scholarly journals Emerging role of deep learning‐based artificial intelligence in tumor pathology

2020 ◽  
Vol 40 (4) ◽  
pp. 154-166 ◽  
Author(s):  
Yahui Jiang ◽  
Meng Yang ◽  
Shuhao Wang ◽  
Xiangchun Li ◽  
Yan Sun
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Tumor Pathology

P-064 Application of an artificial intelligence model for morphologic prediction of fertilization-competent human spermatozoa

2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
T Y Leung ◽  
C L Lee ◽  
P C N Chiu
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Sperm Morphology ◽  
Binding Assay ◽  
Morphological Characteristics ◽  
Selection Method ◽  
Human Spermatozoa ◽  
Sperm Selection ◽  
Binding Ability

Abstract Study question What is the role of artificial intelligence in selecting fertilization-competent human spermatozoa according to their morphological characteristics?  Summary answer The established AI model in this study can be potentially used to select semen samples with superior fertilization potential in clinical settings. What is known already Defective spermatozoa-zona pellucida (ZP) interaction causes subfertility and is a major cause of low IVF fertilization rates. While ICSI benefits patients with defective spermatozoa-ZP binding, a standard method to identify such patients prior to conventional IVF is lacking. The application of artificial intelligence to sperm morphology analysis has become a topic of growing interest owing to the fact that the conventional assessment is highly subjective and time-consuming. Deep-learning, a core element of artificial intelligence (AI), incorporates the convolutional neural networks (CNN) to process all the data composing a digital image through successive layers to identify the underlying pattern. Study design, size, duration The fertilization-competent spermatozoa were isolated according to their binding ability to the ZP. The ZP-bound and -unbound spermatozoa were collected for functional assays and to establish an AI model for morphologic prediction of sperm fertilization potential. Human spermatozoa (n = 289) were isolated from normozoospermic samples. Human oocytes (n = 562) were collected from an assisted reproduction program in Hong Kong. Sample collection has been ongoing and will continue until the end of this study in November 2021. Participants/materials, setting, methods Sperm-ZP binding assay was employed to collect ZP-bound and -unbound spermatozoa. The fertilization potential and genetic quality of the collected spermatozoa were evaluated by our established protocols. Diff-Quik- stained images of ZP-bound and -unbound spermatozoa were collected respectively for the establishment of an AI model. A novel algorithm for sperm image transformation and segmentation was developed to pre-process the images. CNN architecture was then applied on these pre-processed images for feature extraction and model training. Main results and the role of chance Our result showed that the sperm-ZP binding assay had no detrimental effect on sperm viability when compared with the raw samples and unbound-sperm subpopulations. ZP-bound spermatozoa were found with statistically higher acrosome reaction rates, improved DNA integrity, better morphology, lower protamine deficiency and higher methylation level when compared with the unbound spermatozoa. A deep-learning model was trained and validated by analyzing a total of 1,334 and 885 of ZP-bound/unbound spermatozoa to evaluate the predictive power of sperm morphology for ZP binding ability. Our newly trained AI-based model showed initial success in classifying the ZP-bound/ unbound spermatozoa according to their morphological characteristics with high accuracy of 85% and low computational complexity. Limitations, reasons for caution This sperm selection method requires micromanipulation and relatively long processing time to recover ZP-bound spermatozoa. In addition to limited availability, the use of human materials may result in interassay variations affecting the reproducibility of this method among laboratories. Wider implications of the findings In light of current findings, AI-based sperm selection method may provide high predictive values of sperm fertilization potential for clinical purposes. This method is particularly applicable to patients who had poor fertilization outcomes after conventional IVF treatments or those with high degree of defective sperm-ZP binding ability.  Trial registration number not applicable

A Study on Role of A.I. and Robotics in Health Care Sector: Its Impact and Contribution

2021 ◽  
Vol 07 (3&4) ◽  
pp. 7-14
Author(s):  
Devnath Jayaswal ◽  
Keyword(s):  
Artificial Intelligence ◽  
Health Care ◽  
Deep Learning ◽  
Health Care Sector ◽  
Healthcare Sector ◽  
Current Scenario ◽  
Health Complications ◽  
And Robotics ◽  
Major Domain

Health Care is one of the major domain sectors of our country. As this domain has many different aspect of implementation, as per the current scenario of Diseases and health complications. This paper will discuss about how, the Artificial Intelligence (A.I.) and robotics can be beneficial and plays a major role on, health care domain with respect to the Efficiently Diagnose, Developing New Medicines, Earlier Detection of Diseases, Advance Treatment Care, A.I-Deep learning For the Critical Decision’s. As this Information will help to give more clarity on what, A.I. & Robotics contributes for the major Diseases Treatment by the advancement of Technology. This can be beneficial for not only Doctors, Patients, or Firm but can also be helpful for citizen people as well. The objective of this paper is to study the role of AI and Robotics in Healthcare Sector and its impact.

scholarly journals Bioethics in the 21st century: challenges and perspectives

2021 ◽  
Author(s):  
EG Grebenshchikova ◽  
AG Chuchalin
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Genome Editing ◽  
21St Century ◽  
Social Order ◽  
Complex Problem ◽  
Innovative Development ◽  
Ethical Challenges ◽  
Family Connections

In this article, the authors review the role of bioethics in the processes of risk communication and socio-humanistic support for innovative development of technoscience, and analyze its commitment to the concepts of precaution and prevention. More focus is put on certain ethical challenges of the 21st century associated with the development of artificial intelligence, deep learning in medicine, genome editing and ‘new parenthood’ practices. They have exploited the potential of bioethics in ethical and axiological reflection on the prospects of healthcare far-reaching reforms and in sociohumanistic assessment of transformed ideas about the human nature, family connections and established social order. It is shown that the experience of complex problem discussion and solving alongside with advisory mechanisms and bioethical procedures respond to pressing challenges of biotechnoscience and will be in demand in future.

