Accelerated Diffusion-Weighted MR Image Reconstruction Using Deep Neural Networks.

Under-sampling in diffusion-weighted imaging (DWI) decreases the scan time that helps to reduce off-resonance effects, geometric distortions, and susceptibility artifacts; however, it leads to under-sampling artifacts. In this paper, diffusion-weighted MR image (DWI-MR) reconstruction using deep learning (DWI U-Net) is proposed to recover artifact-free DW images from variable density highly under-sampled k-space data. Additionally, different optimizers, i.e., RMSProp, Adam, Adagrad, and Adadelta, have been investigated to choose the best optimizers for DWI U-Net. The reconstruction results are compared with the conventional Compressed Sensing (CS) reconstruction. The quality of the recovered images is assessed using mean artifact power (AP), mean root mean square error (RMSE), mean structural similarity index measure (SSIM), and mean apparent diffusion coefficient (ADC). The proposed method provides up to 61.1%, 60.0%, 30.4%, and 28.7% improvements in the mean AP value of the reconstructed images in our experiments with different optimizers, i.e., RMSProp, Adam, Adagrad, and Adadelta, respectively, as compared to the conventional CS at an acceleration factor of 6 (i.e., AF = 6). The results of DWI U-Net with the RMSProp, Adam, Adagrad, and Adadelta optimizers show 13.6%, 10.0%, 8.7%, and 8.74% improvements, respectively, in terms of mean SSIM with respect to the conventional CS at AF = 6. Also, the proposed technique shows 51.4%, 29.5%, 24.04%, and 18.0% improvements in terms of mean RMSE using the RMSProp, Adam, Adagrad, and Adadelta optimizers, respectively, with reference to the conventional CS at AF = 6. The results confirm that DWI U-Net performs better than the conventional CS reconstruction. Also, when comparing the different optimizers in DWI U-Net, RMSProp provides better results than the other optimizers.

Transfer learning in deep neural network-based receiver coil sensitivity map estimation.

INTRODUCTION: The success of parallel Magnetic Resonance Imaging algorithms like SENSitivity Encoding (SENSE) depends on an accurate estimation of the receiver coil sensitivity maps. Deep learning-based receiver coil sensitivity map estimation depends upon the size of training dataset and generalization capabilities of the trained neural network. When there is a mismatch between the training and testing datasets, retraining of the neural networks is required from a scratch which is costly and time consuming. MATERIALS AND METHODS: A transfer learning approach, i.e., end-to-end fine-tuning is proposed to address the data scarcity and generalization problems of deep learning-based receiver coil sensitivity map estimation. First, generalization capabilities of a pre-trained U-Net (initially trained on 1.5T receiver coil sensitivity maps) are thoroughly assessed for 3T receiver coil sensitivity map estimation. Later, end-to-end fine-tuning is performed on the pre-trained U-Net to estimate the 3T receiver coil sensitivity maps. RESULT AND CONCLUSION: Peak Signal-to-Noise Ratio, Root Mean Square Error and central line profiles (of the SENSE reconstructed images) show a successful SENSE reconstruction by utilizing the receiver coil sensitivity maps estimated by the proposed method.

COVID-19 Repercussions: Office and Residential Emissions in Pakistan.

The purpose of this study is to find empirical evidence on whether work from home or residential emissions reduces office emissions. Based on existing research the study supports that there are short-term effects on office emissions, i.e., carbon emissions do not outshine the long-term effects. The shift from offices to working from home due to COVID-19 regulations meant more people operating from home as maintaining their position in the market was crucial. The potential research area is to understand how this would affect energy usage and carbon emissions. This study has used a before and after mixed approach to collect data from 301 working-from-home employees and 348 top managers who are responsible for monitoring the employees in a work from home setting. Convenience sampling helped collect responses in a timely manner as offices were not allowing visitors and collecting data in person was difficult, so online surveys were conducted. Work from home reduced usage of office equipment, transportation, pollution, etc. The air quality improved considerably but our findings show that the low emissions were only short-lived. This was not a long-term scenario as organizations kept practicing their operations even at home and the emissions stayed in the environment. Future suggestions and implications are also provided. The results give new insights to researchers in the field of sustainability and the environment.

Transfer learning in deep neural network based under-sampled MR image reconstruction.

In Magnetic Resonance Imaging (MRI), the success of deep learning-based under-sampled MR image reconstruction depends on: (i) size of the training dataset, (ii) generalization capabilities of the trained neural network. Whenever there is a mismatch between the training and testing data, there is a need to retrain the neural network from scratch with thousands of MR images obtained using the same protocol. This may not be possible in MRI as it is costly and time consuming to acquire data. In this research, a transfer learning approach i.e. end-to-end fine tuning is proposed for U-Net to address the data scarcity and generalization problems of deep learning-based MR image reconstruction. First the generalization capabilities of a pre-trained U-Net (initially trained on the human brain images of 1.5 T scanner) are assessed for: (a) MR images acquired from MRI scanners of different magnetic field strengths, (b) MR images of different anatomies and (c) MR images under-sampled by different acceleration factors. Later, end-to-end fine tuning of the pre-trained U-Net is proposed for the reconstruction of the above-mentioned MR images (i.e. (a), (b) and (c)). The results show successful reconstructions obtained from the proposed method as reflected by the Structural SIMilarity index, Root Mean Square Error, Peak Signal-to-Noise Ratio and central line profile of the reconstructed images.

Use of fine-needle aspiration in the evaluation of breast lumps.

Background. A study was designed to see the role of fine needle aspiration cytology (FNAC) in palpable breast lumps. Materials and Methods. Four hundred and twenty five (425) patients came to the Department of Pathology King Edward Medical University, Lahore in four years for FNAC of their palpable breast masses from June 2006 to June 2010. FNAC diagnosis was compared with histological diagnosis to see the accuracy of fine needle aspiration cytology for neoplastic lesions. Results. There were 271/425 benign, 120/425 malignant, and 32/425 suspicious smears. Inadequate samples were repeated twice or thrice, and the degree of success was improved with consecutive repeating approaches. The frequency of inadequacy declined from 86 to 18, and 2 for first, second and third attempts, respectively. The number of repeats increased the diagnostic accuracy of aspirates which is statistically significant (P = .000). Invasive ductal carcinoma was the most commonly reported lesion with maximum incidence in the 4th, 5th, and 6th decades followed by invasive lobular carcinoma and other malignant lesions. The sensitivity, specificity, accuracy, negative predictive value, and the positive predictive value of FNAC was 98%, 100%, 98%, 100%, and 97%, respectively. Conclusion. FNAC serves as a rapid, economical, and reliable tool for the diagnosis of palpable breast lesions because the cytopathological examination of these lesions before operation or treatment serves as an important diagnostic modality.