AI pitfalls and what not to do: mitigating bias in AI
Various forms of artificial intelligence (AI) applications are being deployed and used in many
healthcare systems. As the use of these applications increases, we are learning the failures …
healthcare systems. As the use of these applications increases, we are learning the failures …
Empirical data drift detection experiments on real-world medical imaging data
While it is common to monitor deployed clinical artificial intelligence (AI) models for
performance degradation, it is less common for the input data to be monitored for data drift …
performance degradation, it is less common for the input data to be monitored for data drift …
The AI generalization gap: one size does not fit all
M Huisman, G Hannink - Radiology: Artificial Intelligence, 2023 - pubs.rsna.org
Merel Huisman, MD, PhD, is a radiologist at Radboud University Medical Center in
Nijmegen, the Netherlands. Her clinical subspecialty interest is cardiothoracic and …
Nijmegen, the Netherlands. Her clinical subspecialty interest is cardiothoracic and …
Unreading Race: Purging Protected Features from Chest X-ray Embeddings
Purpose: To analyze and remove protected feature effects in chest radiograph embeddings
of deep learning models. Materials and Methods: An orthogonalization is utilized to remove …
of deep learning models. Materials and Methods: An orthogonalization is utilized to remove …
[HTML][HTML] Evaluation of AI-based Gleason grading algorithms" in the wild"
The biopsy Gleason score is an important prognostic marker for prostate cancer patients. It
is, however, subject to substantial variability among pathologists. Artificial intelligence (AI) …
is, however, subject to substantial variability among pathologists. Artificial intelligence (AI) …
Reconsidering Conclusions of Bias Assessment in Medical Imaging Foundation Models
AS Chaudhari, C Bluethgen, D Ouyang - Radiology: Artificial …, 2023 - pubs.rsna.org
Editor: In the November 2023 issue of Radiology: Artificial Intelligence, Dr Glocker and
colleagues report that a deep learning model for chest radiograph interpretation depicted …
colleagues report that a deep learning model for chest radiograph interpretation depicted …
Benchmarking bias: Expanding clinical AI model card to incorporate bias reporting of social and non-social factors
Clinical AI model reporting cards should be expanded to incorporate a broad bias reporting
of both social and non-social factors. Non-social factors consider the role of other factors …
of both social and non-social factors. Non-social factors consider the role of other factors …
When AUC-ROC and accuracy are not accurate: what everyone needs to know about evaluating artificial intelligence in radiology
M Huisman - European Radiology, 2024 - Springer
The current diagnostic AI tools in medical imaging, once developed, essentially become a
static diagnostic test, similar to traditional diagnostics. As radiologists, we understand the …
static diagnostic test, similar to traditional diagnostics. As radiologists, we understand the …
Doctor's Orders—Why Radiologists Should Consider Adjusting Commercial Machine Learning Applications in Chest Radiography to Fit Their Specific Needs
FP Schweikhard, A Kosanke, S Lange, ML Kromrey… - Healthcare, 2024 - mdpi.com
This retrospective study evaluated a commercial deep learning (DL) software for chest
radiographs and explored its performance in different scenarios. A total of 477 patients (284 …
radiographs and explored its performance in different scenarios. A total of 477 patients (284 …
Multivariate Analysis on Performance Gaps of Artificial Intelligence Models in Screening Mammography
Although deep learning models for abnormality classification can perform well in screening
mammography, the demographic, imaging, and clinical characteristics associated with …
mammography, the demographic, imaging, and clinical characteristics associated with …