieval (CBIR) systems are designed to retrieve images that are relevant, based on detailed analysis of latent image characteristics, thus eliminating the dependency of natural language tags, text descriptions, or keywords associated with the images. A CBIR system maintains high-level image visuals in the form of feature vectors, which the retrieval engine leverages for similarity-based matching and ranking for a given query image. In this paper, a CBIR system is proposed for the retrieval of medical images (CBMIR) for enabling the early detection and classification of lung diseases based on lung X-ray images. The proposed CBMIR system is built on the predictive power of deep neural models for the identification and classification of disease-specific features using transfer learning based models trained on standard COVID-19 Chest X-ray image datasets. Experimental evaluation on the standard dataset revealed that the proposed approach achieved an improvement of 49.71% in terms of precision, averaging across various distance metrics. Also, an improvement of 26.55% was observed in the area under precision-recall curve (AUPRC) values across all subclasses.

Chronic Ocular Diseases (COD) such as myopia, diabetic retinopathy, age-related macular degeneration, glaucoma, and cataract can affect the eye and may even lead to severe vision impairment or blindness. According to a recent World Health Organization (WHO) report on vision, at least 2.2 billion individuals worldwide suffer from vision impairment. Often, overt signs indicative of COD do not manifest until the disease has progressed to an advanced stage. However, if COD is detected early, vision impairment can be avoided by early intervention and cost-effective treatment. Ophthalmologists are trained to detect COD by examining certain minute changes in the retina, such as microaneurysms, macular edema, hemorrhages, and alterations in the blood vessels. The range of eye conditions is diverse, and each of these conditions requires a unique patient-specific treatment. Convolutional neural networks (CNNs) have demonstrated significant potential in multi-disciplinary fields, including the detection of a variety of eye diseases. In this study, we combined several preprocessing approaches with convolutional neural networks to accurately detect COD in eye fundus images. To the best of our knowledge, this is the first work that provides a qualitative analysis of preprocessing approaches for COD classification using CNN models. Experimental results demonstrate that CNNs trained on the region of interest segmented images outperform the models trained on the original input images by a substantial margin. Additionally, an ensemble of three preprocessing techniques outperformed other state-of-the-art approaches by 30% and 3%, in terms of Kappa and F1 scores, respectively. The developed prototype has been extensively tested and can be evaluated on more comprehensive COD datasets for deployment in the clinical setup.

Effective code assignment for patient clinical records in a hospital plays a significant role in the process of standardizing medical records, mainly for streamlining clinical care delivery, billing, and managing insurance claims. The current practice employed is manual coding, usually carried out by trained medical coders, making the process subjective, error-prone, inexact, and time-consuming. To alleviate this cost-intensive process, intelligent coding systems built on patients' structured electronic medical records are critical. Classification of medical diagnostic codes, like ICD-10, is widely employed to categorize patients' clinical conditions and associated diagnoses. In this work, we present a neural model $\mathcal{LAJA}$ , built on Label Attention Transformer Architectures for automatic assignment of ICD-10 codes. Our work is benchmarked on the CodiEsp dataset, a dataset for automatic clinical coding systems for multilingual medical documents, used in the eHealth CLEF 2020-Multilingual Information Extraction Shared Task. The experimental results reveal that the proposed $\mathcal{LAJA}$ variants outperform their basic BERT counterparts by 33-49% in terms of standard metrics like precision, recall, F1-score and mean average precision. The label attention mechanism also enables direct extraction of textual evidence in medical documents that map to the clinical ICD-10 diagnostic codes.

Sketch-based Image Retrieval (SBIR) is an approach where natural images are retrieved according to the given input sketch query. SBIR has many applications, for example, searching for a product given the sketch pattern in digital catalogs, searching for missing people given their prominent features from a digital people photo repository etc. The main challenge involved in implementing such a system is the absence of semantic information in the sketch query. In this work, we propose a combination of image prepossessing and deep learning-based methods to tackle this issue. A binary image highlighting the edges in the natural image is obtained using Canny-Edge detection algorithm. The deep features were extracted by an ImageNet based CNN model. Cosine similarity and Euclidean distance measures are adopted to generate the rank list of candidate natural images. Relevance feedback using Rocchio’s method is used to adapt the query of sketch images and feature weights according to relevant images and non-relevant images. During the experimental evaluation, the proposed approach achieved a Mean average precision (MAP) of 71.84%, promising performance in retrieving relevant images for the input query sketch images.

