scholarly journals Deep Learning Achieves Neuroradiologist-Level Performance in Detecting Hydrocephalus

2021 ◽  
Author(s):  
Yu Huang ◽  
Raquel Moreno ◽  
Rachna Malani ◽  
Alicia Meng ◽  
Nathaniel Swinburne ◽  
...  
Keyword(s):  
Patient Population ◽  
State Of The Art ◽  
Clinical Population ◽  
List Type ◽  
Convolutional Network ◽  
Brain Scans ◽  
Mri Brain ◽  
Volumetric Features ◽  
Significant Difference ◽  
Brain Tissues

AbstractPurposeWe aim to develop automated detection of hydrocephalus requiring treatment in a heterogeneous patient population referred for MRI brain scans, and compare performance to that of neuroradiologists.Materials and MethodsWe leveraged 496 clinical MRI brain scans (259 hydrocephalus) collected retrospectively at a single clinical site from patients aged 2–90 years (mean 54) referred for any reason. Sixteen MRI scans (ten hydrocephalus) were segmented semi-automatically in 3D to delineate ventricles, extraventricular CSF, and brain tissues. A 3D CNN was trained on these segmentations and subsequently used to automatically segment the remaining 480 scans. To detect hydrocephalus, volumetric features such as volumes of ventricles and temporal horns were computed from the segmentation and were used to train a linear classifier. Machine performance was evaluated in a diagnosis dataset where hydrocephalus was confirmed as requiring surgical intervention, and compared to four neuroradiologists on a random subset of 240 scans. The pipeline was tested on a separate screening dataset of 205 scans collected from a routine clinical population aged 1–95 years (mean 56) to predict the majority reading from four neuroradiologists using images alone.ResultsWhen compared to the neuroradiologists at a matched sensitivity, the machine did not show a significant difference in specificity (proportions test, p > 0.05). The machine demonstrated comparable performance in independent diagnosis and screening datasets. Overall ROC performance compared favorably with the state-of-the-art (AUC 0.82–0.93).ConclusionHydrocephalus can be detected automatically from MRI in a heterogeneous patient population with performance equivalent to that of neuroradiologists.Summary statementA two-stage automated pipeline was developed to segment head MRI and extract volumetric features to accurately and efficiently detect hydrocephalus that required shunting and achieved performance comparable to that of trained neuroradiologists.Key PointsWe developed a state-of-the-art 3D deep convolutional network to perform fully automated segmentation of the ventricles, extraventricular cerebrospinal fluid, and brain tissues in anisotropic MRI brain scans in a heterogeneous patient population.Volumetric features extracted from anatomical segmentations can be used to classify hydrocephalus (which may require neurosurgical intervention) vs. non-hydrocephalus.When tested in an independent dataset, the network achieved performance comparable to that of expert neuroradiologists.

scholarly journals Efficient End-to-End Sentence-Level Lipreading with Temporal Convolutional Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6975
Author(s):  
Tao Zhang ◽  
Lun He ◽  
Xudong Li ◽  
Guoqing Feng
Keyword(s):  
Performance Improvement ◽  
State Of The Art ◽  
Error Rates ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Sentence Level ◽  
End To End ◽  
High Level ◽  
Improved Accuracy ◽  
Talking Face

Lipreading aims to recognize sentences being spoken by a talking face. In recent years, the lipreading method has achieved a high level of accuracy on large datasets and made breakthrough progress. However, lipreading is still far from being solved, and existing methods tend to have high error rates on the wild data and have the defects of disappearing training gradient and slow convergence. To overcome these problems, we proposed an efficient end-to-end sentence-level lipreading model, using an encoder based on a 3D convolutional network, ResNet50, Temporal Convolutional Network (TCN), and a CTC objective function as the decoder. More importantly, the proposed architecture incorporates TCN as a feature learner to decode feature. It can partly eliminate the defects of RNN (LSTM, GRU) gradient disappearance and insufficient performance, and this yields notable performance improvement as well as faster convergence. Experiments show that the training and convergence speed are 50% faster than the state-of-the-art method, and improved accuracy by 2.4% on the GRID dataset.

scholarly journals Clinically applicable artificial intelligence system for dental diagnosis with CBCT

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Matvey Ezhov ◽  
Maxim Gusarev ◽  
Maria Golitsyna ◽  
Julian M. Yates ◽  
Evgeny Kushnerev ◽  
...  
Keyword(s):  
State Of The Art ◽  
Model Development ◽  
Clinical Effectiveness ◽  
Anatomical Landmarks ◽  
Periapical Lesion ◽  
Artificial Intelligence System ◽  
Intelligence System ◽  
Significant Difference ◽  
Diagnostic Capabilities ◽  
Lesion Localization

