-
Journal of Magnetic Resonance Imaging :... Apr 2019Deep learning is a branch of artificial intelligence where networks of simple interconnected units are used to extract patterns from data in order to solve complex... (Review)
Review
Deep learning is a branch of artificial intelligence where networks of simple interconnected units are used to extract patterns from data in order to solve complex problems. Deep-learning algorithms have shown groundbreaking performance in a variety of sophisticated tasks, especially those related to images. They have often matched or exceeded human performance. Since the medical field of radiology mainly relies on extracting useful information from images, it is a very natural application area for deep learning, and research in this area has rapidly grown in recent years. In this article, we discuss the general context of radiology and opportunities for application of deep-learning algorithms. We also introduce basic concepts of deep learning, including convolutional neural networks. Then, we present a survey of the research in deep learning applied to radiology. We organize the studies by the types of specific tasks that they attempt to solve and review a broad range of deep-learning algorithms being utilized. Finally, we briefly discuss opportunities and challenges for incorporating deep learning in the radiology practice of the future. Level of Evidence: 3 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;49:939-954.
Topics: Algorithms; Artificial Intelligence; Deep Learning; Diagnostic Tests, Routine; Humans; Image Processing, Computer-Assisted; Machine Learning; Magnetic Resonance Imaging; Neural Networks, Computer; Radiography; Radiology
PubMed: 30575178
DOI: 10.1002/jmri.26534 -
Dento Maxillo Facial Radiology Jan 2022In the last few years, artificial intelligence (AI) research has been rapidly developing and emerging in the field of dental and maxillofacial radiology. Dental...
In the last few years, artificial intelligence (AI) research has been rapidly developing and emerging in the field of dental and maxillofacial radiology. Dental radiography, which is commonly used in daily practices, provides an incredibly rich resource for AI development and attracted many researchers to develop its application for various purposes. This study reviewed the applicability of AI for dental radiography from the current studies. Online searches on PubMed and IEEE Xplore databases, up to December 2020, and subsequent manual searches were performed. Then, we categorized the application of AI according to similarity of the following purposes: diagnosis of dental caries, periapical pathologies, and periodontal bone loss; cyst and tumor classification; cephalometric analysis; screening of osteoporosis; tooth recognition and forensic odontology; dental implant system recognition; and image quality enhancement. Current development of AI methodology in each aforementioned application were subsequently discussed. Although most of the reviewed studies demonstrated a great potential of AI application for dental radiography, further development is still needed before implementation in clinical routine due to several challenges and limitations, such as lack of datasets size justification and unstandardized reporting format. Considering the current limitations and challenges, future AI research in dental radiography should follow standardized reporting formats in order to align the research designs and enhance the impact of AI development globally.
Topics: Artificial Intelligence; Dental Caries; Humans; Radiography; Radiography, Dental, Digital; Radiology
PubMed: 34233515
DOI: 10.1259/dmfr.20210197 -
Clinical Radiology Mar 2023
Topics: Humans; Radiology; Radiography
PubMed: 36642647
DOI: 10.1016/j.crad.2022.10.015 -
European Radiology Dec 2023To investigate the view of clinicians on diagnostic radiology and its future.
OBJECTIVE
To investigate the view of clinicians on diagnostic radiology and its future.
METHODS
Corresponding authors who published in the New England Journal of Medicine and the Lancet between 2010 and 2022 were asked to participate in a survey about diagnostic radiology and its future.
RESULTS
The 331 participating clinicians gave a median score of 9 on a 0-10 point scale to the value of medical imaging in improving patient-relevant outcomes. 40.6%, 15.1%, 18.9%, and 9.5% of clinicians indicated to interpret more than half of radiography, ultrasonography, CT, and MRI examinations completely by themselves, without consulting a radiologist or reading the radiology report. Two hundred eighty-nine clinicians (87.3%) expected an increase in medical imaging utilization in the coming 10 years, whereas 9 clinicians (2.7%) expected a decrease. The need for diagnostic radiologists in the coming 10 years was expected to increase by 162 clinicians (48.9%), to remain stable by 85 clinicians (25.7%), and to decrease by 47 clinicians (14.2%). Two hundred clinicians (60.4%) expected that artificial intelligence (AI) will not make diagnostic radiologists redundant in the coming 10 years, whereas 54 clinicians (16.3%) thought the opposite.
CONCLUSION
Clinicians who published in the New England Journal of Medicine or the Lancet attribute high value to medical imaging. They generally need radiologists for cross-sectional imaging interpretation, but for a considerable proportion of radiographs, their service is not required. Most expect medical imaging utilization and the need for diagnostic radiologists to increase in the foreseeable future, and do not expect AI to make radiologists redundant.
CLINICAL RELEVANCE STATEMENT
The views of clinicians on radiology and its future may be used to determine how radiology should be practiced and be further developed.
