RESUMEN

OBJECTIVES: This study aimed to evaluate the impact of 3D-printed mannequins on the training of predoctoral students. METHODS: Two 3D-printed training models were developed: a traditional model that simulates a sound adult patient and a customized model with pathological and physiological changes (impacted third molar and edentulous region). Students accomplished their pre-clinical training divided into a control group (CG, n = 23), which had access to the traditional model, and a test group (TG, n = 20), which had access to both models. Afterward, they performed a full mouth series on patients and filled out a perception questionnaire. Radiographs were evaluated for technical parameters. Descriptive statistics and the Mann-Whitney test were used to compare the groups. RESULTS: Students provided positive feedback regarding the use of 3D printing. The TG reported a more realistic training experience than the CG (P = .037). Both groups demonstrated good clinical performance (CG = 7.41; TG = 7.52), and no significant differences were observed between them. CONCLUSIONS: 3D printing is an option for producing simulators for pre-clinical training in Oral Radiology, reducing student stress and increasing confidence during clinical care.

Asunto(s)

Asunto(s)

RESUMEN

Las enfermedades quísticas renales son condiciones frecuentes cuya etiología puede ser muy heterogénea, por lo que se requiere un adecuado abordaje para su diagnóstico y manejo. El objetivo de este trabajo fue ilustrar parte del espectro de la enfermedad renal quística por medio de casos clínicos manejados en la Fundación Valle del Lili. Se describen 11 casos clínicos que incluyen enfermedades como displasia multiquística renal, enfermedad poliquística renal autosómica dominante y autosómica recesiva, entre otras. Las enfermedades quísticas renales varían en su presentación clínica, historia natural, hallazgos imagenológicos, bases genéticas y fisiopatológicas, por consiguiente, el enfoque diagnóstico y el manejo integral se debe realizar de forma individualizada y con un abordaje multidisciplinario.

Renal cystic diseases are common conditions whose etiology can be highly heterogeneous. They require a correct approach for adequate diagnosis and management. We aimed to illustrate part of the spectrum of renal cystic diseases through some clinical cases managed in our service. We describe 11 clinical cases including clinical entities such as renal multicystic dysplasia, and autosomal dominant and autosomal recessive polycystic renal disease, among other pathologies. Renal cystic diseases are heterogeneous in their clinical presentation, natural history, radiological findings, and genetic and pathophysiological basis. An integral clinical approach is needed to get a clear etiological diagnosis and offer adequate individualized care and follow-up for patients.

Asunto(s)

Asunto(s)

RESUMEN

RATIONALE AND OBJECTIVES: Although PBL is widely used in several countries, especially in medicine courses, its application in teaching other higher education courses, which involve fundamentals applied to radiology, is still little explored. Therefore, we aim to evaluate the implementation of Problem-Based Learning (PBL) in a higher education institution's radiology and biomedicine technologist course, focusing on specific radiology-related disciplines. MATERIALS AND METHODS: An interventional study was developed with 78 students. An active methodology model was created and implemented for one of the groups of participants. At the beginning of each semester, students of both groups were evaluated with pre-tests. At the end of the semesters, the students performed a post-test and a validated evaluation of the discipline methodology. Repeated measures generalized linear regressive models with robust error estimators were used to evaluate test outcomes. RESULTS: A significant interaction among the methodologies was found (p=0.020), with better results from students exposed to the active methodology (initial and final grades were 7.18 and 7.57 in the active methodology, respectively, and 7.45 and 6.89 in the traditional methodology, respectively). In addition, students' evaluation regarding the quality of the methodology was favorable to the active methodology with statistical significance (p<0.05) in 16 of the 22 items evaluated. CONCLUSIONS: The students' positive response and performance were attributed to the interaction and innovation of the methodology compared to conventional methods, highlighting the effectiveness of PBL in higher education in radiology and its potential for more participatory and contextualized learning.

