RESUMO
INTRODUCTION AND IMPORTANCE: Congenital transmesenteric hernia is a rare form of hernia and intestinal obstruction. Autopsy studies report an incidence of 0.2-0.9 % of internal hernias, causing intestinal obstruction in 4.1 % of all cases. CASE PRESENTATION: A 35-year-old female patient, with no surgical history, presented with severe abdominal pain in the right hemiabdomen, nausea, and vomiting. She was initially unsuccessfully treated for gastritis. Upon admission to our unit, she had stable vital signs but severe abdominal pain. An acute abdomen was diagnosed, and a diagnostic laparoscopy converted to open surgery revealed an internal transmesenteric hernia with partial intestinal obstruction. A right hemicolectomy with ileotransverse anastomosis was performed. CLINICAL DISCUSSION: Diagnosing this condition is challenging due to nonspecific symptoms and signs, and radiological investigations may not provide sufficient information. The clinical features of a transmesenteric hernia can mimic more common causes of acute abdominal pain, such as appendicitis, complicating early identification. Computed tomography (CT) is the most useful imaging modality, but even with CT, the diagnosis can be difficult due to the rarity of the condition and the lack of specific signs. CONCLUSION: Early intervention and surgical correction in this case were crucial to preventing mortality associated with internal hernias. EVIDENCE BASED MEDICINE RANKING: Level IV.
RESUMO
RATIONALE AND OBJECTIVES: Large Language Models can capture the context of radiological reports, offering high accuracy in detecting unexpected findings. We aim to fine-tune a Robustly Optimized BERT Pretraining Approach (RoBERTa) model for the automatic detection of unexpected findings in radiology reports to assist radiologists in this relevant task. Second, we compared the performance of RoBERTa with classical convolutional neural network (CNN) and with GPT4 for this goal. MATERIALS AND METHODS: For this study, a dataset consisting of 44,631 radiological reports for training and 5293 for the initial test set was used. A smaller subset comprising 100 reports was utilized for the comparative test set. The complete dataset was obtained from our institution's Radiology Information System, including reports from various dates, examinations, genders, ages, etc. For the study's methodology, we evaluated two Large Language Models, specifically performing fine-tuning on RoBERTa and developing a prompt for ChatGPT. Furthermore, extending previous studies, we included a CNN in our comparison. RESULTS: The results indicate an accuracy of 86.15% in the initial test set using the RoBERTa model. Regarding the comparative test set, RoBERTa achieves an accuracy of 79%, ChatGPT 64%, and the CNN 49%. Notably, RoBERTa outperforms the other systems by 30% and 15%, respectively. CONCLUSION: Fine-tuned RoBERTa model can accurately detect unexpected findings in radiology reports outperforming the capability of CNN and ChatGPT for this task.
RESUMO
Nowadays, the use of advanced MRI sequences such as Diffusion-Weighted Imaging (DWI) or Perfusion-Weighted Imaging (PWI) in the field of musculoskeletal (MSK) radiology remains limited compared to other anatomical regions and subspecialties. Several reasons underpin this, primarily technical challenges, and a longstanding reliance on conventional and morphological evaluations of soft tissue and bone lesions. Experienced radiologists often assert that these advanced sequences don't offer added diagnostic value, claiming that a morphological approach suffices. However, in our opinion, the role of these advanced MRI sequences extends beyond merely naming an MSK lesion. In this commentary, we elucidate how these sequences can aid radiologists in various scenarios, from determining patient prognosis and tracking treatment progress to enhancing clinical-radiological correlations or guiding less experienced radiologists in evaluating soft tissues or bone tumors.
