Monitoring continuous BP signal is an important issue, because blood pressure (BP) varies over days, minutes, or even seconds for short-term cases. Most of photoplethysmography (PPG)-based BP ...estimation methods are susceptible to noise and only provides systolic blood pressure (SBP) and diastolic blood pressure (DBP) prediction. Here, instead of estimating a discrete value, we focus on different perspectives to estimate the whole waveform of BP. We propose a novel deep learning model to learn how to perform signal-to-signal translation from PPG to arterial blood pressure (ABP). Furthermore, using a raw PPG signal only as the input, the output of the proposed model is a continuous ABP signal. Based on the translated ABP signal, we extract the SBP and DBP values accordingly to ease the comparative evaluation. Our prediction results achieve average absolute error under 5 mmHg, with 70% confidence for SBP and 95% confidence for DBP without complex feature engineering. These results fulfill the standard from Association for the Advancement of Medical Instrumentation (AAMI) and the British Hypertension Society (BHS) with grade A. From the results, we believe that our model is applicable and potentially boosts the accuracy of an effective signal-to-signal continuous blood pressure estimation.
This paper proposes a novel task-consistency learning method that enables us to train a vacant space detection network (target task) based on the logic consistency with the semantic outcomes from a ...flow-based motion behavior classifier (source task) in a parking lot. Note that the source task can introduce false detection during task-consistency learning, which implies noisy rewards or supervision. The target network can be trained in a reinforcement learning setting by appropriately designing the reward mechanism upon semantic consistency. We also introduce a novel symmetric constraint to detect corrupted samples and reduce the effect of noisy rewards. Unlike conventional corrupted learning methods that use only training losses to identify corrupted samples, our symmetric constraint also explores the relationship among training samples to improve performance. Compared with conventional supervised detection methods, the main contribution of our work is the ability to learn a vacant space detector via semantic consistency rather than supervised labels. The dynamic learning property allows the proposed detector to be easily deployed and updated in various lots without heavy human loads. Experiments demonstrate that our noisy task consistency mechanism can be successfully applied to train a vacant space detector from scratch.
Due to the growing public awareness of cardiovascular disease (CVD), blood pressure (BP) estimation models have been developed based on physiological parameters extracted from both electrocardiograms ...(ECGs) and photoplethysmograms (PPGs). Still, in order to enhance the usability as well as reduce the sensor cost, researchers endeavor to establish a generalized BP estimation model using only PPG signals. In this paper, we propose a deep neural network model capable of extracting 32 features exclusively from PPG signals for BP estimation. The effectiveness and accuracy of our proposed model was evaluated by the root mean square error (RMSE), mean absolute error (MAE), the Association for the Advancement of Medical Instrumentation (AAMI) standard and the British Hypertension Society (BHS) standard. Experimental results showed that the RMSEs in systolic blood pressure (SBP) and diastolic blood pressure (DBP) are 4.643 mmHg and 3.307 mmHg, respectively, across 9000 subjects, with 80.63% of absolute errors among estimated SBP records lower than 5 mmHg and 90.19% of absolute errors among estimated DBP records lower than 5 mmHg. We demonstrated that our proposed model has remarkably high accuracy on the largest BP database found in the literature, which shows its effectiveness compared to some prior works.
Locally advanced colon cancer (LACC) is associated with surgical challenges during R0 resection, increased postoperative complications, and unfavorable treatment outcomes. Neoadjuvant concurrent ...chemoradiotherapy followed by surgical resection is an effective treatment strategy that can increase the complete surgical resection rate and improve the patient survival rate. This study investigated the efficacy and toxicity of concurrent chemoradiotherapy in patients with LACC as well as the prognosis and long-term clinical outcomes of these patients.
From January 2012 to July 2020, we retrospectively reviewed the real-world data of 75 patients with LACC who received neoadjuvant concurrent chemoradiotherapy. The chemotherapy regimen consisted of folinic acid, 5-fluorouracil, and oxaliplatin (FOLFOX). The following data were obtained from medical records: patients' characteristics, pathologic results, toxicity, and long-term oncologic outcome.