In modern healthcare practices, diagnosis and treatment for certain complex illnesses require specific information on the patients' background, genealogy, heredity, demographic data etc. Even with a similar diagnosis, treatments may need to designed specifically to adapt well to the patients' genetic, cultural, and lifestyle aspects. Precision medicine mainly deals with enabling personalized care based on a given patient's conditions in a scientifically rigorous way. Because this entails recommending personalized therapies to patients and has the potential to affect the health of other people, the performance of a designed system must be accurate and exact. In this paper, a precision information retrieval system is proposed that leverages structured and unstructured data to retrieve relevant knowledge for enabling personalized recommendations. The proposed pipeline is validated with the clinical trial dataset of the Precision medicine track of TREC 2017. A set of relevant ranked clinical trials for a given condition/disease that could not be cured using any of the traditional treatments suggested are retrieved using structured and unstructured patient data. We employ multiple IR techniques like Best Match 25, query reformulation and re-ranking facilitated through deep neural networks, focusing on extracting highly accurate and relevant trials. The proposed pipeline achieved a high score of 0.58 in terms of Normalized Discounted Cumulative Gain (NDCG) score for ranking the relevant clinical trials, outperforming the state-of-the-art approaches.

Knee Osteoarthritis (OA) is a medical condition affecting the knee joint that causes pain due to the cartilage wear-and-tear. The severity of the impairment is graded by experienced radiologists as per standardized grading systems like the Kellgren–Lawrence(KL) grading scheme. Early detection and classification of knee OA in a patient before it increases in severity can significantly aid in corrective measures and benefit humankind. In this work, we propose a DL model to automatically segment the knee region and predict onset of Knee OA with X-ray scans. A comparative study using an ensemble model consisting of a YOLOv5 object detection algorithm for knee joint segmentation is also proposed. Various classification models such as VGG16, Resnet etc., are experimented with for the KL grade classification. The detailed experiments are conducted to understand the need for the region of interest segmentation step in KL grade classification. The proposed Clinical Decision Support System (CDSS) can help the medical practitioners perform preemptive screening based on X-ray scans for detecting onset earlier and for enabling required treatment.

COVID-19 has been designated as a once-in-a-century pandemic, and its impact is still being felt severely in many countries, due to the extensive human and green casualties. While several vaccines are under various stage of development, effective screening procedures that help detect the disease at early stages in a non-invasive and resource-optimized manner are the need of the hour. X-ray imaging is fairly accessible in most healthcare institutions and can prove useful in diagnosing this respiratory disease. Although a chest X-ray scan is a viable method to detect the presence of this disease, the scans must be analyzed by trained experts accurately and quickly if large numbers of tests are to be processed. In this paper, a benchmarking study of different preprocessing techniques and state-of-the-art deep learning models is presented to provide comprehensive insights into both the objective and subjective evaluation of their performance. To analyze and prevent possible sources of bias, we preprocessed the dataset in two ways - first, we segmented the lungs alone, and secondly, we formed a bounding box around the lung and used only this area to train. Among the models chosen to benchmark, which were DenseNet201, EfficientNetB7, and VGG-16, DenseNet201 performed better for all three datasets.

The COVID-19 pandemic has affected the world on a global scale, infecting nearly 68 million people across the world, with over 1 5 million fatalities as of December 2020 A cost-effective early-screening strategy is crucial to prevent new outbreaks and to curtail the rapid spread Chest X-ray images have been widely used to diagnose various lung conditions such as pneumonia, emphysema, broken ribs and cancer In this work, we explore the utility of chest X-ray images and available expert-written diagnosis reports, for training neural network models to learn disease representations for diagnosis of COVID-19 A manually curated dataset consisting of 450 chest X-rays of COVID-19 patients and 2,000 non-COVID cases, along with their diagnosis reports were collected from reputed online sources Convolutional neural network models were trained on this multimodal dataset, for prediction of COVID-19 induced pneumonia A comprehensive clinical decision support system powered by ensemble deep learning models (CADNN) is designed and deployed on the web The system also provides a relevance feedback mechanism through which it learns multimodal COVID-19 representations for supporting clinical decisions Copyright © 2021 by SCITEPRESS – Science and Technology Publications, Lda All rights reserved

