Reliable communication of data in modern wireless systems requires accurate channel state information (CSI). Sounding Reference Signal (SRS) based CSI acquisition enables the estimation of the channel between the base station and user equipment through the uplink transmission of known SRS by the user equipment to the base station. However, limited SRS resources and limited Signal to Noise Ratio (SNR) coverage for which SRS-based CSI acquisition can be performed renders the acquisition of CSI challenging. We propose an approach to perform sparse non-uniform SRS resource allocation and use a masked auto-encoder with a vision transformer backbone to reconstruct full band channel from partial sub-band information. Experiments on data emulating transmission over CDL-A, B, and C channels demonstrate that the proposed method can achieve state-of-the-art normalized mean square error (NMSE) using only 25% of the band information. This translates to a four fold increase in SRS resource capacity and 6dB improvement in SRS coverage under current 5G NR specifications.

Coronary artery disease (CAD) is one of the most common causes of sudden cardiac arrest, accounting for a large percentage of global mortality. A timely diagnosis and detection may save a person's life. The research suggests a methodological framework for non-invasive risk stratification based on information only possible after invasive coronary angiography. Novel clinical, chemical, and molecular cardiac biomarkers were used as input features from an especially collected dataset. Following a thorough evaluative search in the biomarker feature space, the optimum parameters for classifier or regression technique (regressor) were selected using K-fold cross-validation. Ten machine learning (ML) classifiers were employed in classification tasks to determine the number of affected cardiac vessels, the Gensini group, and the severity of CAD with 82.58%, 86.26%, and 90.91% accuracy, respectively. Eleven approaches were used in regression tasks to calculate stenosis percentage and Gensini score, with R-squared values of 0.58 and 0.56, respectively. Following a thorough evaluative search in the biomarkers feature space, the optimum feature and classifier or regressor set were selected using K-fold cross-validation. The biomarkers and classifier or regressor combinations serve as the foundation for the proposed risk stratification framework, incorporating clinical protocol. Finally, our proposed framework is compared to state-of-the-art studies, offering a robust, well-rounded, early detection capable, and novel 'biomarkers-ML combination' approach to risk stratification.

Atrial Fibrillation (AF) with high mortality rate needs to be monitored and detected accurately. AF is indicated as varying pulse-to-pulse intervals in a PPG signal. To record Photoplethysmography (PPG) signal, wrist-watches are used. AF detection is made using features, discriminating AF from Normal Sinus Rhythm (NSR). The presence of Premature Atrial and Ventricular Contraction$(\text{PAC}/\text{PVC})$in subjects due to its randomness may lead to false AF detection. The proposed methodology utilizes Convolutional Neural Network (CNN) on Time-Frequency spectra (TFS) along with signal processing for classification of PPG signal into AF, NSR and$\text{PAC}/\text{PVC}$, The Poincare plot based$\text{PAC}/\text{PVC}$detection implemented in this paper not only separates$\text{PAC}/\text{PVC}$from NSR and AF but also improves the accuracy of AF and NSR detection. The results for training and testing are validated on UMass Simband dataset (Smartwatch PPG Data with AF, NSR, PAC, PVC) and MIMIC III dataset (Finger Tips Pulse Oximetry PPG data with AF, NSR,$\text{PAC}/\text{PVC})$., The experimental results have shown that the proposed system gives higher accuracy, sensitivity and specificity values for both datasets.

Modern vehicles are extremely complex embedded systems that integrate software and hardware from a large set of contributors. Modeling standards like EAST-ADL have shown promising results to reduce complexity and expedite system development. However, such standards are unable to cope with the growing demands of the automotive industry. A typical example of this phenomenon is autonomous vehicle perception (AVP) where deep learning architectures (DLA) are required for computer vision (CV) tasks like real-time object recognition and detection. However, existing modeling standards in the automotive industry are unable to manage such CV tasks at a higher abstraction level. Consequently, system development is currently accomplished through modeling approaches like EAST-ADL while DLA-based CV features for AVP are implemented in isolation at a lower abstraction level. This significantly compromises productivity due to integration challenges. In this article, we introduce MoDLF - A Model-Driven Deep learning Framework to design deep convolutional neural network (DCNN) architectures for AVP tasks. Particularly, Model Driven Architecture (MDA) is leveraged to propose a metamodel along with a conformant graphical modeling workbench to model DCNNs for CV tasks in AVP at a higher abstraction level. Furthermore, Model-To-Text (M2T) transformations are provided to generate executable code for MATLAB® and Python. The framework is validated via two case studies on benchmark datasets for key AVP tasks. The results prove that MoDLF effectively enables model-driven architectural exploration of deep convnets for AVP system development while supporting integration with renowned existing standards like EAST-ADL.

