Other affiliations: Guru Gobind Singh Indraprastha University
Bio: Soumi Ray is an academic researcher from Indian Institute of Technology Roorkee. The author has contributed to research in topics: Segmentation & Region growing. The author has an hindex of 3, co-authored 8 publications receiving 30 citations. Previous affiliations of Soumi Ray include Guru Gobind Singh Indraprastha University.
TL;DR: A fully automatic and fast Computer Aided Diagnosis is designed, using the proposed method, to segment hemorrhage automatically, in the absence of an expert, for further inspections like checking severity, volume, size, shape and type of hemorrhage.
Abstract: This article has proposed an intelligent knowledge driven method to segment hemorrhage from brain CT images using the information of pixel intensity population and distribution. A mathematical model is designed to identify the unexpected variation in pixel intensity population in a brain CT image having hemorrhage. Complete batch of multi-slice CT scan images is taken as input. Fusion of knowledge of brain anatomy with intensity distribution information of CT brain image results in a unique solution for hemorrhage segmentation. To test the robustness, segmentation of different types of hemorrhage of different patients is done using the proposed method. The results are accepted and validated by radiology experts. A fully automatic and fast Computer Aided Diagnosis (CAD) is designed, using the proposed method, to segment hemorrhage automatically, in the absence of an expert, for further inspections like checking severity, volume, size, shape and type of hemorrhage. Competence of the CAD is tested against mostly used established clustering methods to demonstrate its potential.
TL;DR: This paper is an effort to explain uncertainty in comparatively simple way to give an idea about the error propagation in a measurement and the calculation of associated uncertainty.
TL;DR: This literature has proposed three fast and easy computable image features to improve computer vision by offering more human-like vision power by not based on image pixels absolute or relative intensity.
Abstract: This literature has proposed three fast and easy computable image features to improve computer vision by offering more human-like vision power. These features are not based on image pixels absolute or relative intensity; neither based on shape or colour. So, no complex pixel by pixel calculation is required. For human eyes, pixel by pixel calculation is like seeing an image with maximum zoom which is done only when a higher level of details is required. Normally, first we look at an image to get an overall idea about it to know whether it deserves further investigation or not. This capacity of getting an idea at a glance is analysed and three basic features are proposed to empower computer vision. Potential of proposed features is tested and established through different medical dataset. Achieved accuracy in classification demonstrates possibilities and potential of the use of the proposed features in image processing.
TL;DR: Though depending on the study outcome, the impact of CoVid19 in India can be predicted, the required lockdown period cannot be calculated due to data limitation.
Abstract: Purpose We are currently in the middle of a global crisis. Covid19 pandemic has suddenly threatened the existence of human life. Till date, as no medicine or vaccine is discovered, the best way to fight against this pandemic is prevention. The impact of different environmental, social, economic and health parameters is unknown and under research. It is important to identify the factors which can weaken the virus, and the nations which are more vulnerable to this virus. Materials and Methods Data of weather, vaccination trends, life expectancy, lung disease, number of infected people in the pre-lockdown and post-lockdown period of highly infected nations are collected. These are extracted from authentic online resources and published reports. Analysis is done to find the possible impact of each parameter on CoVid19. Results CoVid19 has no linear correlation with any of the selected parameters, though few parameters have depicted non-linear relationship in the graphs. Further investigations have shown better result for some parameters. A combination of the parameters results in a better correlation with infection rate. Conclusions Though depending on the study outcome, the impact of CoVid19 in India can be predicted, the required lockdown period cannot be calculated due to data limitation.
TL;DR: A robust automatic segmentation system is presented which is capable of segment complete brain matter from CT slices, without any lose in information, and shows highest sensitivity and more than 96% accuracy in all cases.
Abstract: Computed tomography imaging is well accepted for its imaging speed, image contrast & resolution and cost Thus it has wide use in detection and diagnosis of brain diseases But unfortunately reported works on CT segmentation is not very significant In this paper, a robust automatic segmentation system is presented which is capable of segment complete brain matter from CT slices, without any lose in information The proposed method is simple, fast, accurate and completely automatic It can handle multislice CT scan in single run From a given multislice CT dataset, one slice is selected automatically to form masks for segmentation Two types of masks are created to handle nasal slices in a better way Masks are created from selected reference slice using automatic seed point selection and region growing technique One mask is designed for brain matter and another includes the skull of the reference slice This second mask is used as global reference mask for all slices whereas the brain matter mask is implemented on only adjacent slices and continuously modified for better segmentation Slices in given dataset are divided into two batches, before reference slice and after reference slice Each batch segmented separately Successive propagation of brain matter mask has demonstrated very high potential in reported segmentation Presented result shows highest sensitivity and more than 96% accuracy in all cases Resulted segmented images can be used for any brain disease diagnosis or further image analysis
TL;DR: A novel correlation learning mechanism (CLM) for deep neural network architectures that combines convolutional neural network (CNN) with classic architecture that helps CNN to find the most adequate filers for pooling and convolution layers.