Asunto(s)

RESUMEN

Radiology has a number of characteristics that make it an especially suitable medical discipline for early artificial intelligence (AI) adoption. These include having a well-established digital workflow, standardized protocols for image storage, and numerous well-defined interpretive activities. The more than 200 commercial radiologic AI-based products recently approved by the Food and Drug Administration (FDA) to assist radiologists in a number of narrow image-analysis tasks such as image enhancement, workflow triage, and quantification, corroborate this observation. However, in order to leverage AI to boost efficacy and efficiency, and to overcome substantial obstacles to widespread successful clinical use of these products, radiologists should become familiarized with the emerging applications in their particular areas of expertise. In light of this, in this article we survey the existing literature on the application of AI-based techniques in neuroradiology, focusing on conditions such as vascular diseases, epilepsy, and demyelinating and neurodegenerative conditions. We also introduce some of the algorithms behind the applications, briefly discuss a few of the challenges of generalization in the use of AI models in neuroradiology, and skate over the most relevant commercially available solutions adopted in clinical practice. If well designed, AI algorithms have the potential to radically improve radiology, strengthening image analysis, enhancing the value of quantitative imaging techniques, and mitigating diagnostic errors.

A radiologia tem uma série de características que a torna uma disciplina médica especialmente adequada à adoção precoce da inteligência artificial (IA), incluindo um fluxo de trabalho digital bem estabelecido, protocolos padronizados para armazenamento de imagens e inúmeras atividades interpretativas bem definidas. Tal adequação é corroborada pelos mais de 200 produtos radiológicos comerciais baseados em IA recentemente aprovados pelo Food and Drug Administration (FDA) para auxiliar os radiologistas em uma série de tarefas restritas de análise de imagens, como quantificação, triagem de fluxo de trabalho e aprimoramento da qualidade das imagens. Entretanto, para o aumento da eficácia e eficiência da IA, além de uma utilização clínica bem-sucedida dos produtos que utilizam essa tecnologia, os radiologistas devem estar atualizados com as aplicações em suas áreas específicas de atuação. Assim, neste artigo, pesquisamos na literatura existente aplicações baseadas em IA em neurorradiologia, mais especificamente em condições como doenças vasculares, epilepsia, condições desmielinizantes e neurodegenerativas. Também abordamos os principais algoritmos por trás de tais aplicações, discutimos alguns dos desafios na generalização no uso desses modelos e introduzimos as soluções comercialmente disponíveis mais relevantes adotadas na prática clínica. Se cautelosamente desenvolvidos, os algoritmos de IA têm o potencial de melhorar radicalmente a radiologia, aperfeiçoando a análise de imagens, aumentando o valor das técnicas de imagem quantitativas e mitigando erros de diagnóstico.

Asunto(s)

RESUMEN

La Dra. Raquel Pérez González, más conocida entre colegas, alumnos y compañeros de trabajo por "la profe Raquel", obtuvo el título de Medicina en el año 1976. Comenzó por vía directa la residencia de Radiología y obtuvo el título de especialista de primer grado en 1979. Se convirtió así, el Hospital Militar Central "Dr. Carlos J. Finlay", en la cuna de su formación profesional y en años posteriores, en la casa que la vio crecer, especialmente como maestra de numerosas generaciones de radiólogos e imagenólogos. Hoy reposan en el jardín del Departamento de Imagenología, parte de sus cenizas, custodiadas por el amor que fue capaz de cultivar. En el 2016, una paciente femenina de 60 años de edad, acudió a la consulta de gastroenterología, con dolor abdominal difuso. La radiografía de abdomen simple, anteroposterior, en posición acostado mostró, una imagen en "muela de cangrejo", visible al tomar el aire dentro del hemicolon transverso izquierdo, como contraste, el cual bordea por ese lado parcialmente, una opacidad de partes blandas, que se extiende desde el mesogastrio, hasta la fosa ilíaca derecha, donde se observa el signo del menisco. Los estudios de imágenes realizados, evidenciaron signos radiológicos típicos de invaginación por causa tumoral maligna. En varias ocasiones, la profesora Raquel utilizó la imagen de este caso, como pregunta en exámenes de promoción de residentes. La publicación de este caso constituye un homenaje a quien será siempre un paradigma de docente.