Summary Spinal cord is the one of the most important organs in the central nervous system (CNS). It acts as the main processing hub which serves as the main passage line for information transfer from brain to the rest of the body. It supports the whole skeleton structure along with mobility, bending, turning, twisting and so forth. Several factors may result in the deformity of spine such as a major injury, fracture or a defect by birth. In this research, we have discussed two modules: one is for vertebrae localization and spine segmentation and the second one is for analysis of spine dis‐proportionality. A recent approach of YOLOv5 is used for the localization of vertebrae in combination with Mask RCNN for segmentation of spinal column. The combined results from both these modules are used for feature extraction which supports our classification‐based shape analysis module. The AASCE 2019 challenge dataset is used to evaluate the experimental results and the value of mAP achieved is 0.94 at 0.5 IOU threshold of YOLOv5 model. The proposed technique with novel feature set achieved an average classification accuracy of 94.69%.

Abstract In this research, a novel customized deep learning model is proposed to detect Tuberculosis (TB) from chest X‐rays (CXR). The model is utilized for three experimentations: (i) classification of CXR image as healthy or TB infected, (ii) sub‐classification of infected images to TB specific manifestations, and (iii) classification of CXR image to thoracic disease manifestations. The National Institute of Health (NIH) CXR is used for experimentation. For the first two experimentations, the subset of the dataset is used containing only 10 TB specific manifestations, whereas, the entire NIH CXR dataset is used for the third experiment. The F1 score for binary classification of TB in experiment 1 is calculated as 0.92 which is higher than the average F1 score of the radiologists. The average accuracy for classifying TB specific manifestations in experiment 2 is recorded as 0.84. Finally, the average accuracy of the thoracic disease classification is recorded as 0.82 in experiment 3. The proposed system outperformed the existing approaches reporting higher AUC for each manifestation. Whereas, to the best of knowledge it is the first such attempt on NIH CXR dataset for TB and TB specific manifestation classification and the proposed system showed promising results.

Prostate cancer is the second most aggressive type of cancer among men aged over 45, and it has a major effect on people's lives. Early diagnosis and grading of prostate cancer from tissue images is necessary. Large scale inter observer reproducibility exists in grading the prostate biopsies. This leads us to move towards a computer based model that can accurately detect and grade the cancerous prostate from non-cancerous one. The paper is focused on deep learning based models to automatically grade the prostate cancer from tissue microarray images. Deep learning models directly learn the features via convolutional layers. Two datasets have been used for implementation of our proposed model, Harvard dataset and Gleason Challenge 2019. Our proposed UNET based architecture is used for training as well as validation and testing. We used four different deep learning models, VGG19, ResNet50, Mobilenetv2 and ResNext50 for our UNET based encoder. With our proposed framework, we have achieved 0.728 and 0.732 average Cohen’s kappa with F1 on both datasets respectively. The results show that our proposed UNET based deep learning model shows better performance as compared to other state of the art models.

The identification of retinal lesions plays a vital role in accurately classifying and grading retinopathy. Many researchers have presented studies on optical coherence tomography (OCT) based retinal image analysis over the past. However, to the best of our knowledge, there is no framework yet available that can extract retinal lesions from multi-vendor OCT scans and utilize them for the intuitive severity grading of the human retina. To cater this lack, we propose a deep retinal analysis and grading framework (RAG-FW). RAG-FW is a hybrid convolutional framework that extracts multiple retinal lesions from OCT scans and utilizes them for lesion-influenced grading of retinopathy as per the clinical standards. RAG-FW has been rigorously tested on 43,613 scans from five highly complex publicly available datasets, containing multi-vendor scans, where it achieved the mean intersection-over-union score of 0.8055 for extracting the retinal lesions and the accuracy of 98.70% for the correct severity grading of retinopathy.

