RESUMEN
Radiomics refers to the extraction of mineable data from medical imaging and has been applied within oncology to improve diagnosis, prognostication, and clinical decision support, with the goal of delivering precision medicine. The authors provide a practical approach for successfully implementing a radiomic workflow from planning and conceptualization through manuscript writing. Applications in oncology typically are either classification tasks that involve computing the probability of a sample belonging to a category, such as benign versus malignant, or prediction of clinical events with a time-to-event analysis, such as overall survival. The radiomic workflow is multidisciplinary, involving radiologists and data and imaging scientists, and follows a stepwise process involving tumor segmentation, image preprocessing, feature extraction, model development, and validation. Images are curated and processed before segmentation, which can be performed on tumors, tumor subregions, or peritumoral zones. Extracted features typically describe the distribution of signal intensities and spatial relationship of pixels within a region of interest. To improve model performance and reduce overfitting, redundant and nonreproducible features are removed. Validation is essential to estimate model performance in new data and can be performed iteratively on samples of the dataset (cross-validation) or on a separate hold-out dataset by using internal or external data. A variety of noncommercial and commercial radiomic software applications can be used. Guidelines and artificial intelligence checklists are useful when planning and writing up radiomic studies. Although interest in the field continues to grow, radiologists should be familiar with potential pitfalls to ensure that meaningful conclusions can be drawn. Online supplemental material is available for this article. Published under a CC BY 4.0 license.
Asunto(s)
Inteligencia Artificial , Procesamiento de Imagen Asistido por Computador , Diagnóstico por Imagen , Humanos , Oncología Médica , RadiografíaRESUMEN
BACKGROUND: The coexistence of joint hypermobility syndrome (JHS) and spondyloarthropathy (SpA) presents a challenging clinical conundrum due to the contradictory clinical signs that may be present. Classic features such as restricted spinal movement or early morning back stiffness may not be present. Timely diagnosis and appropriate management of these patients are difficult as they tend to have lower scores on validated objective measures. METHODS: We performed a medical records review study to identify patients with both JHS and SpA who had presented to the Leicester Spondyloarthropathy clinic. Patients were diagnosed with axial SpA if they met the Assessment of SpondyloArthritis international Society classification criteria. Their imaging was reviewed by a consultant musculoskeletal radiologist. RESULTS: Four cases were identified from the patient database (female; average age, 37.5 years). All patients presented with lower back pain or sacroiliac joint pain but preserved spinal movement with a negative Schober's test. Two had a history of symptoms for more than 10 years. All had a Beighton score of greater than 6. Three of the patients were HLA positive, and 3 had a positive family history. All patients thus far have had their symptoms adequately controlled on nonsteroidal anti-inflammatory drugs and physiotherapy. CONCLUSIONS: The coexistence of JHS and SpA is rare but important to recognize. These patients are difficult to diagnose as they may present late because of preserved spinal movements. It is unclear whether the preserved flexibility masks the true extent of disease or whether clinically they represent a less severe disease phenotype.
Asunto(s)
Inestabilidad de la Articulación/congénito , Imagen por Resonancia Magnética/métodos , Espondiloartropatías/diagnóstico , Adolescente , Adulto , Artralgia , Dolor de Espalda/diagnóstico , Dolor de Espalda/etiología , Femenino , Humanos , Inestabilidad de la Articulación/diagnóstico , Masculino , Persona de Mediana Edad , Fenotipo , Espondiloartritis/diagnósticoAsunto(s)
Imagen por Resonancia Magnética , Terapia Neoadyuvante , Neoplasias del Recto , Humanos , Neoplasias del Recto/diagnóstico por imagen , Neoplasias del Recto/terapia , Neoplasias del Recto/tratamiento farmacológico , Neoplasias del Recto/patología , Terapia Neoadyuvante/métodos , Imagen por Resonancia Magnética/métodos , Masculino , Femenino , Resultado del Tratamiento , Persona de Mediana Edad , AncianoRESUMEN
Rectal tumors extending beyond the total mesorectal excision (TME) plane (beyond-TME) require particular multidisciplinary expertise and oncologic considerations when planning treatment. Imaging is used at all stages of the pathway, such as local tumor staging/restaging, creating an imaging-based "roadmap" to plan surgery for optimal tumor clearance, identifying treatment-related complications, which may be suitable for radiology-guided intervention, and to detect recurrent or metastatic disease, which may be suitable for radiology-guided ablative therapies. Beyond-TME and exenterative surgery have gained acceptance as potentially curative procedures for advanced tumors. Understanding the role, techniques, and pitfalls of current imaging techniques is important for both radiologists involved in the treatment of these patients and general radiologists who may encounter patients undergoing surveillance or patients presenting with surgical complications or intercurrent abdominal pathology. This review aims to outline the current and emerging roles of imaging in patients with beyond-TME and recurrent rectal malignancy, focusing on practical tips for image interpretation and surgical planning in the beyond-TME setting. Keywords: Abdomen/GI, Rectum, Oncology © RSNA, 2024.