AI in radiology: Legal responsibilities and the car paradox.

The integration of AI in radiology raises significant legal questions about responsibility for errors. Radiologists fear AI may introduce new legal challenges, despite its potential to enhance diagnostic accuracy. AI tools, even those approved by regulatory bodies like the FDA or CE, are not perfect, posing a risk of failure. The key issue is how AI is implemented: as a stand-alone diagnostic tool or as an aid to radiologists. The latter approach could reduce undesired side effects. However, it's unclear who should be held liable for AI failures, with potential candidates ranging from engineers and radiologists involved in AI development to companies and department heads who integrate these tools into clinical practice. The EU's AI Act, recognizing AI's risks, categorizes applications by risk level, with many radiology-related AI tools considered high risk. Legal precedents in autonomous vehicles offer some guidance on assigning responsibility. Yet, the existing legal challenges in radiology, such as diagnostic errors, persist. AI's potential to improve diagnostics raises questions about the legal implications of not using available AI tools. For instance, an AI tool improving the detection of pediatric fractures could reduce legal risks. This situation parallels innovations like car turn signals, where ignoring available safety enhancements could lead to legal problems. The debate underscores the need for further research and regulation to clarify AI's role in radiology, balancing innovation with legal and ethical considerations.

Evaluation of large language models performance against humans for summarizing MRI knee radiology reports: A feasibility study.

OBJECTIVES: This study addresses the critical need for accurate summarization in radiology by comparing various Large Language Model (LLM)-based approaches for automatic summary generation. With the increasing volume of patient information, accurately and concisely conveying radiological findings becomes crucial for effective clinical decision-making. Minor inaccuracies in summaries can lead to significant consequences, highlighting the need for reliable automated summarization tools. METHODS: We employed two language models - Text-to-Text Transfer Transformer (T5) and Bidirectional and Auto-Regressive Transformers (BART) - in both fine-tuned and zero-shot learning scenarios and compared them with a Recurrent Neural Network (RNN). Additionally, we conducted a comparative analysis of 100 MRI report summaries, using expert human judgment and criteria such as coherence, relevance, fluency, and consistency, to evaluate the models against the original radiologist summaries. To facilitate this, we compiled a dataset of 15,508 retrospective knee Magnetic Resonance Imaging (MRI) reports from our Radiology Information System (RIS), focusing on the findings section to predict the radiologist's summary. RESULTS: The fine-tuned models outperform the neural network and show superior performance in the zero-shot variant. Specifically, the T5 model achieved a Rouge-L score of 0.638. Based on the radiologist readers' study, the summaries produced by this model were found to be very similar to those produced by a radiologist, with about 70% similarity in fluency and consistency between the T5-generated summaries and the original ones. CONCLUSIONS: Technological advances, especially in NLP and LLM, hold great promise for improving and streamlining the summarization of radiological findings, thus providing valuable assistance to radiologists in their work.

Automatic generation of conclusions from neuroradiology MRI reports through natural language processing.

PURPOSE: The conclusion section of a radiology report is crucial for summarizing the primary radiological findings in natural language and essential for communicating results to clinicians. However, creating these summaries is time-consuming, repetitive, and prone to variability and errors among different radiologists. To address these issues, we evaluated a fine-tuned Text-To-Text Transfer Transformer (T5) model for abstractive summarization to automatically generate conclusions for neuroradiology MRI reports in a low-resource language. METHODS: We retrospectively applied our method to a dataset of 232,425 neuroradiology MRI reports in Spanish. We compared various pre-trained T5 models, including multilingual T5 and those newly adapted for Spanish. For precise evaluation, we employed BLEU, METEOR, ROUGE-L, CIDEr, and cosine similarity metrics alongside expert radiologist assessments. RESULTS: The findings are promising, with the models specifically fine-tuned for neuroradiology MRI achieving scores of 0.46, 0.28, 0.52, 2.45, and 0.87 in the BLEU-1, METEOR, ROUGE-L, CIDEr, and cosine similarity metrics, respectively. In the radiological experts' evaluation, they found that in 75% of the cases evaluated, the conclusions generated by the system were as good as or even better than the manually generated conclusions. CONCLUSION: The methods demonstrate the potential and effectiveness of customizing state-of-the-art pre-trained models for neuroradiology, yielding automatic MRI report conclusions that nearly match expert quality. Furthermore, these results underscore the importance of designing and pre-training a dedicated language model for radiology report summarization.