Retinal lesions play a vital role in the accurate classification of retinal abnormalities. Many researchers have proposed deep lesion-aware screening systems that analyze and grade the progression of retinopathy. However, to the best of our knowledge, no literature exploits the tendency of these systems to generalize across multiple scanner specifications and multi-modal imagery. Towards this end, this paper presents a detailed evaluation of semantic segmentation, scene parsing and hybrid deep learning systems for extracting the retinal lesions such as intra-retinal fluid, sub-retinal fluid, hard exudates, drusen, and other chorioretinal anomalies from fused fundus and optical coherence tomography (OCT) imagery. Furthermore, we present a novel strategy exploiting the transferability of these models across multiple retinal scanner specifications. A total of 363 fundus and 173,915 OCT scans from seven publicly available datasets were used in this research (from which 297 fundus and 59,593 OCT scans were used for testing purposes). Overall, a hybrid retinal analysis and grading network (RAGNet), backboned through ResNet50, stood first for extracting the retinal lesions, achieving a mean dice coefficient score of 0.822. Moreover, the complete source code and its documentation are released at http://biomisa.org/index.php/downloads/.

Optical coherence tomography imaging modality mostly used in biomedical imaging, technique for the examination of retina, and becoming an essential tool for having a 3-D image of retina. Retinal layers analysis of an SD-OCT image facilities the diagnosis and monitoring of various ocular diseases such as Age related Degeneration, Macular Edema, Diabetic Retinopathy and glaucoma. Segmentation of retinal layers in an OCT Images has been a rigorous task due to speckle noise in an image. This paper presents a methods for the extraction of Inner Limiting Membrane (ILM) layer in extremely noisy OCT images. Compared with existing algorithms for the extraction of Inner Limiting Membrane layer (ILM). We also compared diagnostic accuracy of interpolating algorithms and aimed to suggest best interpolating algorithm for delineation of retinal layers focusing glaucoma detection for extremely noisy images. The ILM Layer and Retinal Epithelium Layer will determine the Cup to disc ratio (CDR) that is significant investigating factor for glaucoma diagnosis. The data set having 79 images, including normal, suspect and glaucoma subjects.

Glaucoma is a blindness causing eye disease if not treated in time and caused by the increase in the cup‐to‐disc region (CDR). A novel method for extraction of the inner limiting membrane (ILM) and retinal pigment epithelium (RPE) layers from optical coherence tomography scans is proposed. A new colour channels mean based quality assessment step is applied to segment out ILM layer for different quality images. During RPE segmentation, a new ‘centroid based thresholding’ method is proposed to remove extended ILM regions. The method uses both the ILM layer and RPE breakpoints for a cup and disc calculation, respectively. A novel criterion for horizontal/flat cup diameter based on the average RPE break points is proposed. Based on calculated CDRs, the system classifies the subject as normal or glaucomatous. The average sensitivity, accuracy, and specificity of the proposed system are 87, 79 and 72%, respectively, on the Armed Forces Institute of Ophthalmology dataset when correlated with clinical annotations and CDR computer generated values. The proposed system has shown the higher correlated result of 92.59% sensitivity with the senior most ophthalmologists. It promotes the e‐health field at the retinal level and employed as the decision support system by the young doctors.

Segmentation is the pre-requisite process in most of the computer aided diagnosis systems for medical imaging. Presence of different artifacts makes segmentation of skin lesion very difficult. Abnormal growth of artifacts can appear as false positives and can degrade the performance of the diagnosis systems. It can be avoided only when false structures are removed while extracting the lesion. To address this issue, this paper proposes deep leaning for skin lesion segmentation. Within this framework, automated skin lesion segmentation is proposed which achieves high accuracy segmentation of skin lesion. Our proposed architecture is 31 layers deep with same filter size. The validity of the proposed techniques is tested on two publically available databases of PH2 and ISIC 2017. Experimental results show the efficiency of the proposed approaches. The proposed method gives Dice Coefficient of 92.3% for PH2 Dataset while Dice Coefficient of 85.5% for ISIC 2017 Dataset.

Extraction of retinal layers from optical coherence tomography (OCT) scans is critical for analyzing retinal anomalies and manual segmentation of these retinal layers is a very cumbersome task. Recently, deep learning has gained much popularity in medical image analysis due to its underlying precision and robustness. Many researchers have utilized deep learning for extracting retinal layers from OCT images. However, to the best of our knowledge, there is no literature available that presents a robust segmentation framework that is able to extract retinal layers from OCT scans having different retinal pathological syndromes. Therefore, this paper presents a deep convolutional neural network and structure tensor-based segmentation framework (CNN-STSF) for the fully automated segmentation of up to eight retinal layers from normal as well as diseased OCT scans. First of all, the proposed framework computes coherent tensor from the candidate scan through which retinal layers are extracted. Afterwards, the pixels representing the layers are further classified using cloud based deep convolutional neural network (CNN) model trained on 1,200 retinal layers patches. CNN model in the proposed framework computes the probability of each layer pixels and assign it to be part of that layer for which it has the highest probability. The proposed framework was tested and validated on more than 39,000 retinal OCT scans from different publicly available datasets and from local Armed Forces Institute of Ophthalmology (AFIO) dataset where it outperformed all the existing solutions by achieving the overall layer segmentation accuracy of 0.9375.

