Explore the vast range of titles available.

Echocardiography is a commonly used and cost-effective test to assess heart conditions. During the test, cardiologists and technicians observe two cardiac phases—end-systolic (ES) and end-diastolic (ED)—which are critical for calculating heart chamber size and ejection fraction. However, non-essential frames called Non-ESED frames may appear between these phases. Currently, technicians or cardiologists manually detect these phases, which is time-consuming and prone to errors. To address this, an automated and efficient technique is needed to accurately detect cardiac phases and minimize diagnostic errors. In this paper, we propose a deep learning model called DeepPhase to assist cardiology personnel. Our convolutional neural network (CNN) learns from echocardiography images to identify the ES, ED, and Non-ESED phases without the need for left ventricle segmentation or electrocardiograms. We evaluate our model on three echocardiography image datasets, including the CAMUS dataset, the EchoNet Dynamic dataset, and a new dataset we collected from a cardiac hospital (CardiacPhase). Our model outperforms existing techniques, achieving 0.96 and 0.82 area under the curve (AUC) on the CAMUS and CardiacPhase datasets, respectively. We also propose a novel cropping technique to enhance the model’s performance and ensure its relevance to real-world scenarios for ES, ED, and Non ES-ED classification.

The automated analysis of medical diagnostic videos, such as ultrasound and endoscopy, provides significant benefits in clinical practice by improving the efficiency and accuracy of diagnosis. Deep learning techniques show remarkable success in analyzing these videos by automating tasks such as classification, detection, and segmentation. In this paper, we review the application of deep learning techniques for analyzing medical diagnostic videos, with a focus on ultrasound and endoscopy. The methodology for selecting the papers consists of two major steps. First, we selected around 350 papers based on the relevance of their titles to our topic. Second, we chose the research articles that focus on deep learning and medical diagnostic videos based on our inclusion and exclusion criteria. We found that convolutional neural networks (CNNs) and long short-term memory (LSTM) are the two most commonly used models that achieve good results in analyzing different types of medical videos. We also found various limitations and open challenges. We highlight the limitations and open challenges in this field, such as labeling and preprocessing of medical videos, class imbalance, and time complexity, as well as incorporating expert knowledge, k-shot learning, live feedback from experts, and medical history with video data. Our review can encourage collaborative research with domain experts and patients to improve the diagnosis of diseases from medical videos.

Deep learning (DL) is a type of machine learning capable of processing large quantities of data to provide analytic results based on a particular framework’s parameters and aims. DL is widely used in a variety of fields, including medicine. Currently, there are various DL-based prediction models for predicting cancer probability and survival. However, the specific problem is that no integrated system can predict cancer survival, probability, and presence in the medical patient’s samples. Therefore, this research investigates the latest literature in the field of DL-based cancer prediction models for predicting the cancer probability and the patient survival rate. The name of this proposed model is Multimodal Incremental Recurrent Deep Neural Network; it can perform the analysis, prediction, and diagnosis of cancer using multi-dimensional data processing. It can also predict the cancer possibility and survival using incremental recurrent neural networks. The components of the proposed taxonomy are Data, Prediction technique, and View (DPV). This research’s contribution is the critical analysis of the latest literature on the DL-based systems that can predict cancer and its outcomes. It provides a theoretical model that can predict the possibility, presence, and survival of cancer by processing multi-dimensional medical samples of the patient to make accurate predictions. We also highlight the importance of the proposed taxonomy.

Gastric cancer is the fourth most commonly diagnosed malignancy and the second leading cause of cancer-related mortality worldwide. Recent research suggests that tissue stem cells and the self renewal transcription factor, octamer-binding transcription factor 4 (Oct4), could be involved in the development of certain tumors. The aim of this study was to investigate the expression pattern of Oct4 in normal human stomach and during multistep gastric carcinogenesis. Pyloric antral mucosal tissues were obtained from consenting individuals undergoing endoscopy (due to upper gastrointestinal symptoms) and gastrectomy (due to pyloric antral adenocarcinoma). Some tissue samples were processed to assemble an array of tissue sections representing multistep carcinogenesis and probed using anti-Oct4 antibodies and lectins specific for α-L-fucose or N-acetyl-D-glucosamine. Some tissue samples were processed for subcellular fractionation and western blot analysis using the same antibodies. The results revealed that Oct4-expressing cells were found in the proliferative cell compartment of the pit-gland units of microscopically normal gastric mucosal biopsies. Mucosal tissues with evidence of severe gastritis, metaplastic/dysplastic transformation and gastric cancer showed a significant increase in the expression of Oct4 (the labeled area increased from 2% in the control to 6 and 16% in the gastritis and cancerous tissues, respectively), suggesting a role for Oct4 in the early stages of cancer development. Furthermore, the data revealed an alteration in the subcellular distribution of Oct4, possibly due to the inhibition of cytoplasm-to-nucleus translocation during carcinogenesis. In conclusion, this study demonstrates an alteration in the expression pattern and nuclear translocation of Oct4 during gastric carcinogenesis and may be helpful in designing new modalities for the early detection and/or therapy of gastric cancer.

