Automatic classification and prioritisation of actionable BI-RADS categories using natural language processing models.

AIM: To facilitate the routine tasks performed by radiologists in their evaluation of breast radiology reports, by enhancing the communication of relevant results to referring physicians via a natural language processing (NLP)-based system to classify and prioritise Breast Imaging Reporting Data System (BI-RADS). MATERIALS AND METHODS: A NLP-based system was developed to classify and prioritise BI-RADS categories from breast ultrasound and mammogram reports, with the potential to streamline and speed up the standard procedures that radiologists must follow to evaluate and categorise breast imaging results. BI-RADS category extraction was divided into two specific tasks: (1) multi-label classification of BI-RADS categories (0-6) and (2) classification of high-priority (BI-RADS 0, 3, 4 and 5) and low priority (BI-RADS 1, 2, and 6) reports according to the previous BI-RADS assessment. RESULTS: To develop the NLP tool, three different Bidirectional Encoder Representations from Transformers (BERT)-based models (XLM-RoBERTa, BETO, and Bio-BERT-Spanish) were trained and tested on three distinct corpora (containing only breast ultrasound reports, only mammogram reports, or both), and achieved an accuracy of 74.29-77.5% in detecting BI-RADS categories and 88.52-91.02% in prioritising reports. CONCLUSION: The system designed can effectively classify all BI-RADS categories present in a single radiology report. In the clinical setting, such an automated tool can assist radiologists in evaluating breast radiology reports and decision-making tasks and enhance the speed of communicating priority BI-RADS reports to referring physicians.

Strengths, weaknesses, opportunities, and threat analysis of dual-energy CT in head and neck imaging.

Technological development of dual-energy computed tomography (DECT) can play an important role in head and neck area. Multiple innovative applications have evolved, optimizing images, achieving metallic artifact reduction, differentiating materials with better primary tumor delineation, thyroid cartilage and bone invasion. Furthermore, quantification algorithms allow measuring iodine concentration, reflecting the blood supply of a lesion indirectly. DECT enables acquiring images with lower radiation doses and iodine intravenous contrast load to obtain the same CT values.. However, DECT uses ionizing radiation, which does not occur with MRI, and requires long post-processing times. Artifacts on iodine maps may be a potential source of pseudolesions. Besides, photon-counting CT scanners are a promising technique that may displace some DECT advantages. A review analyzing the current status of DECT applied to head and neck imaging from the scope of strengths, weaknesses, opportunities, and threatsanalysis would be very interesting to facilitate a realistic, fact-based, data-driven look of this technique.

Análisis de las fortalezas, oportunidades, debilidades y amenazas de la tomografía computarizada de doble energía en el diagnóstico por la imagen de la cabeza y el cuello / Strengths, weaknesses, opportunities, and threat analysis of dual-energy CT in head and neck imaging

El desarrollo tecnológico de la tomografía computarizada de energía dual (TCED) en el área de la cabeza y el cuello ha supuesto un avance importante, ya que se han desarrollado múltiples aplicaciones para optimizar las imágenes y reducir los artefactos metálicos, así como para diferenciar los materiales, permitiendo una mejor delineación del tumor primario, del cartílago tiroideo y la invasión ósea. Además, los algoritmos de cuantificación permiten medir la concentración de yodo, lo que refleja el flujo de sangre que llega a una lesión de forma indirecta. Permite adquirir imágenes con menores dosis de radiación y menor cantidad de contraste yodado para obtener los mismos valores de TC. Sin embargo, utiliza radiaciones ionizantes y el posprocesamiento de las imágenes consume tiempo, y los artefactos en los mapas de yodo pueden suponer una fuente potencial de pseudolesiones. Además, los escáneres de TC con tecnología de recuento de fotones son una técnica prometedora que puede desplazar algunas de las ventajas de la TCED.Esta revisión hace un análisis de la TCED aplicada a las imágenes de cabeza y cuello desde el ámbito del análisis de las fortalezas, oportunidades, debilidades y amenazas para facilitar una visión realista, basada en datos, de esta técnica.(AU)

