| 1. |
- Javaheripour, Nooshin, et al.
(författare)
-
Altered resting-state functional connectome in major depressive disorder : a mega-analysis from the PsyMRI consortium
- 2021
-
Ingår i: Translational Psychiatry. - : Springer Nature. - 2158-3188. ; 11:1
-
Tidskriftsartikel (refereegranskat)abstract
- Major depressive disorder (MDD) is associated with abnormal neural circuitry. It can be measured by assessing functional connectivity (FC) at resting-state functional MRI, that may help identifying neural markers of MDD and provide further efficient diagnosis and monitor treatment outcomes. The main aim of the present study is to investigate, in an unbiased way, functional alterations in patients with MDD using a large multi-center dataset from the PsyMRI consortium including 1546 participants from 19 centers (). After applying strict exclusion criteria, the final sample consisted of 606 MDD patients (age: 35.8 +/- 11.9 y.o.; females: 60.7%) and 476 healthy participants (age: 33.3 +/- 11.0 y.o.; females: 56.7%). We found significant relative hypoconnectivity within somatosensory motor (SMN), salience (SN) networks and between SMN, SN, dorsal attention (DAN), and visual (VN) networks in MDD patients. No significant differences were detected within the default mode (DMN) and frontoparietal networks (FPN). In addition, alterations in network organization were observed in terms of significantly lower network segregation of SMN in MDD patients. Although medicated patients showed significantly lower FC within DMN, FPN, and SN than unmedicated patients, there were no differences between medicated and unmedicated groups in terms of network organization in SMN. We conclude that the network organization of cortical networks, involved in processing of sensory information, might be a more stable neuroimaging marker for MDD than previously assumed alterations in higher-order neural networks like DMN and FPN.
|
|
| 2. |
- Javed, Muhammad Ahsan, et al.
(författare)
-
Impact of intensified chemotherapy in metastatic pancreatic ductal adenocarcinoma (PDAC) in clinical routine in Europe
- 2019
-
Ingår i: Pancreatology (Print). - : Elsevier. - 1424-3903 .- 1424-3911. ; 19:1, s. 97-104
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is associated with poor prognosis. Gemcitabine is the standard chemotherapy for patients with metastatic pancreatic adenocarcinoma (MPA). Randomized clinical trials evaluating intensified chemotherapies including FOLFIRINOX and nab-paclitaxel plus gemcitabine (NAB+GEM) have shown improvement in survival. Here, we have evaluated the efficacy of intensified chemotherapy versus gemcitabine monotherapy in real-life settings across Europe.METHODS: A retrospective multi-center study including 1056 MPA patients, between 2012 and 2015, from nine centers in UK, Germany, Italy, Hungary and the Swedish registry was performed. Follow-up was at least 12 months. Cox proportional Harzards regression was used for uni- and multivariable evaluation of prognostic factors.RESULTS: Of 1056 MPA patients, 1030 (98.7%) were assessable for survival analysis. Gemcitabine monotherapy was the most commonly used regimen (41.3%), compared to FOLFIRINOX (n = 204, 19.3%), NAB+GEM (n = 81, 7.7%) and other gemcitabine- or 5-FU-based regimens (n = 335, 31.7%). The median overall survival (OS) was: FOLFIRINOX 9.9 months (95%CI 8.4-12.6), NAB+GEM 7.9 months (95%CI 6.2-10.0), other combinations 8.5 months (95%CI 7.7-9.3) and gemcitabine monotherapy 4.9 months (95%CI 4.4-5.6). Compared to gemcitabine monotherapy, any combination of chemotherapeutics improved the survival with no significant difference between the intensified regimens. Multivariable analysis showed an association between treatment center, male gender, inoperability at diagnosis and performance status (ECOG 1-3) with poor prognosis.CONCLUSION: Gemcitabine monotherapy was predominantly used in 2012-2015. Intensified chemotherapy improved OS in comparison to gemcitabine monotherapy. In real-life settings, the OS rates of different treatment approaches are lower than shown in randomized phase III trials.
|
|
| 3. |
- Krug, Silvia, et al.