Dr. Raquel Pérez González, better known among colleagues, students and co-workers as "professor Raquel", obtained her degree in Medicine in 1976. She began her Radiology residency directly and obtained the title of first-class specialist degree in 1979. Thus, the Central Military Hospital "Dr. Carlos J. Finlay" is the cradle of her professional training and in later years, in her home where she saw her grow up, especially as a teacher to numerous generations of radiologists and imaging scientists. Today, part of her ashes rest in the garden of the Imaging Department, guarded by the love that she was able to cultivate. In 2016, a 60-year-old female patient attended the gastroenterology clinic with diffuse abdominal pain. The simple, anteroposterior abdominal x-ray, in the lying position, showed a "crab claw" image, visible when breathing into the left transverse hemicolon, as contrast, which partially borders on that side, a soft tissue opacity, which extends from the mesogastrium to the right iliac fossa, where the meniscus sign is observed. The imaging studies performed showed typical radiological signs of invagination due to malignant tumor. On several occasions, Professor Raquel used the image of this case as a question in resident promotion exams. The publication of this case constitutes a tribute to someone who will always be a paradigm of a teacher.

Asunto(s)

RESUMEN

Although lung cancer (LC) is one of the most common and lethal tumors, only 15% of patients are diagnosed at an early stage. Smoking is still responsible for more than 85% of cases. Lung cancer screening (LCS) with low-dose CT (LDCT) reduces LC-related mortality by 20%, and that reduction reaches 38% when LCS by LDCT is combined with smoking cessation. In the last decade, a number of countries have adopted population-based LCS as a public health recommendation. Albeit still incipient, discussion on this topic in Brazil is becoming increasingly broad and necessary. With the aim of increasing knowledge and stimulating debate on LCS, the Brazilian Society of Thoracic Surgery, the Brazilian Thoracic Association, and the Brazilian College of Radiology and Diagnostic Imaging convened a panel of experts to prepare recommendations for LCS in Brazil. The recommendations presented here were based on a narrative review of the literature, with an emphasis on large population-based studies, systematic reviews, and the recommendations of international guidelines, and were developed after extensive discussion by the panel of experts. The following topics were reviewed: reasons for screening; general considerations about smoking; epidemiology of LC; eligibility criteria; incidental findings; granulomatous lesions; probabilistic models; minimum requirements for LDCT; volumetric acquisition; risks of screening; minimum structure and role of the multidisciplinary team; practice according to the Lung CT Screening Reporting and Data System; costs versus benefits of screening; and future perspectives for LCS.

Asunto(s)

Asunto(s)

RESUMEN

Atraumatic muscle disorders comprise a very wide range of skeletal muscle diseases, including metabolic, inflammatory, autoimmune, infectious, ischemic, and neoplastic involvement of the muscles. Therefore, one must take clinical and laboratory data into consideration to elucidate the differential diagnoses, as well as the distribution of the muscle compromise along the body-whether isolated or distributed along the body in a symmetric or asymmetrical fashion. Assessment of muscular disorders often requires imaging investigation before image-guided biopsy or more invasive procedures; therefore, radiologists should understand the advantages and limitations of imaging methods for proper lesion evaluation and be aware of the imaging features of such disorders, thus contributing to proper decision-making and good patient outcomes. In this review, we propose a systematic approach for the assessment of muscle disorders based on their main imaging presentation, dividing them into patterns that can be easily recognized.

