An artificial intelligence algorithm that differentiates anterior ethmoidal artery location on sinus computed tomography scans

AbstractObjectiveDeep learning using convolutional neural networks represents a form of artificial intelligence where computers recognise patterns and make predictions based upon provided datasets. This study aimed to determine if a convolutional neural network could be trained to differentiate the location of the anterior ethmoidal artery as either adhered to the skull base or within a bone ‘mesentery’ on sinus computed tomography scans.MethodsCoronal sinus computed tomography scans were reviewed by two otolaryngology residents for anterior ethmoidal artery location and used as data for the Google Inception-V3 convolutional neural network base. The classification layer of Inception-V3 was retrained in Python (programming language software) using a transfer learning method to interpret the computed tomography images.ResultsA total of 675 images from 388 patients were used to train the convolutional neural network. A further 197 unique images were used to test the algorithm; this yielded a total accuracy of 82.7 per cent (95 per cent confidence interval = 77.7–87.8), kappa statistic of 0.62 and area under the curve of 0.86.ConclusionConvolutional neural networks demonstrate promise in identifying clinically important structures in functional endoscopic sinus surgery, such as anterior ethmoidal artery location on pre-operative sinus computed tomography.

Download Full-text

An artificial intelligence algorithm that identifies middle turbinate pneumatisation (concha bullosa) on sinus computed tomography scans

The Journal of Laryngology & Otology ◽

10.1017/s0022215120000444 ◽

2020 ◽

Vol 134 (4) ◽

pp. 328-331 ◽

Cited By ~ 1

Author(s):

P Parmar ◽

A-R Habib ◽

D Mendis ◽

A Daniel ◽

M Duvnjak ◽

...

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Computed Tomography ◽

Diagnostic Accuracy ◽

Convolutional Neural Network ◽

Middle Turbinate ◽

Concha Bullosa ◽

Computed Tomography Images ◽

Computed Tomography Scans ◽

Neural Network Algorithm

AbstractObjectiveConvolutional neural networks are a subclass of deep learning or artificial intelligence that are predominantly used for image analysis and classification. This proof-of-concept study attempts to train a convolutional neural network algorithm that can reliably determine if the middle turbinate is pneumatised (concha bullosa) on coronal sinus computed tomography images.MethodConsecutive high-resolution computed tomography scans of the paranasal sinuses were retrospectively collected between January 2016 and December 2018 at a tertiary rhinology hospital in Australia. The classification layer of Inception-V3 was retrained in Python using a transfer learning method to interpret the computed tomography images. Segmentation analysis was also performed in an attempt to increase diagnostic accuracy.ResultsThe trained convolutional neural network was found to have diagnostic accuracy of 81 per cent (95 per cent confidence interval: 73.0–89.0 per cent) with an area under the curve of 0.93.ConclusionA trained convolutional neural network algorithm appears to successfully identify pneumatisation of the middle turbinate with high accuracy. Further studies can be pursued to test its ability in other clinically important anatomical variants in otolaryngology and rhinology.

Download Full-text

Variability of the Anterior Ethmoid Artery in Endoscopic Sinus Surgery

Ear Nose & Throat Journal ◽

10.1177/0145561320950488 ◽

2020 ◽

pp. 014556132095048

Author(s):

Mohamed A. Taha ◽

Christian A. Hall ◽

Harry E. Zylicz ◽

Margaret B. Westbrook ◽

William T. Barham ◽

...

Keyword(s):

