scholarly journals Artificial intelligence in multiparametric prostate cancer imaging with focus on deep-learning methods

2020 ◽  
Vol 189 ◽  
pp. 105316 ◽  
Author(s):  
Rogier R. Wildeboer ◽  
Ruud J.G. van Sloun ◽  
Hessel Wijkstra ◽  
Massimo Mischi
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Cancer Imaging ◽  
Learning Methods

AB1161 ARTIFICIAL INTELLIGENCE FOR RHEUMATOLOGY

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 1871-1872
Author(s):  
A. C. Genç ◽  
F. Turkoglu Genc ◽  
A. B. Kara ◽  
L. Genc Kaya ◽  
Z. Ozturk ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Sacroiliac Joint ◽  
Axial Skeleton ◽  
Observer Agreement ◽  
Mri Findings ◽  
Learning Methods ◽  
Expert Radiologist ◽  
Active Sacroiliitis

Background:Magnetic resonance imaging (MRI) of sacroiliac (SI) joints is used to detect early sacroiliitis(1). There can be an interobserver disagreement in MRI findings of SI joints of spondyloarthropathy patients between a rheumatologist, a local radiologist, and an expert radiologist(2). Artificial Intelligence and deep learning methods to detect abnormalities have become popular in radiology and other medical fields in recent years(3). Search for “artificial intelligence” and “radiology” in Pubmed for the last five years returned around 1500 clinical studies yet no results were retrieved for “artificial intelligence” and “rheumatology”.Objectives:Artificial Intelligence (AI) can help to detect the pathological area like sacroiliitis or not and also allows us to characterize it as quantitatively rather than qualitatively in the SI-MRI.Methods:Between the years of 2015 and 2019, 8100 sacroiliac MRIs were taken at our center. The MRIs of 1150 patients who were reported as active or chronic sacroiliitis from these sacroiliac MRIs or whose MRIs were considered by the primary physician in favor of sacroiliitis was included in the study. 1441 MRI coronal STIR sequence of 1150 patients were tagged as ‘’active sacroiliitis’’ and trained to detect and localize active sacroiliitis and provide prediction performance. This model is available for various operating systems. (Image1)Results:Precision score, the percentage of sacroiliac images of the trained model, is 87.1%. Recall, the percentage of the total sacroiliac MRIs correctly classified by the model, is 82.1% and the mean average precision (mAP) of the model is 89%.Conclusion:There are gray areas in medicine like sacroiliitis. Inter-observer variability can be reduced by AI and deep learning methods. The efficiency and reliability of health services can be increased in this way.References:[1]Jans L, Egund N, Eshed I, Sudoł-Szopińska I, Jurik AG. Sacroiliitis in Axial Spondyloarthritis: Assessing Morphology and Activity. Semin Musculoskelet Radiol. 2018;22: 180–188.[2]B. Arnbak, T. S. Jensen, C. Manniche, A. Zejden, N. Egund, and A. G. Jurik, “Spondyloarthritis-related and degenerative MRI changes in the axial skeleton—an inter- and intra-observer agreement study,”BMC Musculoskeletal Disorders, vol. 14, article 274, 2013.[3]Rueda, Juan C et al. “Interobserver Agreement in Magnetic Resonance of the Sacroiliac Joints in Patients with Spondyloarthritis.”International journal of rheumatology(2017).Image1.Bilateral active sacroiliitis detected automatically by AI model (in right sacroiliac joint 75.6%> (50%), in left sacroiliac joint 65% (>50%))Disclosure of Interests:None declared

scholarly journals Performance analysis of pre-trained transfer learning models for the classification of the rolling bearing faults

2021 ◽  
Vol 2070 (1) ◽  
pp. 012141
Author(s):  
Pavan Sharma ◽  
Hemant Amhia ◽  
Sunil Datt Sharma
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Manufacturing Industry ◽  
Rolling Bearing ◽  
Performance Comparison ◽  
Learning Methods ◽  
Training Time ◽  
Bearing Faults ◽  
Artificial Intelligence Techniques

Abstract Nowadays, artificial intelligence techniques are getting popular in modern industry to diagnose the rolling bearing faults (RBFs). The RBFs occur in rotating machinery and these are common in every manufacturing industry. The diagnosis of the RBFs is highly needed to reduce the financial and production losses. Therefore, various artificial intelligence techniques such as machine and deep learning have been developed to diagnose the RBFs in the rotating machines. But, the performance of these techniques has suffered due the size of the dataset. Because, Machine learning and deep learning methods based methods are suitable for the small and large datasets respectively. Deep learning methods have also been limited to large training time. In this paper, performance of the different pre-trained models for the RBFs classification has been analysed. CWRU Dataset has been used for the performance comparison.

scholarly journals Explainable Artificial Intelligence (xAI) Approaches and Deep Meta-Learning Models

2020 ◽  
Author(s):  
Evren Dağlarli
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Black Box ◽  
Learning Models ◽  
Learning Methods ◽  
Data Set ◽  
Box Models ◽  
Explainable Artificial Intelligence ◽  
Artificial Neural ◽  
Black Box Models