RESUMO
INTRODUCTION AND IMPORTANCE: Polybrachysyndactyly is the combination of malformations and is considered a congenital anomaly that is very difficult to treat. In addition to presenting as a disabling entity, it is a reason for little acceptance under the aesthetic standards established by society. CASE PRESENTATION: 6-year-old male patient with polybrachysyndactyly in all 4 extremities. The parents rejected surgery at a younger age, however, the social/aesthetic pressure exerted on the patient at school and the child's inability to perform activities in a common way, motivated them to make a new decision. CLINICAL DISCUSSION: Different surgical techniques were used on all four extremities. A soft tissue technique was performed on the pinkies of both feet and ray cuts to correct syndactyly of both thumbs of the feet and middle fingers of both hands, and excision. Extirpations were obtained: one thumb of the right foot, one thumb of the left foot and two middle fingers (one of each hand). He was discharged after recovery from surgery. CONCLUSION: Cases of polysyndactyly are considered extremely rare, the first thing to evaluate is the presence of other signs that could be part of a syndromic association in order to proceed with surgical intervention that allows the patient to lead a life as far away from aesthetic stigmas that could damage his mental health. EVIDENCE BASED MEDICINE RANKING: Level IV.
RESUMO
BACKGROUND AND OBJECTIVES: In the last decade, there has been a growing interest in applying artificial intelligence (AI) systems to breast cancer assessment, including breast density evaluation. However, few models have been developed to integrate textual mammographic reports and mammographic images. Our aims are (1) to generate a natural language processing (NLP)-based AI system, (2) to evaluate an external image-based software, and (3) to develop a multimodal system, using the late fusion approach, by integrating image and text inferences for the automatic classification of breast density according to the American College of Radiology (ACR) guidelines in mammograms and radiological reports. METHODS: We first compared different NLP models, three based on n-gram term frequency - inverse document frequency and two transformer-based architectures, using 1533 unstructured mammogram reports as a training set and 303 reports as a test set. Subsequently, we evaluated an external image-based software using 303 mammogram images. Finally, we assessed our multimodal system taking into account both text and mammogram images. RESULTS: Our best NLP model achieved 88 % accuracy, while the external software and the multimodal system achieved 75 % and 80 % accuracy, respectively, in classifying ACR breast densities. CONCLUSION: Although our multimodal system outperforms the image-based tool, it currently does not improve the results offered by the NLP model for ACR breast density classification. Nevertheless, the promising results observed here open the possibility to more comprehensive studies regarding the utilization of multimodal tools in the assessment of breast density.
RESUMO
Dual-energy CT (DECT) imaging has broadened the potential of CT imaging by offering multiple postprocessing datasets with a single acquisition at more than one energy level. DECT shows profound capabilities to improve diagnosis based on its superior material differentiation and its quantitative value. However, the potential of dual-energy imaging remains relatively untapped, possibly due to its intricate workflow and the intrinsic technical limitations of DECT. Knowing the clinical advantages of dual-energy imaging and recognizing its limitations and pitfalls is necessary for an appropriate clinical use. The aims of this paper are to review the physical and technical bases of DECT acquisition and analysis, to discuss the advantages and limitations of DECT in different clinical scenarios, to review the technical constraints in material labeling and quantification, and to evaluate the cutting-edge applications of DECT imaging, including artificial intelligence, qualitative and quantitative imaging biomarkers, and DECT-derived radiomics and radiogenomics.
RESUMO
MRI plays a crucial role in assessment of patients with muscle injuries. The healing process of these injuries has been studied in depth from the pathophysiologic and histologic points of view and divided into destruction, repair, and remodeling phases, but the MRI findings of these phases have not been fully described, to our knowledge. On the basis of results from 310 MRI studies, including both basal and follow-up studies, in 128 athletes with muscle tears including their clinical evolution, the authors review MRI findings in muscle healing and propose a practical imaging classification based on morphology and signal intensity that correlates with histologic changes. The proposed phases, which can overlap, are destruction (phase 1), showing myoconnective tissue discontinuity and featherlike edema; repair (phase 2), showing filling in of the connective tissue gaps by a hypertrophic immature scar; and remodeling (phase 3), showing scar maturation and regression of the edema. A final healed stage can be identified with MRI, which is characterized by persistence of a slight fusiform thickening of the connective tissue. This information can be obtained from a truncated MRI protocol with three acquisitions, preferably performed with a 3-T magnet. During MRI follow-up of muscle injuries, other important features to be assessed are changes in muscle edema and specific warning signs, such as persistent intermuscular edema, new connective tear, and scar rupture. An understanding of the MRI appearance of normal and abnormal muscle healing and warning signs, along with cooperation with a multidisciplinary team, enable optimization of return to play for the injured athlete. ©RSNA, 2024 See the invited commentary by Flores in this issue.