Computed Tomography ◽

Skull Base ◽

Statistical Significance ◽

Sinus Surgery ◽

Preoperative Imaging ◽

Computed Tomography Scans ◽

Ethmoidal Artery ◽

Anterior Ethmoidal Artery ◽

The Right ◽

Anterior Ethmoid Artery

Introduction: The anterior ethmoidal artery (AEA) demonstrates anatomic variability relative to its descent from the anterior skull base. Our study’s objective was to assess for correlation of AEA descent and laterality, in addition to correlation of AEA descent and the presence of supraorbital ethmoid cells (SOEC) and concha bullosae (CB). Method: A retrospective study was performed at a tertiary rhinology center from January 2019 to January 2020. Noncontrast maxillofacial computed tomography scans were examined independently by 2 fellowship trained rhinologists. The vertical distance from both left and right AEAs to the ipsilateral skull base were compared and correlated with the presence of ipsilateral SOEC and CB. Results: Computed tomography scans from 50 subjects were included. Mean age was 50.68 years (40% females). The distance of AEA to the skull base was greater on the left when compared to the right (62% vs 48%) ( P < .05). The left AEA had an average descent of 2.84 mm versus 1.78 mm on the right ( P < .05). An SOEC was present in 56% of cases. Thirty-eight percent of subjects had both SOEC and AEA descent on the right, while 52% of subjects had both on the left. This reached a statistical significance on both sides ( P < .05). Concha bullosa was present in 35% of cases, with both AEA descent and CB present in 16% on the right, and 32% on the left. Conclusion: The AEA displays variability in vertical descent from the skull base, with greater variability on the left. These findings implore vigilance with evaluation of preoperative imaging and during sinus surgery, especially in the presence of SOEC and CB.

Download Full-text

An Approximate GEMM Unit for Energy-Efficient Object Detection

Sensors ◽

10.3390/s21124195 ◽

2021 ◽

Vol 21 (12) ◽

pp. 4195

Author(s):

Ratko Pilipović ◽

Vladimir Risojević ◽

Janko Božič ◽

Patricio Bulić ◽

Uroš Lotrič

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Neural Networks ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Energy Efficient ◽

Graphics Processing Units ◽

Matrix Multiplication ◽

Approximate Computing ◽

General Matrix

Edge computing brings artificial intelligence algorithms and graphics processing units closer to data sources, making autonomy and energy-efficient processing vital for their design. Approximate computing has emerged as a popular strategy for energy-efficient circuit design, where the challenge is to achieve the best tradeoff between design efficiency and accuracy. The essential operation in artificial intelligence algorithms is the general matrix multiplication (GEMM) operation comprised of matrix multiplication and accumulation. This paper presents an approximate general matrix multiplication (AGEMM) unit that employs approximate multipliers to perform matrix–matrix operations on four-by-four matrices given in sixteen-bit signed fixed-point format. The synthesis of the proposed AGEMM unit to the 45 nm Nangate Open Cell Library revealed that it consumed only up to 36% of the area and 25% of the energy required by the exact general matrix multiplication unit. The AGEMM unit is ideally suited to convolutional neural networks, which can adapt to the error induced in the computation. We evaluated the AGEMM units’ usability for honeybee detection with the YOLOv4-tiny convolutional neural network. The results implied that we can deploy the AGEMM units in convolutional neural networks without noticeable performance degradation. Moreover, the AGEMM unit’s employment can lead to more area- and energy-efficient convolutional neural network processing, which in turn could prolong sensors’ and edge nodes’ autonomy.

Download Full-text

Radiological anatomy of the anterior ethmoidal artery for functional endoscopic sinus surgery

The Journal of Laryngology & Otology ◽

10.1017/s0022215107008158 ◽

2007 ◽

Vol 122 (3) ◽

pp. 264-267 ◽

Cited By ~ 28

Author(s):

S E McDonald ◽

P J Robinson ◽

D A Nunez

Keyword(s):

Computed Tomography ◽

Skull Base ◽

Sinus Surgery ◽

Radiological Anatomy ◽

Base Level ◽

Computed Tomography Scans ◽

Ethmoidal Artery ◽

Anterior Ethmoidal Artery ◽

Ethmoidal Foramen ◽

Anterior Ethmoidal Foramen

AbstractAim:This study investigated the extent to which the anterior ethmoidal artery and anterior ethmoidal foramen could be reliably identified on routine coronal sinus computed tomography scans. Where they could be identified, the relationship of these structures with the vertical height of the skull base, and their distance from an anterior landmark, were measured.Methods:Fifty consecutive coronal sinus computed tomography scans were viewed independently by two observers. Scans were reviewed when the observers' opinions differed.Results:Inter-observer concordance was high. The anterior ethmoidal foramen was visualised in 95 per cent of cases bilaterally and in the remaining 5 per cent unilaterally. The anterior ethmoidal artery was visualised in 33 per cent of scans. The anterior ethmoidal foramen was at skull base level in 72 per cent of sides studied, and below it in the remainder. The distance from the lacrimal crest to the anterior ethmoidal foramen was 22.4 mm (mean; standard deviation 3.7).Conclusion:The anterior ethmoidal foramen is a reliable landmark on coronal computed tomography scans of the paranasal sinuses. From this, the position of the anterior ethmoidal artery can be inferred.