Diabetic retinopathy (DR), a chronic disease in which the retina is damaged due to small vessel damage caused by diabetes mellitus, is one of the leading causes of vision impairment in diabetic patients. Detection of the earliest clinical sign of the advent of DR is a critical requirement for intervention and effective treatment. Ophthalmologists are trained to identify DR, based on examining specific minute changes in the eye - microaneurysms, retinal haemorrhages, macular edema and changes in the retinal blood vessels. Segmentation of microaneurysms (MA) is a critical requirement for the early diagnosis of DR and has been the primary focus of the research community over the past few years. In this work, a systematic review of existing literature is carried out to examine the diagnostic use of automated MA detection and segmentation for early DR diagnosis. We mainly focus on existing early DR diagnosis techniques to understand their strengths and weaknesses. Though early diagnosis is performed using colour fundus photography, fluorescein angiography or optical coherence tomography angiography images, our study is limited to colour fundus based techniques. The early DR diagnosis methodologies reviewed in this article can be broadly classified into classical image processing, conventional machine learning (ML), and deep learning (DL) based techniques. Though significant progress has been achieved in these three classes of early DR diagnosis, several challenges and gaps still exist, underscoring a considerable scope for the development of fully automated, user-friendly early DR diagnosis and grading systems. We discuss in detail the challenges that need to be addressed in designing such effective, efficient, and robust algorithms for early DR diagnosis systems and also the ample scope for future research in this area.

Microbial keratitis is an infection of the cornea of the eye that is commonly caused by prolonged contact lens wear, corneal trauma, pre-existing systemic disorders and other ocular surface disorders. It can result in severe visual impairment if improperly managed. According to the latest World Vision Report, at least 4.2 million people worldwide suffer from corneal opacities caused by infectious agents such as fungi, bacteria, protozoa and viruses. In patients with fungal keratitis (FK), often overt symptoms are not evident, until an advanced stage. Furthermore, it has been reported that clear discrimination between bacterial keratitis and FK is a challenging process even for trained corneal experts and is often misdiagnosed in more than 30% of the cases. However, if diagnosed early, vision impairment can be prevented through early cost-effective interventions. In this work, we propose a multi-scale convolutional neural network (MS-CNN) for accurate segmentation of the corneal region to enable early FK diagnosis. The proposed approach consists of a deep neural pipeline for corneal region segmentation followed by a ResNeXt model to differentiate between FK and non-FK classes. The model trained on the segmented images in the region of interest, achieved a diagnostic accuracy of 88.96%. The features learnt by the model emphasize that it can correctly identify dominant corneal lesions for detecting FK.

Face depicts a wide range of information about identity, age, sex, race as well as emotional and mental state. Facial expressions play crucial role in social interactions and commonly used in the behavioral interpretation of emotions. Automatic facial expression recognition is one of the interesting and challenging problem in computer vision due to its potential applications such as Human Computer Interaction(HCI), behavioral science, video games etc. In this paper, a novel method for automatically recognizing facial expressions using Deep Convolutional Neural Network(DCNN) features is proposed. The proposed model focuses on recognizing the facial expressions of an individual from a single image. The feature extraction time is significantly reduced due to the usage of general purpose graphic processing unit (GPGPU). From an evaluation on two publicly available facial expression datasets, we have found that using DCNN features, we can achieve the state-of-the-art recognition rate.

Modern graphics processors provide high processing power, and furthermore, frameworks like CUDA increase their usability as high-performance co-processors for general-purpose computing. The Graphical Processing Units (GPUs) can be easily programmed using CUDA. This paper presents an efficient parallel implementation of CPU scheduling algorithms on modern The Graphical Processing Units (GPUs). The proposed method achieves high speed by efficiently exploiting the data parallelism computing of the The Graphical Processing Units (GPUs).

Many a times violating traffic rules leads to accidents. Many countries have adopted systems involving surveillance cameras at accident zones. Monitoring each frame to detect the violators is unrealistic. Automation of this process is highly desirable for reliable and robust monitoring of traffic rules violations. With deep learning techniques on GPU, the violation detection can be automated and performed in real time on surveillance video. This paper proposes a novel technique to summarize the traffic surveillance videos that uses Faster Regions with Convolutions Neural Networks(R-CNN) to automatically detect violators. As the proof of concept, an attempt is made to implement the proposed method to detect the two-wheeler riders without helmet. Long duration videos can be summarized into very short video that includes details about only rules violators.

Visual cryptography scheme (VCS), is a cryptography technique where visual information is encrypted in such a way that decryption can be fulfilled with human visual system by direct stacking of the encrypted shares. Rotation visual cryptography is advanced technique of VCS where direct stacking of shares will not uphold the original image. In the existing literature, encryption techniques of VCS take longer time that can be substantially reduced by using CUDA. The proposed method uses CUDA for computationally intensive independent tasks performed on pixels during the rotation VCS. Parallel implementation of VCS will be faster and can be adopted in many real time applications that requires image security. Results show that the proposed method is 40-50 times faster than the existing encryption techniques.