Search

Time-Slotted Channel Hopping (TSCH), an operational mode of the IEEE 802.15.4e standard, imposes a high workload on the embedded processor, mainly due to its precise timing. The limited embedded processor of an edge device cannot satisfy the considerable memory footprint and computational complexity caused by functions that need precise timing in the protocol stack. Moving such duties to hardware seems to be a viable path towards offloading the processor and releasing its resource to be used for running firmware related to the implementation of the upper layers of the protocol stack as well as the application. In this work, a TSCH protocol hardware accelerator is designed and integrated within the digital baseband processor of an IEEE 802.15.4 transceiver. The whole system is implemented targeting the TSMC 65 nm technology. The designed TSCH accelerator has an efficient interface and is totally configurable by the software. It efficiently controls the transceiver, frees up embedded processor cycles, and reduces the interrupt callback to the processor. Therefore, the TSCH hardware accelerator makes it possible to use a cheaper embedded processor or to operate the processor on a lower clock speed which results in lower power consumption. The power analysis of the implemented system shows that, in the minimal setting of the TSCH accelerator, only 0.1% is added to the power consumption of the digital baseband processor. The power overhead increases to 5.6% for supporting three parallel slotframes which is a widely used TSCH setting in multi-hop networks. In return, the embedded processor is relaxed of processing TSCH timing related interrupts that are required for software-based TSCH implementation. [ABSTRACT FROM AUTHOR]

Networks-on-Chip (NoC) is an impending research area for designing future System-on-Chip (SoC). NoC futures are allied with intellectual property (IP) reusability, parallel communication within IPs and scalability against standard interconnection NoC topology. In this paper, we introduce a new hybrid topology namely Four Regular Dense Spidergon (FRDS) based deterministic NoC architecture with 64 cores. We propose cluster and generic heuristic based approach For mapping of applications onto FRDS topology. Genetic algorithm (GA) ＋ simulated annealing (SA) have been considered under generic heuristic approach for successful mapping of core into topology and fair comparison of the performance of the proposed FRDS. Under normalized condition with respect to Mesh, experimental findings of proposed FRDS against real benchmark traces provide an average improvement on execution time with 1.20% and 4.81% over DMesh and ZMesh. Further, an average improvement on energy consumption was obtained 8.13% and 5.35% over DMesh and ZMesh. We adopt constant geometric traffic and the synthetic traffic pattern to measure the performance of proposed FRDS. The experimental results clearly indicates an improvement in power latency product under geometric traffic by 16.27% and 12.23% over DMesh and ZMesh. Similarly under synthetic traffic pattern, the proposed FRDS offers an improvement up to 22.51% and 45.53% over DMesh and ZMesh respectively. To realize the effectiveness of the link usage, brief evaluation of link utilization has been carried out with balanced load. • Four Regular Dense Spidergon (FRDS) – irregular NoC architecture • Unicast-multicast routing adopt for promising deadlock-free high-performance routing within the network • Promising improvements over mean packet latency; the total power of the network; and power latency product • Analysis of link utilization to understand the usage of directional and diagonal links of network topology • Analyzed with standard and real-time application benchmarks [ABSTRACT FROM AUTHOR]

High single instruction multiple data (SIMD) efficiency and low power consumption have made graphic processing units (GPUs) an ideal platform for many complex computational applications. Thousands of threads can be created by programmers and grouped into fixed-size SIMD batches, known as warps. High throughput is then achieved by concurrently executing such warps with minimal control overhead. However, if a branch instruction occurs, which assigns different paths to different threads, one warp will be broken into multiple warps that have to be executed serially, consequently reducing the efficiency advantage of SIMD. In this paper, the contemporary fixed-size warp design is abandoned for a hybrid warp size (HWS) mechanism. Mixed-size warps are generated according to HWS and are scheduled and issued flexibly. The simulation results show that this mechanism yields an average speedup of 1.20 over the baseline architecture for a wide variety of general purpose GPU applications. The paper also integrates HWS with dynamic warp formation (DWF), which is a well-known branch handling mechanism used to improve SIMD utilization by forming new warps out of split warps in real time. The simulation results show that the combination of DWF and HWS generates an average speedup of 1.27 over the DWF-only platform with an estimated area increase of about 1% of DWF. [ABSTRACT FROM AUTHOR]