(författare)
-
Comparing BLE and NB-IoT as communication options for smart viticulture IoT applications
- 2021
-
Ingår i: 2021 IEEE Sensors Applications Symposium (SAS). - 9781728194318
-
Konferensbidrag (refereegranskat)abstract
- Choosing the appropriate communication technology for outdoor applications has been a challenge over years and let to many different options. This makes it difficult for designers and users to chose the best option for their setup as each option has unique pros and cons. In this paper, we evaluate and compare Narrow Band Internet of Things (NB-IoT) and Bluetooth Low Energy (BLE) regarding their applicability for a smart viticulture scenario. We study how the node density and system energy consumption varies for various configurations and are thus able to highlight challenges in deployments as well as tradeoffs between the technologies.
|
|
| 4. |
- Krug, Silvia, et al.
(författare)
-
Suitability of Communication Technologies for Harvester-Powered IoT-Nodes
- 2019
-
Ingår i: IEEE International Workshop on Factory Communication Systems - Proceedings, WFCS. - : Institute of Electrical and Electronics Engineers (IEEE). - 9781728112688
-
Konferensbidrag (refereegranskat)abstract
- The Internet of Things introduces Internet connectivity to things and objects in the physical world and thus enables them to communicate with other nodes via the Internet directly. This enables new applications that for example allow seamless process monitoring and control in industrial environments. One core requirement is that the nodes involved in the network have a long system lifetime, despite limited access to the power grid and potentially difficult propagation conditions. Energy harvesting can provide the required energy for this long lifetime if the node is able to send the data based on the available energy budget. In this paper, we therefore analyze and evaluate which common IoT communication technologies are suitable for nodes powered by energy harvesters. The comparison includes three different constraints from different energy sources and harvesting technologies besides several communication technologies. Besides identifying possible technologies in general, we evaluate the impact of duty-cycling and different data sizes. The results in this paper give a road map for combining energy harvesting technology with IoT communication technology to design industrial sensor nodes.
|
|
| 5. |
- Le, Nha, et al.
(författare)
-
Real-world clinical practice of intensified chemotherapies for metastatic pancreatic cancer : results from a Pan-European questionnaire study
- 2016
-
Ingår i: Digestion. - : S. Karger AG. - 0012-2823 .- 1421-9867. ; 94:4, s. 222-229
-
Tidskriftsartikel (refereegranskat)abstract
- Introduction: Recently, FOLFIRINOX and gemcitabine + nab-paclitaxel have been introduced as a novel intensified chemotherapy regimen for patients with metastasized pancreatic cancer. This study aims to analyze the real-world clinical practice with FOLFIRINOX and gemcitabine + nab-paclitaxel across Europe.Methods: Invitations to participate in an anonymous web-based questionnaire were sent via e-mail to 5,420 doctors in 19 European countries through the network of national gastroenterological, oncological, surgical and pancreatic societies as well as the European Pancreatic Club. The questionnaire consisted of 20 questions, 14 regarding the use of intensified chemotherapy, 4 regarding demographics of the participants, and 1 to verify the active involvement in the management of metastatic pancreatic cancer.Results: Two hundred and thirteen responses were received and 153 entries were valid for analysis. Of those, 63.4% came from an academic institution, 51% were oncologists, and 52% treated more than 25 cases per year. A majority of responses (71%) were from Italy (40%), Germany (23%), and Spain (8%). As first-line therapy, 11% used gemcitabine +/- erlotinib, 42% used FOLFIRINOX, and 47% used gemcitabine + nab-paclitaxel. Of the intensified regimens, both were applied to equal parts, but the likelihood of protocol deviation was higher when using FOLFIRINOX (p < 0.01). FOLFIRINOX was considered more toxic than gemcitabine + nab-paclitaxel (neutropenia 88 vs. 68%; polyneuropathy 42 vs. 41%; rapid deterioration 42 vs. 31%). FOLFIRINOX was rated to achieve longer survival with an acceptable quality of life (52 vs. 44%). Moreover, 57% of participants thought that gemcitabine + nab-paclitaxel should be the backbone for further clinical trials in pancreatic cancer.Conclusion: Intensified chemotherapy is widely used in pancreatic cancer patients in Europe following its recent clinical approval. Interestingly, nab-paclitaxel and FOLFIRINOX were used at comparable frequency although the latter had to be de-escalated more often.
|
|
| 6. |
- Onus, Umut, et al.
