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.

How to do and evaluate DWI and DCE-MRI sequences for diabetic foot assessment.

MRI evaluation of the diabetic foot is still a challenge not only from an interpretative but also from a technical point of view. The incorporation of advanced sequences such as diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI into standard protocols for diabetic foot assessment could aid radiologists in differentiating between neuropathic osteoarthropathy (Charcot's foot) and osteomyelitis. This distinction is crucial as both conditions can coexist in diabetic patients, and they require markedly different clinical management and have distinct prognoses. Over the past decade, several studies have explored the effectiveness of DWI and dynamic contrast-enhanced MRI (DCE-MRI) in distinguishing between septic and reactive bone marrow, as well as soft tissue involvement in diabetic patients, yielding promising results. DWI, without the need for exogenous contrast, can provide insights into the cellularity of bone marrow and soft tissues. DCE-MRI allows for a more precise evaluation of soft tissue and bone marrow perfusion compared to conventional post-gadolinium imaging. The data obtained from these sequences will complement the traditional MRI approach in assessing the diabetic foot. The objective of this review is to familiarize readers with the fundamental concepts of DWI and DCE-MRI, including technical adjustments and practical tips for image interpretation in diabetic foot cases.

Quiste óseo aneurismático: Presentación de un caso / Aneurysmal Bone Cyst: Case Report

El quiste óseo aneurismático es una lesión expansiva, de pared fina, de contenido quístico, y con niveles líquido-líquido. Su etiología es incierta, suele asociarse a traumatismo, probablemente debido a obstrucción venosa o a la formación de fístulas que se producen tras la contusión. Los pacientes refieren dolor, que puede ser de comienzo insidioso o abrupto debido a una fractura patológica. Los quistes óseos aneurismáticos se clasifican, según su etiología, en primarios o secundarios a una lesión subyacente, como displasia fibrosa, condroblastoma, tumor de células gigantes u osteosarcoma. Se presenta el caso de una paciente que consulta por dolor localizado en la región plantar izquierda, no asociado a traumas, a quien se le diagnosticó un quiste óseo aneurismático, con hallazgos definitivos en resonancia magnética (RM) y comprobación histológica.

The aneurysmal bone cyst is an expansive, thin-wall lesion with cystic content, and with the presence of liquid-liquid levels. Its etiology is uncertain, usually associated with trauma, probably due to a venous obstruction or the formation of fistulas that are produced by contusion. Patients report pain, which may be of insidious onset or abrupt onset due to a pathological fracture. Aneurysmal bone cysts are classified according to their etiology in primary, or secondary to an underlying lesion, such as fibrous dysplasia, chondroblastoma, giant cell tumor or osteosarcoma. We present the case of a patient who consulted for pain located in left plantar region, not associated with trauma, who was diagnosed with an aneurysmal bone cyst, with definitive magnetic resonance findings and histological verification.

Surface primary bone tumors: Systematic approach and differential diagnosis.

Surface primary bone tumors may appear similar to their intramedullary counterpart, but because they are rare, they may pose diagnostic challenges when showing different characteristics compared to their intramedullary counterpart. It is important for radiologists to recognize the imaging findings for various uncommon surface primary bone tumors, which may help to reduce the differential diagnosis or to lead to a specific diagnosis. Radiography is typically used for first-line imaging. If necessary, it is followed by CT or MRI for evaluation and characterization of surface bone tumors. The aim of this article is to review the imaging findings and differential diagnosis for surface primary bone tumors.