• Computer vision system for timely image capture for swine carcass assessment. • Pig carcass detection, head & tail detection for pose classification. • System that captures lateral and dorsal views of pig carcasses. • Operating in real-time on edge devices. High animal welfare standards are essential for sustainable pork production. Current on-farm welfare assessments present challenges including cost, time consumption, and biosecurity risks. This study presents the initial step towards an automated animal welfare assessment system for swine carcasses. We introduce a computer vision system for capturing dorsal and lateral views of pig carcasses. The proposed system consists of a tracking and image acquisition system, which captures comprehensive lateral and dorsal views of pig carcasses as they pass by a camera installed at a slaughterhouse. During evaluation, the system achieved an accuracy of 92.5 % (74 out of 80 detections in a video with 40 carcasses) with minimal false positives and undetected positions, operating in real-time at 41.65 frames per second (FPS) with high confidence. The Detection manager module led to a remarkable reduction in erroneous detections, dropping from 38.75 % to 3.75 %. In addition to tail position data, leveraging head position data as an auxiliary mechanism substantially reduced missed detections to 6.25 % and erroneous detections to 1.25 %. This underscores the critical role of auxiliary mechanisms in enhancing system performance. This system marks the initial phase in developing an automated welfare assessment tool, paving the way for real-time welfare monitoring of carcasses in pork production. [ABSTRACT FROM AUTHOR]

• A field-programmable gate array (FPGA) based spiking neural network (SNN) accelerator architecture is proposed. • Approximate arithmetic units are utilized to realize energy efficient hardware implementation. • A variable precision method is proposed to minimize bit-width of weights. • The feasibility of utilizing the proposed method is verified via different SNN models. Spiking neural networks (SNNs) have been getting more research attention in recent years as the way they process information is suitable for building neuromorphic systems effectively. However, realizing SNNs on hardware is computationally expensive. To improve their efficiency for hardware implementation, a field-programmable gate array (FPGA) based SNN accelerator architecture is proposed and implemented using approximate arithmetic units. To identify the minimal required bit-width for approximate computation without any performance loss, a variable precision method is utilized to represent weights of the SNN. Unlike the conventional reduced precision method applied to all weights uniformly, the proposed variable precision method allows different bit-widths to represent weights and provide the feasibility of maximizing truncation effort for each weight. Four SNNs adopting different network configurations and training datasets are established to compare the performance of proposed accelerator architecture using the variable precision method with the proposed one using the conventional reduced precision method. Based on the experimental results, more than 40% of the weights require less bit-width when applying the variable precision method instead of the reduced precision method. With the variable precision method, the proposed architecture achieves 28% fewer ALUTs and 29% less power consumption than the proposed one using the reduced precision method. [ABSTRACT FROM AUTHOR]

Different artifacts will manifest, whenever an image is compressed by a lossy compression algorithm. Higher frequency details present in the image may tend to be eliminated by compression. In certain cases, compression may introduce small image structures and noise. This phenomenon will limit the image quality thereby making images to appear much less pleasant to the human eye. Furthermore, other machine learning tasks like object detectors performance will be reduced due to compression. In this paper, we introduce a novel deep neural network with densely connected parallel convolutions to remove such artifacts and to recover the original image from its perturbed version. The proposed algorithm is named as densely connected parallel convolutional neural network in short DPCNN. Parallel convolution provides model parallelism and reduce the training burden. Furthermore, the dense skip connections provide short paths for gradient back-propagation and alleviates the gradient vanishing problem. Moreover, skip connections reduce the feature redundancy by combining features from different levels and increases the learning efficiency. However, these skip connections increase the model complexity. A bottleneck layer is used to keep the model compactness and to reduce the model complexity. The proposed approach can be used as a preprocessing step in different computer vision tasks where images are degraded by compression. Different from other methods, the proposed method is able to remove compression artifacts generated at any quality factor (QF). The experiments on benchmark datasets show the superiority of the proposed method over other methods quantitatively and qualitatively. • Parallel convolutional layer provides model parallelism and achieves faster training. • Efficient flow of information and gradients is achieved with dense skip connections. • Reconstruction accuracy is improved with collective knowledge of the feature representations. • Bottleneck layer reduces the computational complexity and improves the model efficiency. [ABSTRACT FROM AUTHOR]