Abstract: Modern medical clinics support medical examinations with computer systems which use Computational Intelligence on the way to detect potential health problems in more efficient way. One of the most important applications is evaluation of CT brain scans, where the most precise results come from deep learning approaches. In this article, we propose a novel correlation learning mechanism (CLM) for deep neural network architectures that combines convolutional neural network (CNN) with classic architecture. The support neural network helps CNN to find the most adequate filers for pooling and convolution layers. As a result, the main neural classifier learns faster and reaches higher efficiency. Results show that our CLM model is able to reach about 96% accuracy, and about 95% precision and recall. We have described our proposed mechanism and discussed numerical results to draw conclusions and show future works.
TL;DR: The proposed system is based on a lightweight deep neural network architecture composed of a convolutional neural network that takes as input individual CT slices, and a Long Short-Term Memory (LSTM) network that take as input multiple feature embeddings provided by the CNN.
Abstract: In this paper, we present our system for the RSNA Intracranial Hemorrhage Detection challenge, which is based on the RSNA 2019 Brain CT Hemorrhage dataset. The proposed system is based on a lightweight deep neural network architecture composed of a convolutional neural network (CNN) that takes as input individual CT slices, and a Long Short-Term Memory (LSTM) network that takes as input multiple feature embeddings provided by the CNN. For efficient processing, we consider various feature selection methods to produce a subset of useful CNN features for the LSTM. Furthermore, we reduce the CT slices by a factor of 2×, which enables us to train the model faster. Even if our model is designed to balance speed and accuracy, we report a weighted mean log loss of 0.04989 on the final test set, which places us in the top 30 ranking (2%) from a total of 1345 participants. While our computing infrastructure does not allow it, processing CT slices at their original scale is likely to improve performance. In order to enable others to reproduce our results, we provide our code as open source. After the challenge, we conducted a subjective intracranial hemorrhage detection assessment by radiologists, indicating that the performance of our deep model is on par with that of doctors specialized in reading CT scans. Another contribution of our work is to integrate Grad-CAM visualizations in our system, providing useful explanations for its predictions. We therefore consider our system as a viable option when a fast diagnosis or a second opinion on intracranial hemorrhage detection are needed.
TL;DR: In this article, the authors proposed a methodology, termed virtual in-situ calibration, to solve the critical issue of uncalibrated problematic sensors, which could significantly compromise the systems' performance and lead to unintended loss of energy efficiency in buildings.
TL;DR: The importance of assumptions and strong correlation between short-term projections but uncertainties for long-term predictions are shown, and short- term predictions may be revised as more and more data become available.
Abstract: Background The mathematical modelling of coronavirus disease-19 (COVID-19) pandemic has been attempted by a wide range of researchers from the very beginning of cases in India Initial analysis of available models revealed large variations in scope, assumptions, predictions, course, effect of interventions, effect on health-care services, and so on Thus, a rapid review was conducted for narrative synthesis and to assess correlation between predicted and actual values of cases in India Methods A comprehensive, two-step search strategy was adopted, wherein the databases such as Medline, google scholar, MedRxiv, and BioRxiv were searched Later, hand searching for the articles and contacting known modelers for unpublished models was resorted The data from the included studies were extracted by the two investigators independently and checked by third researcher Results Based on the literature search, 30 articles were included in this review As narrative synthesis, data from the studies were summarized in terms of assumptions, model used, predictions, main recommendations, and findings The Pearson’s correlation coefficient (r) between predicted and actual values (n = 20) was 07 (p = 0002) with R2 = 049 For Susceptible, Infected, Recovered (SIR) and its variant models (n = 16) ‘r’ was 065 (p = 002) The correlation for long-term predictions could not be assessed due to paucity of information Conclusion Review has shown the importance of assumptions and strong correlation between short-term projections but uncertainties for long-term predictions Thus, short-term predictions may be revised as more and more data become available The assumptions too need to expand and firm up as the pandemic evolves
TL;DR: This paper proposes an encoder-decoder convolutional neural network (ED-Net) architecture to comprehensively utilizing both the low-level and high-level semantic information, and compares the results of ED-Net with nine state-of-the-art methods in the literature.
Abstract: Intracerebral hemorrhage (ICH) is the most serious type of stroke, which results in a high disability or mortality rate. Therefore, accurate and rapid ICH region segmentation is of great significance for clinical diagnosis and treatment of ICH. In this paper, we focus on deep neural networks to automatically segment ICH regions. Firstly, we propose an encoder-decoder convolutional neural network (ED-Net) architecture to comprehensively utilizing both the low-level and high-level semantic information. Specifically, the encoder is used to extract multi-scale semantic feature information, while the decoder integrates them to form a unified ICH feature representation. Secondly, we introduce a synthetic loss function by paying more attention to the small ICH regions to overcome the data imbalanced problem. Thirdly, to improve the clinical adaptability of the proposed model, we collect 480 patient cases with ICH from four hospitals to construct a multi-center dataset, in which each case contains the first and review CT scans. In particular, CT scans of different patients are diverse, which greatly increases the difficulty of segmentation. Finally, we evaluate ED-Net on the multi-center ICH clinical dataset from different model parameters and different loss functions. We also compare the results of ED-Net with nine state-of-the-art methods in the literature. Both quantitative and visual results have shown that ED-Net outperforms other methods by providing more accurate and stable performance.