On the Interpretability of Artificial Intelligence in Radiology:                     Challenges and Opportunities

Reyes, Mauricio; Meier, Raphael; Pereira, Sérgio; Silva, Carlos A.; Dahlweid, Fried-Michael; Tengg-Kobligk, Hendrik von; Summers, Ronald M.; Wiest, Roland

doi:10.1148/ryai.2020190043

Cited by 309 publications

(244 citation statements)

References 33 publications

Supporting

Mentioning

243

Contrasting

Unclassified

Order By: Relevance

“…Although that term is not completely accurate as the model parameters are available and can be inspected, the reality is that those parameters are hard to explain, and it is difficult to translate their meaning into general principles and rules that can be understood by humans. The ability to draw a line between the inference that the network derives from the data and understandable governing principles is an area of active research in the AI community that needs to mature 79 .…”

Section: Ai Limitations and Challengesmentioning

confidence: 99%

Artificial Intelligence in COPD: New Venues to Study a Complex Disease

Estépar¹

2021

BRN

View full text Add to dashboard Cite

Section: Ai Limitations and Challengesmentioning

confidence: 99%

Artificial Intelligence in COPD: New Venues to Study a Complex Disease

Estépar¹

2021

BRN

View full text Add to dashboard Cite

“…• The use of patient data to develop and commercialize these models [14]; • The (lack of) interpretability and transparency on how an algorithm arrived at its output [15]; • The potential sources of bias that may cloud a model's predictions and reinforce social inequality [16].…”

Section: Noteworthy Topic 1: Ethics In Ssiimentioning

confidence: 99%

Notable Papers and Trends from 2019 in Sensors, Signals, and Imaging Informatics

Hsu¹,

Baumgartner

Deserno

2020

Yearb Med Inform

View full text Add to dashboard Cite

Objective: To highlight noteworthy papers that are representative of 2019 developments in the fields of sensors, signals, and imaging informatics. Method: A broad literature search was conducted in January 2020 using PubMed. Separate predefined queries were created for sensors/signals and imaging informatics using a combination of Medical Subject Heading (MeSH) terms and keywords. Section editors reviewed the titles and abstracts of both sets of results. Papers were assessed on a three-point Likert scale by two co-editors, rated from 3 (do not include) to 1 (should be included). Papers with an average score of 2 or less were then read by all three section editors, and the group nominated top papers based on consensus. These candidate best papers were then rated by at least six external reviewers. Results: The query related to signals and sensors returned a set of 255 papers from 140 unique journals. The imaging informatics query returned a set of 3,262 papers from 870 unique journals. Based on titles and abstracts, the section co-editors jointly filtered the list down to 50 papers from which 15 candidate best papers were nominated after discussion. A composite rating after review determined four papers which were then approved by consensus of the International Medical Informatics Association (IMIA) Yearbook editorial board. These best papers represent different international groups and journals. Conclusions: The four best papers represent state-of-the-art approaches for processing, combining, and analyzing heterogeneous sensor and imaging data. These papers demonstrate the use of advanced machine learning techniques to improve comparisons between images acquired at different time points, fuse information from multiple sensors, and translate images from one modality to another.

show abstract

“…(ii) Explainable AI, where neural networks can, for example, produce the regions of the image that provide the most decisive information supporting the predicted image level label, are covered in more detail in recent reviews [16], [17]. Recently, these approaches are accompanied by domain fusion, for example augmenting MRI of Alzheimer [18] patients with meta-data to learn the MRI signature of Alzheimer disease, or fusing diagnostic reports with image data [19] to offer interpretable improved diagnosis.…”

Section: Challenges In Current Approachesmentioning

confidence: 99%