• Wavelet based cross connected residual-in-dense grouped CNN is proposed for SR. • The rich content of the image, i.e., edges is extracted using wavelet transform. • The residual connection is adopted that ease the training and improve the efficiency. • The computational complexity is reduced by adopting grouped convolutions. In clinical analysis and diagnosis, high resolution (HR) computed tomography (CT) images are required for proper treatment of a patient. Developing HR medical images by X-ray CT devices require extended radiation exposure with large radiative dosages, putting the patient at potential risk of inducing cancer. So, radiation exposure should be reduced. However, photon starvation and beam hardening in low-dose X-rays will cause severe artifacts. Thus, an accurate reconstruction of low-dose X-ray CT images is required. To this end, we propose a wavelet based multi-channel and multi-scale cross connected residual-in-dense grouped convolutional neural network (WCRDGCNN) for accurate super resolution (SR) of medical images. The adopted filter groups reduce the connection weights, thereby reducing the computational complexity. Gradient vanishing problem is tackled by using residual and dense skip connections. The extensive experimentation results on benchmark datasets show that our method outperforms the state-of-the-art SR methods. [ABSTRACT FROM AUTHOR]

The primacy of memristors for the realization of the synaptic circuit makes this element a promising component for implementing Artificial Neural Networks (ANN). However, integrating memristors with other ANN components is still an open area of research. Therefore, a circuit-level hybrid CMOS/Memristor architecture for implementing Bidirectional Associative Memory (BAM) is proposed in this paper. A passive bi-directional pre-differentiation crossbar architecture has been utilized and applied for the realization of synaptic weights. A compact, low voltage CMOS neuron that consumes a low amount of power is also designed. The noise tolerance of the proposed hardware is evaluated for typical networks with different sizes and a number of stored patterns. It is demonstrated that the hardware pattern retrieval rate is similar to its software-based counterpart. The influence of memristor non-idealities on BAM is also investigated for the first time, and a practical method has been introduced to deal with this issue. In comparison to the available circuit-level hardware implementation of memristive associative memories, the proposed circuit consumes significantly less power and retrieves the stored patterns notably faster. [ABSTRACT FROM AUTHOR]

To assist radiologists in breast cancer classification in automated breast ultrasound (ABUS) imaging, we propose a computer-aided diagnosis based on a convolutional neural network (CNN) that classifies breast lesions as benign and malignant. The proposed CNN adopts a modified Inception-v3 architecture to provide efficient feature extraction in ABUS imaging. Because the ABUS images can be visualized in transverse and coronal views, the proposed CNN provides an efficient way to extract multiview features from both views. The proposed CNN was trained and evaluated on 316 breast lesions (135 malignant and 181 benign). An observer performance test was conducted to compare five human reviewers' diagnostic performance before and after referring to the predicting outcomes of the proposed CNN. Our method achieved an area under the curve (AUC) value of 0.9468 with five-folder cross-validation, for which the sensitivity and specificity were 0.886 and 0.876, respectively. Compared with conventional machine learning-based feature extraction schemes, particularly principal component analysis (PCA) and histogram of oriented gradients (HOG), our method achieved a significant improvement in classification performance. The proposed CNN achieved a >10% increased AUC value compared with PCA and HOG. During the observer performance test, the diagnostic results of all human reviewers had increased AUC values and sensitivities after referring to the classification results of the proposed CNN, and four of the five human reviewers' AUCs were significantly improved. The proposed CNN employing a multiview strategy showed promise for the diagnosis of breast cancer, and could be used as a second reviewer for increasing diagnostic reliability. [ABSTRACT FROM AUTHOR]

Since the retinal blood vessel has been acknowledged as an indispensable element in both ophthalmological and cardiovascular disease diagnosis, the accurate segmentation of the retinal vessel tree has become the prerequisite step for automated or computer-aided diagnosis systems. In this paper, a supervised method is presented based on a pre-trained fully convolutional network through transfer learning. This proposed method has simplified the typical retinal vessel segmentation problem from full-size image segmentation to regional vessel element recognition and result merging. Meanwhile, additional unsupervised image post-processing techniques are applied to this proposed method so as to refine the final result. Extensive experiments have been conducted on DRIVE, STARE, CHASE_DB1 and HRF databases, and the accuracy of the cross-database test on these four databases is state-of-the-art, which also presents the high robustness of the proposed approach. This successful result has not only contributed to the area of automated retinal blood vessel segmentation but also supports the effectiveness of transfer learning when applying deep learning technique to medical imaging. [ABSTRACT FROM AUTHOR]

