Convolutional neural networks in medical image understanding: a survey

DR Sarvamangala, RV Kulkarni - Evolutionary intelligence, 2022 - Springer
Imaging techniques are used to capture anomalies of the human body. The captured images
must be understood for diagnosis, prognosis and treatment planning of the anomalies …

Wilds: A benchmark of in-the-wild distribution shifts

PW Koh, S Sagawa, H Marklund… - International …, 2021 - proceedings.mlr.press
Distribution shifts—where the training distribution differs from the test distribution—can
substantially degrade the accuracy of machine learning (ML) systems deployed in the wild …

Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports

HY Zhou, X Chen, Y Zhang, R Luo, L Wang… - Nature Machine …, 2022 - nature.com
Pre-training lays the foundation for recent successes in radiograph analysis supported by
deep learning. It learns transferable image representations by conducting large-scale fully …

Learning loss for test-time augmentation

I Kim, Y Kim, S Kim - Advances in neural information …, 2020 - proceedings.neurips.cc
Data augmentation has been actively studied for robust neural networks. Most of the recent
data augmentation methods focus on augmenting datasets during the training phase. At the …

Code and data sharing practices in the radiology artificial intelligence literature: a meta-research study

K Venkatesh, SM Santomartino, J Sulam… - Radiology: Artificial …, 2022 - pubs.rsna.org
Purpose To evaluate code and data sharing practices in original artificial intelligence (AI)
scientific manuscripts published in the Radiological Society of North America (RSNA) …

Towards low-cost and efficient malaria detection

W Sultani, W Nawaz, S Javed… - 2022 IEEE/CVF …, 2022 - ieeexplore.ieee.org
Malaria, a fatal but curable disease claims hundreds of thousands of lives every year. Early
and correct diagnosis is vital to avoid health complexities, however, it depends upon the …

An accurate and explainable deep learning system improves interobserver agreement in the interpretation of chest radiograph

HH Pham, HQ Nguyen, HT Nguyen, LT Le… - IEEE Access, 2022 - ieeexplore.ieee.org
Interpretation of chest radiographs (CXR) is a difficult but essential task for detecting thoracic
abnormalities. Recent artificial intelligence (AI) algorithms have achieved radiologist-level …

Recalibration of deep learning models for abnormality detection in smartphone-captured chest radiograph

PC Kuo, CC Tsai, DM López, A Karargyris… - NPJ digital …, 2021 - nature.com
Image-based teleconsultation using smartphones has become increasingly popular. In
parallel, deep learning algorithms have been developed to detect radiological findings in …

VisualCheXbert: addressing the discrepancy between radiology report labels and image labels

S Jain, A Smit, SQH Truong, CDT Nguyen… - Proceedings of the …, 2021 - dl.acm.org
Automatic extraction of medical conditions from free-text radiology reports is critical for
supervising computer vision models to interpret medical images. In this work, we show that …

Backdoor attacks on the DNN interpretation system

S Fang, A Choromanska - Proceedings of the AAAI Conference on …, 2022 - ojs.aaai.org
Interpretability is crucial to understand the inner workings of deep neural networks (DNNs).
Many interpretation methods help to understand the decision-making of DNNs by generating …