Shruti Jain

Aim: The study investigates the creation and assessment of Machine Learning (ML) models using different classifiers such as Support Vector Machine (SVM), logistic regression, decision tree, k-nearest neighbour (kNN), and Artificial Neural Network (ANN) for the automated identification of tuberculosis (TB) from chest X-ray (CXR) images. Background: As a persistent worldwide health concern, TB requires early detection for effective treatment and control of the infection. The differential diagnosis of TB is a challenge, even for experienced radiologists. With the use of automated processing of CXR images which are reasonable and frequently used for TB diagnosis, employing Artificial Intelligence (AI) techniques provides novel possibilities Objective: The objective of the study was to identify respiratory disorders, radiologists devote a lot of time reviewing each of the CXR images. As such, they can identify the type of disease using automated methods based on AI algorithms. This work advances the diagnosis of TB via machine learning, which may result in early treatment options and enhanced outcomes for patients. Method: The disease was classified using distinct parameters like edge, shape, and Gray Level Difference Statistics (GLDS) on splitting of the dataset at 70:30 and 80:20. Results: It was observed that authors attained 93.5% accuracy using SVM with linear kernel for a 70:30 data split considering hybrid parameters. The comparison was made considering different feature extraction techniques, different dataset splitting, existing work, and another dataset. Conclusion: The designed model using SVM, decision tree, kNN, ANN, and logistic regression was compared using other state-of-the-art techniques, other datasets, different feature extraction techniques, and different splitting of data. AI has great promise for enhancing tuberculosis detection, which will ultimately lead to an earlier diagnosis and improved disease management.

The development of energy-efficient circuits tailored for error-tolerant applications marks a significant advancement in low-power computing, particularly within the realm of approximate computing. This approach addresses the inherent trade-off between precise computation and computational efficiency. This study introduces a novel energy-efficient multiplier specifically designed for image-processing tasks. Integral to the multiplication process are compressors, which play a crucial role in reducing partial products. Moreover, higher-order approximate compressors, including 7:2 and 8:2 configurations, have been meticulously designed and simulated using Verilog coding within the VIVADO environment. The proposed approximated 7:2, and 8:2 compressors utilize 44%, and 41.37% less area, respectively, 52.35%, and 56.61% low-power consumption, respectively, and 13.73%, and 16.77% high speed, respectively, in comparison to exact compressors comparative analysis reveals that these proposed higher-order compressors offer reduced area requirements and lower power consumption compared to existing state-of-the-art techniques. Incorporating these high-performance compressors at the reduction stage of multipliers yields an energy-efficient circuit tailored for error-tolerant applications. The research employs three distinct designs (Design 1, Design 2 and Design 3), each leveraging the proposed higher-order compressors and approximate adders across varying bit-widths (8-, 16-, 32- and 64-bit). Each design presents unique advantages and limitations, catering to the specific requirements of the application.

Background: Diagnosis and treatment planning play a very vital role in improving the survival of oncological patients. However, there is high variability in the shape, size, and structure of the tumor, making automatic segmentation difficult. The automatic and accurate detection and segmentation methods for Brain tumors are proposed in this paper. Methods: A modified ResNet50 model was used for tumor detection, and a ResUNetmodel-based convolutional neural network for segmentation is proposed in this paper. The detection and segmentation were performed on the same dataset consisting of pre-contrast, FLAIR, and postcontrast MRI images of 110 patients collected from the cancer imaging archive. Due to the use of residual networks, the authors observed improvement in evaluation parameters, such as accuracy for tumor detection and dice similarity coefficient for tumor segmentation. Results: The accuracy of tumor detection and dice similarity coefficient achieved by the segmentation model were 96.77% and 0.893, respectively, for the TCIA dataset. The results were compared based on manual segmentation and existing segmentation techniques. The tumor mask was also individually compared to the ground truth using the SSIM value. The proposed detection and segmentation models were validated on BraTS2015 and BraTS2017 datasets, and the results were consensus. Conclusion: The use of residual networks in both the detection and the segmentation model resulted in improved accuracy and DSC score. DSC score was increased by 5.9% compared to the UNet model, and the accuracy of the model was increased from 92% to 96.77% for the test set.

The energy-efficient error-tolerant circuits have paved the way for a whole new area in low-power consumption applications with approximate computing. The approximate computing fulfills the trade-off requirement of exact computation and provides efficient performance. In this paper, a novel energy-efficient multiplier has been proposed for image processing applications. In the multiplication process, compressors are used as an important component for the reduction of partial products. Higher-order approximate 5:2 and 6:2 compressors are also designed and simulated in VIVADO using Verilog coding. The proposed higher-order compressors result in less area and low-power consumption in comparison with the existing state-of-the-art technique. These high-performance compressors are used at the multipliers’ reduction stage, resulting in an energy-efficient circuit for error-tolerant applications. All the simulations were carried out in VIVADO considering 8-bit inputs. Multiplication performance shows 37.77 % (8-bit) improvement in terms of power consumption in comparison to the conventional multiplier. The multiplication process has been done on the original, negative, and sharpened images using their masks. The proposed multiplier shows 51.36% (original image), 6.04% (negative image), and 22.44% (sharpened image) PSNR improvement in comparison to state-of-the-art work.

Background: Diseases are medical situations that are allied with specific signs and symptoms. A disease may be instigated by internal dysfunction or external factors like pathogens. Cerebrovascular disease can progress from diverse causes, comprising thrombosis, atherosclerosis, cerebral venous thrombosis, or embolic arterial blood clot. Objective: In this paper, authors have proposed a robust framework for the detection of cerebrovascular diseases employing two different proposals which were validated by use of other datasets. Methods: In proposed model 1, the Discrete Fourier transform is used for the fusion of CT and MR images which was classified them using machine learning techniques and pre-trained models while in proposed model 2, the cascaded model was proposed. The performance evaluation parameters like accuracy and losses were evaluated. Results: 92% accuracy was obtained using Support Vector Machine using Gray Level Difference Statistics and Shape features with Principal Component Analysis as a feature selection technique while Inception V3 resulted in 95.6% accuracy while the cascaded model resulted in 96.21% accuracy. Conclusion: The cascaded model is later validated on other datasets which results in 0.11% and 0.14% accuracy improvement over TCIA and BRaTS datasets respectively.