scholarly journals Impact of Image Resolution on Deep Learning Performance in Endoscopy Image Classification: An Experimental Study Using a Large Dataset of Endoscopic Images

Diagnostics ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 2183
Author(s):  
Vajira Thambawita ◽  
Inga Strümke ◽  
Steven A. Hicks ◽  
Pål Halvorsen ◽  
Sravanthi Parasa ◽  
...  
Keyword(s):  
Image Classification ◽  
Image Resolution ◽  
Lesion Detection ◽  
Learning Performance ◽  
Large Dataset ◽  
Endoscopic Image ◽  
And Performance ◽  
The Cost ◽  
Entire Dataset ◽  
Fold Cross Validation

Recent trials have evaluated the efficacy of deep convolutional neural network (CNN)-based AI systems to improve lesion detection and characterization in endoscopy. Impressive results are achieved, but many medical studies use a very small image resolution to save computing resources at the cost of losing details. Today, no conventions between resolution and performance exist, and monitoring the performance of various CNN architectures as a function of image resolution provides insights into how subtleties of different lesions on endoscopy affect performance. This can help set standards for image or video characteristics for future CNN-based models in gastrointestinal (GI) endoscopy. This study examines the performance of CNNs on the HyperKvasir dataset, consisting of 10,662 images from 23 different findings. We evaluate two CNN models for endoscopic image classification under quality distortions with image resolutions ranging from 32 × 32 to 512 × 512 pixels. The performance is evaluated using two-fold cross-validation and F1-score, maximum Matthews correlation coefficient (MCC), precision, and sensitivity as metrics. Increased performance was observed with higher image resolution for all findings in the dataset. MCC was achieved at image resolutions between 512 × 512 pixels for classification for the entire dataset after including all subclasses. The highest performance was observed with an MCC value of 0.9002 when the models were trained on the highest resolution and tested on the same resolution. Different resolutions and their effect on CNNs are explored. We show that image resolution has a clear influence on the performance which calls for standards in the field in the future.

scholarly journals Harnessing clinical annotations to improve deep learning performance in prostate segmentation

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0253829
Author(s):  
Karthik V. Sarma ◽  
Alex G. Raman ◽  
Nikhil J. Dhinagar ◽  
Alan M. Priester ◽  
Stephanie Harmon ◽  
...  
Keyword(s):  
Hausdorff Distance ◽  
Large Scale ◽  
State Of The Art ◽  
Learning Performance ◽  
Research Quality ◽  
Large Dataset ◽  
Template Model ◽  
Prostate Segmentation ◽  
Original Dataset ◽  
Entire Dataset

Purpose Developing large-scale datasets with research-quality annotations is challenging due to the high cost of refining clinically generated markup into high precision annotations. We evaluated the direct use of a large dataset with only clinically generated annotations in development of high-performance segmentation models for small research-quality challenge datasets. Materials and methods We used a large retrospective dataset from our institution comprised of 1,620 clinically generated segmentations, and two challenge datasets (PROMISE12: 50 patients, ProstateX-2: 99 patients). We trained a 3D U-Net convolutional neural network (CNN) segmentation model using our entire dataset, and used that model as a template to train models on the challenge datasets. We also trained versions of the template model using ablated proportions of our dataset, and evaluated the relative benefit of those templates for the final models. Finally, we trained a version of the template model using an out-of-domain brain cancer dataset, and evaluated the relevant benefit of that template for the final models. We used five-fold cross-validation (CV) for all training and evaluation across our entire dataset. Results Our model achieves state-of-the-art performance on our large dataset (mean overall Dice 0.916, average Hausdorff distance 0.135 across CV folds). Using this model as a pre-trained template for refining on two external datasets significantly enhanced performance (30% and 49% enhancement in Dice scores respectively). Mean overall Dice and mean average Hausdorff distance were 0.912 and 0.15 for the ProstateX-2 dataset, and 0.852 and 0.581 for the PROMISE12 dataset. Using even small quantities of data to train the template enhanced performance, with significant improvements using 5% or more of the data. Conclusion We trained a state-of-the-art model using unrefined clinical prostate annotations and found that its use as a template model significantly improved performance in other prostate segmentation tasks, even when trained with only 5% of the original dataset.