Age-related Macular Degeneration (AMD) is an eye disease which affects elderly people. Cholesterol deposits in central part of retina, known as macula, damages the photoreceptors present in a particular area of eye. AMD usually effects only central vision of patient. In medical field various imaging techniques are used for diagnosis of eye diseases. Optical Coherence Tomography (OCT) is a relatively newer technique that is found to be very useful in analyzing eyes. In this research, we used OCT images to automatically detect and classify AMD. First we extract the retinal layer known as Retinal Pigment Epithelium by utilizing Graph Theory Dynamic Programming technique, after successfully enhancing the quality of OCT image by using Wiener filter. We used a unique feature set consisting of features extracted from difference signal of RPE and Inner Segment Outer Segment layer of RPE. Feature set includes approximation coefficient, entropy and spectrum energy of the resulting difference signal. Support Vector Machine classifier was used to classify AMD affected and normal image. The developed system gives an accuracy of 95% for AMD detection.

Glaucoma is a group of eye disorders that damage the optic nerve. Considering a single eye condition for the diagnosis of glaucoma has failed to detect all glaucoma cases accurately. A reliable computer‐aided diagnosis system is proposed based on a novel combination of hybrid structural and textural features. The system improves the decision‐making process after analysing a variety of glaucoma conditions. It consists of two main modules hybrid structural feature‐set (HSF) and hybrid texture feature‐set (HTF). HSF module can classify a sample using support vector machine (SVM) from different structural glaucoma condition and the HTF module analyses the sample founded on various texture and intensity‐based features and again using SVM makes a decision. In the case of any conflict in the results of both modules, a suspected class is introduced. A novel algorithm to compute the super‐pixels has also been proposed to detect the damaged cup. This feature alone outperformed the current state‐of‐the‐art methods with 94% sensitivity. Cup‐to‐disc ratio calculation method for cup and disc segmentation, involving two different channels has been introduced increasing the overall accuracy. The proposed system has given exceptional results with 100% accuracy for glaucoma referral.

Optic disc is one of the fundamental regions located in the internal retina that helps ophthalmologists in analysis and early diagnosis of many retinal diseases such as optic atrophy, optic neuritis, papilledema, ischemic optic neuropathy, glaucoma and diabetic retinopathy. An accurate and early diagnosis requires an accurate optic disc examination. Presence of different retinal abnormalities and non-uniform illumination make optic disc localization a challenging task. There is a need to detect and localize optic disc from fundus images with high accuracy to make the diagnosis using Computer Aided Systems developed for ophthalmic disease diagnosis more reliable. Proposed algorithm provides a novel optic disc localization and segmentation technique that detects multiple candidate optic disc regions from fundus image using enhancement and segmentation. The proposed system then extracts a hybrid feature set for each candidate region consisting of vessel based and intensity based features which are finally fed to SVM classifier. Final decision of Optic disc region is done after computing Manhattan distance from the mean of training data feature matrix. The evaluation of proposed system has been done on publicly available datasets and one local dataset and results shows the validity of proposed system.

Healthcare is very important factor in every body's life and Information technology. It is playing an important role in providing better health with number of advancements. Internet of things (IoT) is an emerging technology. Due to its popularity in technology and internet world, IoT is rising in every field of life and so in health sector. Health is something in which its focus is more concentrated due to its hypnotic features. In our previous work we have defined and provided IoT based hospital management information system (HMIS). As IoT is aimed to connect everything to Internet, there are billions of sensors which are attached to things to access data and connect these things to internet. So the data provided by these sensors is growing very fast. We need to handle this big data on personals gadgets as well on central databases. To deal with this problem, in this paper we have presented IoT based architectural framework with context awareness for hospital management systems. We have introduced context awareness as a middleware on IoT's architecture above network layer to overcome the problem of data management. Patient's data would be placed on a cloud and only the required information would be available on their personal gadgets like smart phones and laptops etc.