AbstractIn this study, a novel AI system based on deep learning methods was evaluated to determine its real-time performance of CBCT imaging diagnosis of anatomical landmarks, pathologies, clinical effectiveness, and safety when used by dentists in a clinical setting. The system consists of 5 modules: ROI-localization-module (segmentation of teeth and jaws), tooth-localization and numeration-module, periodontitis-module, caries-localization-module, and periapical-lesion-localization-module. These modules use CNN based on state-of-the-art architectures. In total, 1346 CBCT scans were used to train the modules. After annotation and model development, the AI system was tested for diagnostic capabilities of the Diagnocat AI system. 24 dentists participated in the clinical evaluation of the system. 30 CBCT scans were examined by two groups of dentists, where one group was aided by Diagnocat and the other was unaided. The results for the overall sensitivity and specificity for aided and unaided groups were calculated as an aggregate of all conditions. The sensitivity values for aided and unaided groups were 0.8537 and 0.7672 while specificity was 0.9672 and 0.9616 respectively. There was a statistically significant difference between the groups (p = 0.032). This study showed that the proposed AI system significantly improved the diagnostic capabilities of dentists.

scholarly journals A trade-off between classical and quantum circuit size for an attack against CSIDH

2020 ◽  
Vol 15 (1) ◽  
pp. 4-17
Author(s):  
Jean-François Biasse ◽  
Xavier Bonnetain ◽  
Benjamin Pring ◽  
André Schrottenloher ◽  
William Youmans
Keyword(s):  
Endomorphism Ring ◽  
State Of The Art ◽  
Quantum Circuit ◽  
List Type ◽  
Hard Problem ◽  
Trade Off ◽  
Classical State ◽  
Security Parameter ◽  
The Cost ◽  
Quadratic Order

AbstractWe propose a heuristic algorithm to solve the underlying hard problem of the CSIDH cryptosystem (and other isogeny-based cryptosystems using elliptic curves with endomorphism ring isomorphic to an imaginary quadratic order 𝒪). Let Δ = Disc(𝒪) (in CSIDH, Δ = −4p for p the security parameter). Let 0 < α < 1/2, our algorithm requires:A classical circuit of size $2^{\tilde{O}\left(\log(|\Delta|)^{1-\alpha}\right)}.$A quantum circuit of size $2^{\tilde{O}\left(\log(|\Delta|)^{\alpha}\right)}.$Polynomial classical and quantum memory.Essentially, we propose to reduce the size of the quantum circuit below the state-of-the-art complexity $2^{\tilde{O}\left(\log(|\Delta|)^{1/2}\right)}$ at the cost of increasing the classical circuit-size required. The required classical circuit remains subexponential, which is a superpolynomial improvement over the classical state-of-the-art exponential solutions to these problems. Our method requires polynomial memory, both classical and quantum.

Multi-Graph Cooperative Learning Towards Distant Supervised Relation Extraction

2021 ◽  
Vol 12 (5) ◽  
pp. 1-21
Author(s):  
Changsen Yuan ◽  
Heyan Huang ◽  
Chong Feng
Keyword(s):  
Cooperative Learning ◽  
State Of The Art ◽  
Relation Extraction ◽  
Sentence Length ◽  
Universal Relation ◽  
Dependency Parsing ◽  
Convolutional Network ◽  
Syntactic Features ◽  
Use Dependency

The Graph Convolutional Network (GCN) is a universal relation extraction method that can predict relations of entity pairs by capturing sentences’ syntactic features. However, existing GCN methods often use dependency parsing to generate graph matrices and learn syntactic features. The quality of the dependency parsing will directly affect the accuracy of the graph matrix and change the whole GCN’s performance. Because of the influence of noisy words and sentence length in the distant supervised dataset, using dependency parsing on sentences causes errors and leads to unreliable information. Therefore, it is difficult to obtain credible graph matrices and relational features for some special sentences. In this article, we present a Multi-Graph Cooperative Learning model (MGCL), which focuses on extracting the reliable syntactic features of relations by different graphs and harnessing them to improve the representations of sentences. We conduct experiments on a widely used real-world dataset, and the experimental results show that our model achieves the state-of-the-art performance of relation extraction.

