MADR-Net: multi-level attention dilated residual neural network for segmentation of medical images.

Medical image segmentation has made a significant contribution towards delivering affordable healthcare by facilitating the automatic identification of anatomical structures and other regions of interest. Although convolution neural networks have become prominent in the field of medical image segmentation, they suffer from certain limitations. In this study, we present a reliable framework for producing performant outcomes for the segmentation of pathological structures of 2D medical images. Our framework consists of a novel deep learning architecture, called deep multi-level attention dilated residual neural network (MADR-Net), designed to improve the performance of medical image segmentation. MADR-Net uses a U-Net encoder/decoder backbone in combination with multi-level residual blocks and atrous pyramid scene parsing pooling. To improve the segmentation results, channel-spatial attention blocks were added in the skip connection to capture both the global and local features and superseded the bottleneck layer with an ASPP block. Furthermore, we introduce a hybrid loss function that has an excellent convergence property and enhances the performance of the medical image segmentation task. We extensively validated the proposed MADR-Net on four typical yet challenging medical image segmentation tasks: (1) Left ventricle, left atrium, and myocardial wall segmentation from Echocardiogram images in the CAMUS dataset, (2) Skin cancer segmentation from dermoscopy images in ISIC 2017 dataset, (3) Electron microscopy in FIB-SEM dataset, and (4) Fluid attenuated inversion recovery abnormality from MR images in LGG segmentation dataset. The proposed algorithm yielded significant results when compared to state-of-the-art architectures such as U-Net, Residual U-Net, and Attention U-Net. The proposed MADR-Net consistently outperformed the classical U-Net by 5.43%, 3.43%, and 3.92% relative improvement in terms of dice coefficient, respectively, for electron microscopy, dermoscopy, and MRI. The experimental results demonstrate superior performance on single and multi-class datasets and that the proposed MADR-Net can be utilized as a baseline for the assessment of cross-dataset and segmentation tasks.

A Domain-Shift Invariant CNN Framework for Cardiac MRI Segmentation Across Unseen Domains.

The emergence of various deep learning approaches in diagnostic medical image segmentation has made machines capable of accomplishing human-level accuracy. However, the generalizability of these architectures across patients from different countries, Magnetic Resonance Imaging (MRI) scans from distinct vendors, and varying imaging conditions remains questionable. In this work, we propose a translatable deep learning framework for diagnostic segmentation of cine MRI scans. This study aims to render the available SOTA (state-of-the-art) architectures domain-shift invariant by utilizing the heterogeneity of multi-sequence cardiac MRI. To develop and test our approach, we curated a diverse group of public datasets and a dataset obtained from private source. We evaluated 3 SOTA CNN (Convolution neural network) architectures i.e., U-Net, Attention-U-Net, and Attention-Res-U-Net. These architectures were first trained on a combination of three different cardiac MRI sequences. Next, we examined the M&M (multi-center & mutli-vendor) challenge dataset to investigate the effect of different training sets on translatability. The U-Net architecture, trained on the multi-sequence dataset, proved to be the most generalizable across multiple datasets during validation on unseen domains. This model attained mean dice scores of 0.81, 0.85, and 0.83 for myocardial wall segmentation after testing on unseen MyoPS (Myocardial Pathology Segmentation) 2020 dataset, AIIMS (All India Institute of Medical Sciences) dataset and M&M dataset, respectively. Our framework achieved Pearson's correlation values of 0.98, 0.99, and 0.95 between the observed and predicted parameters of end diastole volume, end systole volume, and ejection fraction, respectively, on the unseen Indian population dataset.

Techno-economic analysis of ethanol production from lignocellulosic biomass-a comparison of fermentation, thermo catalytic, and chemocatalytic technologies.

Bioethanol produced from 2nd generation biomass comprising of agricultural residues and forest wastes is a viable alternate fuel. Besides fermentation and biomass gasification to syngas and its further conversion to ethanol, a direct chemocatalytic conversion of lignocellulosic biomass into ethanol is being investigated as a viable route which avoids the emission of greenhouse gases. In this work, a detailed configuration of chemocatalytic route is simulated and optimized for minimizing the cost of ethanol production. The economic feasibility of ethanol production through the chemocatalytic pathway is analyzed. The techno-economic analysis is conducted in terms of ethanol selectivity and ethanol production cost. The obtained results show that biomass feedstock and catalyst have major contributions to the production cost. The proposed route is found to be giving a lower ethanol selling price as compared to the well-researched routes of biomass fermentation to ethanol and biomass gasification followed by syngas conversion to ethanol.

In Vitro Identification of the Hamiltonian Cycle Using a Circular Structure Assisted DNA Computer.

Adleman's illustration of molecular computing using DNA paved the way toward an entirely new direction of computing (Adleman, L. M. Science 1994, 266, 1021). The exponential time complex combinatorial problem on a traditional computer turns out to be a separation problem involving a polynomial number of steps in DNA computing experiments. Despite being a promising concept, the implementations of existing DNA computing procedures were restricted only to the smaller size formulations. In this work, we demonstrate a structure assisted DNA computing procedure on a bigger size Hamiltonian cycle problem involving 18 vertices. The developed model involves the formation and digestion of circular structure DNA, iteratively over multiple stages to eliminate the incorrect solutions to the given combinatorial problem. A high accuracy is obtained compared to other structure assisted models, which enable one to solve the bigger size problems.