The Experts below are selected from a list of 34359 Experts worldwide ranked by ideXlab platform
Oki Kwon - One of the best experts on this subject based on the ideXlab platform.
-
machine learning for detecting moyamoya disease in plain skull radiography using a convolutional neural network
EBioMedicine, 2019Co-Authors: Tackeun Kim, Jaehyuk Heo, Dong Kyu Jang, Leonard Sunwoo, Joonghee Kim, Kyong Joon Lee, Si Hyuk Kang, Sang Jun Park, Oki KwonAbstract:Abstract Background Recently, innovative attempts have been made to identify moyamoya disease (MMD) by focusing on the morphological differences in the head of MMD patients. Following the Recent Revolution in the development of deep learning (DL) algorithms, we designed this study to determine whether DL can distinguish MMD in plain skull radiograph images. Methods Three hundred forty-five skull images were collected as an MMD-labeled dataset from patients aged 18 to 50 years with definite MMD. As a control-labeled data set, 408 skull images of trauma patients were selected by age and sex matching. Skull images were partitioned into training and test datasets at a 7:3 ratio using permutation. A total of six convolution layers were designed and trained. The accuracy and area under the receiver operating characteristic (AUROC) curve were evaluated as classifier performance. To identify areas of attention, gradient-weighted class activation mapping was applied. External validation was performed with a new dataset from another hospital. Findings For the institutional test set, the classifier predicted the true label with 84·1% accuracy. Sensitivity and specificity were both 0·84. AUROC was 0·91. MMD was predicted by attention to the lower face in most cases. Overall accuracy for external validation data set was 75·9%. Interpretation DL can distinguish MMD cases within specific ages from controls in plain skull radiograph images with considerable accuracy and AUROC. The viscerocranium may play a role in MMD-related skull features. Fund This work was supported by grant no. 18-2018-029 from the Seoul National University Bundang Hospital Research Fund.
-
Machine learning for detecting moyamoya disease in plain skull radiography using a convolutional neural networkResearch in context
Elsevier, 2019Co-Authors: Tackeun Kim, Jaehyuk Heo, Dong Kyu Jang, Leonard Sunwoo, Joonghee Kim, Kyong Joon Lee, Sang Jun Park, Si-hyuck Kang, Oki KwonAbstract:Background: Recently, innovative attempts have been made to identify moyamoya disease (MMD) by focusing on the morphological differences in the head of MMD patients. Following the Recent Revolution in the development of deep learning (DL) algorithms, we designed this study to determine whether DL can distinguish MMD in plain skull radiograph images. Methods: Three hundred forty-five skull images were collected as an MMD-labeled dataset from patients aged 18 to 50 years with definite MMD. As a control-labeled data set, 408 skull images of trauma patients were selected by age and sex matching. Skull images were partitioned into training and test datasets at a 7:3 ratio using permutation. A total of six convolution layers were designed and trained. The accuracy and area under the receiver operating characteristic (AUROC) curve were evaluated as classifier performance. To identify areas of attention, gradient-weighted class activation mapping was applied. External validation was performed with a new dataset from another hospital. Findings: For the institutional test set, the classifier predicted the true label with 84·1% accuracy. Sensitivity and specificity were both 0·84. AUROC was 0·91. MMD was predicted by attention to the lower face in most cases. Overall accuracy for external validation data set was 75·9%. Interpretation: DL can distinguish MMD cases within specific ages from controls in plain skull radiograph images with considerable accuracy and AUROC. The viscerocranium may play a role in MMD-related skull features. Fund: This work was supported by grant no. 18-2018-029 from the Seoul National University Bundang Hospital Research Fund. Keywords: Convolutional neural network, Deep learning, Moyamoya, Skul
Judy Lieberman - One of the best experts on this subject based on the ideXlab platform.
-
Tapping the RNA world for therapeutics
Nature Structural & Molecular Biology, 2018Co-Authors: Judy LiebermanAbstract:Developments in basic RNA biology have spawned RNA-based strategies to generate new types of therapeutics. Judy Lieberman reviews RNA-based drug design and discusses barriers to more widespread applications and possible ways to overcome them. A Recent Revolution in RNA biology has led to the identification of new RNA classes with unanticipated functions, new types of RNA modifications, an unexpected multiplicity of alternative transcripts and widespread transcription of extragenic regions. This development in basic RNA biology has spawned a corresponding Revolution in RNA-based strategies to generate new types of therapeutics. Here, I review RNA-based drug design and discuss barriers to broader applications and possible ways to overcome them. Because they target nucleic acids rather than proteins, RNA-based drugs promise to greatly extend the domain of ‘druggable’ targets beyond what can be achieved with small molecules and biologics.
-
Tapping the RNA world for therapeutics.
Nature structural & molecular biology, 2018Co-Authors: Judy LiebermanAbstract:A Recent Revolution in RNA biology has led to the identification of new RNA classes with unanticipated functions, new types of RNA modifications, an unexpected multiplicity of alternative transcripts and widespread transcription of extragenic regions. This development in basic RNA biology has spawned a corresponding Revolution in RNA-based strategies to generate new types of therapeutics. Here, I review RNA-based drug design and discuss barriers to broader applications and possible ways to overcome them. Because they target nucleic acids rather than proteins, RNA-based drugs promise to greatly extend the domain of ‘druggable’ targets beyond what can be achieved with small molecules and biologics.
Horst D. Simon - One of the best experts on this subject based on the ideXlab platform.