Download Full-text

Convolutional Neural Networks for Leaf Image-Based Plant Disease Classification

IAES International Journal of Artificial Intelligence (IJ-AI) ◽

10.11591/ijai.v8.i4.pp328-341 ◽

2019 ◽

Vol 8 (4) ◽

pp. 328

Author(s):

Sachin B. Jadhav

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Plant Diseases ◽

Experimental Results ◽

Disease Classification ◽

Soybean Leaves ◽

Soybean Diseases ◽

Validation Strategy

<span lang="EN-US">Plant pathologists desire soft computing technology for accurate and reliable diagnosis of plant diseases. In this study, we propose an efficient soybean disease identification method based on a transfer learning approach by using a pre-trained convolutional neural network (CNN’s) such as AlexNet, GoogleNet, VGG16, ResNet101, and DensNet201. The proposed convolutional neural networks were trained using 1200 plant village image dataset of diseased and healthy soybean leaves, to identify three soybean diseases out of healthy leaves. Pre-trained CNN used to enable a fast and easy system implementation in practice. We used the five-fold cross-validation strategy to analyze the performance of networks. In this study, we used a pre-trained convolutional neural network as feature extractors and classifiers. The experimental results based on the proposed approach using pre-trained AlexNet, GoogleNet, VGG16, ResNet101, and DensNet201 networks achieve an accuracy of 95%, 96.4 %, 96.4 %, 92.1%, 93.6% respectively. The experimental results for the identification of soybean diseases indicated that the proposed networks model achieves the highest accuracy</span>

Download Full-text

Document Localization in Images Taken by Smartphones Using a Fully Convolutional Neural Network

10.21203/rs.3.rs-952656/v1 ◽

2021 ◽

Author(s):

Shima Baniadamdizaj ◽

Mohammadreza Soheili ◽

Azadeh Mansouri

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Deep Convolutional Neural Networks ◽

Opposite Hand ◽

Processing Strategies ◽

Document Localization

Abstract Today integration of facts from virtual and paper files may be very vital for the expertise control of efficient. This calls for the record to be localized at the photograph. Several strategies had been proposed to resolve this trouble; however, they may be primarily based totally on conventional photograph processing strategies that aren't sturdy to intense viewpoints and backgrounds. Deep Convolutional Neural Networks (CNNs), on the opposite hand, have demonstrated to be extraordinarily sturdy to versions in history and viewing attitude for item detection and classification responsibilities. We endorse new utilization of Neural Networks (NNs) for the localization trouble as a localization trouble. The proposed technique ought to even localize photos that don't have a very square shape. Also, we used a newly accrued dataset that has extra tough responsibilities internal and is in the direction of a slipshod user. The end result knowledgeable in 3 exclusive classes of photos and our proposed technique has 83% on average. The end result is as compared with the maximum famous record localization strategies and cell applications.

Download Full-text

The Role and Utilization of CNN in Automatic Logo Based Document Image Retrieval Methods

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i3.1.16786 ◽

2018 ◽

Vol 7 (3.1) ◽

pp. 13

Author(s):

Raveendra K ◽

R Vinoth Kanna

Keyword(s):

Neural Network ◽

Neural Networks ◽

Feature Extraction ◽

Image Retrieval ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Document Image ◽

Retrieval Process ◽

Pictorial Representations

Automatic logo based document image retrieval process is an essential and mostly used method in the feature extraction applications. In this paper the architecture of Convolutional Neural Network (CNN) was elaborately explained with pictorial representations in order to understand the complex Convolutional Neural Networks process in a simplified way. The main objective of this paper is to effectively utilize the CNN in the process of automatic logo based document image retrieval methods.