KEY POINTS
• Clinicians generally regard medical imaging as high-value care and expect to use more medical imaging in the future. • Clinicians mainly need radiologists for cross-sectional imaging interpretation while they interpret a substantial proportion of radiographs completely by themselves. • The majority of clinicians expects that the need for diagnostic radiologists will not decrease (half of them even expect that we need more) and does not believe that AI will replace radiologists.
Topics: Humans; Artificial Intelligence; Radiology; Radiologists; Radiography; Surveys and Questionnaires
PubMed: 37436504
DOI: 10.1007/s00330-023-09897-2 -
Pediatric Radiology Jan 2023
Topics: Humans; United States; Radiology; Radiography; Academic Medical Centers
PubMed: 36255458
DOI: 10.1007/s00247-022-05535-z -
Canadian Association of Radiologists... Nov 2022Emergency Radiology is a clinical practice and an academic discipline that has rapidly gained increasing global recognition among radiology and emergency/critical care... (Review)
Review
Emergency Radiology is a clinical practice and an academic discipline that has rapidly gained increasing global recognition among radiology and emergency/critical care departments and trauma services around the world. As with other subspecialties, Emergency Radiology practice has a unique scope and purpose and presents with its own unique challenges. There are several advantages of having a dedicated Emergency Radiology section, perhaps most important of which is the broad clinical skillset that Emergency Radiologists are known for. This multi-society paper, representing the views of Emergency Radiology societies in Canada and Europe, outlines several value-oriented contributions of Emergency Radiologists and briefly discusses the current state of Emergency Radiology as a subspecialty.
Topics: Canada; Forecasting; Humans; Radiography; Radiologists; Radiology
PubMed: 35470687
DOI: 10.1177/08465371221088924 -
European Radiology Apr 2023
Topics: Humans; Radiology; Radiography
PubMed: 36355198
DOI: 10.1007/s00330-022-09224-1 -
RoFo : Fortschritte Auf Dem Gebiete Der... Aug 2023Radiology reports mostly contain free-text, which makes it challenging to obtain structured data. Natural language processing (NLP) techniques transform free-text...
PURPOSE
Radiology reports mostly contain free-text, which makes it challenging to obtain structured data. Natural language processing (NLP) techniques transform free-text reports into machine-readable document vectors that are important for creating reliable, scalable methods for data analysis. The aim of this study is to classify unstructured radiograph reports according to fractures of the distal fibula and to find the best text mining method.
MATERIALS & METHODS
We established a novel German language report dataset: a designated search engine was used to identify radiographs of the ankle and the reports were manually labeled according to fractures of the distal fibula. This data was used to establish a machine learning pipeline, which implemented the text representation methods bag-of-words (BOW), term frequency-inverse document frequency (TF-IDF), principal component analysis (PCA), non-negative matrix factorization (NMF), latent Dirichlet allocation (LDA), and document embedding (doc2vec). The extracted document vectors were used to train neural networks (NN), support vector machines (SVM), and logistic regression (LR) to recognize distal fibula fractures. The results were compared via cross-tabulations of the accuracy (acc) and area under the curve (AUC).
RESULTS
In total, 3268 radiograph reports were included, of which 1076 described a fracture of the distal fibula. Comparison of the text representation methods showed that BOW achieved the best results (AUC = 0.98; acc = 0.97), followed by TF-IDF (AUC = 0.97; acc = 0.96), NMF (AUC = 0.93; acc = 0.92), PCA (AUC = 0.92; acc = 0.9), LDA (AUC = 0.91; acc = 0.89) and doc2vec (AUC = 0.9; acc = 0.88). When comparing the different classifiers, NN (AUC = 0,91) proved to be superior to SVM (AUC = 0,87) and LR (AUC = 0,85).
CONCLUSION
An automated classification of unstructured reports of radiographs of the ankle can reliably detect findings of fractures of the distal fibula. A particularly suitable feature extraction method is the BOW model.
KEY POINTS
· The aim was to classify unstructured radiograph reports according to distal fibula fractures.. · Our automated classification system can reliably detect fractures of the distal fibula.. · A particularly suitable feature extraction method is the BOW model..
CITATION FORMAT
· Dewald CL, Balandis A, Becker LS et al. Automated Classification of Free-Text Radiology Reports: Using Different Feature Extraction Methods to Identify Fractures of the Distal Fibula. Fortschr Röntgenstr 2023; 195: 713 - 719.
Topics: Fibula; Radiography; Algorithms; Machine Learning; Natural Language Processing; Radiology
PubMed: 37160146
DOI: 10.1055/a-2061-6562 -
Scandinavian Journal of Pain Jul 2019
Topics: Back Pain; Humans; Low Back Pain; Radiography; Radiology
PubMed: 31228862
DOI: 10.1515/sjpain-2019-2011 -
RoFo : Fortschritte Auf Dem Gebiete Der... Sep 2022
Topics: Animals; Raccoons; Radiography; Radiology
PubMed: 36027881
DOI: 10.1055/a-1888-9285