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

Author(s):  
B Michael Moores

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.

Author(s):  
Krishna Kumar Joshi ◽  
Neelam Joshi ◽  
Ravi Ray Chaudhari

Nowadays, Artificial intelligence is an important part in everyone's life. It can be derived in two categories named as Machine learning and deep learning. Machine learning is the emerging field of the current era. With the help of the machine learning, we can develop the computers in such a way so that they can learn themselves. There are various types of leaning algorithms used for machine learning. With the help of these algorithms, machines can learn various things and they can behave almost like the human beings. Nowadays, the role of the machine is not limited in some defined fields only; it is playing an important role in almost every field such as education, entertainment, medical diagnosis etc. In this research paper, the basics about machine learning is discussed we have discussed about various learning techniques such as supervised learning, unsupervised learning and reinforcement learning in detail. A small portion is also used to cover some basics about the Convolutional Neural Networks (CNN). Some information about the various languages and APIs, designed and mostly used for Machine Learning and its applications are also provided in this paper.


2021 ◽  
Author(s):  
Ramy Abdallah ◽  
Clare E. Bond ◽  
Robert W.H. Butler

<p>Machine learning is being presented as a new solution for a wide range of geoscience problems. Primarily machine learning has been used for 3D seismic data processing, seismic facies analysis and well log data correlation. The rapid development in technology with open-source artificial intelligence libraries and the accessibility of affordable computer graphics processing units (GPU) makes the application of machine learning in geosciences increasingly tractable. However, the application of artificial intelligence in structural interpretation workflows of subsurface datasets is still ambiguous. This study aims to use machine learning techniques to classify images of folds and fold-thrust structures. Here we show that convolutional neural networks (CNNs) as supervised deep learning techniques provide excellent algorithms to discriminate between geological image datasets. Four different datasets of images have been used to train and test the machine learning models. These four datasets are a seismic character dataset with five classes (faults, folds, salt, flat layers and basement), folds types with three classes (buckle, chevron and conjugate), fault types with three classes (normal, reverse and thrust) and fold-thrust geometries with three classes (fault bend fold, fault propagation fold and detachment fold). These image datasets are used to investigate three machine learning models. One Feedforward linear neural network model and two convolutional neural networks models (Convolution 2d layer transforms sequential model and Residual block model (ResNet with 9, 34, and 50 layers)). Validation and testing datasets forms a critical part of testing the model’s performance accuracy. The ResNet model records the highest performance accuracy score, of the machine learning models tested. Our CNN image classification model analysis provides a framework for applying machine learning to increase structural interpretation efficiency, and shows that CNN classification models can be applied effectively to geoscience problems. The study provides a starting point to apply unsupervised machine learning approaches to sub-surface structural interpretation workflows.</p>


2020 ◽  
Vol 40 (4) ◽  
pp. 154-166 ◽  
Author(s):  
Yahui Jiang ◽  
Meng Yang ◽  
Shuhao Wang ◽  
Xiangchun Li ◽  
Yan Sun

Diagnostics ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 2032
Author(s):  
Ahmad Chaddad ◽  
Jiali Li ◽  
Qizong Lu ◽  
Yujie Li ◽  
Idowu Paul Okuwobi ◽  
...  

Radiomics with deep learning models have become popular in computer-aided diagnosis and have outperformed human experts on many clinical tasks. Specifically, radiomic models based on artificial intelligence (AI) are using medical data (i.e., images, molecular data, clinical variables, etc.) for predicting clinical tasks such as autism spectrum disorder (ASD). In this review, we summarized and discussed the radiomic techniques used for ASD analysis. Currently, the limited radiomic work of ASD is related to the variation of morphological features of brain thickness that is different from texture analysis. These techniques are based on imaging shape features that can be used with predictive models for predicting ASD. This review explores the progress of ASD-based radiomics with a brief description of ASD and the current non-invasive technique used to classify between ASD and healthy control (HC) subjects. With AI, new radiomic models using the deep learning techniques will be also described. To consider the texture analysis with deep CNNs, more investigations are suggested to be integrated with additional validation steps on various MRI sites.


2020 ◽  
Vol 3 (2) ◽  
pp. 77
Author(s):  
Mokeddem Allal

This article describes the contribution of artificial intelligence (AI) to the literature collection process, which has become more efficient and more homogeneous. In this context, the researcher will receive his literature not only according to his field. Moreover, the literature is strongly linked to scientific and academic ambitions. AI through its deep learning techniques offers the possibility of speeding up the process of collecting augmented literature via an approach based on the annotation of scientific names and none-scientific names related to the field. AI provides original or reproduced research avenues with reliable and precise results. In this article, we have highlighted how to develop conceptual framework based on scientific and none-scientific names related to the area of expertise, all ensuring the reproducibility, reliability and accuracy of the study.


2021 ◽  
Vol 1 ◽  
Author(s):  
Shanshan Wang ◽  
Guohua Cao ◽  
Yan Wang ◽  
Shu Liao ◽  
Qian Wang ◽  
...  

Artificial intelligence (AI) as an emerging technology is gaining momentum in medical imaging. Recently, deep learning-based AI techniques have been actively investigated in medical imaging, and its potential applications range from data acquisition and image reconstruction to image analysis and understanding. In this review, we focus on the use of deep learning in image reconstruction for advanced medical imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET). Particularly, recent deep learning-based methods for image reconstruction will be emphasized, in accordance with their methodology designs and performances in handling volumetric imaging data. It is expected that this review can help relevant researchers understand how to adapt AI for medical imaging and which advantages can be achieved with the assistance of AI.


2021 ◽  
pp. 20210406
Author(s):  
Jarrel Seah ◽  
Zoe Brady ◽  
Kyle Ewert ◽  
Meng Law

Artificial Intelligence (AI), including deep learning, is currently revolutionising the field of medical imaging, with far reaching implications for almost every facet of diagnostic imaging, including patient radiation safety. This paper introduces basic concepts in deep learning and provides an overview of its recent history and its application in tomographic reconstruction as well as other applications in medical imaging to reduce patient radiation dose, as well as a brief description of previous tomographic reconstruction techniques. This review also describes the commonly used deep learning techniques as applied to tomographic reconstruction and draws parallels to current reconstruction techniques. Finally, this paper reviews some of the estimated dose reductions in computed tomography (CT) and positron emission tomography (PET) in the recent literature enabled by deep learning, as well as some of the potential problems that may be encountered such as the obscuration of pathology, and highlights the need for additional clinical reader studies from the imaging community.


2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
T Y Leung ◽  
C L Lee ◽  
P C N Chiu

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


Sign in / Sign up

Export Citation Format

Share Document