Previously, the 2-D convolutional neural networks (2-D-CNNs) have been introduced to classify the human activity based on micro-Doppler radar. Whereas these methods can achieve high accuracy, their ...application is limited by their high computational complexity. In this letter, an end-to-end 1-D convolutional neural network (1-D-CNN) is first proposed for radar-based sensors for human activity classification. In the proposed 1-D-CNN, the inception densely block (ID-Block) tailored for the 1-D-CNN is proposed. The ID-Block incorporated the three techniques: inception module, dense network, and network-in-network techniques. With these techniques, the proposed network not only achieve a high classification accuracy but also keep the computational complexity at a low level. The experiments results show that the classification accuracy of the proposed method is 96.1% for human activity classification that is higher than that of existing state-of-art 2-D-CNN methods while the computational speed of forward propagation is increased by about (<inline-formula> <tex-math notation="LaTeX">2.71\times </tex-math></inline-formula> to <inline-formula> <tex-math notation="LaTeX">29.68\times </tex-math></inline-formula>) of the existing 2-D-CNN methods.
Diabetic retinopathy (DR) is an important cause of blindness worldwide. However, DR is hard to be detected in the early stages, and the diagnostic procedure can be time-consuming even for the ...experienced experts. Therefore, a computer-aided diagnosis method based on deep learning algorithms is proposed to automatedly diagnose the referable diabetic retinopathy by classifying color retinal fundus photographs into two grades. In this paper, a novel convolutional neural network model with the Siamese-like architecture is trained with a transfer learning technique. Different from the previous works, the proposed model accepts binocular fundus images as inputs and learns their correlation to help to make a prediction. In the case with a training set of only 28 104 images and a test set of 7024 images, an area under the receiver operating curve of 0.951 is obtained by the proposed binocular model, which is 0.011 higher than that obtained by the existing monocular model. To further verify the effectiveness of the binocular design, a binocular model for five-class DR detection is also trained and evaluated on a 10% validation set. The result shows that it achieves a kappa score of 0.829 which is higher than that of the existing non-ensemble model.
Many deep learning (DL) models have shown exceptional promise in radar-based human activity recognition (HAR) area. For radar-based HAR, the raw data is generally converted into a 2-D spectrogram by ...using short-time Fourier transform (STFT). All the existing DL methods treat the spectrogram as an optical image, and thus the corresponding architectures such as 2-D convolutional neural networks (2D-CNNs) are adopted in those methods. These 2-D methods that ignore temporal characteristics ordinarily lead to a complex network with a huge amount of parameters but limited recognition accuracy. In this paper, for the first time, the radar spectrogram is treated as a time sequence with multiple channels. Hence, we propose a DL model composed of 1-D convolutional neural networks (1D-CNNs) and long short-term memory (LSTM). The experiments results show that the proposed model can extract spatio-temporal characteristics of the radar data and thus achieves the best recognition accuracy and relatively low complexity compared to the existing 2D-CNN methods.
Human detection and activity classification has recently become a key technology in many applications, e.g., human computer interaction and surveillance for public and industrial security. In this ...work, we propose a novel end-to-end deep learning-based framework called the Fourier convolutional neural network (F-Convents) to tackle this problem. The input of F-ConvNet consists of raw frames of radar data. It is fed to a new layer called the Fourier layer, which transforms the raw radar signal into a domain optimized for the classification task. A novel weight initialization method tailored for the Fourier layer is also proposed. Moreover, we use dilated convolutions to further improve both performance and efficiency. To achieve better convergence and accuracy, a multi-scale and multi-task loss consisting of cross-entropy and triplet loss with a novel training paradigm called dynamic training is proposed. Experimental results show that F-ConvNet surpasses state-of-the-art methods by 3% in terms of classification accuracy.
Currently, limited data on tyrosine kinase inhibitors as neoadjuvant therapy exist. This prospective study aimed to investigate the efficacy and safety of preoperative gefitinib in patients with ...stage II-IIIA operable non–small cell lung cancer (NSCLC).