Assuntos
Traumatismos em Atletas , Imageamento por Ressonância Magnética , Músculo Esquelético , Cicatrização , Humanos , Imageamento por Ressonância Magnética/métodos , Traumatismos em Atletas/diagnóstico por imagem , Traumatismos em Atletas/classificação , Músculo Esquelético/diagnóstico por imagem , Músculo Esquelético/lesões , MasculinoRESUMO
This paper presents the implementation of two automated text classification systems for prostate cancer findings based on the PI-RADS criteria. Specifically, a traditional machine learning model using XGBoost and a language model-based approach using RoBERTa were employed. The study focused on Spanish-language radiological MRI prostate reports, which has not been explored before. The results demonstrate that the RoBERTa model outperforms the XGBoost model, although both achieve promising results. Furthermore, the best-performing system was integrated into the radiological company's information systems as an API, operating in a real-world environment.
RESUMO
Despite not being the first imaging modality for thyroid gland assessment, Magnetic Resonance Imaging (MRI), thanks to its optimal tissue contrast and spatial resolution, has provided some advancements in detecting and characterizing thyroid abnormalities. Recent research has been focused on improving MRI sequences and employing advanced techniques for a more comprehensive understanding of thyroid pathology. Although not yet standard practice, advanced MRI sequences have shown high accuracy in preliminary studies, correlating well with histopathological results. They particularly show promise in determining malignancy risk in thyroid lesions, which may reduce the need for invasive procedures like biopsies. In this line, functional MRI sequences like Diffusion Weighted Imaging (DWI), Dynamic Contrast-Enhanced MRI (DCE-MRI), and Arterial Spin Labeling (ASL) have demonstrated their potential usefulness in evaluating both diffuse thyroid conditions and focal lesions. Multicompartmental DWI models, such as Intravoxel Incoherent Motion (IVIM) and Diffusion Kurtosis Imaging (DKI), and novel methods like Amide Proton Transfer (APT) imaging or artificial intelligence (AI)-based analyses are being explored for their potential valuable insights into thyroid diseases. This manuscript reviews the critical physical principles and technical requirements for optimal functional MRI sequences of the thyroid and assesses the clinical utility of each technique. It also considers future prospects in the context of advanced MR thyroid imaging and analyzes the current role of advanced MRI sequences in routine practice.
Assuntos
Imageamento por Ressonância Magnética , Humanos , Imageamento por Ressonância Magnética/métodos , Neoplasias da Glândula Tireoide/diagnóstico por imagem , Doenças da Glândula Tireoide/diagnóstico por imagem , Meios de ContrasteRESUMO
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.
Assuntos
Inteligência Artificial , Responsabilidade Legal , Radiologia , Humanos , Radiologia/legislação & jurisprudência , Radiologia/ética , Inteligência Artificial/legislação & jurisprudência , Erros de Diagnóstico/legislação & jurisprudência , Erros de Diagnóstico/prevenção & controle , Radiologistas/legislação & jurisprudênciaRESUMO
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.