The State of the Art in Management Education Applicable to Aerospace Activities

1967 ◽  
Vol 71 (677) ◽  
pp. 344-348
Author(s):  
J. V. Connolly
Keyword(s):  
Management Education ◽  
State Of The Art ◽  
Aerospace Industry ◽  
List Type ◽  
Industrial Training ◽  
The Past ◽  
The Subject ◽  
Economic Necessity ◽  
The Uk ◽  
The Impact

During the past two years, there has been a sharp acceleration to the interest which industry has displayed in the subject of management education. This can be attributed to these factors: —(a) A more widespread realisation of the gap developing between the UK and a number of foreign economies, as manifested by diverging rates of the major economic indicators.(b) The attainment of top-management responsibilities by a younger generation of managers, many of whom had been given some earlier training and who were more conscious of its value than the incumbents of the job from earlier generations.(c) The publication of the Franks, Robbins and (in the aerospace industry) the Plowden reports.(d) The impact of the Industrial Training Boards making it manifest, in terms of serious levies, that training was an economic necessity and therefore must be investigated thoroughly.Notwithstanding the widespread awakening of interest, it is very belated and sets numerous problems. The problems are in two areas—scale and quality.

scholarly journals A series of five population-specific Indian brain templates and atlases spanning ages 6 to 60 years

2020 ◽  
Author(s):  
Bharath Holla ◽  
Paul A. Taylor ◽  
Daniel R. Glen ◽  
John A. Lee ◽  
Nilakshi Vaidya ◽  
...  
Keyword(s):  
Brain Morphology ◽  
Good Representation ◽  
List Type ◽  
Spatial Normalization ◽  
Maximum Probability ◽  
Total N ◽  
Brain Scans ◽  
Native Space ◽  
Probability Map ◽  
Population Average

AbstractAnatomical brain templates are commonly used as references in neurological MRI studies, for bringing data into a common space for group-level statistics and coordinate reporting. Given the inherent variability in brain morphology across age and geography, it is important to have templates that are as representative as possible for both age and population. A representative-template increases the accuracy of alignment, decreases distortions as well as potential biases in final coordinate reports. In this study, we developed and validated a new set of T1w Indian brain templates (IBT) from a large number of brain scans (total n=466) acquired across different locations and multiple 3T MRI scanners in India. A new tool in AFNI, make_template_dask.py, was created to efficiently make five age-specific IBTs (ages 6-60 years) as well as maximum probability map (MPM) atlases for each template; for each age-group’s template-atlas pair, there is both a “population-average” and a “typical” version. Validation experiments on an independent Indian structural and functional-MRI dataset show the appropriateness of IBTs for spatial normalization of Indian brains. The results indicate significant structural differences when comparing the IBTs and MNI template, with these differences being maximal along the Anterior-Posterior and Inferior-Superior axes, but minimal Left-Right. For each age-group, the MPM brain atlases provide reasonably good representation of the native-space volumes in the IBT space, except in a few regions with high inter-subject variability. These findings provide evidence to support the use of age and population-specific templates in human brain mapping studies. This dataset is made publicly available (https://hollabharath.github.io/IndiaBrainTemplates).HighlightsA new set of age-specific T1w Indian brain templates for ages 6-60 yr are developed and validated.A new AFNI tool, make_template_dask.py, for the creation of group-based templates.Maximum probability map atlases are also provided for each template.Results indicate the appropriateness of Indian templates for spatial normalization of Indian brains

scholarly journals Fully Convolutional Network for Consistent Voxel-Wise Correspondence

2020 ◽  
Vol 34 (07) ◽  
pp. 12935-12942 ◽  
Author(s):  
Yungeng Zhang ◽  
Yuru Pei ◽  
Yuke Guo ◽  
Gengyu Ma ◽  
Tianmin Xu ◽  
...  
Keyword(s):  
Vector Fields ◽  
State Of The Art ◽  
Displacement Vector ◽  
Cone Beam Ct ◽  
Deformable Registration ◽  
Cone Beam ◽  
Nonlinear Mapping ◽  
Convolutional Network ◽  
Mapping Functions ◽  
Fully Convolutional Network

In this paper, we propose a fully convolutional network-based dense map from voxels to invertible pair of displacement vector fields regarding a template grid for the consistent voxel-wise correspondence. We parameterize the volumetric mapping using a convolutional network and train it in an unsupervised way by leveraging the spatial transformer to minimize the gap between the warped volumetric image and the template grid. Instead of learning the unidirectional map, we learn the nonlinear mapping functions for both forward and backward transformations. We introduce the combinational inverse constraints for the volumetric one-to-one maps, where the pairwise and triple constraints are utilized to learn the cycle-consistent correspondence maps between volumes. Experiments on both synthetic and clinically captured volumetric cone-beam CT (CBCT) images show that the proposed framework is effective and competitive against state-of-the-art deformable registration techniques.

scholarly journals Listening to voices: understanding and self-management of auditory verbal hallucinations in young adults