Reliable Automated medical diagnosis systems are of critical importance.Such systems aid in early detection of diseases and prevention of its further progression.Development of such a reliable and efficient software system is possible using a suitable system development life cycle (SDLC) model only.A SDLC model develops a system in a structured, deliberate and methodical mode and provides a very reliable and efficient system within limited resources and time.Macular edema is the blurring or loss of central vision which is caused as a result of Diabetic Retinopathy and Analysis of OCT images helps in identification of Macular Edema.The aim of this research is the successful detection of Macular Edema using Iterative Prototyping SDLC model.First the extraction of ILM layer has been done by using Active Contour based Segmentation and Curve Fitting Techniques then a new technique is proposed in this research for the successful localization of fovea in retinal ILM layer by using distance based method.Finally the detection of Macular edema has been done on the basis of analysis of fovea region.The system is evaluated using a local dataset of OCT images which is gathered with the help of Armed Forces institute of Ophthalmology.The dataset consists of 550 images and the developed system gives an accuracy of 84%.

A computer-aided diagnostic (CAD) system for effective and accurate pulmonary nodule detection is required to detect the nodules at early stage. This paper proposed a novel technique to detect and classify pulmonary nodules based on statistical features for intensity values using support vector machine (SVM). The significance of the proposed technique is, it uses the nodules features in 2D & 3D and also SVM for the classification that is good to classify the nodules extracted from the image. The lung volume is extracted from Lung CT using thresholding, background removal, hole-filling and contour correction of lung lobe. The candidate nodules are extracted and pruned using the rules based on ground truth of nodules. The statistical features for intensity values are extracted from candidate nodules. The nodule data are up-samples to reduce the biasness. The classifier SVM is trained using data samples. The efficiency of proposed CAD system is tested and evaluated using Lung Image Consortium Database (LIDC) that is standard data-set used in CAD Systems for Lungs Nodule classification. The results obtained from proposed CAD system are good as compare to previous CAD systems. The sensitivity of 96.31% is achieved in the proposed CAD system.

Eye diseases such as diabetic retinopathy may cause blindness. At the advanced stages of diabetic retinopathy further disease progression is stopped using laser treatment. Laser treatment leaves behind marks on the retinal surface that causes misbehaviors in automated retinal diagnostic system. These laser marks hinders the further analysis of the retinal images so it is desirable to detect laser marks and remove them to avoid any unnecessary processing. This paper presents a method to automatically detect laser marks from the retinal images and present some results based on the performance evaluation.

Digital fundus images are commonly used for computer aided diagnosis of different eye disease such as diabetic retinopathy, glaucoma, age related macular degeneration. One issue with fundus cameras is that they provide fundus image only for a small field of view (FOV). This paper presents a novel method to increase the FOV by stitching different fundus images from same patient. The proposed system uses ASIFT based descriptors and generates a blended image by combining all available images. The paper also compares the proposed system with corner, SURF and SIFT based descriptors for same application.

Automatic screening and diagnosis of ocular disease through fundus images are in place and considered worldwide. One of the leading sight loosing disease known as age related macular degeneration (AMD) has many proposed automatic screening systems. These systems detect yellow bright lesion and through the number of lesion and their size the disease is graded as advance and earlier stage. It becomes difficult for these systems to differentiate drusens from exudates another bright lesion associated with Diabetic retinopathy. These two lesions look similar on retinal surface. Differentiating these two lesions can improve the performance of any automatic system. In this paper we proposed a novel approach to discriminate these lesions. The approach consists of two stage procedure. The first stage after pre-processing detects all bright pixels from the image. The suspicious pixels are removed from the detected region. On the second stage bright regions are classified as drusen and exudates through Support Vector Machine (SVM). Proposed method was evaluated on publically available dataset STARE. The system achieve 92% accuracy.

Cooperation among people is of utmost importance in order to get tasks done. Cooperation is required at work to execute different work packages of a large scale project, at a university to share parts of an assignment with respect to deadlines and also to collaboratively plan a party. In this paper

Core point detection is very important in fingerprint classification and matching process. Usually fingerprint images have noisy background and the local orientation field also changes very rapidly in the singular point area. It is difficult to locate the singular point precisely. In this paper, we present a new algorithm for optimal core point detection using improved segmentation and orientation. In our technique detects core point accurately by extracting best region of interest(ROI) from image and using fine orientation field estimation. We present a modified technique for extracting ROI and fine orientation field. The distinct feature of our technique is that it gives high detection percentage of core point even in case of low quality fingerprint images. The proposed algorithm is applied on FVC2004 database. Results of experiments demonstrate improved performance for detecting core point.