Asunto(s)

Asunto(s)

RESUMEN

In this work, an open beam-limiting device, consisting of a rectangular collimator to be coupled to an intraoral dental X-ray device, was made using recycled lead sheets as a radiation-absorbing element. The collimator was designed for 3D printing, and using Spektr 3.0 software, the number of lead sheets needed to absorb excess radiation was calculated. The rectangular collimator reduced the radiation dose to patients by 65% when using four layers of recycled lead sheets (saturating with a 70% reduction in radiation dose at the limit of eight or more sheets of lead). The rectangular collimator does not negatively impact the quality of the radiological image, is available as an open design for 3D printing, and can be built with materials that are easily accessible to the dentist, facilitating its use in clinical practice and reducing the patient's exposure to ionizing radiation.

Asunto(s)

Asunto(s)

RESUMEN

PURPOSE: A critical task in oncology is extracting information related to cancer metastasis from electronic health records. Metastasis-related information is crucial for planning treatment, evaluating patient prognoses, and cancer research. However, the unstructured way in which findings of distant metastasis are often written in radiology reports makes it difficult to extract information automatically. The main aim of this study was to extract distant metastasis findings from free-text imaging and nuclear medicine reports to classify the patient status according to the presence or absence of distant metastasis. MATERIALS AND METHODS: We created a distant metastasis annotated corpus using positron emission tomography-computed tomography and computed tomography reports of patients with prostate, colorectal, and breast cancers. Entities were labeled M1 or M0 according to affirmative or negative metastasis descriptions. We used a named entity recognition model on the basis of a bidirectional long short-term memory model and conditional random fields to identify entities. Mentions were subsequently used to classify whole reports into M1 or M0. RESULTS: The model detected distant metastasis mentions with a weighted average F1 score performance of 0.84. Whole reports were classified with an F1 score of 0.92 for M0 documents and 0.90 for M1 documents. CONCLUSION: These results show the usefulness of the model in detecting distant metastasis findings in three different types of cancer and the consequent classification of reports. The relevance of this study is to generate structured distant metastasis information from free-text imaging reports in Spanish. In addition, the manually annotated corpus, annotation guidelines, and code are freely released to the research community.

Asunto(s)

Asunto(s)

RESUMEN

This prospective exploratory study conducted from January 2023 through May 2023 evaluated the ability of ChatGPT to answer questions from Brazilian radiology board examinations, exploring how different prompt strategies can influence performance using GPT-3.5 and GPT-4. Three multiple-choice board examinations that did not include image-based questions were evaluated: (a) radiology and diagnostic imaging, (b) mammography, and (c) neuroradiology. Five different styles of zero-shot prompting were tested: (a) raw question, (b) brief instruction, (c) long instruction, (d) chain-of-thought, and (e) question-specific automatic prompt generation (QAPG). The QAPG and brief instruction prompt strategies performed best for all examinations (P < .05), obtaining passing scores (≥60%) on the radiology and diagnostic imaging examination when testing both versions of ChatGPT. The QAPG style achieved a score of 60% for the mammography examination using GPT-3.5 and 76% using GPT-4. GPT-4 achieved a score up to 65% in the neuroradiology examination. The long instruction style consistently underperformed, implying that excessive detail might harm performance. GPT-4's scores were less sensitive to prompt style changes. The QAPG prompt style showed a high volume of the "A" option but no statistical difference, suggesting bias was found. GPT-4 passed all three radiology board examinations, and GPT-3.5 passed two of three examinations when using an optimal prompt style. Keywords: ChatGPT, Artificial Intelligence, Board Examinations, Radiology and Diagnostic Imaging, Mammography, Neuroradiology © RSNA, 2023 See also the commentary by Trivedi and Gichoya in this issue.