Imagine there is no paperwork it's easy if you try.

Artificial Intelligence (AI) applied to radiology is so vast that it provides applications ranging from becoming a complete replacement for radiologists (a potential threat) to an efficient paperwork-saving time assistant (an evident strength). Nowadays, there are AI applications developed to facilitate the diagnostic process of radiologists without directly influencing (or replacing) the proper diagnostic decision step. These tools may help to reduce administrative workload, in different scenarios ranging from assisting in scheduling, study prioritization, or report communication, to helping with patient follow-up, including recommending additional exams. These are just a few of the highly time-consuming tasks that radiologists have to deal with every day in their routine workflow. These tasks hinder the time that radiologists should spend evaluating images and caring for patients, which will have a direct and negative impact on the quality of reports and patient attention, increasing the delay and waiting list of studies pending to be performed and reported. These types of AI applications should help to partially face this worldwide shortage of radiologists.

Natural language processing deep learning models for the differential between high-grade gliomas and metastasis: what if the key is how we report them?

OBJECTIVES: The differential between high-grade glioma (HGG) and metastasis remains challenging in common radiological practice. We compare different natural language processing (NLP)-based deep learning models to assist radiologists based on data contained in radiology reports. METHODS: This retrospective study included 185 MRI reports between 2010 and 2022 from two different institutions. A total of 117 reports were used for the training and 21 were reserved for the validation set, while the rest were used as a test set. A comparison of the performance of different deep learning models for HGG and metastasis classification has been carried out. Specifically, Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), a hybrid version of BiLSTM and CNN, and a radiology-specific Bidirectional Encoder Representations from Transformers (RadBERT) model were used. RESULTS: For the classification of MRI reports, the CNN network provided the best results among all tested, showing a macro-avg precision of 87.32%, a sensitivity of 87.45%, and an F1 score of 87.23%. In addition, our NLP algorithm detected keywords such as tumor, temporal, and lobe to positively classify a radiological report as HGG or metastasis group. CONCLUSIONS: A deep learning model based on CNN enables radiologists to discriminate between HGG and metastasis based on MRI reports with high-precision values. This approach should be considered an additional tool in diagnosing these central nervous system lesions. CLINICAL RELEVANCE STATEMENT: The use of our NLP model enables radiologists to differentiate between patients with high-grade glioma and metastasis based on their MRI reports and can be used as an additional tool to the conventional image-based approach for this challenging task. KEY POINTS: • Differential between high-grade glioma and metastasis is still challenging in common radiological practice. • Natural language processing (NLP)-based deep learning models can assist radiologists based on data contained in radiology reports. • We have developed and tested a natural language processing model for discriminating between high-grade glioma and metastasis based on MRI reports that show high precision for this task.

CARES: A Corpus for classification of Spanish Radiological reports.

This paper presents a new corpus of radiology medical reports written in Spanish and labeled with ICD-10. CARES (Corpus of Anonymised Radiological Evidences in Spanish) is a high-quality corpus manually labeled and reviewed by radiologists that is freely available for the research community on HuggingFace. These types of resources are essential for developing automatic text classification tools as they are necessary for training and tuning computational systems. However, in the medical domain these are very difficult to obtain for different reasons including privacy and data protection issues or the involvement of medical specialists in the generation of these resources. We present a corpus labeled and reviewed by radiologists in their daily practice that is available for research purposes. In addition, after describing the corpus and explaining how it has been generated, a first experimental approach is carried out using several machine learning algorithms based on transformer language models such as BioBERT and RoBERTa to test the validity of this linguistic resource. The best performing classifier achieved 0.8676 micro and 0.8328 macro f1-score and these results encourage us to continue working in this research line.

Natural Language Processing in Pathology: Current Trends and Future Insights.