Return on Invesment (ROI) of Software Product: A Systematic Literature Review

2015 ◽  
Vol 6 (1) ◽  
pp. 50-57
Author(s):  
Rizqa Raaiqa Bintana ◽  
Putri Aisyiyah Rakhma Devi ◽  
Umi Laili Yuhana
Keyword(s):  
Return On Investment ◽  
Assessment Criteria ◽  
Software Product ◽  
And Performance ◽  
Rational Consideration ◽  
Actual Return ◽  
The Cost ◽  
Investment Models ◽  
The Impact

The quality of the software can be measured by its return on investment. Factors which may affect the return on investment (ROI) is the tangible factors (such as the cost) dan intangible factors (such as the impact of software to the users or stakeholder). The factor of the software itself are assessed through reviewing, testing, process audit, and performance of software. This paper discusses the consideration of return on investment (ROI) assessment criteria derived from the software and its users. These criteria indicate that the approach may support a rational consideration of all relevant criteria when evaluating software, and shows examples of actual return on investment models. Conducted an analysis of the assessment criteria that affect the return on investment if these criteria have a disproportionate effort that resulted in a return on investment of a software decreased. Index Terms - Assessment criteria, Quality assurance, Return on Investment, Software product

scholarly journals Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross Entropy

Entropy ◽  
2021 ◽  
Vol 23 (7) ◽  
pp. 816
Author(s):  
Pingping Liu ◽  
Xiaokang Yang ◽  
Baixin Jin ◽  
Qiuzhan Zhou
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Network Model ◽  
Rapid Development ◽  
Image Data ◽  
Lesion Detection ◽  
Great Success

Diabetic retinopathy (DR) is a common complication of diabetes mellitus (DM), and it is necessary to diagnose DR in the early stages of treatment. With the rapid development of convolutional neural networks in the field of image processing, deep learning methods have achieved great success in the field of medical image processing. Various medical lesion detection systems have been proposed to detect fundus lesions. At present, in the image classification process of diabetic retinopathy, the fine-grained properties of the diseased image are ignored and most of the retinopathy image data sets have serious uneven distribution problems, which limits the ability of the network to predict the classification of lesions to a large extent. We propose a new non-homologous bilinear pooling convolutional neural network model and combine it with the attention mechanism to further improve the network’s ability to extract specific features of the image. The experimental results show that, compared with the most popular fundus image classification models, the network model we proposed can greatly improve the prediction accuracy of the network while maintaining computational efficiency.

scholarly journals Gaze awareness and metacognitive suggestions by a pedagogical conversational agent: an experimental investigation on interventions to support collaborative learning process and performance

2020 ◽  
Vol 15 (4) ◽  
pp. 469-498 ◽  
Author(s):  
Yugo Hayashi
Keyword(s):  
Collaborative Learning ◽  
Real Time ◽  
Learning Process ◽  
Common Ground ◽  
Learning Performance ◽  
Conversational Agent ◽  
Learning Gains ◽  
Computer Supported Collaborative Learning ◽  
Collaborative Process ◽  
And Performance

AbstractResearch on collaborative learning has revealed that peer-collaboration explanation activities facilitate reflection and metacognition and that establishing common ground and successful coordination are keys to realizing effective knowledge-sharing in collaborative learning tasks. Studies on computer-supported collaborative learning have investigated how awareness tools can facilitate coordination within a group and how the use of external facilitation scripts can elicit elaborated knowledge during collaboration. However, the separate and joint effects of these tools on the nature of the collaborative process and performance have rarely been investigated. This study investigates how two facilitation methods—coordination support via learner gaze-awareness feedback and metacognitive suggestion provision via a pedagogical conversational agent (PCA)—are able to enhance the learning process and learning gains. Eighty participants, organized into dyads, were enrolled in a 2 × 2 between-subject study. The first and second factors were the presence of real-time gaze feedback (no vs. visible gaze) and that of a suggestion-providing PCA (no vs. visible agent), respectively. Two evaluation methods were used: namely, dialog analysis of the collaborative process and evaluation of learning gains. The real-time gaze feedback and PCA suggestions facilitated the coordination process, while gaze was relatively more effective in improving the learning gains. Learners in the Gaze-feedback condition achieved superior learning gains upon receiving PCA suggestions. A successful coordination/high learning performance correlation was noted solely for learners receiving visible gaze feedback and PCA suggestions simultaneously (visible gaze/visible agent). This finding has the potential to yield improved collaborative processes and learning gains through integration of these two methods as well as contributing towards design principles for collaborative-learning support systems more generally.

scholarly journals TransMed: Transformers Advance Multi-Modal Medical Image Classification