This paper proposes a constructive partitioning approach as an effective mapping approach for 2D Networks-on-Chip. Cluster-based mapping approach offers a promising improvement on the fastest initial mapping against the standard Networks-on-Chip (NoC) architecture. In this paper, the spectral partitioning algorithm is adopted for the fastest mapping with NoC, named SMA. The proposed spectral partitioning-based mapping approach (SMA) explores the efficacious NoC mapping concerning communication bandwidth, average hop counts, and total power consumption NoC architecture. The experimental analysis indicates that the proposed SMA outperforms existing partitioning approaches. [ABSTRACT FROM AUTHOR]

• We utilize LSTM in order to overcome the resistance of complex XOR-APUF. • We combine LSTM with the Fully Connected to reach better modeling accuracy. • We use PyTorch and Python 3.7 in the Google Colab to implement the attack model. • We improve the accuracy, runtime, and needed CRPs in the proposed attack. Physical Unclonable Functions (PUFs) have been proposed as potential hardware security primitives for various cryptographic applications in recent years. The idea of generating a unique fingerprint for each silicon chip by leveraging variations in the hardware manufacturing has created even more amazing comfortable, and affordable possibilities. On the other hand, some PUFs have shown to be vulnerable to modeling attacks. In this study, we investigate the ability of new Deep Learning (DL)-based technique as potential modeling attacks against more complicated PUF structures. To that end, we utilize the advantage of Long-Short Term Memory (LSTM) for attacking XOR-Arbiter PUFs (XOR-APUFs) for the first time. By combining the proposed LSTM with Fully Connected (FC) neural network, our FC-LSTM obtains 99% modeling accuracy on 7-XOR-APUF and 8-XOR-APUF. Furthermore, our experiments show that, despite the precise mathematical models of PUFs, our proposed modeling attacks effectively overcome the constraints imposed by prior studies in a shorter period of time and with fewer sets of training Challenge-Response Pairs (CRPs). [ABSTRACT FROM AUTHOR]

Abstract: In this work we propose a high performance elliptic curve cryptographic processor over GF(2163) for the applications that require high performance. It has three finite field (FF) RISC cores and a main controller to achieve instruction-level parallelism (ILP) for elliptic curve point multiplication. Customized instructions are proposed to decrease clock cycles. The interconnection among three FF cores and the main controller is obtained based on the analysis of both data dependency and critical path. The proposed design can reach 185MHz with 20,807 slices when implemented on Xilinx XC4VLX80 FPGA device and 263MHz with 217,904 gates when synthesized with TSMC .18μm CMOS technology. [Copyright &y& Elsevier]

Abstract: A light-emitting diode (LED) was fabricated using a commercial InGaN LED (460nm) and bivalent fluorescein salt dispersed in an epoxy matrix, as a primary light source and a luminescence conversion (LUCO) material, respectively. The LUCO LED emitted white light, which faded almost completely within 1h when a current of 20mA was continuously supplied. Based on the FT-IR, UV–visible and XPS spectral data, a large portion of bivalent fluorescein salt in the epoxy matrix underwent photochemical reactions, generating neutral fluorescein on irradiation with blue light. However, when bivalent fluorescein salt was dispersed in poly(methyl methacrylate) instead of epoxy, the luminous output of the resulting LUCO LED decreased much more slowly during continuous operation. Furthermore, the chemical structure of bivalent fluorescein salt remained unaltered during irradiation with blue light when the freeze-dried salt was kept under high vacuum. It was concluded that bivalent fluorescein salt should be almost completely protected from the environment for application as a LUCO material when coupled with a blue LED. [Copyright &y& Elsevier]