BJPsych Open ◽  
2021 ◽  
Vol 7 (S1) ◽  
pp. S19-S20
Author(s):  
Peter Denno ◽  
Stephanie Wallis ◽  
Jonathan Ives ◽  
Stephen Wood ◽  
Matthew Broome ◽  
...  
Keyword(s):  
Identity Formation ◽  
Coping Strategies ◽  
Belief Systems ◽  
Management Strategies ◽  
Clinical Population ◽  
Photo Elicitation ◽  
Self Management ◽  
List Type ◽  
Auditory Verbal Hallucinations ◽  
Dysfunctional Relationships

AimsAuditory Verbal Hallucinations (AVH) are a hallmark of psychosis, but affect many other clinical populations. Patients’ understanding and self-management of AVH may differ between diagnostic groups, change over time, and influence clinical outcomes.We aimed to explore patients’ understanding and self-management of AVH in a young adult clinical population.Method35 participants reporting frequent AVH were purposively sampled from a youth mental health service, to capture experiences across psychosis and non-psychosis diagnoses. Diary and photo-elicitation methodologies were used – participants were asked to complete diaries documenting experiences of AVH, and to take photographs representing these experiences. In-depth, unstructured interviews were held, using participant-produced materials as a topic guide. Conventional content analysis was conducted, deriving results from the data in the form of themes.ResultThree themes emerged: (1)Searching for answers, forming identities – voice-hearers sought to explain their experiences, resulting in the construction of identities for voices, and descriptions of relationships with them. These identities were drawn from participants’ life-stories (e.g., reflecting trauma), and belief-systems (e.g., reflecting supernatural beliefs, or mental illness). Some described this process as active / volitional. Participants described re-defining their own identities in relation to those constructed for AVH (e.g. as diseased, 'chosen', or persecuted), others considered AVH explicitly as aspects of, or changes in, their personality.(2)Coping strategies and goals – patients’ self-management strategies were diverse, reflecting the diverse negative experiences of AVH. Strategies were related to a smaller number of goals, e.g. distraction, soothing overwhelming emotions, 'reality-checking', and retaining agency.(3)Outlook – participants formed an overall outlook reflecting their self-efficacy in managing AVH. Resignation and hopelessness in connection with disabling AVH are contrasted with outlooks of “acceptance” or integration, which were described as positive, ideal, or mature.ConclusionTrans-diagnostic commonalities in understanding and self-management of AVH are highlighted - answer-seeking and identity-formation processes; a diversity of coping strategies and goals; and striving to accept the symptom. Descriptions of “voices-as-self”, and dysfunctional relationships with AVH, could represent specific features of voice-hearing in personality disorder, whereas certain supernatural/paranormal identities and explanations were clearly delusional. However, no aspect of identity-formation was completely unique to psychosis or non-psychosis diagnostic groups. The identity-formation process, coping strategies, and outlooks can be seen as a framework both for individual therapies and further research.

scholarly journals MR-GCN: Multi-Relational Graph Convolutional Networks based on Generalized Tensor Product

2020 ◽  
Author(s):  
Zhichao Huang ◽  
Xutao Li ◽  
Yunming Ye ◽  
Michael K. Ng
Keyword(s):  
Tensor Product ◽  
Convolution Operator ◽  
State Of The Art ◽  
Single Type ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Node Classification ◽  
Relational Graphs ◽  
Eigen Decomposition ◽  
Single Relation

Graph Convolutional Networks (GCNs) have been extensively studied in recent years. Most of existing GCN approaches are designed for the homogenous graphs with a single type of relation. However, heterogeneous graphs of multiple types of relations are also ubiquitous and there is a lack of methodologies to tackle such graphs. Some previous studies address the issue by performing conventional GCN on each single relation and then blending their results. However, as the convolutional kernels neglect the correlations across relations, the strategy is sub-optimal. In this paper, we propose the Multi-Relational Graph Convolutional Network (MR-GCN) framework by developing a novel convolution operator on multi-relational graphs. In particular, our multi-dimension convolution operator extends the graph spectral analysis into the eigen-decomposition of a Laplacian tensor. And the eigen-decomposition is formulated with a generalized tensor product, which can correspond to any unitary transform instead of limited merely to Fourier transform. We conduct comprehensive experiments on four real-world multi-relational graphs to solve the semi-supervised node classification task, and the results show the superiority of MR-GCN against the state-of-the-art competitors.

A cooperative framework for segmentation of MRI brain scans

2000 ◽  
Vol 20 (1) ◽  
pp. 77-93 ◽  
Author(s):  
Laurence Germond ◽  
Michel Dojat ◽  
C Taylor ◽  
C Garbay
Keyword(s):  
Brain Scans ◽  
Mri Brain
Sign in / Sign up

Export Citation Format

Share Document