Reflecting recent major advances in the field of artificial intelligence, Developing the Digital Lung, From First Lung CT to Clinical AI, by Dr. John Newell, is your go-to reference for all aspects of applied artificial intelligence in lung disease development, including application to clinical medicine. It provides a unique overview of the field, beginning with a review of the origins of artificial intelligence in the mid-1970s and progressing to its application to clinical medicine in the early 2020s. Organized based on the four stages of development, this practical, easy-to-use resource helps you effectively apply artificial intelligences to lung imaging.Traces the development of precise quantitative CT of diffuse lung disease through the use of applied AI, leading to faster effective diagnosis of patients with lung disease.
Reviews CT manufacturers, models and scanning protocol used to produce the 3D digital maps of the lungs.
Discusses how the data processed by AI algorithms can produce measures of emphysema, air trapping, and airway wall thickening in subjects with COPD and measures of pulmonary fibrosis and traction bronchiectasis in idiopathic pulmonary fibrosis (IPF).
Demonstrates the differences between reactive machine AI and limited memory AI methods.
Includes comprehensive case studies and current information on cloud computing.
An eBook version is included with purchase. The eBook allows you to access all of the text, figures and references, with the ability to search, customize your content, make notes and highlights, and have content read aloud.
Author(s): John D. Newell
Publisher: Elsevier
Year: 2023
Language: English
Pages: 155
City: Philadelphia
Developing the Digital Lung: From First Lung CT to Clinical AI
Copyright
Contents
Dedication
Preface
Confidence is ClinicalKey
Acknowledgments
Any screen. Any time. Anywhere.
1
Introduction to Lung CT AI
AI: An Intelligent Agent
AI Definitions and Levels
Diagnosis of COPD, ILD, Lung Cancer, and Other Smoking-Related Diseases
Information for Healthcare Providers and Administrators, Patients, and Researchers
Describing Lung CT AI in Three Stages
References
2
Three-Dimensional (3D) Digital Images of the Lung Using X-ray Computed Tomography
The Digital Lung
X-ray Computed Tomography
X-rays
Important Components of an X-ray Computed Tomographic (CT) Scanner
CT X-ray Tube
CT X-ray Beam Shape and Energy Spectrum
X-ray CT Detectors
CT Gantry
CT Table, Isocenter, Scan Pitch, and Scanning Modes
Scanning Modes
Collection of a Scanned Object’s Projection Data
Image Reconstruction
FBP Versus Iterative Reconstruction Methods.
Scan Field of View (SFOV), Display Field of View (DFOV), and Reconstruction Matrix Size
Hounsfield Units and the CT Voxel
Visually Display of Lung Images
Quantitative CT Metrics
CT Scanning Protocols
X-ray CT Radiation Dose
Brief History of X-ray CT
The First Head and Body CT Scanners – 1971 to 1975 (EMI, ACTA, Ohio Nuclear)
Rapid Evolution of CT Scanner Designs
Moderate-Resolution Whole Lung Acquisition in a Single Breath—Spiral CT Scanner
High-Resolution Lung CT in a Single Breath for All Patients: Multidetector Spiral CT Scanners
References
3
X-ray CT Scanning Protocols for Lung CT AI Applications
Early Work in the Development of QCT Scanning Protocols
Workshop: Quantitative Computed Tomography Scanning in Longitudinal Studies of Emphysema
Can X-ray CT Detect and Quantify Pulmonary Emphysema?
Single Versus Multiple Detector Row CT Scanners
Constant and Optimal X-ray Tube Peak Kilovoltage, mAs, and Radiation Dose
Scan Mode and Pitch
Detector Width and Recommended Axial Image Thickness and Spacing
Image Reconstruction
Optimal Lung Volume—Total Lung Capacity (TLC)
Administration of Intravenous Iodinated X-ray CT Contrast Media
X-ray CT Phantoms for Image Quality Assessments
CT Image Analysis
Image Data Transfer, Analysis, and Storage
Summary of the Recommended Quantitative Lung CT Scanning Protocol
Current Recommended Quantitative CT Scanning Protocol
Radiation Dose
MDCT Scanner Models, Scan Mode, Z-Axis Detector Size, Rotation Time, Pitch
DFOV, Isocenter, Scanning at TLC and RV
CT Image Reconstruction
Quality Control
Personnel Training and Certification
CT Scanner Calibration and Certification
CT Scan Acquisition
CT Image Data Transfer
CT Scanner Quality Control
CT Scanner Quality Control Measures, ACR CT Phantom
COPDGene CT Phantom
Current QIBA Lung Density CT Profile
Summary
References
4
Quantitative Assessment of Lung Nodule Size, Shape, and Malignant Potential Using Both Reactive and Limited-Memory Lung ...