• DL models can classify rib fractures: fresh/acute, healed/old and nonfractured/normal. • Classifiers learn from surrounding tissue: background removal shown to lower accuracy. • InceptionV3 Block 7 had 96.0% accuracy & 94.0% recall for acute vs. old vs. normal. • InceptionV3 Block 7 had 97.8% accuracy, 94.6% recall & 94.7% AUC for acute vs. others. • InceptionV3 Block 7 crop inference time is 14/12 ms CPU/GPU, 1.7× faster than baseline. Rib fractures are injuries commonly assessed in trauma wards. Deep learning has demonstrated state-of-the-art accuracy for a variety of tasks, including image classification. This paper assesses the speed-accuracy trade-offs and general suitability of four popular convolutional neural networks to classify rib fractures from axial computed tomography imagery. We transfer learned InceptionV3, ResNet50, MobileNetV2, and VGG16 models, additionally training "decomposed" models comprised of taking only the first n blocks for each block for each architecture. Given that acute (new) fractures are generally most important to detect, we trained two types of models: a classful model with classes acute, old (healed), and normal (non-fractured); and a binary model with acute vs. the other classes. We found that the first 7 blocks of InceptionV3 achieved the best results and general speed-accuracy trade-off. The classful model achieved a 5-fold cross-validation average accuracy and macro recall of 96.00% and 94.0%, respectively. The binary model achieved a 5-fold cross-validation average accuracy, macro recall, and area under receiver operator characteristic curve of 97.76%, 94.6%, and 94.7%, respectively. On a Windows 10 PC with 32GB RAM and an Nvidia 1080ti GPU, the model's average CPU and GPU per-crop inference times were 13.6 and 12.2 ms, respectively. Compared to the InceptionV3 Block 7 classful model, a radiologist with 9 years of experience was less accurate but more sensitive to acute fractures; meanwhile, the deep learning model had fewer false positive diagnoses and better sensitivity to old fractures and normal ribs. The Cohen's Kappa between the two was 0.813. [ABSTRACT FROM AUTHOR]

• 3 Classifiers trained to diagnose erosion (early ankylosing spondylitis sign) from CT. • Random forest with texture features achieved 96% accuracy, 93% recall, and 0.97 AUC. • Modified InceptionV3 achieved 99% accuracy, 98% recall, and 0.97 AUC. • InceptionV3 had 8.4%/9.5% higher sensitivity/specificity than 9-year MSK radiologist. • Modified InceptionV3 could classify one sacroiliac joint in 58.5 ms (Nvidia 1080 ti). Ankylosing spondylitis (AS) is an arthritis with symptoms visible in medical imagery. This paper proposes, to the authors' best knowledge, the first use of statistical machine learning- and deep learning-based classifiers to detect erosion, an early AS symptom, via analysis of computed tomography (CT) imagery, giving some consideration to patient age in so doing. We used gray-level co-occurrence matrices and local binary patterns to generate input features to machine learning algorithms, specifically k -nearest neighbors (k -NN) and random forest. Deep learning solutions based on a modified InceptionV3 architecture were designed and tested, with one classifier produced by training with a cross-entropy loss function and another produced by additionally seeking to minimize validation loss. We found that the random forest classifiers outperform the k -NN classifiers and achieve an eightfold cross-validation average accuracy, recall, and area under receiver operator characteristic curve (ROC AUC) of 96.0%, 92.9%, and 0.97, respectively, for erosion vs. young control patients, and 82.4%, 80.6%, and 0.91, respectively, for erosion vs. old control patients. We found that the deep learning classifier trained without minimizing validation loss was best and achieves an eightfold cross-validation accuracy, recall, and ROC AUC of 99.0%, 97.5%, and 0.97, respectively, for erosion vs. all (combined young and old) control patients; this classifier outperforms a musculoskeletal radiologist with 9 years of experience in raw sensitivity and specificity by 8.4% and 9.5%, respectively. Despite the relatively small dataset on which we trained and cross-validated, our results indicate the potential of machine and deep learning to aid AS diagnosis, and further research using larger datasets should be conducted. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate whether the application of deep learning (DL) could achieve high diagnostic accuracy in differentiating between green colour coding, indicative of tophi, and clumpy artifacts observed in dual-energy computed tomography (DECT) scans., Methods: A comprehensive analysis of 18 704 regions of interest (ROIs) extracted from green foci in DECT scans obtained from 47 patients with gout and 27 gout-free controls was performed. The ROIs were categorized into three size groups: small, medium, and large. Convolutional neural network (CNN) analysis on a per-lesion basis and support vector machine (SVM) analysis on a per-patient basis were performed. The area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value of the models were compared., Results: For small ROIs, the sensitivity and specificity of the CNN model were 81.5% and 96.1%, respectively; for medium ROIs, 82.7% and 96.1%, respectively; for large ROIs, 91.8% and 86.9%, respectively. Additionally, the DL algorithm exhibited accuracies of 88.5%, 88.6%, and 91.0% for small, medium, and large ROIs, respectively. In the per-patient analysis, the SVM approach demonstrated a sensitivity of 87.2%, a specificity of 100%, and an accuracy of 91.8% in distinguishing between patients with gout and gout-free controls., Conclusion: Our study demonstrates the effectiveness of the DL algorithm in differentiating between green colour coding indicative of crystal deposition and clumpy artifacts in DECT scans. With high sensitivity, specificity, and accuracy, the utilization of DL in DECT for diagnosing gout enables precise lesion classification, facilitating early-stage diagnosis and promoting timely intervention approaches., (© The Author(s) 2024. Published by Oxford University Press on behalf of the British Society for Rheumatology. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Schizophrenia (SZ) has been acknowledged as a highly intricate mental disorder for a long time. In fact, individuals with SZ experience a blurred line between fantasy and reality, leading to a lack of awareness about their condition, which can pose significant challenges during the treatment process. Due to the importance of the issue, timely diagnosis of this illness can not only assist patients and their families in managing the condition but also enable early intervention, which may help prevent its advancement. EEG is a widely utilized technique for investigating mental disorders like SZ due to its non-invasive nature, affordability, and wide accessibility. In this study, our main goal is to develop an optimized system that can achieve automatic diagnosis of SZ with minimal input information. To optimize the system, we adopted a strategy of using single-channel EEG signals and integrated knowledge distillation and transfer learning techniques into the model. This approach was designed to improve the performance and efficiency of our proposed method for SZ diagnosis. Additionally, to leverage the pre-trained models effectively, we converted the EEG signals into images using Continuous Wavelet Transform (CWT). This transformation allowed us to harness the capabilities of pre-trained models in the image domain, enabling automatic SZ detection with enhanced efficiency. To achieve a more robust estimate of the model's performance, we employed fivefold cross-validation. The accuracy achieved from the 5-s records of the EEG signal, along with the combination of self-distillation and VGG16 for the P4 channel, is 97.81. This indicates a high level of accuracy in diagnosing SZ using the proposed method., (© 2024. Australasian College of Physical Scientists and Engineers in Medicine.)

