Convolutional Neural Networks for Radiologic Images: A Radiologist’s Guide

Soffer, Shelly; Ben-Cohen, Avi; Shimon, Orit; Amitai, Michal Marianne; Greenspan, Hayit; Klang, Eyal

doi:10.1148/radiol.2018180547

Cited by 411 publications

(266 citation statements)

References 175 publications

Supporting

Mentioning

258

Contrasting

Unclassified

Order By: Relevance

“…The most widely known method of deep learning in medicine is that involving a convolutional neural network (CNN). A CNN is basically composed of three types of layers (35) : the first (convolutional layer) detects and extracts features; the second (pooling layer) selects and reduces the amount of features; and the third (fully connected layer) serves to integrate all of the features extracted by the previous layers, typically by using an MLP-like neural network to perform the final image classification, which is given by the prediction of the most likely class (Figure 7). Another important step in the machine learning process is validation and performance assessment.…”

Section: Image Classification Machine Learning and Deep Learningmentioning

confidence: 99%

Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine

et al. 2019

View full text Add to dashboard Cite

The discipline of radiology and diagnostic imaging has evolved greatly in recent years. We have observed an exponential increase in the number of exams performed, subspecialization of medical fields, and increases in accuracy of the various imaging methods, making it a challenge for the radiologist to “know everything about all exams and regions”. In addition, imaging exams are no longer only qualitative and diagnostic, providing now quantitative information on disease severity, as well as identifying biomarkers of prognosis and treatment response. In view of this, computer-aided diagnosis systems have been developed with the objective of complementing diagnostic imaging and helping the therapeutic decision-making process. With the advent of artificial intelligence, “big data”, and machine learning, we are moving toward the rapid expansion of the use of these tools in daily life of physicians, making each patient unique, as well as leading radiology toward the concept of multidisciplinary approach and precision medicine. In this article, we will present the main aspects of the computational tools currently available for analysis of images and the principles of such analysis, together with the main terms and concepts involved, as well as examining the impact that the development of artificial intelligence has had on radiology and diagnostic imaging.

show abstract

Section: Image Classification Machine Learning and Deep Learningmentioning

confidence: 99%

Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In recent years, a large number of studies have been performed using machine learning in radiology in many different applications including neuroimaging and imaging of the chest and abdomen, where the main interest has been towards oncology imaging and anatomy [12]. In two previous studies, CNNs have been used for the detection of ureteral stones [16,17].…”

Section: Discussionmentioning

confidence: 99%

“…Recent years have seen an enormous interest in artificial neural network (ANN)-based artificial intelligence (AI) in medical imaging [12,13]. Briefly, an ANN is built from a simple mathematical nerve cell model, a neuron, which computes one output value from multiple input values.…”

Section: Introductionmentioning

confidence: 99%

Differentiation of distal ureteral stones and pelvic phleboliths using a convolutional neural network

2020

View full text Add to dashboard Cite

The objectives were to develop and validate a Convolutional Neural Network (CNN) using local features for differentiating distal ureteral stones from pelvic phleboliths, compare the CNN method with a semi-quantitative method and with radiologists' assessments and to evaluate whether the assessment of a calcification and its local surroundings is sufficient for discriminating ureteral stones from pelvic phleboliths in non-contrast-enhanced CT (NECT). We retrospectively included 341 consecutive patients with acute renal colic and a ureteral stone on NECT showing either a distal ureteral stone, a phlebolith or both. A 2.5-dimensional CNN (2.5D-CNN) model was used, where perpendicular axial, coronal and sagittal images through each calcification were used as input data for the CNN. The CNN was trained on 384 calcifications, and evaluated on an unseen dataset of 50 stones and 50 phleboliths. The CNN was compared to the assessment by seven radiologists who reviewed a local 5 × 5 × 5 cm image stack surrounding each calcification, and to a semi-quantitative method using cutoff values based on the attenuation and volume of the calcifications. The CNN differentiated stones and phleboliths with a sensitivity, specificity and accuracy of 94%, 90% and 92% and an AUC of 0.95. This was similar to a majority vote accuracy of 93% and significantly higher (p = 0.03) than the mean radiologist accuracy of 86%. The semi-quantitative method accuracy was 49%. In conclusion, the CNN differentiated ureteral stones from phleboliths with higher accuracy than the mean of seven radiologists' assessments using local features. However, more than local features are needed to reach optimal discrimination. Keywords Computed tomography • Ureteral calculi • Pelvic phlebolith • Deep learning • Convolutional neural networks Abbreviations NECT Non-contrast-enhanced computed tomography CTU CT urography CNN Convolutional neural network 2.5D-CNN 2.5-Dimensional CNN including axial, coronal and sagittal images CAD Computer-aided diagnosis ANN Artificial neural network AI Artificial intelligence FC layer Fully connected layer PACS Picture archiving and communication system MPR Multiplanar reconstructions CI Confidence interval ROC Receiver operating characteristic AUC Area under the curve ROI Region of interest Key points A Convolutional Neural Network for classifying pelvic calcifications was developed and validated.

show abstract

“…Globally, Python is currently the most frequently used programming language for deep learning [62][63][64]. However, libraries such as Tensorflow or Caffe [66] provide alternatives supporting C++ and Matlab [67].…”

Section: Deep Learning Libraries and Architecturesmentioning

confidence: 99%

Deep learning workflow in radiology: a primer

et al. 2020

View full text Add to dashboard Cite

Interest for deep learning in radiology has increased tremendously in the past decade due to the high achievable performance for various computer vision tasks such as detection, segmentation, classification, monitoring, and prediction. This article provides step-by-step practical guidance for conducting a project that involves deep learning in radiology, from defining specifications, to deployment and scaling. Specifically, the objectives of this article are to provide an overview of clinical use cases of deep learning, describe the composition of multi-disciplinary team, and summarize current approaches to patient, data, model, and hardware selection. Key ideas will be illustrated by examples from a prototypical project on imaging of colorectal liver metastasis. This article illustrates the workflow for liver lesion detection, segmentation, classification, monitoring, and prediction of tumor recurrence and patient survival. Challenges are discussed, including ethical considerations, cohorting, data collection, anonymization, and availability of expert annotations. The practical guidance may be adapted to any project that requires automated medical image analysis.

show abstract

Convolutional Neural Networks for Radiologic Images: A Radiologist’s Guide

Cited by 411 publications

References 175 publications

Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine

Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine

Differentiation of distal ureteral stones and pelvic phleboliths using a convolutional neural network

Deep learning workflow in radiology: a primer

Contact Info

Product

Resources

About