AI in health and medicine

P Rajpurkar, E Chen, O Banerjee, EJ Topol - Nature medicine, 2022 - nature.com
Artificial intelligence (AI) is poised to broadly reshape medicine, potentially improving the
experiences of both clinicians and patients. We discuss key findings from a 2-year weekly …

Universeg: Universal medical image segmentation

VI Butoi, JJG Ortiz, T Ma, MR Sabuncu… - Proceedings of the …, 2023 - openaccess.thecvf.com
While deep learning models have become the predominant method for medical image
segmentation, they are typically not capable of generalizing to unseen segmentation tasks …

Checklist for evaluation of image-based artificial intelligence reports in dermatology: CLEAR derm consensus guidelines from the international skin imaging …

R Daneshjou, C Barata, B Betz-Stablein… - JAMA …, 2022 - jamanetwork.com
Importance The use of artificial intelligence (AI) is accelerating in all aspects of medicine and
has the potential to transform clinical care and dermatology workflows. However, to develop …

Guidelines and evaluation of clinical explainable AI in medical image analysis

W Jin, X Li, M Fatehi, G Hamarneh - Medical image analysis, 2023 - Elsevier
Explainable artificial intelligence (XAI) is essential for enabling clinical users to get informed
decision support from AI and comply with evidence-based medical practice. Applying XAI in …

Scribbleprompt: Fast and flexible interactive segmentation for any medical image

HE Wong, M Rakic, J Guttag, AV Dalca - arXiv preprint arXiv:2312.07381, 2023 - arxiv.org
Semantic medical image segmentation is a crucial part of both scientific research and
clinical care. With enough labelled data, deep learning models can be trained to accurately …

Visual explanations for the detection of diabetic retinopathy from retinal fundus images

V Boreiko, I Ilanchezian, MS Ayhan, S Müller… - … conference on medical …, 2022 - Springer
In medical image classification tasks like the detection of diabetic retinopathy from retinal
fundus images, it is highly desirable to get visual explanations for the decisions of black-box …

A deep learning approach for detection of shallow anterior chamber depth based on the hidden features of fundus photographs

TK Yoo, IH Ryu, JK Kim, IS Lee, HK Kim - Computer methods and programs …, 2022 - Elsevier
Abstract Background and Objectives Patients with angle-closure glaucoma (ACG) are
asymptomatic until they experience a painful attack. Shallow anterior chamber depth (ACD) …

Tyche: Stochastic In-Context Learning for Medical Image Segmentation

M Rakic, HE Wong, JJG Ortiz… - Proceedings of the …, 2024 - openaccess.thecvf.com
Existing learning-based solutions to medical image segmentation have two important
shortcomings. First for most new segmentation tasks a new model has to be trained or fine …

Shared interest... sometimes: Understanding the alignment between human perception, vision architectures, and saliency map techniques

K Morrison, A Mehra, A Perer - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Empirical studies have shown that attention-based architectures outperform traditional
convolutional neural networks (CNN) in terms of accuracy and robustness. As a result …

Feature Interpretation Using Generative Adversarial Networks (FIGAN): A framework for visualizing a CNN's learned features

KA Hasenstab, J Huynh, S Masoudi, GM Cunha… - IEEE …, 2023 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) are increasingly being explored and used for a
variety of classification tasks in medical imaging, but current methods for post hoc …