In recent days, non-communicable diseases (NCDs) require more attention since they require specialized infrastructure for treatment. As per the cancer population registry estimate, nearly 800,000 new cancer cases will be detected yearly. The statistics alarm the need for early cancer detection and diagnosis. Cancer identification can be made either through manual efforts or by computer-aided algorithms. Manual efforts-based cancer detection is labor intensive and also offers more time complexity. In contrast, computer-aided algorithms offer feasibility in reducing time and manual efforts. With the motivation to develop a computer-aided diagnosis system for NCD, we developed a cancer detection methodology. In the present article, a deep learning (DL)-based cancer identification model is developed. In DL-based architectures, the features are generally extracted using convolutional neural networks. The proposed attention-guided, densely connected residual, and dilated convolution deep neural network called DeepHistoNet acquire precise patterns for classification. Experimentation has been carried out on Kasturba Medical College (KMC), TCGA-LIHC, and LC25000 datasets to prove the robustness of the model. Performance evaluation metrics like F1-score, sensitivity, specificity, recall, and accuracy validate the experimentation. Experimental results demonstrate that the proposed DeepHistoNet model outperforms the other state-of-the-art methods. The proposed model has been able to classify the KMC liver dataset with 97.1% accuracy and 0.9867 value of area under the curve-receiver operating characteristic curve (AUC-ROC), which is the best result obtained compared to the state-of-the-art techniques. The performance of the DeepHistoNet has been even better on the LC25000 dataset. On the LC25000 dataset, the proposed model achieved 99.8% classification accuracy. To our knowledge, DeepHistoNet is a novel approach for multiple histopathological image classification. RESEARCH HIGHLIGHTS: A novel robust DL model is proposed for histopathological image carcinoma classification. The precise patterns for accurate classification are extracted using dense cross-connected residual blocks. Spatial attention is provided to the network so that the spatial information is not lost during the feature extraction. DeepHistoNet is trained and evaluated on the liver, lung, and colon histopathology datasets to demonstrate its resilience. The results are promising and outperform state-of-the-art techniques. The proposed methodology has obtained the AUC-ROC value of 0.9867 with a classification accuracy of 97.1% on the KMC dataset. The proposed DeepHistoNet has classified the LC25000 dataset with 99.8% accuracy. The results are the best obtained till date., (© 2023 Wiley Periodicals LLC.)