Asunto(s)

Asunto(s)

RESUMEN

Nowadays, alternative methods that do not use formaldehyde to preserve cadavers must be used due to this substance's toxicity. Synthetic models are a training option for teaching, but cost makes their use unviable in most underdeveloped countries. The present study's main objective was to develop a model for education and researching thorax radiology in cadavers of chemically prepared dogs. Megaesophagus, pleural effusion, pneumothorax, and bronchography, as well as pulmonary insufflation, were simulated in 32 dogs cadavers, which received 150 mL/kg of pure ethyl alcohol solution with 5% glycerin followed by injection of 120 mL/kg of a solution containing 20% sodium chloride, 1% sodium nitrite and 1% sodium nitrate; they were kept refrigerated between 2 to 6 °C, for 30, 60, 90 or 120 days (G30, G60, G90, G120). There was no contamination, putrid odor, or subcutaneous emphysema. The pulmonary insufflation was kept, and the color and the consistency were similar to a fresh corpse after 120 days of conservation. It was possible to perform radiographic procedures, and almost all affections could be greatly mimicked. Megaesophagus and bronchography were easily simulated. Pneumothorax was the most challenging condition to be reproduced, especially in cadavers with some liquid in the thorax. The alcoholic and curing salt solutions are an embalming alternative with low financial and environmental costs and proved to preserve corpses.

Nos dias atuais, métodos alternativos e que não utilizem o formaldeído para conservação de cadáveres devem ser empregados, devido à toxicidade desse agente. Modelos sintéticos são opção de treinamento para o ensino, mas geralmente o preço inviabiliza seu uso na maioria dos países subdesenvolvidos. O objetivo do presente trabalho foi desenvolver um modelo visando ao ensino e pesquisa da radiologia torácica em cadáveres de cães quimicamente preparados. Foram simulados megaesôfago, efusão pleural, pneumotórax e broncografia, além de insuflação pulmonar, em 32 cadáveres de cães, que receberam 150 mL/kg de solução de álcool etílico puro com 5% de glicerina seguido de injeção de 120 mL/kg de solução contendo 20% de cloreto de sódio, 1% de nitrito de sódio e 1% de nitrato de sódio, mantidos sob refrigeração entre 2 e 6 graus, por 30, 60, 90 ou 120 dias (G30, G60, G90, G120). Não houve contaminação, odor pútrido ou enfisema subcutâneo. A insuflação pulmonar foi mantida, e a cor e a consistência foram semelhantes a um cadáver fresco após 120 dias de conservação. Em todos os grupos foi possível realizar os procedimentos radiográficos e quase todas afecções puderam ser grandemente mimetizadas. O megaesôfago e a broncografia foram facilmente simuladas. O pneumotórax foi a afecção mais difícil de ser simulada principalmente nos cadáveres com um pouco de líquido na cavidade torácica. A solução alcoólica e de sal de cura são uma alternativa de embalsamamento com baixo custo financeiro e ambiental e comprovadamente conservam cadáveres.

Asunto(s)

RESUMEN

Objetivo: investigar a literatura relacionada à aplicação e desempenho da Inteligência Artificial (IA) em exames de imagem odontológicos. Revisão de literatura: foram incluídos 70 trabalhos experimentais e revisões sistemáticas da literatura, publicados em inglês, no período entre 2018 e 2021, que analisaram a aplicabilidade da IA na detecção automática de: pontos cefalométricos, lesões de cárie, lesões apicais, perda óssea periodontal, sistemas de implantes, cistos e tumores odontogênicos, osteoporose, sinusite maxilar, terceiros molares e canal mandibular, ateromas em carótida, fratura radicular vertical, osteoartrite em articulação temporomandibular, avaliação de morfologia radicular e numeração dentária. Resultados:58,73% dos trabalhos analisados mostrou acurácia diagnóstica acima de 80% com a utilização de IA. Discussão: A maior limitação encontrada foi em relação à aquisição de amostras em quantidade suficiente para treinamento e teste dos modelos, já que imagens radiográficas têm sua disponibilidade limitada por questões éticas e legais relativas aos pacientes e Instituições. A falta de padronização na segmentação e processamento das imagens foi outro fator a influenciar os resultados obtidos, dificultando comparação e generalização. Apesar disso, diversos estudos apresentaram sugestões ou possíveis aperfeiçoamentos para pesquisas futuras, de forma a reduzir estas limitações. Conclusão: A aplicação da IA no diagnóstico por imagens mostrou-se promissora nas diversas áreas pesquisadas, com desempenhos muito semelhantes ou mesmo superiores, muitas vezes, ao desempenho dos profissionais humanos. Contudo, para a legitimação de sua utilização como parte do fluxo de trabalho na clínica, limitações ainda presentes devem ser superadas, especialmente no treinamento dos algoritmos para obtenção de melhores valores de acurácia.