Of the 75 patients, 13 (17.3%) had pathologic complete responses. Hematologic adverse effects were the most common (grade 1 anemia: 80.0% and leukopenia: 82.7%). Conversely, grade 2 or 3 adverse effects were relatively uncommon (<10%). Pathologic N downstaging, ypT0, and pathologic complete responses were significant prognostic factors for patient survival. Multivariate analysis revealed that pathologic N downstaging was an independent predictor of patients' overall survival (P = 0.019). The estimated 5-year overall and disease-free survival rates were 68.6% and 50.6%, and the medians of overall and disease-free survival periods were 72.3 and 58.7 months, respectively. Moreover, patients with pathologic complete responses had improved overall survival (P = 0.039) and an improved local recurrence control rate (P = 0.042) but an unfavorable distant metastasis control rate (P = 0.666) in the long-term follow-up.
The long-term oncologic outcome of patients with LACC following concurrent chemoradiotherapy is acceptable, and the adverse effects seem to be tolerable. Pathologic N downstaging was an independent prognostic factor for patients' overall survival. However, a large prospective, randomized control study is required to confirm the current results.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The phenomenal advances of cloud computing technology have given rise to the research area of privacy-preserving signal processing, which aims to preserve information privacy even when the signals ...are processed in an insecure environment. Privacy-preserving information hiding is a multidisciplinary study that has opened up a great deal of intriguing real-life applications, such as data exfiltration prevention, data origin authentication, and electronic data management. Information hiding is a practice of embedding intended messages into carrier signals through imperceptible alterations. In view of some content-sensitive scenarios, however, the ability to preserve perfect copies of signals is of crucial importance, for instance, considering the inadequate robustness of recent artificial intelligence-aided automated systems against noise perturbations. Reversibility of information hiding systems is a valuable property that permits recovery of original carrier signals if desired. In this paper, we propose a novel privacy-preserving reversible information hiding scheme inspired by the mathematical concept of quadratic residues. A quadratic residue has four (not necessarily distinct) square roots, which enables payloads to be encoded in a dynamic fashion. Furthermore, a predictive model based upon the projection theorem is devised to assist carrier signal recovery. The experimental results showed significant improvements over the state-of-the-art methods with regard to capacity, fidelity, and reversibility.
The SOTA methods proposed voxelization or pillarization to regularize unordered point clouds, improving computing efficiency for LiDAR-based 3D object detection. However, they usually trade partial ...accuracy for speed. Thus, we bring up a new problem setting: "Is it possible to keep high detection accuracy while point-cloud quantization is applied?". To this end, we found that the inconsistent sparsity of the point cloud over the depth distance, which is still an open question, might be the main reason. To address the inconsistency effect, we first proposed a new pillar-based vehicle detection model, named SVDnet, in which novel plug-ins are introduced in its backbone and neck. Specifically, a novel low-rank objective is designed to force the backbone to extract distance/sparsity-aware features and suppress the other feature variations among vehicle samples. Next, we alleviated the remaining feature inconsistency resulting from distance/sparsity in the neck by dynamic feature selection and adaptive feature fusion. Here, feature selection is realized by a position attention network, while feature fusion is achieved by a Distance Alignment Ratio-generation Network (DARN). Later, the selected and fused features, less sensitive to sparsity, are concatenated and fed to an SSD-like detection head. Besides, we also integrate the proposed plug-ins with multiple pillar/voxel-based methods for performance boosting. Our evaluation shows that SVDnet improves the average precision of the distant cases by 8.11% with only 0.23 milliseconds speed drop compared with PointPillars. Furthermore, the extensional results validate that our plug-ins can help SOTA pillar/voxel-based methods to gain noticeable improvement, especially for far-range objects.
There exist many types of intelligent security sensors in the environment of the Internet of Things (IoT) and cloud computing. Among them, the sensor for biometrics is one of the most important ...types. Biometric sensors capture the physiological or behavioral features of a person, which can be further processed with cloud computing to verify or identify the user. However, a low-resolution (LR) biometrics image causes the loss of feature details and reduces the recognition rate hugely. Moreover, the lack of resolution negatively affects the performance of image-based biometric technology. From a practical perspective, most of the IoT devices suffer from hardware constraints and the low-cost equipment may not be able to meet various requirements, particularly for image resolution, because it asks for additional storage to store high-resolution (HR) images, and a high bandwidth to transmit the HR image. Therefore, how to achieve high accuracy for the biometric system without using expensive and high-cost image sensors is an interesting and valuable issue in the field of intelligent security sensors. In this paper, we proposed DDA-SRGAN, which is a generative adversarial network (GAN)-based super-resolution (SR) framework using the dual-dimension attention mechanism. The proposed model can be trained to discover the regions of interest (ROI) automatically in the LR images without any given prior knowledge. The experiments were performed on the CASIA-Thousand-v4 and the CelebA datasets. The experimental results show that the proposed method is able to learn the details of features in crucial regions and achieve better performance in most cases.
