Residual U-Network for Breast Tumor Segmentation from Magnetic Resonance Images

Breast cancer positions as the most well-known threat and the main source of malignant growth-related morbidity and mortality throughout the world.It is apical of all new cancer incidences analyzed among females.Two features substantially inuence the classication accuracy of malignancy and benignity in automated cancer diagnostics.These are the precision of tumor segmentation and appropriateness of extracted attributes required for the diagnosis.In this research,the authors have proposed a ResU-Net(Residual U-Network)model for breast tumor segmentation.The proposed methodology renders augmented,and precise identication of tumor regions and produces accurate breast tumor segmentation in contrast-enhanced MR images.Furthermore,the proposed framework also encompasses the residual network technique,which subsequently enhances the performance and displays the improved training process.Over and above,the performance of ResU-Net has experimentally been analyzed with conventional U-Net,FCN8,FCN32.Algorithm performance is evaluated in the form of dice coefcient and MIoU(Mean Intersection of Union),accuracy,loss,sensitivity,specicity,F1score.Experimental results show that ResU-Net achieved validation accuracy&dice coefcient value of 73.22%&85.32%respectively on the Rider Breast MRI dataset and outperformed as compared to the other algorithms used in experimentation.

COVID19 Classification Using CT Images via Ensembles of Deep Learning Models

The recent COVID-19 pandemic caused by the novel coronavirus,severe acute respiratory syndrome coronavirus 2(SARS-CoV-2),has had a significant impact on human life and the economy around the world.A reverse transcription polymerase chain reaction(RT-PCR)test is used to screen for this disease,but its low sensitivity means that it is not sufficient for early detection and treatment.As RT-PCR is a time-consuming procedure,there is interest in the introduction of automated techniques for diagnosis.Deep learning has a key role to play in the field of medical imaging.The most important issue in this area is the choice of key features.Here,we propose a set of deep learning features based on a system for automated classification of computed tomography(CT)images to identify COVID-19.Initially,this method was used to prepare a database of three classes:Pneumonia,COVID19,and Healthy.The dataset consisted of 6000 CT images refined by a hybrid contrast stretching approach.In the next step,two advanced deep learning models(ResNet50 and DarkNet53)were fine-tuned and trained through transfer learning.The features were extracted from the second last feature layer of both models and further optimized using a hybrid optimization approach.For each deep model,the Rao-1 algorithm and the PSO algorithm were combined in the hybrid approach.Later,the selected features were merged using the new minimum parallel distance non-redundant(PMDNR)approach.The final fused vector was finally classified using the extreme machine classifier.The experimental process was carried out on a set of prepared data with an overall accuracy of 95.6%.Comparing the different classification algorithms at the different levels of the features demonstrated the reliability of the proposed framework.

Overview of robotic colorectal surgery:Current and future practical developments

Minimal access surgery has revolutionised colorectal surgery by offering reduced morbidity and mortality over open surgery,while maintaining oncological and functional outcomes with the disadvantage of additional practical challenges. Robotic surgery aids the surgeon in overcoming these challenges. Uptake of robotic assistance has been relatively slow,mainly because of the high initial and ongoing costs of equipment but also because of limited evidence of improved patient outcomes. Advances in robotic colorectal surgery will aim to widen the scope of minimal access surgery to allow larger and more complex surgery through smaller access and natural orifices and also to make the technology more economical,allowing wider dispersal and uptake of robotic technology. Advances in robotic endoscopy will yield self-advancing endoscopes and a widening role for capsule endoscopy including the development of motile and steerable capsules able to deliver localised drug therapy and insufflation as well as being recharged from an extracorporeal power source to allow great longevity. Ultimately robotic technology may advance to the point where many conventional surgical interventions are no longer required. With respect to nanotechnology,surgery may eventually become obsolete.

Computerized White Matter and Gray Matter Extraction from MRI of Brain Image

Automated segmentation of white matter (WM) and gray matter (GM) is a very important task for detecting multiple diseases. The paper proposed a simple method for WM and GM extraction form magnetic resonance imaging (MRI) of brain. The proposed methods based on binarization, wavelet decomposition, and convexhull produce very effective results in the context of visual inspection and as well as quantifiably. It tested on three different (Transvers, Sagittal, Coronal) types of MRI of brain image and the validation of experiment indicate accurate detection and segmentation of the interesting structures or particular region of MRI of brain image.

