Explaining the black-box smoothly—a counterfactual approach

S Singla, M Eslami, B Pollack, S Wallace… - Medical image …, 2023 - Elsevier
Abstract We propose a BlackBox Counterfactual Explainer, designed to explain image
classification models for medical applications. Classical approaches (eg,, saliency maps) …

Chest X-ray image analysis with combining 2D and 1D convolutional neural network based classifier for rapid cardiomegaly screening

JX Wu, CC Pai, CD Kan, PY Chen, WL Chen… - IEEE …, 2022 - ieeexplore.ieee.org
Cardiomegaly is an asymptomatic disease. Symptoms, such as palpitations, chest tightness,
and shortness of breath, may be the early indications of cardiac hypertrophy, which can be …

Posteroanterior chest X-ray image classification with a multilayer 1D convolutional neural network-based classifier for cardiomegaly level screening

CH Lin, FZ Zhang, JX Wu, NS Pai, PY Chen, CC Pai… - Electronics, 2022 - mdpi.com
Palpitations, chest tightness, and shortness of breath are early indications of cardiomegaly,
which is an asymptomatic disease. Their causes and treatment strategies are different due to …

Deep learning‐based high‐dimensional multiple regression estimator for chest x‐ray image classification in rapid cardiomegaly screening

PY Chen, CH Lin, HY Peng, FZ Zhang… - Translational …, 2023 - Wiley Online Library
Chest x‐ray (CXR) examination is a common first‐line, non‐invasive, and rapid screening
method in clinical examinations. The posteroanterior (PA) and anteroposterior (AP) view …

External validation of deep learning algorithms for cardiothoracic ratio measurement

W Chaisangmongkon, I Chamveha, T Promwiset… - IEEE …, 2021 - ieeexplore.ieee.org
Recent advances in machine learning have made it possible to create automated systems
for medical image diagnosis. Cardiothoracic ratio (CTR) measurement, a common …

Deep Learning for Medical Imaging From Diagnosis Prediction to its Counterfactual Explanation

S Singla - arXiv preprint arXiv:2209.02929, 2022 - arxiv.org
Deep neural networks (DNN) have achieved unprecedented performance in computer-
vision tasks almost ubiquitously in business, technology, and science. While substantial …

The clinical associations with cardiomegaly in patients undergoing evaluation for pulmonary hypertension

B Daines, S Rao, O Hosseini, S Prieto… - Journal of Community …, 2021 - Taylor & Francis
Background Chest radiographs can identify important abnormalities in patients undergoing
diagnostic evaluation for cardiovascular diseases. Cardiomegaly often reflects cardiac …

[PDF][PDF] Assessment of the cardiothoracic ratio and its association with gender and age: a Nigerian study

BS Ominde, PO Enakpoya, J Ikubor… - Gal. Int. J. Heal. Sci …, 2023 - academia.edu
Cardiothoracic ratio (CTR) evaluation is a useful screening method used to detect
cardiomegaly. It varies in different populations due to genetic, geographical and …

Deep Learning for Medical Imaging

S Singla - 2022 - search.proquest.com
Deep neural networks (DNN) have achieved unprecedented performance in computer-
vision tasks almost ubiquitously in business, technology, and science. While substantial …

Validade do índice cardiotorácico em radiografias de tórax como método diagnóstico de cardiomegalias

LFC Maronezi - 2020 - rd.uffs.edu.br
RESUMO O presente Trabalho de Conclusão de Curso da graduação em Medicina da
Universidade Federal da Fronteira Sul (UFFS), campus Passo Fundo/RS, foi elaborado de …