This was a single-arm, phase II trial performed in the Shanghai Cancer Center. Between August 2013 and October 2015, patients with operable stage II-IIIA NSCLC with epidermal growth factor receptor (EGFR) exon 19 deletion or exon 21 L858R mutation were enrolled. Patients were treated with preoperative gefitinib (250 mg once daily for 42 days), followed by surgical resection. The primary endpoint was objective response rate (ORR); secondary endpoints were the rate of major pathologic response (MPR), disease-free survival (DFS), overall survival, and adverse events (AEs). ORR was defined as the proportion of patients achieving complete response or partial response radiologically. MPR was defined as no more than 10% viable tumor.
Of the 35 eligible patients, 33 were considered as intention-to-treat population. ORR, the primary endpoint, was 54.5% (95% confidence interval CI, 37.7-70.7), and the rate of MPR was 24.2% (95% CI, 11.9-40.4). Median DFS was 33.5 months (95% CI, 19.7-47.3); median overall survival was not reached. Skin toxicity (24/35,68.6%) and gastrointestinal symptoms (17/35,48.6%) were the most common AEs; no patients reported grade 3 or 4 AEs. After surgery, 4 patients experienced chylothorax (4/33,12.1%). Patients with MPR had a prolonged survival compared with those without (DFS, P = .019).
Neoadjuvant therapy with gefitinib in patients with stage II-IIIA NSCLC is safe and may be a viable treatment for patients whose tumors have EGFR mutations. Patients with MPR were associated with improved survival.
Display omitted
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Abstract
Background
Previous studies have indicated coronavirus disease 2019 (COVID-19) patients with cancer have a high fatality rate.
Methods
We conducted a systematic review of studies that ...reported fatalities in COVID-19 patients with cancer. A comprehensive meta-analysis that assessed the overall case fatality rate and associated risk factors was performed. Using individual patient data, univariate and multivariable logistic regression analyses were used to estimate odds ratios (OR) for each variable with outcomes.
Results
We included 15 studies with 3019 patients, of which 1628 were men; 41.0% were from the United Kingdom and Europe, followed by the United States and Canada (35.7%), and Asia (China, 23.3%). The overall case fatality rate of COVID-19 patients with cancer measured 22.4% (95% confidence interval CI = 17.3% to 28.0%). Univariate analysis revealed age (OR = 3.57, 95% CI = 1.80 to 7.06), male sex (OR = 2.10, 95% CI = 1.07 to 4.13), and comorbidity (OR = 2.00, 95% CI = 1.04 to 3.85) were associated with increased risk of severe events (defined as the individuals being admitted to the intensive care unit, or requiring invasive ventilation, or death). In multivariable analysis, only age greater than 65 years (OR = 3.16, 95% CI = 1.45 to 6.88) and being male (OR = 2.29, 95% CI = 1.07 to 4.87) were associated with increased risk of severe events.
Conclusions
Our analysis demonstrated that COVID-19 patients with cancer have a higher fatality rate compared with that of COVID-19 patients without cancer. Age and sex appear to be risk factors associated with a poorer prognosis.
Surgery for pre- and minimally invasive lung adenocarcinoma Zhang, Yang; Ma, Xiangyi; Shen, Xuxia ...
Journal of thoracic and cardiovascular surgery/The Journal of thoracic and cardiovascular surgery/The journal of thoracic and cardiovascular surgery,
February 2022, 2022-02-00, 20220201, Volume:
163, Issue:
2
Journal Article
Peer reviewed
Open access
Adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) are the pre- and minimally invasive forms of lung adenocarcinoma. We aimed to investigate safety results and survival outcomes ...following different types of surgical resection in a large sample of patients with AIS/MIA.
Medical records of patients with lung AIS/MIA who underwent surgery between 2012 and 2017 were retrospectively reviewed. Clinical characteristics, surgical types and complications, recurrence-free survival, and overall survival were investigated.
A total of 1644 patients (422 AIS and 1222 MIA) were included. The overall surgical complication rate was significantly lower in patients receiving wedge resection (1.0%), and was comparable between patients undergoing segmentectomy (3.3%) or lobectomy (5.6%). Grade ≥ 3 complications occurred in 0.1% of patients in the wedge resection group, and in a comparable proportion of patients in the segmentectomy group (1.5%) and the lobectomy group (1.5%). There was no lymph node metastasis. The 5-year recurrence-free survival rate was 100%. The 5-year overall survival rate in the entire cohort was 98.8%, and was comparable among the wedge resection group (98.8%), the segmentectomy group (98.2%), and the lobectomy group (99.4%).