Assuntos
Estudos de Viabilidade , Imageamento por Ressonância Magnética , Processamento de Linguagem Natural , Redes Neurais de Computação , Humanos , Sistemas de Informação em Radiologia , Joelho/diagnóstico por imagem , Estudos RetrospectivosRESUMO
Susceptibility-weighted imaging (SWI) has become a standard component of most brain MRI protocols. While traditionally used for detecting and characterising brain hemorrhages typically associated with stroke or trauma, SWI has also shown promising results in glioma assessment. Numerous studies have highlighted SWI's role in differentiating gliomas from other brain lesions, such as primary central nervous system lymphomas or metastases. Additionally, SWI aids radiologists in non-invasively grading gliomas and predicting their phenotypic profiles. Various researchers have suggested incorporating SWI as an adjunct sequence for predicting treatment response and for post-treatment monitoring. A significant focus of these studies is on the detection of intratumoural susceptibility signals (ITSSs) in gliomas, which are indicative of microhemorrhages and vessels within the tumour. The quantity, distribution, and characteristics of these ITSSs can provide radiologists with more precise information for evaluating and characterising gliomas. Furthermore, the potential benefits and added value of performing SWI after the administration of gadolinium-based contrast agents (GBCAs) have been explored. This review offers a comprehensive, educational, and practical overview of the potential applications and future directions of SWI in the context of glioma assessment. CLINICAL RELEVANCE STATEMENT: SWI has proven effective in evaluating gliomas, especially through assessing intratumoural susceptibility signal changes, and is becoming a promising, easily integrated tool in MRI protocols for both pre- and post-treatment assessments. KEY POINTS: ⢠Susceptibility-weighted imaging is the most sensitive sequence for detecting blood and calcium inside brain lesions. ⢠This sequence, acquired with and without gadolinium, helps with glioma diagnosis, characterisation, and grading through the detection of intratumoural susceptibility signals. ⢠There are ongoing challenges that must be faced to clarify the role of susceptibility-weighted imaging for glioma assessment.
RESUMO
Noninvasive differential diagnosis of brain tumors is currently based on the assessment of magnetic resonance imaging (MRI) coupled with dynamic susceptibility contrast (DSC). However, a definitive diagnosis often requires neurosurgical interventions that compromise patients' quality of life. We apply deep learning on DSC images from histology-confirmed patients with glioblastoma, metastasis, or lymphoma. The convolutional neural network trained on â¼50,000 voxels from 40 patients provides intratumor probability maps that yield clinical-grade diagnosis. Performance is tested in 400 additional cases and an external validation cohort of 128 patients. The tool reaches a three-way accuracy of 0.78, superior to the conventional MRI metrics cerebral blood volume (0.55) and percentage of signal recovery (0.59), showing high value as a support diagnostic tool. Our open-access software, Diagnosis In Susceptibility Contrast Enhancing Regions for Neuro-oncology (DISCERN), demonstrates its potential in aiding medical decisions for brain tumor diagnosis using standard-of-care MRI.
Assuntos
Neoplasias Encefálicas , Aprendizado Profundo , Humanos , Qualidade de Vida , Neoplasias Encefálicas/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos , PerfusãoRESUMO
Infective endocarditis (IE) is a complex multisystemic disease resulting from infection of the endocardium, the prosthetic valves, or an implantable cardiac electronic device. The clinical presentation of patients with IE varies, ranging from acute and rapidly progressive symptoms to a more chronic disease onset. Because of its severe morbidity and mortality rates, it is necessary for radiologists to maintain a high degree of suspicion in evaluation of patients for IE. Modified Duke criteria are used to classify cases as "definite IE," "possible IE," or "rejected IE." However, these criteria are limited in characterizing definite IE in clinical practice. The use of advanced imaging techniques such as cardiac CT and nuclear imaging has increased the accuracy of these criteria and has allowed possible IE to be reclassified as definite IE in up to 90% of cases. Cardiac CT may be the best choice when there is high clinical suspicion for IE that has not been confirmed with other imaging techniques, in cases of IE and perivalvular involvement, and for preoperative treatment planning or excluding concomitant coronary artery disease. Nuclear imaging may have a complementary role in prosthetic IE. The main imaging findings in IE are classified according to the site of involvement as valvular (eg, abnormal growths [ie, "vegetations"], leaflet perforations, or pseudoaneurysms), perivalvular (eg, pseudoaneurysms, abscesses, fistulas, or prosthetic dehiscence), or extracardiac embolic phenomena. The differential diagnosis of IE includes evaluation for thrombus, pannus, nonbacterial thrombotic endocarditis, Lambl excrescences, papillary fibroelastoma, and caseous necrosis of the mitral valve. The location of the lesion relative to the surface of the valve, the presence of a stalk, and calcification or enhancement at contrast-enhanced imaging may offer useful clues for their differentiation. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.