(författare)
-
Trade-off between Spectral Feature Extractors for Machine Health Prognostics on Microcontrollers
- 2022
-
Ingår i: CIVEMSA 2022 - IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, Proceedings. - : IEEE. - 9781665434454
-
Konferensbidrag (refereegranskat)abstract
- Machine learning methods have shown a high impact on machine health prognostics solutions. However, most studies stop after building a model on a server or pc, without deploying it to embedded systems close to the machinery. Bringing machine learning models to small embedded systems with a small energy budget does require adapted models and raw time series data processing to handle resource constraints while maintaining high model performance. Feature extraction plays a crucial role in this process. One of the most common methods for machinery data feature is its spectral information, that are extracted via digital filters. Calculating spectral features on microcontrollers has a great impact on the computational requirements of the overall estimations. In this paper, we analyze mel-spectrogram and infinite impulse response (IIR) based spectral feature extractors regarding their estimation performances and their computational requirements. The goal is to evaluate possible trade-offs when selecting one feature extractor over the other. To achieve this, we study the cost of both methods theoretically and via run-time measurements after analyzing the feature design space to ensure good model performance. Our results show that by selecting an appropriate filter to the problem, its feature space dimensionality and, consequently, its computational load can be reduced.
|
|
| 7. |
- Pandey, Rick, et al.
(författare)
-
Towards Deploying DNN Models on Edge for Predictive Maintenance Applications
- 2023
-
Ingår i: Electronics. - : MDPI AG. - 2079-9292. ; 12:3
-
Tidskriftsartikel (refereegranskat)abstract
- Almost all rotating machinery in the industry has bearings as their key building block and most of these machines run 24 × 7. This makes bearing health prediction an active research area for predictive maintenance solutions. Many state of the art Deep Neural Network (DNN) models have been proposed to solve this. However, most of these high performance models are computationally expensive and have high memory requirements. This limits their use to very specific industrial applications with powerful hardwares deployed close the the machinery. In order to bring DNN-based solutions to a potential use in the industry, we need to deploy these models on Microcontroller Units (MCUs) which are cost effective and energy efficient. However, this step is typically neglected in literature as it poses new challenges. The primary concern when inferencing the DNN models on MCUs is the on chip memory of the MCU that has to fit the model, the data and additional code to run the system. Almost all the state of the art models fail this litmus test since they feature too many parameters. In this paper, we show the challenges related to the deployment, review possible solutions and evaluate one of them showing how the deployment can be realized and what steps are needed. The focus is on the steps required for the actual deployment rather than finding the optimal solution. This paper is among the first to show the deployment on MCUs for a predictive maintenance use case. We first analyze the gap between State Of The Art benchmark DNN models for bearing defect classification and the memory constraint of two MCU variants. Additionally, we review options to reduce the model size such as pruning and quantization. Afterwards, we evaluate a solution to deploy the DNN models by pruning them in order to fit them into microcontrollers. Our results show that most models under test can be reduced to fit MCU memory for a maximum loss of (Formula presented.) in average accuracy of the pruned models in comparison to the original models. Based on the results, we also discuss which methods are promising and which combination of model and feature work best for the given classification problem.
|
|
| 8. |
- Pandey, Rick, et al.
(författare)
-
Weighted Pruning with Filter Search to Deploy DNN Models on Microcontrollers
- 2023
-
Ingår i: 2023 IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS). - : IEEE conference proceedings. - 9798350358056 ; , s. 1077-1082
-
Konferensbidrag (refereegranskat)abstract
- Predictive Maintenance (PdM) helps to determine the condition of in-service industrial equipment and components and their timely replacement. This can be achieved by Artificial Intelligence (AI) enabled information systems. AI has been used extensively in addressing the condition monitoring problems. Most existing Deep Neural Network (DNN) models which are capable of solving PdM problems have a large memory foot print and are functional on remote machines using cloud based infrastructure only. In order to inference them close to the process, they need to run on memory constrained devices like microcontrollers (MCUs). In this work, we propose a weighted pruning algorithm to reduce the number of trainable parameters in the DNN model for bearing fault classification to enable its execution on the MCU. In addition to the pruning, we reduce the trainable model parameters by making an extensive filter size search. The model size is reduced without compromising on the performance of the pruned models by using the magnitude based method. In case of AlexNet, LeNet and Autoencoder we could reduce the model size upto 89%, 39% and 54% respectively with the new approach in comparison to the magnitude based state of the art approach.
|
|
| 9. |
- Schober, Marvin, et al.