-
The Recent Revolution in High Performance Computing
MRS Bulletin, 1997Co-Authors: Horst D. SimonAbstract:Recent events in the high-performance computing industry have concerned scientists and the general public regarding a crisis or a lack of leadership in the field. That concern is understandable considering the industry's history from 1993 to 1996. Cray Research, the historic leader in supercomputing technology, was unable to survive financially as an independent company and was acquired by Silicon Graphics. Two ambitious new companies that introduced new technologies in the late 1980s and early 1990s—Thinking Machines and Kendall Square Research—were commercial failures and went out of business. And Intel, which introduced its Paragon supercomputer in 1994, discontinued production only two years later. During the same time frame, scientists who had finished the laborious task of writing scientific codes to run on vector parallel supercomputers learned that those codes would have to be rewritten if they were to run on the next-generation, highly parallel architecture. Scientists who are not yet involved in high-performance computing are understandably hesitant about committing their time and energy to such an apparently unstable enterprise. However, beneath the commercial chaos of the last several years, a technological Revolution has been occurring. The good news is that the Revolution is over, leading to five to ten years of predictable stability, steady improvements in system performance, and increased productivity for scientific applications. It is time for scientists who were sitting on the fence to jump in and reap the benefits of the new technology.
Stephen M. Sagar - One of the best experts on this subject based on the ideXlab platform.
-
The current role of anti-emetic drugs in oncology: a Recent Revolution in patient symptom control.
Cancer treatment reviews, 1991Co-Authors: Stephen M. SagarAbstract:The symptoms of nausea and vomiting as a consequence of anticancer therapy are of major concern to all physicians practising in clinical oncology (142). Emesis is an important toxic side-effect of most chemotherapy regimens and certain radiotherapeutic techniques involving either irradiation of large volumes or irradiation of the upper abdomen. Severe nausea and vomiting may lead to withdrawal of potentially curative treatment, such as chemotherapy for malignant teratoma and radiotherapy for seminoma. The aim of palliative treatment to improve the quality of life may be defeated by the induction of emesis. Emesis refers specifically to vomiting, but is part of a syndrome consisting of appetite loss, nausea, retching and vomiting. Associated with these major complaints are symptoms of anxiety, listlessness, salivation, lethargy and somnolence. Nausea is associated with loss of gastric tone and decreased peristalsis. Retching consists of synchronized labored movements of the respiratory muscles and stomach. Vomiting is produced by forceful and sustained contraction of the diaphragm and abdominal muscles coordinated with opening of the pyloric sphincter and emptying of the stomach. The physical consequences of prolonged emesis include oesophageal tears, skeletal fractures, dehydration, electrolyte imbalance and weight loss. It may be associated with anticipatory nausea and vomiting (ANV) and long-term psychiatric morbidity (72). ANV is more likely to develop after the tburth course of treatment and is a consequence of poorly controlled emesis during the initial courses leading to classical Pavlovian conditioning. Anticipatory nausea may develop in 35% and vomiting in 16% of patients resulting in the refusal to receive further chemotherapy by up to 10% of patients (14). The problem of emesis secondary to chemotherapy commenced with the introduction of the nitrogen mustards about 50 years ago (211) and emesis associated with external beam radiotherapy was documented by Court-Brown in 1953 (71). In the absence of effective anti-emetic drugs, the morbidity was accepted as an unavoidable consequence of anticancer therapy. The dose-dependent efficacy of cisplatin was initially limited by its major toxicity of nausea and vomiting (114). This led to a major effort to develop and assess anti-emetic medication over the past decade. The emetogenicity of anticancer therapy depends on multiple factors and these have complicated the objective assessment of anti-emetic efficacy. Chemotherapy agents can be categorized according to their ability to induce emesis (Table 1), but this is further
Marian Beekman - One of the best experts on this subject based on the ideXlab platform.
-
Activity recognition using wearable sensors for tracking the elderly
User Modeling and User-Adapted Interaction, 2020Co-Authors: Stylianos Paraschiakos, Ricardo Cachucho, Matthijs Moed, Diana Heemst, Simon Mooijaart, Eline P. Slagboom, Arno Knobbe, Marian BeekmanAbstract:A population group that is often overlooked in the Recent Revolution of self-tracking is the group of older people. This growing proportion of the general population is often faced with increasing health issues and discomfort. In order to come up with lifestyle advice towards the elderly, we need the ability to quantify their lifestyle, before and after an intervention. This research focuses on the task of activity recognition (AR) from accelerometer data. With that aim, we collect a substantial labelled dataset of older individuals wearing multiple devices simultaneously and performing a strict protocol of 16 activities (the GOTOV dataset, $$N=28$$ N = 28 ). Using this dataset, we trained Random Forest AR models, under varying sensor set-ups and levels of activity description granularity. The model that combines ankle and wrist accelerometers (GENEActiv) produced the best results (accuracy $$>80\%$$ > 80 % ) for 16-class classification. At the same time, when additional physiological information is used, the accuracy increased ( $$>85\%$$ > 85 % ). To further investigate the role of granularity in our predictions, we developed the LARA algorithm, which uses a hierarchical ontology that captures prior biological knowledge to increase or decrease the level of activity granularity (merge classes). As a result, a 12-class model in which the different paces of walking were merged showed a performance above $$93\%$$ 93 % . Testing this 12-class model in labelled free-living pilot data, the mean balanced accuracy appeared to be reasonably high, while using the LARA algorithm, we show that a 7-class model (lying down, sitting, standing, household, walking, cycling, jumping) was optimal for accuracy and granularity. Finally, we demonstrate the use of the latter model in unlabelled free-living data from a larger lifestyle intervention study. In this paper, we make the validation data as well as the derived prediction models available to the community.