Assuntos
Falso Aneurisma , Endocardite Bacteriana , Endocardite , Humanos , Endocardite Bacteriana/diagnóstico , Endocardite Bacteriana/microbiologia , Endocardite Bacteriana/patologia , Endocardite/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos , Imagem MultimodalRESUMO
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.
Assuntos
Inteligência Artificial , Radiologia , Humanos , Radiologia/métodos , Radiologistas , Fluxo de Trabalho , Carga de TrabalhoRESUMO
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.
Assuntos
Processamento de Linguagem Natural , Radiologia , Humanos , Estudos Retrospectivos , Idioma , Imageamento por Ressonância MagnéticaRESUMO
Introducción: La anatomía hepática siempre ha sido un reto por su complejidad y variabilidad. En los últimos años, el abaratamiento de los costes ha permitido la generación de modelos 3D individualizados para cada paciente que pueden facilitar el abordaje quirúrgico de las lesiones. El objetivo principal fue determinar la utilidad del modelado 3D preoperatorio para la planificación quirúrgica en pacientes con lesiones hepáticas. Métodos: Se trata de un estudio de casos de 38 pacientes intervenidos por lesiones hepáticas múltiples ocupantes de espacio, en el cual, en un grupo seleccionado, en 19 pacientes se utilizó un modelo impreso 3D para planificar la cirugía (grupo 3D) y el otro grupo sin el modelo impreso 3D (grupo control). Resultados: Se observó una diferencia de medias significativa en el número de lesiones; mayor en el grupo 3D al realizar el test de Wilcoxon (p < 0,001) y un mayor número de casos con afectación vascular en este mismo grupo al realizar Chi cuadrado Pearson (p = 0,008). El resto de variables no mostraron diferencias estadísticamente significativas. A pesar de esto, la mortalidad se redujo a 0 cuando se usan modelos impresos en 3D. Conclusión: La impresión 3D permite planear, de manera más precisa, cirugías complejas del hígado, ayuda a la inclusión y exclusión de los pacientes para la cirugía, disminuyendo el tiempo de la sala de operaciones, la posterior hospitalización y las complicaciones quirúrgicas.
Introduction: Liver anatomy has always been a challenge due to its complexity and variability. In recent years, lower costs has allowed the generation of individualized 3D models for each patient, which can facilitate the surgical approach to liver lesions. The main objective was to determine usefulness of preoperative 3D modeling for surgical planning in patients with liver lesions. Methods: Quasi-experimental before-after study. 19 cases were included in which surgery was planned using a 3D printed model (13 bilobar hepatectomies, 3 of them with vascular involvement, and 6 unilobar hepatectomies, 1 of them with vascular involvement), and another 19 cases whose planning was carried out without a 3D printed model (7 bilobar segmental hepatic resections and 12 unilobar segmental resections. None of these cases had vascular involvement). Results: A significant difference in mean lesion count was observed, higher in the group of cases when performing the Wilcoxon test (p < 0.001), and a higher number of cases with vascular involvement in the same group when performing the Pearson chi-square test (p = 0.008). The rest of the variables did not show statistically significant differences. Despite this, mortality was reduced to 0 when 3D printed models were used. Conclusion: 3D printing allows for more precise planning of complex liver surgeries, helps with the inclusion and exclusion of patients for surgery, reduces operating room time, postoperative hospitalization, and surgical complications.