Purpose: Medical imaging can be used to estimate a patient's biological age, which may provide complementary information to clinicians compared to chronological age. In this study, we aimed to develop a method to estimate a patient's age based on their chest CT scan. Additionally, we investigated whether chest CT estimated age is a more accurate predictor of lung cancer risk compared to chronological age., Methods: To develop our age prediction model, we utilized composite CT images and Inception-ResNet-v2. The model was trained, validated, and tested on 13,824 chest CT scans from the National Lung Screening Trial, with 91% for training, 5% for validation, and 4% for testing. Additionally, we independently tested the model on 1849 CT scans collected locally. To assess chest CT estimated age as a risk factor for lung cancer, we computed the relative lung cancer risk between two groups. Group 1 consisted of individuals assigned a CT age older than their chronological age, while Group 2 comprised those assigned a CT age younger than their chronological age., Results: Our analysis revealed a mean absolute error of 1.84 years and a Pearson's correlation coefficient of 0.97 for our local data when comparing chronological age with the estimated CT age. The model showed the most activation in the area associated with the lungs during age estimation. The relative risk for lung cancer was 1.82 (95% confidence interval, 1.65-2.02) for individuals assigned a CT age older than their chronological age compared to those assigned a CT age younger than their chronological age., Conclusion: Findings suggest that chest CT age captures some aspects of biological aging and may be a more accurate predictor of lung cancer risk than chronological age. Future studies with larger and more diverse patients are required for the generalization of the interpretations., (© 2023. CARS.)

Purpose: The usage of iodinated contrast media (ICM) can improve the sensitivity and specificity of computed tomography (CT) for many clinical indications. However, the adverse effects of ICM administration can include renal injury, life-threatening allergic-like reactions, and environmental contamination. Deep learning (DL) models can generate full-dose ICM CT images from non-contrast or low-dose ICM administration or generate non-contrast CT from full-dose ICM CT. Eliminating the need for both contrast-enhanced and non-enhanced imaging or reducing the amount of required contrast while maintaining diagnostic capability may reduce overall patient risk, improve efficiency and minimize costs. We reviewed the current capabilities of DL to reduce the need for contrast administration in CT., Methods: We conducted a systematic review of articles utilizing DL to reduce the amount of ICM required in CT, searching MEDLINE, Embase, Compendex, Inspec, and Scopus to identify papers published from 2016 to 2022. We classified the articles based on the DL model and ICM reduction., Results: Eighteen papers met the inclusion criteria for analysis. Of these, ten generated synthetic full-dose (100%) ICM from real non-contrast CT, while four augmented low-dose to full-dose ICM CT. Three used DL to create synthetic non-contrast CT from real 100% ICM CT, while one paper used DL to translate the 100% ICM to non-contrast CT and vice versa. DL models commonly used generative adversarial networks trained and tested by paired contrast-enhanced and non-contrast or low ICM CTs. Image quality metrics such as peak signal-to-noise ratio and structural similarity index were frequently used for comparing synthetic versus real CT image quality., Conclusion: DL-generated contrast-enhanced or non-contrast CT may assist in diagnosis and radiation therapy planning; however, further work to optimize protocols to reduce or eliminate ICM for specific pathology is still needed along with a dedicated assessment of the clinical utility of these synthetic images., (© 2023. CARS.)

The pulse transit time (PTT) based method has been suggested as a continuous, cuffless and non-invasive approach to estimate blood pressure. It is of paramount importance to accurately determine the pulse transit time from the measured electrocardiogram (ECG) and photoplethysmo-gram (PPG) signals. We apply the celebrated Hilbert-Huang Transform (HHT) to process both the ECG and PPG signals, and improve the accuracy of the PTT estimation. Further, the blood pressure variation is obtained by using a well-established formula reflecting the relationship between the blood pressure and the estimated PTT. Simulation results are provided to illustrate the effectiveness of the proposed method.