Aim:to investigate the literature related to the application and performance of Artificial Intelligence (AI) in the analysis of dental imaging. Literature review: 70 experimental studies and systematic literature reviews published in English between 2018 and 2021 were included, which analyzed the applicability of AI models in the automatic detection of the following: cephalometric landmarks, dental caries, periapical diseases, alveolar bone loss, dental implant, odontogenic cysts and tumors, osteoporosis, maxillary sinusitis, third molars and mandibular canal, carotid atheromas, vertical root fracture, osteoarthritis in temporomandibular joint, evaluation of root morphology and numbering of dental elements. Results: 58.73% of the analyzed studies showed diagnostic accuracy above 80%.Discussion:the greatest methodological limitation was the acquisition of samples in sufficient quantity for training and testing phases, since radiographic images are limited to their availability due to ethical and legal issues related to patients and institutions. Lack of standardization in the segmentation and image processing was another factor to influence the results, which was difficult to compare and generalize. Despite this, several studies presented suggestions or possible improvements for future research, in order to reduce the impact of these limitations. Conclusion:the investigation of the applicability of AI in theanalysis of dental radiographic images seems to be still in its early days. The implementation of AI tools as radiologists'auxiliaries in their daily practice depends on overcoming the limitations of current studies and obtaining better diagnostic accuracy indices in future evaluations.

Asunto(s)

RESUMEN

OBJECTIVE: The aim of this study was to compare the capacity of American Thyroid Association and Thyroid Imaging Reporting and Data System developed by the American College of Radiology in predicting malignancy risk of thyroid nodules and to verify which one is better at avoiding unnecessary fine needle aspiration. METHODS: This was a cross-sectional study with 565 thyroid nodules, followed at a tertiary care hospital, in an iodine-replete area. Those were classified as American Thyroid Association and Thyroid Imaging Reporting and Data System developed by the American College of Radiology systems and stratified according to the Bethesda classification of fine needle aspiration. The values of sensibility, specificity, positive predictive value, and negative predictive value accuracy were calculated. Also, the percentage of unnecessary biopsies was presented. RESULTS: The mean age of the individuals was 58.2±13.5 [26-90] years for benign nodules and 41.7±15.6 [23-66] years for malignant nodules (p=0.002). Regarding gender, 92.6% (n=150) of the individuals with benign nodules and 85.7% (n=06) with malignant nodules were females (p=0.601). For American Thyroid Association, 90.9% of sensibility, 51.4% of specificity, 52.6% of accuracy, 10.2% of positive predictive value, and 98.9% of negative predictive value were found. For Thyroid Imaging Reporting and Data System developed by the American College of Radiology, 90.9% of sensibility, 49.7% of specificity, 52.1% of accuracy, 9.9% of positive predictive value, and 98.9% of negative predictive value were found. .Notably, 12.3% of unnecessary fine needle aspiration were found in American Thyroid Association and 44.4% were found in Thyroid Imaging Reporting and Data System developed by the American College of Radiology. CONCLUSION: Both Thyroid Imaging Reporting and Data System developed by the American College of Radiology and American Thyroid Association are able to predict the malignancy risk of thyroid nodules. Thyroid Imaging Reporting and Data System developed by the American College of Radiology was better at avoiding unnecessary fine needle aspiration.

Asunto(s)