The role of pain neuroscience education in the management of chronic musculoskeletal pain:a physiotherapeutic approach

Psychological,social,and environmental variables all have a role in the development,management,and treatment of chronic pain problems.Poor advice from healthcare professionals regarding movement,radiological findings,exercises,and the benefits of electrotherapeutic modalities may affect the mood and cognitive-psychological dimensions of patients with chronic musculoskeletal pain.As per the available literature evidence as of now the inclusion of pain neuroscience education followed by bio-psychosocial assessment sessions in place of standard advice-based,clinician-dominated,and passive physiotherapy care may result in better clinical outcomes in the practice.

A hierarchical clustering approach for colorectal cancer molecular subtypes identification from gene expression data

Background Colorectal cancer(CRC)is the second leading cause of cancer fatalities and the third most common human disease.Identifying molecular subgroups of CRC and treating patients accordingly could result in better therapeutic success compared with treating all CRC patients similarly.Studies have highlighted the significance of CRC as a major cause of mortality worldwide and the potential benefits of identifying molecular subtypes to tailor treatment strategies and improve patient outcomes.Methods This study proposed an unsupervised learning approach using hierarchical clustering and feature selection to identify molecular subtypes and compares its performance with that of conventional methods.The proposed model contained gene expression data from CRC patients obtained from Kaggle and used dimension reduction techniques followed by Z-score-based outlier removal.Agglomerative hierarchy clustering was used to identify molecular subtypes,with a P-value-based approach for feature selection.The performance of the model was evaluated using various classifiers including multilayer perceptron(MLP).Results The proposed methodology outperformed conventional methods,with the MLP classifier achieving the highest accuracy of 89%after feature selection.The model successfully identified molecular subtypes of CRC and differentiated between different subtypes based on their gene expression profiles.Conclusion This method could aid in developing tailored therapeutic strategies for CRC patients,although there is a need for further validation and evaluation of its clinical significance.

An improved brain MR image binarization method as a preprocessing for abnormality detection and features extraction

This paper propose a computerized method of magnetic resonance imaging （MR/） of brain binarization for the uses of preprocessing of features extraction and brain ab- normality identification. One of the main problems of MR/ binarization is that many pixels of brain part cannot be cor- rectly binarized due to extensive black background or large variation in contrast between background and foreground of MR/. We have proposed a binarization that uses mean, vari- ance, standard deviation and entropy to determine a thresh- old value followed by a non-gamut enhancement which can overcome the binarization problem of brain component. The proposed binarization technique is extensively tested with a variety of MR/and generates good binarization with im- proved accuracy and reduced error. A comparison is carried out among the obtained outcome with this innovative method with respect to other well-known methods.

Atherosclerotic plaque classification in carotid ultrasound images using machine learning and explainable deep learning

Objective The incidence of cardiovascular diseases(CVD)is rising rapidly worldwide.Some forms of CVD,such as stroke and heart attack,are more common among patients with certain conditions.Atherosclerosis development is a major factor underlying cardiovascular events,such as heart attack and stroke,and its early detection may prevent such events.Ultrasound imaging of carotid arteries is a useful method for diagnosis of atherosclerotic plaques;however,an automated method to classify atherosclerotic plaques for evaluation of early-stage CVD is needed.Here,we propose an automated method for classification of high-risk atherosclerotic plaque ultrasound images.Methods Five deep learning(DL)models(VGG16,ResNet-50,GoogLeNet,XceptionNet,and SqueezeNet)were used for automated classification and the results compared with those of a machine learning(ML)-based technique,involving extraction of 23 texture features from ultrasound images and classification using a Support Vector Machine classifier.To enhance model interpretability,output gradient-weighted convolutional activation maps(GradCAMs)were generated and overlayed on original images.Results A series of indices,including accuracy,sensitivity,specificity,F1-score,Cohen-kappa index,and area under the curve values,were calculated to evaluate model performance.GradCAM output images allowed visualization of the most significant ultrasound image regions.The GoogLeNet model yielded the highest accuracy(98.20%).Conclusion ML models may be also suitable for applications requiring low computational resource.Further,DL models could be more completely automated than ML models.