(författare)
-
New Advances in the Treatment of Metastatic Pancreatic Cancer
- 2015
-
Ingår i: Digestion. - : S. Karger. - 0012-2823 .- 1421-9867. ; 92:3, s. 175-184
-
Forskningsöversikt (refereegranskat)abstract
- Background: Pancreatic ductal adenocarcinoma (PDAC) is characterised by an extremely poor overall survival (OS) compared to other solid tumours. As the incidence of the disease is rising and the treatment options are limited, PDAC is projected to be the 2nd leading cause of cancer-related deaths in the United States by 2030. A majority of patients are not eligible for curative resection at the time of diagnosis, and those that are resected will often relapse within the first few years after surgery. Summary: Until recently, the nucleoside analogue gemcitabine has been the standard of care for patients with non-resectable PDAC with only marginal effects on OS. In 2011, the gemcitabine-free FOLFIRINOX regimen (folinic acid, fluorouracil, irinotecan and oxaliplatin) showed a significant survival advantage for patients with metastatic PDAC in a phase III trial. In 2013, the Metastatic Pancreatic Adenocarcinoma Trial phase III trial with nano-formulated albumin-bound paclitaxel (nab-paclitaxel) in combination with gemcitabine also resulted in a significant survival extension compared to gemcitabine monotherapy. However, both intensified therapy regimens show a broad spectrum of side effects and patients need to be carefully selected for the most appropriate protocol. Key Message: In this study, recent advances in the chemotherapeutic options available to treat metastatic PDAC and their implications for today's treatment choices are reviewed.
|
|
| 10. |
- Vu Trung, Kien, et al.
(författare)
-
Endoscopic papillectomy for ampullary lesions of minor papilla
- 2024
-
Ingår i: Gastrointestinal Endoscopy. - 0016-5107. ; 99:4, s. 587-595.e1
-
Tidskriftsartikel (refereegranskat)abstract
- Background and Aims: Ampullary lesions (ALs) of the minor duodenal papilla are extremely rare. Endoscopic papillectomy (EP) is a routinely used treatment for AL of the major duodenal papilla, but the role of EP for minor AL has not been accurately studied. Methods: We identified 20 patients with ALs of minor duodenal papilla in the multicentric database from the Endoscopic Papillectomy vs Surgical Ampullectomy vs Pancreatitcoduodenectomy for Ampullary Neoplasm study, which included 1422 EPs. We used propensity score matching (nearest-neighbor method) to match these cases with ALs of the major duodenal papilla based on age, sex, histologic subtype, and size of the lesion in a 1:2 ratio. Cohorts were compared by means of chi-square or Fisher exact test as well as Mann-Whitney U test. Results: Propensity score–based matching identified a cohort of 60 (minor papilla 20, major papilla 40) patients with similar baseline characteristics. The most common histologic subtype of lesions of minor papilla was an ampullary adenoma in 12 patients (3 low-grade dysplasia and 9 high-grade dysplasia). Five patients revealed nonneoplastic lesions. Invasive cancer (T1a), adenomyoma, and neuroendocrine neoplasia were each found in 1 case. The rate of complete resection, en-bloc resection, and recurrences were similar between the groups. There were no severe adverse events after EP of lesions of minor papilla. One patient had delayed bleeding that could be treated by endoscopic hemostasis, and 2 patients showed a recurrence in surveillance endoscopy after a median follow-up of 21 months (interquartile range, 12-50 months). Conclusions: EP is safe and effective in ALs of the minor duodenal papilla. Such lesions could be managed according to guidelines for EP of major duodenal papilla.
|
|