Technological development of dual-energy computed tomography (DECT) can play an important role in head and neck area. Multiple innovative applications have evolved, optimizing images, achieving metallic artifact reduction, differentiating materials with better primary tumor delineation, thyroid cartilage and bone invasion. Furthermore, quantification algorithms allow measuring iodine concentration, reflecting the blood supply of a lesion indirectly.DECT enables acquiring images with lower radiation doses and iodine intravenous contrast load to obtain the same CT values. However, DECT uses ionizing radiation, which does not occur with MRI, and requires long post-processing times. Artifacts on iodine maps may be a potential source of pseudolesions. Besides, photon-counting CT scanners are a promising technique that may displace some DECT advantages.A review analyzing the current status of DECT applied to head and neck imaging from the scope of strengths, weaknesses, opportunities, and threatsanalysis would be very interesting to facilitate a realistic, fact-based, data-driven look of this technique.(AU)

Artificial intelligence in radiology: relevance of collaborative work between radiologists and engineers for building a multidisciplinary team.

The use of artificial intelligence (AI) algorithms in the field of radiology is becoming more common. Several studies have demonstrated the potential utility of machine learning (ML) and deep learning (DL) techniques as aids for radiologists to solve specific radiological challenges. The decision-making process, the establishment of specific clinical or radiological targets, the profile of the different professionals involved in the development of AI solutions, and the relation with partnerships and stakeholders are only some of the main issues that have to be faced and solved prior to starting the development of radiological AI solutions. Among all the players in this multidisciplinary team, the communication between radiologists and data scientists is essential for a successful collaborative work. There are specific skills that are inherent to radiological and medical training that are critical for identifying anatomical or clinical targets as well as for segmenting or labelling lesions. These skills would then have to be transferred, explained, and taught to the data science experts to facilitate their comprehension and integration into ML or DL algorithms. On the other hand, there is a wide range of complex software packages, deep neural-network architectures, and data transfer processes for which radiologists need the expertise of software engineers and data scientists in order to select the optimal manner to analyse and post-process this amount of data. This paper offers a summary of the top five challenges faced by radiologists and data scientists including tips and tricks to build a successful AI team.

Actualización en la valoración de los nervios periféricos mediante resonancia magnética: de la neurografía morfológica a la funcional / Update in the evaluation of peripheral nerves by MRI, from morphological to functional neurography

El estudio los nervios periféricos (NNPP) mediante técnicas de imagen ha experimentado un notable crecimiento en la última década. Más allá del abordaje clásico y todavía vigente mediante ecografía de los NNPP, el desarrollo de nuevas técnicas neurográficas a partir de secuencias morfológicas convencionales (incluyendo estudios 3D isotrópicos con supresión grasa) está permitiendo valorar los distintos NNPP y plexos incluyendo pequeñas ramas terminales sensitivas y/o motoras con gran precisión. El uso de secuencias potenciadas en difusión (DWI) y tensor de difusión (DTI) ha permitido abrir un nuevo horizonte en los estudios de neurografía. Este nuevo abordaje proporciona información morfológica y funcional acerca de la estructura interna y fisiopatología de los NNPP y las distintas patologías relacionadas con ellos. En esta actualización realizamos una puesta al día de las distintas modalidades de neurografía mediante resonancia magnética disponibles para el estudio de los NNPP, con especial atención a las nuevas secuencias basadas en difusión

Imaging studies of peripheral nerves have increased considerably in the last ten years. In addition to the classical and still valid study by ultrasound, new neurographic techniques developed from conventional morphological sequences (including 3D isotropic studies with fat suppression) are making it possible to assess different peripheral nerves and plexuses, including small sensory and/or motor branches, with great precision. Diffusion-weighted sequences and diffusion tensor imaging have opened a new horizon in neurographic studies. This new approach provides morphological and functional information about the internal structure and pathophysiology of the peripheral nerves and diseases that involve them. This update reviews the different MR neurography techniques available for the study of the peripheral nerves, with special emphasis on new sequences based on diffusion

Update in the evaluation of peripheral nerves by MRI, from morphological to functional neurography. / Actualización en la valoración de los nervios periféricos mediante resonancia magnética: de la neurografía morfológica a la funcional.