The explainable artificial intelligence (xAI) is one of the interesting issues that has emerged recently. Many researchers are trying to deal with the subject with different dimensions and interesting results that have come out. However, we are still at the beginning of the way to understand these types of models. The forthcoming years are expected to be years in which the openness of deep learning models is discussed. In classical artificial intelligence approaches, we frequently encounter deep learning methods available today. These deep learning methods can yield highly effective results according to the data set size, data set quality, the methods used in feature extraction, the hyper parameter set used in deep learning models, the activation functions, and the optimization algorithms. However, there are important shortcomings that current deep learning models are currently inadequate. These artificial neural network-based models are black box models that generalize the data transmitted to it and learn from the data. Therefore, the relational link between input and output is not observable. This is an important open point in artificial neural networks and deep learning models. For these reasons, it is necessary to make serious efforts on the explainability and interpretability of black box models.

Detection of prostate cancer and determination of its significance using explainable artificial intelligence.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 5555-5555
Author(s):  
Okyaz Eminaga ◽  
Andreas Loening ◽  
Andrew Lu ◽  
James D Brooks ◽  
Daniel Rubin
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Input Data ◽  
Human Perception ◽  
Diagnostic Potential ◽  
Explainable Artificial Intelligence ◽  
Multiple Biopsy ◽  
Validation Set

5555 Background: The variation of the human perception has limited the potential of multi-parametric magnetic resonance imaging (mpMRI) of the prostate in determining prostate cancer and identifying significant prostate cancer. The current study aims to overcome this limitation and utilizes an explainable artificial intelligence to leverage the diagnostic potential of mpMRI in detecting prostate cancer (PCa) and determining its significance. Methods: A total of 6,020 MR images from 1,498 cases were considered (1,785 T2 images, 2,719 DWI images, and 1,516 ADC maps). The treatment determined the significance of PCa. Cases who received radical prostatectomy were considered significant, whereas cases with active surveillance and followed for at least two years were considered insignificant. The negative biopsy cases have either a single biopsy setting or multiple biopsy settings with the PCa exclusion. The images were randomly divided into development (80%) and test sets (20%) after stratifying according to the case in each image type. The development set was then divided into a training set (90%) and a validation set (10%). We developed deep learning models for PCa detection and the determination of significant PCa based on the PlexusNet architecture that supports explainable deep learning and volumetric input data. The input data for PCa detection was T2-weighted images, whereas the input data for determining significant PCa include all images types. The performance of PCa detection and determination of significant PCa was measured using the area under receiving characteristic operating curve (AUROC) and compared to the maximum PiRAD score (version 2) at the case level. The 10,000 times bootstrapping resampling was applied to measure the 95% confidence interval (CI) of AUROC. Results: The AUROC for the PCa detection was 0.833 (95% CI: 0.788-0.879) compared to the PiRAD score with 0.75 (0.718-0.764). The DL models to detect significant PCa using the ADC map or DWI images achieved the highest AUROC [ADC: 0.945 (95% CI: 0.913-0.982; DWI: 0.912 (95% CI: 0.871-0.954)] compared to a DL model using T2 weighted (0.850; 95% CI: 0.791-0.908) or PiRAD scores (0.604; 95% CI: 0.544-0.663). Finally, the attention map of PlexusNet from mpMRI with PCa correctly showed areas that contain PCa after matching with corresponding prostatectomy slice. Conclusions: We found that explainable deep learning is feasible on mpMRI and achieves high accuracy in determining cases with PCa and identifying cases with significant PCa.

A Study on Deep Learning Methods in the Concept of Digital Industry 4.0

2021 ◽  
pp. 318-339
Author(s):  
Mehmet Ali Şimşek ◽  
Zeynep Orman
Keyword(s):  
Artificial Intelligence ◽  
Decision Making ◽  
Deep Learning ◽  
Industry 4.0 ◽  
Production Efficiency ◽  
Learning Technologies ◽  
High Potential ◽  
Data Sets ◽  
Learning Methods ◽  
Intelligence Studies

Nowadays, the main features of Industry 4.0 are interpreted to the ability of machines to communicate with each other and with a system, increasing the production efficiency and development of the decision-making mechanisms of robots. In these cases, new analytical algorithms of Industry 4.0 are needed. By using deep learning technologies, various industrial challenging problems in Industry 4.0 can be solved. Deep learning provides algorithms that can give better results on datasets owing to hidden layers. In this chapter, deep learning methods used in Industry 4.0 are examined and explained. In addition, data sets, metrics, methods, and tools used in the previous studies are explained. This study can lead to artificial intelligence studies with high potential to accelerate the implementation of Industry 4.0. Therefore, the authors believe that it will be very useful for researchers and practitioners who want to do research on this topic.

MEDSAL Project - Salinization of critical groundwater reserves in coastal Mediterranean areas: Identification, risk assessment and sustainable management with the use of integrated modelling and smart ICT tools

2020 ◽  
Author(s):  
Evangelos Tziritis ◽  
Vassilis Aschonitis ◽  
Gabriella Balacco ◽  
Petros Daras ◽  
Charalampos Doulgeris ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Risk Assessment ◽  
Deep Learning ◽  
Mediterranean Area ◽  
Groundwater Salinization ◽  
Learning Methods ◽  
Modeling Tools ◽  
Isotope Data ◽  
The Mediterranean ◽  
Groundwater Reserves

<p>MEDSAL is a research project (www.medsal.net) focusing on groundwater salinization in the Mediterranean area, funded by the PRIMA Program (Partnership for Research and Innovation in the Mediterranean Area), and running for 36 months starting from September 2019. MEDSAL constitutes a joint Euro-Mediterranean cooperation network of organizations from Mediterranean countries and associated states of the EU contributing national funds. The partnership involves eight academic partners from seven countries (plus an external collaborator – private firm), covering a wide range of academic experts in various scientific fields (e.g. hydrogeology, hydrogeochemistry, environmental isotopes, modeling, hydro-informatics, geostatistics, machine learning).</p><p>MEDSAL aims at developing innovative methods to identify various sources and processes of salinization and at providing an integrated set of modeling tools that capture the dynamics and risks of salinization. Thereby, it aims to secure the availability and quality of groundwater reserves in Mediterranean coastal areas, which are amongst the most vulnerable regions in the world to water scarcity and quality degradation. MEDSAL encompasses six (6) test sites located in five (5) countries: Rhodope, Greece, (ii) Samos Island, Greece, (iii) Salento, Italy, (iv) Tarsus, Turkey, (v) Boufichia, Tunisia, and (vi) Bouteldja, Algeria.</p><p>MEDSAL’s principal objectives are the following: a) Deliver new tools for the identification of complex salinization sources and processes, b) Exploit the potential of Artificial intelligence and Deep Learning methods to improve detection of patterns in multi-dimensional hydrogeochemical and isotope data, c) Elaborate tailor-made risk assessment and development of management plans by coupling salinization forecasts with climate change impacts and future scenarios, and d) Develop a public domain web-GIS Observatory for monitoring, alerting, decision support and management of coastal groundwater reserves around the Mediterranean.</p><p>MEDSAL is expected to have a significant impact on water resources availability and quality by improving the identification and development of adequate strategies and measures for the protection and management of salinization in coastal aquifers. In this context, MEDSAL will provide innovative classification and detection methods of groundwater salinization types for Mediterranean coasts, also in complex karstic and data-scarce environments. These outcomes will be reached by better integration of hydrogeochemical and environmental isotope data with physical-based groundwater flow and transport models and advanced geostatistics. Artificial intelligence and deep learning methods will be also used to improve the detection of patterns in multi-dimensional hydrogeochemical and isotope data.</p>

DDV: A Taxonomy for Deep Learning Methods in Detecting Prostate Cancer

2021 ◽  
Author(s):  
Abeer Alsadoon ◽  
Ghazi Al-Naymat ◽  
Omar Hisham Alsadoon ◽  
P. W. C. Prasad
Keyword(s):  
Prostate Cancer ◽  
Deep Learning ◽  
Learning Methods

scholarly journals Feasibility of Synthetic Computed Tomography Images Generated from Magnetic Resonance Imaging Scans Using Various Deep Learning Methods in the Planning of Radiation Therapy for Prostate Cancer

Cancers ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 40
Author(s):  
Gyu Sang Yoo ◽  
Huan Minh Luu ◽  
Heejung Kim ◽  
Won Park ◽  
Hongryull Pyo ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Computed Tomography ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Soft Tissue ◽  
Ct Images ◽  
Learning Approaches ◽  
Learning Methods ◽  
Computed Tomography Images ◽  
The Mean

We aimed to evaluate and compare the qualities of synthetic computed tomography (sCT) generated by various deep-learning methods in volumetric modulated arc therapy (VMAT) planning for prostate cancer. Simulation computed tomography (CT) and T2-weighted simulation magnetic resonance image from 113 patients were used in the sCT generation by three deep-learning approaches: generative adversarial network (GAN), cycle-consistent GAN (CycGAN), and reference-guided CycGAN (RgGAN), a new model which performed further adjustment of sCTs generated by CycGAN with available paired images. VMAT plans on the original simulation CT images were recalculated on the sCTs and the dosimetric differences were evaluated. For soft tissue, a significant difference in the mean Hounsfield unites (HUs) was observed between the original CT images and only sCTs from GAN (p = 0.03). The mean relative dose differences for planning target volumes or organs at risk were within 2% among the sCTs from the three deep-learning approaches. The differences in dosimetric parameters for D98% and D95% from original CT were lowest in sCT from RgGAN. In conclusion, HU conservation for soft tissue was poorest for GAN. There was the trend that sCT generated from the RgGAN showed best performance in dosimetric conservation D98% and D95% than sCTs from other methodologies.

Sign in / Sign up

Export Citation Format

Share Document