Diagnostics ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1384
Author(s):  
Yin Dai ◽  
Yifan Gao ◽  
Fayu Liu
Keyword(s):  
Image Analysis ◽  
Image Classification ◽  
Long Range ◽  
Medical Image ◽  
Large Scale ◽  
Medical Images ◽  
Medical Image Analysis ◽  
Lesion Detection ◽  
Tumor Segmentation ◽  
Medical Image Classification

Over the past decade, convolutional neural networks (CNN) have shown very competitive performance in medical image analysis tasks, such as disease classification, tumor segmentation, and lesion detection. CNN has great advantages in extracting local features of images. However, due to the locality of convolution operation, it cannot deal with long-range relationships well. Recently, transformers have been applied to computer vision and achieved remarkable success in large-scale datasets. Compared with natural images, multi-modal medical images have explicit and important long-range dependencies, and effective multi-modal fusion strategies can greatly improve the performance of deep models. This prompts us to study transformer-based structures and apply them to multi-modal medical images. Existing transformer-based network architectures require large-scale datasets to achieve better performance. However, medical imaging datasets are relatively small, which makes it difficult to apply pure transformers to medical image analysis. Therefore, we propose TransMed for multi-modal medical image classification. TransMed combines the advantages of CNN and transformer to efficiently extract low-level features of images and establish long-range dependencies between modalities. We evaluated our model on two datasets, parotid gland tumors classification and knee injury classification. Combining our contributions, we achieve an improvement of 10.1% and 1.9% in average accuracy, respectively, outperforming other state-of-the-art CNN-based models. The results of the proposed method are promising and have tremendous potential to be applied to a large number of medical image analysis tasks. To our best knowledge, this is the first work to apply transformers to multi-modal medical image classification.

Characterisation of Static Strip Seal Flow

2007 ◽  
Author(s):  
Arash Farahani ◽  
Peter Childs
Keyword(s):  
Gas Flow ◽  
Pressure Ratio ◽  
Flow Characteristics ◽  
Main Stream ◽  
Cfd Modelling ◽  
Height Range ◽  
And Performance ◽  
Nozzle Guide ◽  
The Cost ◽  
Cooling Air

Strip seals are used in gas turbine engines between two static elements or between components which do not move relative to each other, such as Nozzle Guide Vanes (NGVs). The key role of a strip seal between NGV segments is sealing between the flow through the main stream annulus and the internal air system, a further purpose is to limit the inter-segmental movements. In general the shape of the strip seal is a rectangular strip that fits into two slots in adjacent components. The minimum clearance required for static strip seals must be found by accounting for thermal expansion, misalignment, and application, to allow correct fitment of the strip seals. Any increase in leakage raises the cost due to an increase in the cooling air use, which is linked to specific fuel consumption, and it can also alter gas flow paths and performance. The narrow path within the seal assembly, especially the height has the most significant affect on leakage. The height range of the narrow path studied in this paper is 0.01–0.06 mm. The behaviour of the flow passing through the narrow path has been studied using CFD modelling and measurements in a bespoke rig. The CFD and experimental results show that normalized leakage flow increases with pressure ratio before reaching a maximum. The main aim of this paper is to provide new experimental data to verify the CFD modelling for static strip seals. The typical flow characteristics validated by CFD modelling and experiments can be used to predict the flow behaviour for future static strip seal designs.

scholarly journals Alert: An Adaptive Low-Latency Event-Driven MAC Protocol for Wireless Sensor Networks

2011 ◽  
Vol 2011 ◽  
pp. 1-19
Author(s):  
Vinod Namboodiri ◽  
Abtin Keshavarzian
Keyword(s):  
Mac Protocol ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Network Applications ◽  
Alarm Systems ◽  
Minimum Latency ◽  
Multiple Sensor ◽  
Protocol Execution ◽  
And Performance ◽  
The Cost

Collection of rare but delay-critical messages from a group of sensor nodes is a key process in many wireless sensor network applications. This is particularly important for security-related applications like intrusion detection and fire alarm systems. An event sensed by multiple sensor nodes in the network can trigger many messages to be sent simultaneously. We present Alert, a MAC protocol for collecting event-triggered urgent messages from a group of sensor nodes with minimum latency and without requiring any cooperation or prescheduling among the senders or between senders and receiver during protocol execution. Alert is designed to handle multiple simultaneous messages from different nodes efficiently and reliably, minimizing the overall delay to collect all messages along with the delay to get the first message. Moreover, the ability of the network to handle a large number of simultaneous messages does not come at the cost of excessive delays when only a few messages need to be handled. We analyze Alert and evaluate its feasibility and performance with an implementation on commodity hardware. We further compare Alert with existing approaches through simulations and show the performance improvement possible through Alert.