Sublobar resection, especially wedge resection without lymph node dissection, may be the preferred surgical procedure for patients with AIS/MIA. If there are no risk factors, postoperative follow-up intervals may be extended. These implications should be validated in further studies.
Display omitted
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
This study investigated the accuracy of intraoperative frozen section (FS) diagnosis for predicting the final pathology (FP) of peripheral small-sized lung adenocarcinoma and evaluated its usefulness ...in sublobar resection.
The records of 803 patients with clinical stage I peripheral lung adenocarcinoma who underwent sublobar resection for FS diagnosis to guide surgical strategy were reviewed. The surgical extension was mainly based on FS. The FS were stratified into atypical adenomatous hyperplasia, adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma. The diagnostic accuracy of FS, the reasons for the discrepancy between FS and FP, and the clinical influence of the FS errors were evaluated. To assess the survival of patients with different subtypes after surgery, 301 patients were identified for prognosis evaluation.
The total concordance rate between FS and FP was 84.4%. When atypical adenomatous hyperplasia, AIS, and MIA were classified together as a low-risk group, the concordance rate was 95.9%. Most discrepant cases were the underestimation of AIS and MIA. The diagnostic accuracy of FS for tumors ≤ 1 cm and larger than 1 cm in diameter was 79.6% and 90.8%, respectively (P < .01). The FS errors had significant clinical impact on 0.9% of the 803 patients due to insufficient resection. The 5-year recurrence-free survival rate (100%) was significantly better for the patients with AIS/MIA than for patients with invasive adenocarcinoma (74.1%, P < .01).
Frozen pathology has a high concordance rate with FP. Precise diagnosis by intraoperative FS is an effective method to guide resection strategy for peripheral small-sized lung adenocarcinoma.
Abstract Purpose To assess hypo-fractionated particle beam therapy (PBT)’s efficacy relative to that of photon stereotactic body radiotherapy (SBRT) for early stage (ES) non-small cell lung cancer ...(NSCLC). Methods Eligible studies were identified through extensive searches of the PubMed, Medline, Google-scholar, and Cochrane library databases from 2000 to 2016. Original English publications of ES NSCLC were included. A meta-analysis was performed to compare the survival outcome, toxicity profile, and patterns of failure following each treatment. Results 72 SBRT studies and 9 hypo-fractionated PBT studies (mostly single-arm) were included. PBT was associated with improved overall survival (OS; p = 0.005) and progression-free survival (PFS; p = 0.01) in the univariate meta-analysis. The OS benefit did not reach its statistical significance after inclusion of operability into the final multivariate meta-analysis ( p = 0.11); while the 3-year local control (LC) still favored PBT ( p = 0.03). Conclusion Although hypo-fractionated PBT may lead to additional clinical benefit when compared with photon SBRT, no statistically significant survival benefit from PBT over SBRT was observed in the treatment of ES NSCLC in this hypothesis-generating meta-analysis after adjusting for potential confounding variables.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Extreme poverty can be alleviated through entrepreneurship, but starting a business can be elusive among impoverished people, partly due to a lack of access to entrepreneurial opportunities. In the ...current literature, the source of entrepreneurial opportunity for the poor remains unclear. To address this knowledge gap, we used the opportunity co-creation perspective to examine the impact of opportunity co-creation on the entrepreneurial performance of the poor and its various influence pathways. We developed a chain multiple mediation model and surveyed 330 poor entrepreneurs from the Wuling Mountain Region, which used to be one of the 14 contiguous poverty-stricken areas in China until the end of 2020 when the country announced the eradication of extreme poverty. Data analysis was done using structural equation modeling (SEM). The results suggest that opportunity co-creation has a direct positive effect on the entrepreneurial performance of the poor and an indirect positive effect through the chain mediating effect of opportunity beliefs and entrepreneurial behavior. The findings confirm that opportunity co-creation is a critical factor for entrepreneurs in poor areas to overcome the lack of entrepreneurial opportunities and can also contribute to a better understanding of opportunity beliefs and entrepreneurial behavior. Furthermore, these results have important implications for poor entrepreneurs and provide opportunity co-creation solutions for poverty reduction through entrepreneurship.