scholarly journals The ethical adoption of artificial intelligence in radiology

BJR|Open ◽  
2020 ◽  
Vol 2 (1) ◽  
pp. 20190020 ◽  
Author(s):  
Keshav Shree Mudgal ◽  
Neelanjan Das
Keyword(s):  
Artificial Intelligence ◽  
Health Authority ◽  
Training Data ◽  
Current Understanding ◽  
Prediction System ◽  
Knowledge Gaps ◽  
Cause Analysis ◽  
Distant Future ◽  
Root Cause ◽  
Data Usage

Artificial intelligence (AI) is rapidly transforming healthcare—with radiology at the pioneering forefront. To be trustfully adopted, AI needs to be lawful, ethical and robust. This article covers the different aspects of a safe and sustainable deployment of AI in radiology during: training, integration and regulation. For training, data must be appropriately valued, and deals with AI companies must be centralized. Companies must clearly define anonymization and consent, and patients must be well-informed about their data usage. Data fed into algorithms must be made AI-ready by refining, purification, digitization and centralization. Finally, data must represent various demographics. AI needs to be safely integrated with radiologists-in-the-loop: guiding forming concepts of AI solutions and supervising training and feedback. To be well-regulated, AI systems must be approved by a health authority and agreements must be made upon liability for errors, roles of supervised and unsupervised AI and fair workforce distribution (between AI and radiologists), with a renewal of policy at regular intervals. Any errors made must have a root-cause analysis, with outcomes fedback to companies to close the loop—thus enabling a dynamic best prediction system. In the distant future, AI may act autonomously with little human supervision. Ethical training and integration can ensure a "transparent" technology that will allow insight: helping us reflect on our current understanding of imaging interpretation and fill knowledge gaps, eventually moulding radiological practice. This article proposes recommendations for ethical practise that can guide a nationalized framework to build a sustainable and transparent system.

Heterogeneous Weighted Voting-Based Ensemble (HWVE) for Root-Cause Analysis

2020 ◽  
Vol 13 (4) ◽  
pp. 63-74
Author(s):  
Blessy Selvam ◽  
Ravimaran S. ◽  
Sheba Selvam
Keyword(s):  
Root Cause Analysis ◽  
Training Data ◽  
Huge Number ◽  
Weighted Voting ◽  
Cause Analysis ◽  
Aspect Extraction ◽  
Root Cause ◽  
Proposed Model ◽  
Identification Phase ◽  
F Measure

Root-cause analysis has been one of the major requirements of the current information-rich world due to the huge number of opinions available online. This paper presents a heterogeneous weighted voting-based ensemble (HWVE) model for root-cause analysis. The proposed model is composed of an aspect extraction and filtering module, a model-based sentiment identification module, and a ranking module. Domain-based aspect ontologies are created using the available training data and is used for categorization. The input data is passed to the HWVE model for opinion identification and is in-parallel passed to the significance identification phase for aspect identification. The identified aspects are combined with their corresponding sentiments and ranked based on their ontological occurrence levels to provide the final categorized root-causes. Experiments were performed with the five-product dataset, and comparisons were performed with recent models. Results indicate that the proposed model exhibits improved performances of 5%-13% in terms of F-measure when compared to other models.

Root Cause analysis of SG tube ODSCC indications within the tube sheets of NPP biblis unit A

2011 ◽  
pp. 78-86
Author(s):  
R. Kilian ◽  
J. Beck ◽  
H. Lang ◽  
V. Schneider ◽  
T. Schönherr ◽  
...  
Keyword(s):  
Root Cause Analysis ◽  
Cause Analysis ◽  
Root Cause

Rule Construction and its Execution for Root Cause Analysis

2012 ◽  
Vol 132 (10) ◽  
pp. 1689-1697
Author(s):  
Yutaka Kudo ◽  
Tomohiro Morimura ◽  
Kiminori Sugauchi ◽  
Tetsuya Masuishi ◽  
Norihisa Komoda
Keyword(s):  
Root Cause Analysis ◽  
Cause Analysis ◽  
Root Cause

Root Cause Analysis Techniques Using Picosecond Time Resolved LADA

2014 ◽  
Author(s):  
Dan Bodoh ◽  
Kent Erington ◽  
Kris Dickson ◽  
George Lange ◽  
Carey Wu ◽  
...  
Keyword(s):  
Integrated Circuits ◽  
Picosecond Laser ◽  
Root Cause Analysis ◽  
Fault Isolation ◽  
Time Resolved ◽  
Cause Analysis ◽  
Root Cause ◽  
Design And Manufacturing ◽  
Multiple Interactions ◽  
Established Technique

Abstract Laser-assisted device alteration (LADA) is an established technique used to identify critical speed paths in integrated circuits. LADA can reveal the physical location of a speed path, but not the timing of the speed path. This paper describes the root cause analysis benefits of 1064nm time resolved LADA (TR-LADA) with a picosecond laser. It shows several examples of how picosecond TR-LADA has complemented the existing fault isolation toolset and has allowed for quicker resolution of design and manufacturing issues. The paper explains how TR-LADA increases the LADA localization resolution by eliminating the well interaction, provides the timing of the event detected by LADA, indicates the propagation direction of the critical signals detected by LADA, allows the analyst to infer the logic values of the critical signals, and separates multiple interactions occurring at the same site for better understanding of the critical signals.

Analysis of Induced End-of-Life Failures in SRAM Through Nanoprobing

2018 ◽  
Author(s):  
Oberon Dixon-Luinenburg ◽  
Jordan Fine
Keyword(s):  
End Of Life ◽  
Soft Errors ◽  
Cause Analysis ◽  
New Approach ◽  
Performance Loss ◽  
Root Cause ◽  
Long Period ◽  
Atomic Force ◽  
Stress Resultant ◽  
Voltage Stress

Abstract In this paper, we demonstrate a novel nanoprobing approach to establish cause-and-effect relationships between voltage stress and end-of-life performance loss and failure in SRAM cells. A Hyperion II Atomic Force nanoProber was used to examine degradation for five 6T cells on an Intel 14 nm processor. Ten minutes of asymmetrically applied stress at VDD=2 V was used to simulate a ‘0’ bit state held for a long period, subjecting each pullup and pulldown to either VDS or VGS stress. Resultant degradation caused read and hold margins to be reduced by 20% and 5% respectively for the ‘1’ state and 5% and 2% respectively for the ‘0’ state. ION was also reduced, for pulldown and pullup respectively, by 4.5% and 5.4% following VGS stress and 2.6% and 33.8% following VDS stress. Negative read margin failures, soft errors, and read time failures all become more prevalent with these aging symptoms whereas write stability is improved. This new approach enables highly specific root cause analysis and failure prediction for end-of-life in functional on-product SRAM.

Sign in / Sign up

Export Citation Format

Share Document