Imaging studies of peripheral nerves have increased considerably in the last ten years. In addition to the classical and still valid study by ultrasound, new neurographic techniques developed from conventional morphological sequences (including 3D isotropic studies with fat suppression) are making it possible to assess different peripheral nerves and plexuses, including small sensory and/or motor branches, with great precision. Diffusion-weighted sequences and diffusion tensor imaging have opened a new horizon in neurographic studies. This new approach provides morphological and functional information about the internal structure and pathophysiology of the peripheral nerves and diseases that involve them. This update reviews the different MR neurography techniques available for the study of the peripheral nerves, with special emphasis on new sequences based on diffusion.

Técnicas avanzadas de resonancia magnética en patología tumoral de cabeza y cuello / Advanced magnetic resonance imaging techniques for tumors of the head and neck

La resonancia magnética se ha convertido en una herramienta fundamental en la valoración de la patología tumoral de cabeza y cuello. Los detalles anatómicos que proporcionan las imágenes de resonancia son fundamentales para diagnosticar, caracterizar y estadificar tanto la tumoración primaria como las metástasis ganglionares. Además de las mejoras técnicas en las secuencias anatómicas, como es el caso del Dixon para mejorar la supresión de la grasa, se están desarrollando otras secuencias como son la difusión y la perfusión, que dan información molecular, biológica y fisiológica del tumor proporcionando biomarcadores que pueden ayudar a conocer la biología del tumor en el momento del diagnóstico y posteriormente a monitorizar la enfermedad, y facilitan información muy relevante de la respuesta al tratamiento

Magnetic resonance imaging has become a fundamental tool for the evaluation of head and neck tumors. The anatomic details that magnetic resonance images provide are fundamental for diagnosing, characterizing, and staging both primary tumors and lymph node metastases. In addition to technical improvements in anatomic sequences, such as Dixon techniques to improve fat suppression, other sequences being developed, such as diffusion and perfusion, provide molecular, biological, and physiological information about the tumor and are yielding imaging biomarkers that can help in determining the tumor's biology at the time of diagnosis and in the follow-up of the disease. Magnetic resonance imaging also provides very useful information about the response to treatment

Advanced magnetic resonance imaging techniques for tumors of the head and neck. / Técnicas avanzadas de resonancia magnética en patología tumoral de cabeza y cuello.

Magnetic resonance imaging has become a fundamental tool for the evaluation of head and neck tumors. The anatomic details that magnetic resonance images provide are fundamental for diagnosing, characterizing, and staging both primary tumors and lymph node metastases. In addition to technical improvements in anatomic sequences, such as Dixon techniques to improve fat suppression, other sequences being developed, such as diffusion and perfusion, provide molecular, biological, and physiological information about the tumor and are yielding imaging biomarkers that can help in determining the tumor's biology at the time of diagnosis and in the follow-up of the disease. Magnetic resonance imaging also provides very useful information about the response to treatment.

