Chest pathology detection using deep learning with non-medical training

By Yaniv Bar, Idit Diamant, Lior Wolf, Sivan Lieberman, Eli Konen, Hayit Greenspan. IEEE International Symposium on Biomedical Imaging, 2015

370 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/5cc51fb6ecadc853cb4017a43fb644ad1b852bc1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Deep Learning and Convolutional Neural Networks for Medical Image Computing (2017, methodology): “We propose a segmentation propagation algorithm that combines the cues from the initial or partial manual annotations, deep convolutional neural networks (CNN) based single pixel classification and formulate into a constrained dense fully connected conditional random field (CRF) framework [10].”
Convolutional neural networks based transfer learning for diabetic retinopathy fundus image classification (2017, methodology): “In paper [7], a pre-trained CNN model is used as feature generator for feature extraction.”
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, methodology): “, [34]–[36]); using the deep network trained based on ImageNet and fine-tuning to a medical imaging task was helpful in order to speed up training convergence and improve accuracy.”
Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification (2018, positive): “Therefore, transfer learning approaches, as proposed by Bar et al. 6 , were often considered to overcome such problems.”
Comparison of Deep Transfer Learning Strategies for Digital Pathology (2018, background): “Some of the first applications of deep transfer learning in biomedical imaging were reported in [2, 6, 39] for pulmonary nodule detection in chest x-rays and CT-scans using Decaf and OverFeat.”
Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis (2018, background): “ing transfer from non-medical images appeared, for example (Bar et al., 2015; Ciompi et al., 2015).”
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning (2016, methodology): “To complement "offthe-shelf" CNN features, [10] , [9] , [12] all add and integrate various other hand-crafted image features as hybrid inputs for the final CADe classification.”
Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique (2016, methodology): “[25], [26] pre-trained CNNs were used as a feature generator for chest pathology identification.”
SpineNet: Automatically Pinpointing Classification Evidence in Spinal MRIs (2016, background): “Related work: CNNs have been utilized in medical vision problems in two main ways: (1) using networks pre-trained on a larger normally non-medical dataset of natural images, as features, e.g. to detect pathology in chest X-rays [1], and (2) training a network from scratch, e.g. to detect sclerotic m”
Abnormality Detection and Localization in Chest X-Rays using Deep Convolutional Neural Networks (2017, background): “pathology, cardiomegaly, mediastinum and right pleural effusion have been attempted [14].”