CT Assessment of Lung Nodules—CT Versus Projection Radiography (PR)
CT Protocol to Assess Lung Nodules
CT Determination of Lung Nodule Size
CT Determination of Nodule Growth
CT Determination of Nodule Density
CT Determined Nodule Mass, Location, Morphology, Shape, Contour
CT Determined Nodule Texture—Limited-Memory AI
CT Assessment of Lung Tissue Adjacent to the Lung Nodule—Limited-Memory AI
References
5
Using Reactive Machine AI to Derive Quantitative Lung CT Metrics of COPD, ILD, and COVID-19 Pneumonia
Introduction
Normal Lung Structure
QCT Scanning Protocol and Lung Segmentation
Chronic Obstructive Pulmonary Disease (COPD) Induced Changes in Lung Structure
Quantitative CT Metrics of Lung Density in COPD
Mean Lung Density (MLD) for the Detection and Assessment of Emphysema
Low Attenuating Area (LAA) for the Detection and Assessment of Emphysema
15th Percentile Method for the Detection and Assessment of Emphysema
Clinical Value of Using Lung CT AI in Patients with Environmental Exposure to Cigarette Smoke
Clinical Benefit of LAA−950
Interstitial Lung Disease (ILD) Induced Changes in Lung Structure
Lung Density, Volumes, Specific Air and Tissue Volumes in IPF
Histogram Measures of ILD—MLD, Skewness, Kurtosis
Percent High Attenuating Areas (%HAA) in ILD
QCT of COVID-19 Acute Viral Pneumonia
Summary
References
6
Using Reactive Machine AI and Dynamic Changes in Lung Structure to Derive Functional Quantitative Lung CT Metrics of COP ...
Introduction
Expiratory QCT Assessment of Air Trapping Due to Small Airway Disease in the Lung
Whole Lung Assessment of Air Trapping Using LAA in Severe Asthma Patients
Whole Lung Assessment of Air Trapping Using LAA in COPD Patients
Whole Lung Assessment of Air Trapping in the COPDGene 2019 Classes of COPD
Whole Lung Assessment of Air Trapping Using MLD and CT Determined Lung Volumes
Whole Lung Assessment of Air Trapping in Bronchiolitis Obliterans
Assessment of Air Trapping at the Voxel Level Using Image Registration
Parametric Response Map
Disease Probability Map
Assessment of Biomechanics and Tissue Stiffness Using Image Registration
Direct Measurements of Large Airway Geometry Using Lung CT AI
Segmentation of the Airways of the Lungs
QCT Metrics of Airway Geometry
COPDGene Airway Geometry Features and Spirometric Measures of Airflow
Pi10 and COPDGene 2019 Classes of COPD
Summary
References
7
Using Limited Memory Lung CT AI to Derive Advanced Quantitative CT Lung Metrics of COPD, ILD, and COVID-19 Pneumonia
Introduction
Limited Memory Lung CT AI and the Assessment of Emphysema
Adaptive Multiple Feature Method (AMFM) AI Agent (Supervised, Bayesian Classifier)
Deep Learning Enables Automatic Classification of Emphysema Pattern at CT
Limited Memory Lung CT AI and the Assessment of Interstitial Lung Disease (ILD)
AMFM AI Method for Assessing Interstitial Lung Disease
CALIPER (Computer-Aided Lung Informatics for Pathology Evaluation and Rating)
DTA (Data-Driven Textural Analysis for Assessment of Fibrotic Lung Disease)
CNN for COVID-19 Pneumonia
Summary
References
8
Lung CT AI Enables Advanced Computer Modeling of Lung Physiome Structure and Function
Virtual Physiological Human and a Lung Physiome Model
Finite Element Model of Lung Structure and Function
Generating the 3D Finite Element Mesh of the Lung
Generating the Airway Tree Within the 3D Mesh of the Lung
Generating the Pulmonary Vascular Tree
Modeling the Extra-Acinar Pulmonary Vessels
Modeling the Intra-Acinar Pulmonary Vessels
Lung Physiome (LP) Model Applied to the Assessment of Acute Pulmonary Embolism
Results of Lung Physiome Model in Predicting Hypoxemic Risk in APE
Extending the Lung Physiome Model Approach to Using Generic Vascular Anatomy
Summary of Important Concepts of the Lung Physiome Model
References
9
Adoption of Lung CT AI Into Clinical Medicine
Introduction
Healthcare Imaging IT
Electronic Medical Record (EMR)
Picture Archiving and Communication System (PACS)
Radiology Information Software (RIS)
Medical Imaging Reporting and Voice Recognition Software (VR)
Clinical Lung CT AI Software
VIDA Insights–Clinical Lung CT AI Software
VIDA Insights Density/tMPR Reactive Machine AI Tool for Assessing Volumes, LAA, and HAA
VIDA Discovery Limited-Memory AI Texture Tool
Enhanced Visualization of Airways and Subpleural Lung Tissue
VIDA Lung Nodule Tool
VIDA Discovery Lung Ventilation Tool
Responsible AI
References
Index