Brain tumour identification with traditional magnetic resonance imaging (MRI) tends to be time-consuming and in most cases, reading of the resulting images by human agents is prone to error, making it desirable to use automated image segmentation. This is a multi-step process involving: (a) collecting data in the form of raw processed or raw images, (b) removing bias by using pre-processing, (c) processing the image and locating the brain tumour, and (d) showing the tumour affected areas on a computer screen or projector. Several systems have been proposed for medical image segmentation but have not been evaluated in the field. This may be due to ongoing issues of image clarity, grey and white matter present in a scan image, lack of knowledge of the end user and constraints arising from MRI imaging systems. This makes it imperative to develop a comprehensive technique for the accurate diagnosis of brain tumors in MRI images. In this paper, we introduce a taxonomy consisting of ‘Data, Image segmentation processing, and View’ (DIV) which are the major components required to develop a high-end system for brain tumour diagnosis based on deep learning neural networks. The DIV taxonomy is evaluated based on system completeness and acceptance. The utility of the DIV taxonomy is demonstrated by classifying 30 state-of-the-art publications in the domain of medFical image segmentation systems based on deep neural networks. The results demonstrate that few components of medical image segmentation systems have been validated although several have been evaluated by identifying role and efficiency of the components in this domain.

Fast-shrinking dimensions of semiconductor devices are expected to reach sub-10 nm scale in a few years. Although smaller in size and lower in power consumption than today’s CMOS devices, the nanoscaled devices are much less reliable due to manufacturing imperfections (hard errors), and noise and radiation-induced faults (soft errors). Consequently, in addition to timing, area, and power, the reliability has to become a new design criterion. This also means that the topic of reliability has to be incorporated into the circuit design curriculum. In this paper, we propose a course on circuit reliability. We also present in detail, an automated tool for calculation of reliability which could be incorporated into the course as a means for active learning.

In the past, instruction fetch speeds have been improved by using cache schemes that capture the actual program flow. In this paper, we elaborate on the architecture and operation of an instruction cache named Variable-Sized Block Cache (VSBC) that also makes use of the dynamic behavior of a program. Current trace-based cache schemes usually have some instructions stored repeatedly; this redundancy is eliminated in VSBC. Our cache also allows storage of basic blocks of arbitrary sizes, in multiple-way cache structure. An overall comparison of trace miss rate and average trace length shows VSBC to be a better performing cache scheme than TC, using SPECint2000 integer benchmarks.

This paper proposes a model that predicts the complexity of Boolean functions with only XOR/XNOR min-terms using back propagation neural networks (BPNNs) applied to Binary Decision Diagrams (BDDs). The BPNN model (BPNNM) is developed through the training process of experimental data already obtained for XOR/XNOR-based Boolean functions. The outcome of this model is a unique matrix for the complexity estimation over a set of BDDs derived from Boolean expressions with a given number of variables and XOR/XNOR min-terms. The comparison results of the experimental and BPNNM underline the efficiency of this approach, which is capable of providing some useful clues about the complexity of the circuit to be implemented. It also proves the computational capabilities of NNs in providing reliable classification of the complexity of Boolean functions.

The threshold voltages of CMOS logic gates based on modern technology nodes are highly susceptible to variations. As a result, the static noise margin of the gates also varies. In this paper, we present an analytical model for representing the variations in the noise margin. The model can serve as an expedient alternative to Monte Carlo simulations. With three use-cases, we have demonstrated how the model can be used as a first-order sizing mechanism for a variation-prone gate.