P–064 Application of an artificial intelligence model for morphologic prediction of fertilization-competent human spermatozoa

2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
T Y Leung ◽  
C L Lee ◽  
P C N Chiu
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Sperm Morphology ◽  
Binding Assay ◽  
Morphological Characteristics ◽  
Selection Method ◽  
Human Spermatozoa ◽  
Sperm Selection ◽  
Binding Ability

Abstract Study question What is the role of artificial intelligence in selecting fertilization-competent human spermatozoa according to their morphological characteristics? Summary answer: The established AI model in this study can be potentially used to select semen samples with superior fertilization potential in clinical settings. What is known already Defective spermatozoa-zona pellucida (ZP) interaction causes subfertility and is a major cause of low IVF fertilization rates. While ICSI benefits patients with defective spermatozoa-ZP binding, a standard method to identify such patients prior to conventional IVF is lacking. The application of artificial intelligence to sperm morphology analysis has become a topic of growing interest owing to the fact that the conventional assessment is highly subjective and time-consuming. Deep-learning, a core element of artificial intelligence (AI), incorporates the convolutional neural networks (CNN) to process all the data composing a digital image through successive layers to identify the underlying pattern. Study design, size, duration The fertilization-competent spermatozoa were isolated according to their binding ability to the ZP. The ZP-bound and -unbound spermatozoa were collected for functional assays and to establish an AI model for morphologic prediction of sperm fertilization potential. Human spermatozoa (n = 289) were isolated from normozoospermic samples. Human oocytes (n = 562) were collected from an assisted reproduction program in Hong Kong. Sample collection has been ongoing and will continue until the end of this study in November 2021. Participants/materials, setting, methods Sperm-ZP binding assay was employed to collect ZP-bound and -unbound spermatozoa. The fertilization potential and genetic quality of the collected spermatozoa were evaluated by our established protocols. Diff-Quik- stained images of ZP-bound and -unbound spermatozoa were collected respectively for the establishment of an AI model. A novel algorithm for sperm image transformation and segmentation was developed to pre-process the images. CNN architecture was then applied on these pre-processed images for feature extraction and model training. Main results and the role of chance Our result showed that the sperm-ZP binding assay had no detrimental effect on sperm viability when compared with the raw samples and unbound-sperm subpopulations. ZP-bound spermatozoa were found with statistically higher acrosome reaction rates, improved DNA integrity, better morphology, lower protamine deficiency and higher methylation level when compared with the unbound spermatozoa. A deep-learning model was trained and validated by analyzing a total of 1,334 and 885 of ZP-bound/unbound spermatozoa to evaluate the predictive power of sperm morphology for ZP binding ability. Our newly trained AI-based model showed initial success in classifying the ZP-bound/ unbound spermatozoa according to their morphological characteristics with high accuracy of 85% and low computational complexity. Limitations, reasons for caution This sperm selection method requires micromanipulation and relatively long processing time to recover ZP-bound spermatozoa. In addition to limited availability, the use of human materials may result in interassay variations affecting the reproducibility of this method among laboratories. Wider implications of the findings: In light of current findings, AI-based sperm selection method may provide high predictive values of sperm fertilization potential for clinical purposes. This method is particularly applicable to patients who had poor fertilization outcomes after conventional IVF treatments or those with high degree of defective sperm-ZP binding ability. Trial registration number Not applicable

Artificial Intelligence and Deep Learning in Diagnostic Radiology—Is This The Next Phase of Scientific and Technological Development?

2021 ◽  
Author(s):  
B Michael Moores
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Technological Development ◽  
World Market ◽  
Diagnostic Radiology ◽  
Imaging Data ◽  
Performance Requirements ◽  
Patient Protection ◽  
Learning Techniques

Abstract This paper is concerned with the role of science and technology in helping to create change in society. Diagnostic radiology is an example of an activity that has undergone significant change due to such developments, which over the past 40 years have led to a huge increase in the volume of medical imaging data generated. However, these developments have by and large left the human elements of the radiological process (referrer, radiographer and radiologist) intact. Diagnostic radiology has now reached a stage whereby the volume of information generated cannot be fully utilised solely by employing human observers to form clinical opinions, a process that has not changed in over 100 years. In order to address this problem, the potential application of Artificial Intelligence (AI) in the form of Deep Learning (DL) techniques to diagnostic radiology indicates that the next technological development phase may already be underway. The paper outlines the historical development of AI techniques, including Machine Learning and DL Neural Networks and discusses how such developments may affect radiological practice over the coming decades. The ongoing growth in the world market for radiological services is potentially a significant driver for change. The application of AI and DL learning techniques will place quantification of diagnostic outcomes at the heart of performance evaluation and quality standards. The effect this might have on the optimisation process will be discussed and in particular the possible need for automation in order to meet more stringent and standardised performance requirements that might result from these developments. Changes in radiological practices would also impact upon patient protection including the associated scientific support requirements and these are discussed.

Sign in / Sign up

Export Citation Format

Share Document