Download Full-text

A Survey on Techniques used in Medical Imaging Processing

Journal of Physics Conference Series ◽

10.1088/1742-6596/2089/1/012013 ◽

2021 ◽

Vol 2089 (1) ◽

pp. 012013

Author(s):

Priyadarshini Chatterjee ◽

Dutta Sushama Rani

Keyword(s):

Neural Network ◽

Neural Networks ◽

Image Analysis ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Network Architecture ◽

Medical Image Analysis ◽

Artificial Neural ◽

Automated Screening ◽

To Come

Abstract Automated diagnosis of diseases in the recent years have gain lots of advantages and potential. Specially automated screening of cancers has helped the clinicians over the time. Sometimes it is seen that the diagnosis of the clinicians is biased but automated detection can help them to come to a proper conclusion. Automated screening is implemented using either artificial inter connected system or convolutional inter connected system. As Artificial neural network is slow in computation, so Convolutional Neural Network has achieved lots of importance in the recent years. It is also seen that Convolutional Neural Network architecture requires a smaller number of datasets. This also provides them an edge over Artificial Neural Networks. Convolutional Neural Networks is used for both segmentation and classification. Image dissection is one of the important steps in the model used for any kind of image analysis. This paper surveys various such Convolutional Neural Networks that are used for medical image analysis.

Download Full-text

Optimasi Akurasi Metode Convolutional Neural Network untuk Identifikasi Jenis Sampah

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) ◽

10.29207/resti.v5i2.2754 ◽

2021 ◽

Vol 5 (2) ◽

pp. 312-318

Author(s):

Rima Dias Ramadhani ◽

Afandi Nur Aziz Thohari ◽

Condro Kartiko ◽

Apri Junaidi ◽

Tri Ginanjar Laksana ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Computer Science ◽

No Value ◽

Convolutional Neural Networks ◽

Training Process ◽

Indonesian Government ◽

Speed Up ◽

Model Training

Waste is goods / materials that have no value in the scope of production, where in some cases the waste is disposed of carelessly and can damage the environment. The Indonesian government in 2019 recorded waste reaching 66-67 million tons, which is higher than the previous year, which was 64 million tons. Waste is differentiated based on its type, namely organic and anorganic waste. In the field of computer science, the process of sensing the type waste can be done using a camera and the Convolutional Neural Networks (CNN) method, which is a type of neural network that works by receiving input in the form of images. The input will be trained using CNN architecture so that it will produce output that can recognize the object being inputted. This study optimizes the use of the CNN method to obtain accurate results in identifying types of waste. Optimization is done by adding several hyperparameters to the CNN architecture. By adding hyperparameters, the accuracy value is 91.2%. Meanwhile, if the hyperparameter is not used, the accuracy value is only 67.6%. There are three hyperparameters used to increase the accuracy value of the model. They are dropout, padding, and stride. 20% increase in dropout to increase training overfit. Whereas padding and stride are used to speed up the model training process.

Download Full-text

Hand gesture recognition by means of region-based convolutional neural networks

Contemporary Engineering Sciences ◽

10.12988/ces.2017.710154 ◽

2017 ◽

Vol 10 (27) ◽

pp. 1329-1342 ◽

Cited By ~ 2

Author(s):

Javier O. Pinzon Arenas ◽

Robinson Jimenez Moreno ◽

Paula C. Useche Murillo

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Real Time ◽

Convolutional Neural Networks ◽

Gesture Recognition ◽

Hand Gesture ◽

Hand Gestures ◽

The Neural Network ◽

Average Accuracy

This paper presents the implementation of a Region-based Convolutional Neural Network focused on the recognition and localization of hand gestures, in this case 2 types of gestures: open and closed hand, in order to achieve the recognition of such gestures in dynamic backgrounds. The neural network is trained and validated, achieving a 99.4% validation accuracy in gesture recognition and a 25% average accuracy in RoI localization, which is then tested in real time, where its operation is verified through times taken for recognition, execution behavior through trained and untrained gestures, and complex backgrounds.

Download Full-text