Bases de la imagen funcional I: técnicas en uso clínico actualmente / Fundamentals of functional imaging I: current clinical techniques

Con las técnicas de imagen se puede establecer un fenotipo estructural, fisiológico y molecular del cáncer, que ayuda a un diagnóstico y un tratamiento preciso y personalizado. En los últimos años se han introducido y establecido en la práctica clínica diaria varias técnicas radiológicas que permiten estudiar características funcionales de los tumores de forma cuantitativa y reproducible. De esta manera, pueden estimarse la microcirculación, la angiogénesis y la permeabilidad tumoral con estudios de perfusión con contraste realizados mediante adquisiciones dinámicas ultrarrápidas con ecografía, tomografía computarizada o resonancia magnética (RM). La difusión forma parte de todos los protocolos actuales de RM para la evaluación de lesiones oncológicas en cualquier localización anatómica. La difusión informa sobre la ocupación de espacio extracelular/extravascular, y estima de manera indirecta la celularidad y la apoptosis de los tumores, habiéndose demostrado su relación con la agresividad biológica en varias estirpes tumorales, y su utilidad en la evaluación de la respuesta temprana a terapias sistémicas, locales y dirigidas. La espectroscopía de protones de hidrógeno es otra herramienta que se utiliza principalmente en el estudio de las características metabólicas de los tumores cerebrales. La complejidad técnica y la falta de reproducibilidad han limitado su uso clínico en otras áreas anatómicas, aunque existe amplia experiencia en la evaluación del cáncer de próstata y de mama, y en lesiones hepáticas. En esta revisión se analizan las técnicas de imagen radiológicas que permiten evaluar las características fisiológicas y moleculares del cáncer, y que se encuentran ya introducidas en el entorno clínico como las técnicas que evalúan la angiogénesis mediante adquisiciones dinámicas tras la administración de contraste, la difusión con RM o la espectroscopía de protones de hidrógeno con RM, así como sus principales aplicaciones en oncología

Imaging techniques can establish a structural, physiological, and molecular phenotype for cancer, which helps enable accurate diagnosis and personalized treatment. In recent years, various imaging techniques that make it possible to study the functional characteristics of tumors quantitatively and reproducibly have been introduced and have become established in routine clinical practice. Perfusion studies enable us to estimate the microcirculation as well as tumor angiogenesis and permeability using ultrafast dynamic acquisitions with ultrasound, computed tomography, or magnetic resonance (MR) imaging. Diffusion-weighted sequences now form part of state-of-the-art MR imaging protocols to evaluate oncologic lesions in any anatomic location. Diffusion-weighted imaging provides information about the occupation of the extracellular and extravascular space and indirectly estimates the cellularity and apoptosis of tumors, having demonstrated its relation with biologic aggressiveness in various tumor lines and its usefulness in the evaluation of the early response to systemic and local targeted therapies. Another tool is hydrogen proton MR spectroscopy, which is used mainly in the study of the metabolic characteristics of brain tumors. However, the complexity of the technique and its lack of reproducibility have limited its clinical use in other anatomic areas, although much experience with the use of this technique in the assessment of prostate and breast cancers as well as liver lesions has also accumulated. This review analyzes the imaging techniques that make it possible to evaluate the physiological and molecular characteristics of cancer that have already been introduced into clinical practice, such as techniques that evaluate angiogenesis through dynamic acquisitions after the administration of contrast material, diffusion-weighted imaging, or hydrogen proton MR spectroscopy, as well as their principal applications in oncology

Bases de la imagen funcional II: técnicas emergentes de resonancia magnética y nuevos métodos de análisis / Fundamentals of functional imaging II: emerging MR techniques and new methods of analysis

La resonancia magnética (RM) integra en los protocolos multiparamétricos clínicos actuales información estructural, fisiológica y metabólica del cáncer. Existen técnicas emergentes, como ASL, BOLD, RM elastografía, CEST e hiperpolarización, que aportan un nuevo tipo de información y que están cerca de su integración en la clínica diaria. Además, existe un gran interés en el estudio de la heterogeneidad tumoral con imagen como factor pronóstico y de resistencia al tratamiento. Para ello, se están aplicando nuevos métodos de análisis de los protocolos multiparamétricos, y a su vez se están desarrollando nuevos biomarcadores oncológicos integrando la información de la RM con los datos clínicos, analíticos, genéticos e histológicos, gracias a la aplicación del big data y la inteligencia artificial. En esta revisión se analizan varias técnicas emergentes de RM que permiten evaluar las características fisiológicas, metabólicas y mecánicas del cáncer, así como sus principales aplicaciones clínicas. Además, se resumen los métodos de análisis más novedosos de la información radiológica funcional en oncología