Natural language processing (NLP) plays a key role in advancing health care, being key to extracting structured information from electronic health reports. In the last decade, several advances in the field of pathology have been derived from the application of NLP to pathology reports. Herein, a comprehensive review of the most used NLP methods for extracting, coding, and organizing information from pathology reports is presented, including how the development of tools is used to improve workflow. In addition, this article discusses, from a practical point of view, the steps necessary to extract data and encode natural language information for its analytical processing, ranging from preprocessing of text to its inclusion in complex algorithms. Finally, the potential of NLP-based automatic solutions for improving workflow in pathology and their further applications in the near future is highlighted.

Natural Language Processing in Radiology: Update on Clinical Applications.

Radiological reports are a valuable source of information used to guide clinical care and support research. Organizing and managing this content, however, frequently requires several manual curations because of the more common unstructured nature of the reports. However, manual review of these reports for clinical knowledge extraction is costly and time-consuming. Natural language processing (NLP) is a set of methods developed to extract structured meaning from a body of text and can be used to optimize the workflow of health care professionals. Specifically, NLP methods can help radiologists as decision support systems and improve the management of patients' medical data. In this study, we highlight the opportunities offered by NLP in the field of radiology. A comprehensive review of the most commonly used NLP methods to extract information from radiological reports and the development of tools to improve radiological workflow using this information is presented. Finally, we review the important limitations of these tools and discuss the relevant observations and trends in the application of NLP to radiology that could benefit the field in the future.

Combining word embeddings to extract chemical and drug entities in biomedical literature.

BACKGROUND: Natural language processing (NLP) and text mining technologies for the extraction and indexing of chemical and drug entities are key to improving the access and integration of information from unstructured data such as biomedical literature. METHODS: In this paper we evaluate two important tasks in NLP: the named entity recognition (NER) and Entity indexing using the SNOMED-CT terminology. For this purpose, we propose a combination of word embeddings in order to improve the results obtained in the PharmaCoNER challenge. RESULTS: For the NER task we present a neural network composed of BiLSTM with a CRF sequential layer where different word embeddings are combined as an input to the architecture. A hybrid method combining supervised and unsupervised models is used for the concept indexing task. In the supervised model, we use the training set to find previously trained concepts, and the unsupervised model is based on a 6-step architecture. This architecture uses a dictionary of synonyms and the Levenshtein distance to assign the correct SNOMED-CT code. CONCLUSION: On the one hand, the combination of word embeddings helps to improve the recognition of chemicals and drugs in the biomedical literature. We achieved results of 91.41% for precision, 90.14% for recall, and 90.77% for F1-score using micro-averaging. On the other hand, our indexing system achieves a 92.67% F1-score, 92.44% for recall, and 92.91% for precision. With these results in a final ranking, we would be in the first position.

Transfer Learning for Classifying Spanish and English Text by Clinical Specialties.

Transfer learning has demonstrated its potential in natural language processing tasks, where models have been pre-trained on large corpora and then tuned to specific tasks. We applied pre-trained transfer models to a Spanish biomedical document classification task. The main goal is to analyze the performance of text classification by clinical specialties using state-of-the-art language models for Spanish, and compared them with the results using corresponding models in English and with the most important pre-trained model for the biomedical domain. The outcomes present interesting perspectives on the performance of language models that are pre-trained for a particular domain. In particular, we found that BioBERT achieved better results on Spanish texts translated into English than the general domain model in Spanish and the state-of-the-art multilingual model.

Collecting specialty-related medical terms: Development and evaluation of a resource for Spanish.