scholarly journals ИСПОЛЬЗОВАНИЕ ТЕОРИИ НЕЧЕТКИХ МНОЖЕСТВ В ЭКОНОМИЧЕСКОМ АНАЛИЗЕ ИНВЕСТИЦИОННЫХ ПРОЕКТОВ

2018 ◽  
Vol 2 (5(17)) ◽  
pp. 44-48
Author(s):  
Файзиев Р. А. ◽  
Хаитматов У. Т. ◽  
Азаматов О. Х. ◽  
Джуманиязов Ш. Р. ◽  
Хасанова Х. Х.
Keyword(s):  
Integral Characteristic ◽  
Mathematical Methods ◽  
Investment Projects ◽  
Performance Targets ◽  
Methods Of Evaluation ◽  
Interval Approach ◽  
And Performance ◽  
The Cost ◽  
Fuzzy Interval ◽  
Theory Of Fuzzy Sets

The article outlines the main features of the use of the theory of indefinite bundles in the evaluation of the cost-effectiveness of investment projects.He analysis of methods for quantifying the effectiveness of the IP under uncertainty suggests that the existing methods either eliminate the uncertainty from the IP model, which is inappropriate, since uncertainty is an integral characteristic of any forecast, or are unable to formally describe, and take into account all possible varieties of types of uncertainty.Methods based on the theory of fuzzy sets refer to the methods of evaluation and decision-making under conditions of uncertainty. Their use implies the formalization of the initial parameters and performance targets of the IP in the form of a vector of interval values (fuzzy interval), the hit in each interval of which is characterized by a certain degree of uncertainty.Also, the fuzzy-interval approach has advantages in solving the problems of forming an optimal portfolio of investment projects. To solve the problem of forming an optimal IP portfolio, a large number of models for the formation of an optimal IP portfolio have been developed, differing from each other in the form of objective functions, variable properties, used by mathematical methods, and uncertainty.

scholarly journals Proposed Policy Preventive Maintenance Machine Moriseiki NH 4000 DCG Method Of Reliability Center Maintenance (RCM) And Risk Based Maintenance (RBM) Case Study PT. Pudak Scientific

2018 ◽  
Vol 2 (01) ◽  
Author(s):  
Fachri Husaini
Keyword(s):  
Production Capacity ◽  
Cost Of Care ◽  
Maintenance Policy ◽  
Performance Loss ◽  
Acceptance Set ◽  
Maintenance Activities ◽  
And Performance ◽  
The Cost ◽  
A Company

PT Pudak Scientific is a company engaged in the manufacture of aircraft parts industry. Meeting the precise and timely demand of aerospace parts from customers becomes a major corporate responsibility. However, Loss Revenue often occurs due to engine breakdown. So that cause because the production target is not achieved, the product reject, and the delay of delivery. One of the machines that often experience breakdown is Mori seiki NH4000 DCG. Mori seiki NH4000 DCG is the finishing machine for Blank fork End product. The demand for this part is quite large, making it a tough task for the Mori Seiki NH4000 DCG machine. But because the breakdown of the machine is high enough to cause production targets every month are often not met. In addition, Maintenance activities that have not noticed the characteristics of engine damage, as well as the distribution of historical data of the machine causing less effective and efficient actions resulted in substantial Maintenance costs. Based on the results of risk analysis of Mori Seiki NH4000 DCG engine damage, in terms of performance loss system caused by a large enough that is 3.773% of machine production capacity per year. This figure exceeds the risk acceptance criteria by the company that is 2%. Therefore it is necessary to find the appropriate Maintenance policy for the Mori Seiki NH4000 DCG machine. The approach is to use Reliability Centeres Maintenance and Risk Based Maintenance. Based on the above two approaches obtained the appropriate interval time so that the Maintenance activities more effective and can improve the efficiency of treatment by reducing the cost of care previously Rp167.506.286, - per year, to Rp 96.147.061, - per year. With the policy is expected to reduce engine breakdown and performance loss caused. So the number of risks that arise for the future are within the criteria of acceptance set by the company.

Sign in / Sign up

Export Citation Format

Share Document