Current multiparameter MRI protocols integrate structural, physiological, and metabolic information about cancer. Emerging techniques such as arterial spin-labeling (ASL), blood oxygen level dependent (BOLD), MR elastography, chemical exchange saturation transfer (CEST), and hyperpolarization provide new information and will likely be integrated into daily clinical practice in the near future. Furthermore, there is great interest in the study of tumor heterogeneity as a prognostic factor and in relation to resistance to treatment, and this interest is leading to the application of new methods of analysis of multiparametric protocols. In parallel, new oncologic biomarkers that integrate the information from MR with clinical, laboratory, genetic, and histologic findings are being developed, thanks to the application of big data and artificial intelligence. This review analyzes different emerging MR techniques that are able to evaluate the physiological, metabolic, and mechanical characteristics of cancer, as well as the main clinical applications of these techniques. In addition, it summarizes the most novel methods of analysis of functional radiologic information in oncology

RM-Difusión avanzada y biomarcadores en el sistema nervioso central: un nuevo enfoque / Advanced diffusion MRI and biomarkers in the central nervous system: a new approach

La introducción de las secuencias potenciadas en difusión ha supuesto una revolución para la detección y caracterización de la patología del sistema nervioso central. Sin embargo, en numerosas ocasiones, la valoración de dichos estudios se limita a una estimación cualitativa. Además, la complejidad fisiopatológica de las distintas entidades que afectan al sistema nervioso central no siempre puede ser correctamente explicada por los modelos clásicos. El desarrollo de nuevo modelos para el análisis de las secuencias de difusión aporta numerosos parámetros que podrían permitir un abordaje cuantitativo tanto desde el punto de vista del diagnóstico como pronóstico, así como para llevar a cabo la monitorización terapéutica, y podrían ser considerados como potenciales biomarcadores de salud y enfermedad. Realizamos por este motivo una actualización que incluye las bases físicas de los estudios de difusión y tensor de difusión, sus modelos de análisis avanzado (IVIM y Kurtosis) y la significación biológica de los parámetros derivados (AU)

The introduction of diffusion-weighted sequences has revolutionized the detection and characterization of central nervous system (CNS) disease. Nevertheless, the assessment of diffusion studies of the CNS is often limited to qualitative estimation. Moreover, the pathophysiological complexity of the different entities that affect the CNS cannot always be correctly explained through classical models. The development of new models for the analysis of diffusion sequences provides numerous parameters that enable a quantitative approach to both diagnosis and prognosis as well as to monitoring the response to treatment; these parameters can be considered potential biomarkers of health and disease. In this update, we review the physical bases underlying diffusion studies and diffusion tensor imaging, advanced models for their analysis (intravoxel coherent motion and kurtosis), and the biological significance of the parameters derived (AU)

Advanced diffusion MRI and biomarkers in the central nervous system: a new approach. / RM-Difusión avanzada y biomarcadores en el sistema nervioso central: un nuevo enfoque.

The introduction of diffusion-weighted sequences has revolutionized the detection and characterization of central nervous system (CNS) disease. Nevertheless, the assessment of diffusion studies of the CNS is often limited to qualitative estimation. Moreover, the pathophysiological complexity of the different entities that affect the CNS cannot always be correctly explained through classical models. The development of new models for the analysis of diffusion sequences provides numerous parameters that enable a quantitative approach to both diagnosis and prognosis as well as to monitoring the response to treatment; these parameters can be considered potential biomarkers of health and disease. In this update, we review the physical bases underlying diffusion studies and diffusion tensor imaging, advanced models for their analysis (intravoxel coherent motion and kurtosis), and the biological significance of the parameters derived.