BACKGROUND: Controlled vocabularies are fundamental resources for information extraction from clinical texts using natural language processing (NLP). Standard language resources available in the healthcare domain such as the UMLS metathesaurus or SNOMED CT are widely used for this purpose, but with limitations such as lexical ambiguity of clinical terms. However, most of them are unambiguous within text limited to a given clinical specialty. This is one rationale besides others to classify clinical text by the clinical specialty to which they belong. RESULTS: This paper addresses this limitation by proposing and applying a method that automatically extracts Spanish medical terms classified and weighted per sub-domain, using Spanish MEDLINE titles and abstracts as input. The hypothesis is biomedical NLP tasks benefit from collections of domain terms that are specific to clinical subdomains. We use PubMed queries that generate sub-domain specific corpora from Spanish titles and abstracts, from which token n-grams are collected and metrics of relevance, discriminatory power, and broadness per sub-domain are computed. The generated term set, called Spanish core vocabulary about clinical specialties (SCOVACLIS), was made available to the scientific community and used in a text classification problem obtaining improvements of 6 percentage points in the F-measure compared to the baseline using Multilayer Perceptron, thus demonstrating the hypothesis that a specialized term set improves NLP tasks. CONCLUSION: The creation and validation of SCOVACLIS support the hypothesis that specific term sets reduce the level of ambiguity when compared to a specialty-independent and broad-scope vocabulary.

Automatic medical protocol classification using machine learning approaches.

BACKGROUND AND OBJECTIVE: Assignment of medical imaging procedure protocols requires extensive knowledge about patient's data, usually included in radiological request forms and radiological reports. Assignment of protocol is required prior to radiological study acquisition, determining procedure for each patient. The automation of this protocol assignment process could improve the efficiency of patient's diagnosis. Artificial intelligence has proven to be of great help in these healthcare-related problems, and specifically the application of Natural Language Processing (NLP) techniques for extracting information from text reports has been successfully used in automatic text classification tasks. METHODS: In this paper, machine learning classification models based on NLP have been developed using patient's data present in radiological reports and radiological imaging protocols. We have used a real corpus provided by the private medical center "HT medica" composed of almost 700,000 Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) examinations obtained during routine clinical use. We have compared several models including traditional machine learning methods such as support vector machine and random forest, neural networks and transfer language techniques. RESULTS: The results obtained are encouraging taking into account that the system is performing a complex text multiclass classification task. Specifically, for the best proposed system we obtain 92.2% accuracy in the CT dataset and 86.9% in the MRI dataset. CONCLUSIONS: The best machine learning system is potentially efficient, quality and cost effective. For this reason it is currently used in real scenarios by radiologists as decision support tool for assigning protocols of CT and MRI studies.

COVID-19 detection in radiological text reports integrating entity recognition.

COVID-19 diagnosis is usually based on PCR test using radiological images, mainly chest Computed Tomography (CT) for the assessment of lung involvement by COVID-19. However, textual radiological reports also contain relevant information for determining the likelihood of presenting radiological signs of COVID-19 involving lungs. The development of COVID-19 automatic detection systems based on Natural Language Processing (NLP) techniques could provide a great help in supporting clinicians and detecting COVID-19 related disorders within radiological reports. In this paper we propose a text classification system based on the integration of different information sources. The system can be used to automatically predict whether or not a patient has radiological findings consistent with COVID-19 on the basis of radiological reports of chest CT. To carry out our experiments we use 295 radiological reports from chest CT studies provided by the ''HT médica" clinic. All of them are radiological requests with suspicions of chest involvement by COVID-19. In order to train our text classification system we apply Machine Learning approaches and Named Entity Recognition. The system takes two sources of information as input: the text of the radiological report and COVID-19 related disorders extracted from SNOMED-CT. The best system is trained using SVM and the baseline results achieve 85% accuracy predicting lung involvement by COVID-19, which already offers competitive values that are difficult to overcome. Moreover, we apply mutual information in order to integrate the best quality information extracted from SNOMED-CT. In this way, we achieve around 90% accuracy improving the baseline results by 5 points.

Leveraging PubMed to Create a Specialty-Based Sense Inventory for Spanish Acronym Resolution.

Acronyms frequently occur in clinical text, which makes their identification, disambiguation and resolution an important task in clinical natural language processing. This paper contributes to acronym resolution in Spanish through the creation of a set of sense inventories organized by clinical specialty containing acronyms, their expansions, and corpus-driven features. The new acronym resource is composed of 51 clinical specialties with 3,603 acronyms in total, from which we identified 228 language independent acronyms and 391 language dependent expansions. We further analyzed the sense inventory across specialties and present novel insights of acronym usage in biomedical Spanish texts.