As an interdisciplinary research between watermarking and cryptography, privacy-aware reversible watermarking permits a party to entrust the task of embedding watermarks to a cloud service provider ...without compromising information privacy. The early development of schemes was primarily based upon traditional symmetric-key cryptosystems, which involve an extra implementation cost of key exchange. Although recent research attentions were drawn to schemes compatible with asymmetric-key cryptosystems, there were notable limitations in the practical aspects. In particular, the host signal must either be enciphered in a redundant way or be pre-processed prior to encryption, which would largely limit the storage efficiency and scheme universality. To relax the restrictions, we propose a novel research paradigm and devise different schemes compatible with different homomorphic cryptosystems. In the proposed schemes, the encoding function is recognised as an operation of adding noise, whereas the decoding function is perceived as a corresponding denoising process. Both online and offline content-adaptive predictors are developed to assist watermark decoding for various operational requirements. A three-way tradeoff between the capacity, fidelity, and reversibility is analysed mathematically and empirically. It is shown that the proposed schemes achieve the state-of-the-art performance.
Biometrics has been shown to be an effective solution for the identity recognition problem, and iris recognition, as well as face recognition, are accurate biometric modalities, among others. The ...higher resolution inside the crucial region reveals details of the physiological characteristics which provides discriminative information to achieve extremely high recognition rate. Due to the growing needs for the IoT device in various applications, the image sensor is gradually integrated in the IoT device to decrease the cost, and low-cost image sensors may be preferable than high-cost ones. However, low-cost image sensors may not satisfy the minimum requirement of the resolution, which definitely leads to the decrease of the recognition accuracy. Therefore, how to maintain high accuracy for biometric systems without using expensive high-cost image sensors in mobile sensing networks becomes an interesting and important issue. In this paper, we proposed MA-SRGAN, a single image super-resolution (SISR) algorithm, based on the mask-attention mechanism used in Generative Adversarial Network (GAN). We modified the latest state-of-the-art (nESRGAN+) in the GAN-based SR model by adding an extra part of a discriminator with an additional loss term to force the GAN to pay more attention within the region of interest (ROI). The experiments were performed on the CASIA-Thousand-v4 dataset and the Celeb Attribute dataset. The experimental results show that the proposed method successfully learns the details of features inside the crucial region by enhancing the recognition accuracies after image super-resolution (SR).
This aim of this study was to evaluate the effects of time interval between the completion of radiotherapy and robotic-assisted surgery on the outcomes among patients with rectal cancer undergoing ...preoperative concurrent chemoradiotherapy (CCRT).
In total, 116 patients with stage I-III rectal cancer who underwent preoperative CCRT and robotic-assisted surgery between September 2013 and February 2019 were enrolled. Patients were categorized into two groups based on the time interval: group A (10-12 weeks) and group B (≥ 12 weeks).
Among the 116 enrolled patients, 98 (84.5%) had middle and lower rectal cancers. Two (1.7%) patients underwent abdominoperineal resection with a sphincter preservation rate of 98.3%. Thirty-seven (31.9%) patients had a pathologic complete response (pCR). The circumferential resection margin and distal resection margin were positive in 2 (1.7%) and 1 (0.9%) patients, respectively. Therefore, the R0 resection rate was 97.4%. A total of 24 (22.4%) patients experienced postoperative relapse and 12 (10.3%) patients died; these were slightly more common in group B than in group A (28.8% vs 15.8% and 15.3% vs 5.3%, respectively; both P > 0.05); however, this difference was nonsignificant. Three-year disease-free survival (DFS) and overall survival (OS) were 75% and 89%, respectively, among all patients. Non-significant trend of favorable 3-year DFS, 3-year OS, 3-year locoregional control rate and 3-year distant metastasis control rate were observed in group A compared with group B (all P > 0.05).
Robotic-assisted surgery after a longer interval is safe and feasible for patients with rectal cancer undergoing preoperative CCRT. The present study's results suggested that the time interval of 10-12 weeks can be considered because comparable clinical and perioperative outcomes and preferable oncological outcomes were observed for interval of this length. However, future prospective randomized clinical trials are required to verify the present finding.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK