NIMG-55. AUGMENTED INTELLIGENCE IS SUPERIOR TO ARTIFICIAL INTELLIGENCE! HUMAN-COMPUTER SYNERGY FOR GENERATING HIGH QUALITY GLIOBLASTOMA SUB-REGION SEGMENTATIONS

2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi141-vi142
Author(s):  
Satyam Ghodasara ◽  
Ujjwal Baid ◽  
Spyridon Bakas ◽  
Michel Bilello ◽  
Suyash Mohan

Abstract PURPOSE Artificial intelligence (AI) is poised to improve diagnostic methods in neuro-oncologic imaging and contribute to patient management by analyzing pre-operative MRI scans. AI results are better interpreted by compartmentalizing glioblastoma into distinct sub-regions, i.e., necrotic core, enhancing tumor, peritumoral T2/FLAIR signal abnormality (ED). Manual delineation of these sub-regions by expert neuroradiologists is impractical, requiring hours for intricate cases. Computer-aided segmentation (CAS) can mitigate this issue but is limited in the quality of the produced segmentations. We hypothesize that CAS followed by expert refinements is more practical/time-efficient. METHODS CAS was used on a total of 359 glioblastoma patients with four MRI sequences (T1, T1Gd, T2, T2-FLAIR) from each patient. All segmentations were sent to expert neuroradiologist annotators for manual refinements. Once refined, our team including two senior attending neuroradiologists with ≥13 years of experience each, reviewed and either approved or returned the segmentations to individual annotators for further refinements. Total time required to refine and review the finalized segmentations was measured. RESULTS Following one round of refinements by expert annotators, 244/359 (68%) segmentations were approved by our team while 115/359 (32%) segmentations contained a variety of errors that required a second round of refinements. The most common observed errors were 1) missed ED in the anterior/inferior temporal lobes and corpus callosum (37/115 cases, 32%) and 2) erroneous segmentation of normal choroid plexus and blood vessels (14/115 cases, 12%). The expert annotators required 120 hours to refine all 359 segmentations, and our team required 26 additional hours to review them, resulting in 24 minutes/segmentation following CAS. CONCLUSION Our findings support the value of a well-communicated annotation protocol to coordinate CAS and expert annotators. With CAS, our team and expert annotators rapidly finalized segmentations for 359 glioblastoma patients, demonstrating the value of a synergistic approach to creating high quality tumor sub-region segmentations.

Author(s):  
Hsin-Chang Yang ◽  
Wen-Yang Lin ◽  
Chun-Yang Chang ◽  
Cheng-Hong Yang ◽  
Shyi-Ming Chen

The 11th Conference on Artificial Intelligence and Applications (TAAI 2006), which was held during Dec. 15-16, 2006 at Kaohsiung, Taiwan, is the annual conference of Taiwanese Association for Artificial Intelligence. The conference is intended to provide a forum for researchers and scholars in the related fields of artificial intelligence. Past conferences have proven them successful attempts to become the most important meeting of artificial intelligence researchers in Taiwan. This is also true for TAAI 2006, which focuses on various aspects on theory and practice of artificial intelligence. In this special issue, 11 papers presented in the conference are selected and extended for their outstanding performance on the conference. These papers cover wide spreading aspects, which include versatile motion planning, particle swarm optimization, data mining, image retrieval, music retrieval, natural language processing, navigation, fuzzy logic, gaming, and bioinformatics. This issue thus concisely summarizes recent advances in artificial intelligence and its applications. The readers should find them valuable and inspiring. We hope that this issue should provide a valuable resource for their researches. As guest editors of this special issue, we like to express our greatest gratitude to those that help this issue come true. Thanks to all contributors and referees for their elaborate works and careful reviews that assure the high quality of this issue. Special thanks should go to Mr. Makoto Shimada of Fuji Technology Press for his efforts and kind assistance in publishing this issue. Finally, we also like to thank the Editors in Chief of JACIII, Prof. Toshio Fukuda and Prof. Kaoru Hirota, for their generous hospitality in supporting this special issue.


Author(s):  
S.S GRECHIKHIN ◽  

Diagnostics in the practice of a dentist is the key to quality treatment. However, depending on the quality of services provided, the cost of diagnostic methods is set. For a dentist working in a private office, the key to successful diagnostic measures at a high quality level is a priority. However, these methods are expensive for the patient. The purpose of this study is to study the impact of financial incentives on the quality of early diagnosis in the practice of a dentist who provides quality treatment. In the study, we studied clinical cases with full and partial study in terms of diagnostic and neglect x-ray diagnosis from the doctor and from the patient due to a misunderstanding of the importance and necessity of this manipulation. In statistical data analysis, the resulting regression models use a binary variable as a dependent variable on the level of financial costs. Thus, in the course of our research, we found that the number of x-rays significantly increases when dentists receive a fee for services, rather than a salary, and when patients are exempt from paying for additional diagnostic methods. Our results show that financial incentives significantly influence additional high-quality and complete examination of patients.


2016 ◽  
Vol 53 (8) ◽  
pp. 1235-1245 ◽  
Author(s):  
Arnfinn Emdal ◽  
Anders Gylland ◽  
Helene A. Amundsen ◽  
Kristoffer Kåsin ◽  
Michael Long

Challenges in obtaining high quality samples of sensitive low-plasticity clay in an effective manner have been overcome by the development of the mini-block sampler. The starting point for the development of the new sampler was the Sherbrooke block sampler that was first introduced in Canada in 1979. Although the Sherbrooke block sampler can produce high quality samples, its use, particularly in industrial projects, has been limited due to the perceived high costs, practical difficulties, and the time required. This paper outlines details of the development and design of the mini-block sampler together with developed techniques for protection and transportation of the samples and preparation of specimens for laboratory testing. The sampler has been used successfully at five Norwegian clay sites. For two of the sites comparative Sherbrooke samples were available and it is shown that the quality of the mini-block samples is very high and is at least as good as that of the Sherbrooke samples. The work also demonstrates that rigging, preparation, and sampling with the mini-block sampler is fast, practical and is not labour intensive. Furthermore the resulting samples are easy to transport and handle, but still provide sufficient material for extensive laboratory testing.


2018 ◽  
Vol 5 (3) ◽  
pp. 53-66
Author(s):  
H. S. Gevorgyan ◽  
A. A. Kostin ◽  
N. V. Vorobyev ◽  
K. М. Nyushko ◽  
A. G. Muradyan ◽  
...  

Providing a high quality of life for a man after performing radical prostatectomy for prostate cancer is currently one of the topical problems of urology and andrology. Nervous-protective radical prostatectomy is one of the high-tech operations in urology and the surgeon’s task is not only to remove the tumor of the prostate gland, but also to ensure a high quality of life for the patient. The importance and urgency of this problem is evidenced by the fact that most of the issues that arise in patients in conversation with a surgeon before surgical intervention are devoted to it.The National Institute of Health of the USA shows that the incidence of prostate cancer is about 9.5% per year, and the localized form began to occur in younger men. In this regard, the surgeon faces the task not only to cure the patient of malignant education, but also to maintain the erectile function and the continent’s indicators, thereby improving the quality of life.At the present stage, diagnostic methods make it possible to detect early prostate cancer much more often, so that the identification and treatment of such patients become more accessible and allows the use of this operation. However, for the preservation of the neurovascular bundle, it is mandatory to know the anatomical features of this zone.Over the past few decades, anatomical studies have been conducted that described the neuroanatomy of the prostate and the adjacent tissue. This article summarizes the latest results of studies of neuroanatomical studies, some of which contradict the established consensus on pelvic anatomy.


2012 ◽  
Vol 4 (2) ◽  
pp. 16
Author(s):  
A Sulaiman

The research of Distillation And Raw Material Composition Effect of Yield And Quality EssentialOil of Leaves And Stem Patchouli (Pogostemon cablin Benth). This study aimed to examine the influence of the length of distillation and composition of raw materials to the yield and quality of essential oil of patchouli leaves and stems to produce essential oils that have a high quality and yield. The time required to obtain the highest yield of patchouli oil is 8 hours, by composition of 100% leaf (1:0), that is equal to 3.631%, while the lowest yield of patchouli oil are produced from 100% stem (1:0) by distillation of 4 hours, in the amount of 0.10%. Composition that produces patchouli oil with the best quality is 100% stems (0:1) but that yield is lower, while the quality of patchouli oil produced by 100% leaf (1:0) and a mixture of leaf-stem (1:1) quality is still lower than the patchouli oil from the stem, but its yield is better than the yield of oil patchouli by 100% composition of the stem (0:1).Keywords:  essential oil, pogostemon cablin benth, yield


Author(s):  
Andrew A Borkowski ◽  
Narayan A Viswanadham ◽  
L Brannon Thomas ◽  
Rodney D Guzman ◽  
Lauren A Deland ◽  
...  

Coronavirus disease-19 (COVID-19), caused by a novel member of the coronavirus family, is a respiratory disease that rapidly reached pandemic proportions with high morbidity and mortality. It has had a dramatic impact on society and world economies in only a few months. COVID-19 presents numerous challenges to all aspects of healthcare, including reliable methods for diagnosis, treatment, and prevention. Initial efforts to contain the spread of the virus were hampered by the time required to develop reliable diagnostic methods. Artificial intelligence (AI) is a rapidly growing field of computer science with many applications to healthcare. Machine learning is a subset of AI that employs deep learning with neural network algorithms. It can recognize patterns and achieve complex computational tasks often far quicker and with increased precision than humans. In this manuscript, we explore the potential for a simple and widely available test as a chest x-ray (CXR) to be utilized with AI to diagnose COVID-19 reliably. Microsoft CustomVision is an automated image classification and object detection system that is a part of Microsoft Azure Cognitive Services. We utilized publicly available CXR images for patients with COVID-19 pneumonia, pneumonia from other etiologies, and normal CXRs as a dataset to train Microsoft CustomVision. Our trained model overall demonstrated 92.9% sensitivity (recall) and positive predictive value (precision), with results for each label showing sensitivity and positive predictive value at 94.8% and 98.9% for COVID-19 pneumonia, 89% and 91.8% for non-COVID-19 pneumonia, 95% and 88.8% for normal lung. We then validated the program using CXRs of patients from our institution with confirmed COVID-19 diagnoses along with non-COVID-19 pneumonia and normal CXRs. Our model performed with 100% sensitivity, 95% specificity, 97% accuracy, 91% positive predictive value, and 100% negative predictive value. Finally, we developed and described a publicly available website to demonstrate how this technology can be made readily available in the future.


2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Jiehua Zhong

Students must integrate into the development of ethnic education and accept applicable norms and policies, values, and processes so that academics can continue to develop in a good direction for exploring and researching intellectual Ideological and Political Learning (IPL). The creation of a data system for the administration of IPL for university students can boost knowledge and the quality of maintenance of IPL. Therefore, this paper suggests artificial intelligence-based Ideological and Political Learning (AI-IPL) of college students depending on the psychological quality measurements. The AI-IPL method is used for the ideological and political development of the college students to encourage the students both mentally and physically. The AI-IPL method creates the differences in opinion between some of the students, which define the IPL of the eventual tendency towards creative strategy and psychological education method. The thought created by students’ experience must be evaluated for the requirements of learning and the experience of developing high-quality talent by the measure of political growth through innovating intellectual and political learning.


2021 ◽  
Author(s):  
Matvey Ezhov ◽  
Maxim Gusarev ◽  
Maria Golitsyna ◽  
Julian Yates ◽  
Evgeny Kushnerev ◽  
...  

Abstract Cone-beam computed tomography (CBCT) in dental practice is becoming increasingly popular. However, the correct teeth identification, positioning and diagnosis based on CBCT can be tedious and challenging for the untrained eye. This is due to additional training, specific knowledge and time required for analysis and diagnosis. When compared to conventional dental imaging methods. In this study, we introduce a novel artificial intelligence (AI) system that facilitates analysis and diagnosis. This system is based on deep learning approaches that can localize teeth and define pathologies within three-dimensional CBCT scans. The study showed that the diagnostic performance of AI system image interpretation reaches and sometimes exceeds in comparison to clinician’s expertise. In this randomized cross-over trial we demonstrated a significant improvement of aided diagnostic accuracy for various dental diseases in comparison to a group of radiologists that made unaided decisions. AI can be used for both stand-alone CBCT interpretation and as a decision support system to improve quality of diagnostics and time efficiency.


2016 ◽  
Vol 42 (2) ◽  
pp. 106-113
Author(s):  
Tao Machado ◽  
Allex Jardim da Fonseca ◽  
Sandra Maria Franco Buenafuente

Objective: To evaluate the quality of diagnosis and the epidemiological profile of patients with pleural tuberculosis in the state of Roraima, Brazil, in order to provide technical support for the development and implementation of public policies to combat the disease. Methods: This was a cross-sectional study designed to determine the prevalence of pleural forms of tuberculosis in Roraima between 2005 and 2013 and to evaluate the diagnostic criteria used, as well as their determinants. This study was based on secondary data from the Brazilian Case Registry Database, including all reported cases of pleural tuberculosis in the state during the study period. Diagnoses based on bacteriological or histopathological confirmation were defined as high-quality diagnoses. Results: Among the 1,395 cases of tuberculosis reported during the study period, 116 (8.3%) were cases of pleural tuberculosis, accounting for 38.9% of all cases of extrapulmonary tuberculosis in the sample. The incidence rate of pleural tuberculosis did not follow the downward trend observed for the pulmonary form of the disease during the same period. The prevalence of cases with a high-quality diagnosis was 28.5% (95% CI: 20.4-37.6%). In a univariate analysis, none of the demographic or clinical characteristics collected from the database were found to have a significant impact on the outcome (as explanatory variables). Conclusions: The quality of the diagnoses in our study sample was considered unsatisfactory. Limited access to specific diagnostic methods might have contributed to these results.


2020 ◽  
Vol 7 (9) ◽  
pp. 807-814
Author(s):  
Yutaka Kurihara

Recently, FinTech (financial technology) and related services have improved greatly. Along with this trend, AI (artificial intelligence) has received a lot of attention as well. Financial institutions have been introducing FinTech and AI for improving efficiency and the quality of services. The aim of this study is to investigate the deterministic elements of promoting financial services. Focusing on two elements, 1) human skills and 2) social circumstances, empirical analyses are conducted to examine the deterministic elements. The empirical results show that finance skill and digital technological skill are both deterministic elements of financial services. Additionally, population growth, finance and banking regulation, and development and application of technology are also deterministic elements. However, whether the population over 65 years is a deterministic elements or not is not clear. To promote the quality of financial services, not only are human skills important, but social circumstances are also important. To make the circumstances clear is inevitable to promote financial services and to improve efficiency. Making these elements a reality, people will be able to enjoy high quality financial services.


Sign in / Sign up

Export Citation Format

Share Document