This study aimed to evaluate the potential of time-dependent diffusion magnetic resonance imaging (td-dMRI) quantitative parameters in differentiating lymph node metastasis status in breast cancer patients.
We scan the top radiology sources so you don’t have to.
From AI breakthroughs to imaging trends, we serve up real-time radiology insights.
-
Peritumoral radiomics indicate a gradient transition between tumours and their surrounding healthy tissue: A proof-of-concept analysis
Renal tumors represent a heterogeneous group of lesions with varying malignant potential, prognoses, and treatment requirements [1]. Accurate preoperative characterization of these tumors is critical to guide management strategies, especially given the growing emphasis on nephron-sparing surgery and personalized care [2]. Whilecontrast-enhanced computed tomography (CT)remains the mainstay of imaging for renal masses, its diagnostic accuracy in reliably distinguishing between histologic subtypes …
-
Association of breastfeeding duration with longitudinal changes in vertebral bone marrow, paraspinal muscle composition, and metabolic parameters in premenopausal women over five years
To investigate the association between breastfeeding duration and longitudinal changes in MRI-based proton-density fat fraction (PDFF) of vertebral bone marrow, paraspinal musculature (PSM), and metabolic parameters in premenopausal women.
-
LG-nnU-net for multilabel anal sphincter segmentation on MRI: quantitative evaluation in patients with anal fistula
To develop and evaluate a novel deep learning–based segmentation framework (LG-nnU-net) for multilabel segmentation of anal sphincter substructures on MRI, aimed at providing robust quantitative anatomical information without implying operative validation for clinical classification improvement.
-
Enhanced osteoporosis screening via multi-output deep learning: Segmentation and classification of metacarpal radiographs
Osteoporosis screening from radiographic images has traditionally relied on isolated methods that fail to capture the complex interplay between structural segmentation and diagnostic classification. This paper introduce OMO-Net, a novel multi-output deep learning architecture that simultaneously performs segmentation and classification on metacarpal radiographs to accurately detect osteoporosis. Unlike conventional approaches, OMO-Net integrates a ResNet-50–based feature extractor with dedicated…
-
MRI has limited accuracy in diagnosing complex regional pain syndrome Type 1 − a systematic review of the literature
Complex regional pain syndrome (CRPS) is a chronic pain disorder that typically develops after an inciting event, such as trauma or surgery [1]. It is characterized by disproportionate pain that persists over time and usually affects the distal extremities [1]. CRPS presents with a range of sensory, motor, vasomotor, sudomotor, and trophic signs and symptoms, that exceed the level that would be expected following the precipitating event [2]. Current research suggests that CRPS is a multi-mechani…
-
Dual-Phase deep learning Enhances detection of incidental small pancreatic cystic lesion (0.5–3 cm) on Contrast-Enhanced CT
With the widespread use of advanced imaging equipment, an increasing number of pancreatic cystic lesions (PCLs), especially subcentimeter PCLs, are incidentally detected[1]. The reported prevalence of incidental PCLs on contrast-enhanced CT ranges from 2.1 % to 5.4 %[2–5]. Study has revealed that among patients with PCLs, over half presented with a cyst no larger than 3 cm[6]. A systematic review has found that 60 % of incidental PCLs with sufficient data to define the biological nature were muc…
-
Multi-Sequence MRI radiomics model for discrimination of recurrence and pseudoprogression in gliomas
Object.The clinical treatment strategies for glioma recurrence and pseudoprogression are completely different. Precise differentiation between these conditions is essential and radiomics serves as a mature solution to bridge this gap.
-
Multi-modal deep learning for predicting functional outcomes in intracerebral hemorrhage using 3D CT and clinical data
Intracerebral hemorrhage (ICH) is a critical neurological condition with a 30-day mortality rate as high as 35–52 % [1]. Among survivors, only a small proportion regain functional independence, placing a substantial economic and caregiving burden on families and society [2]. Therefore, accurately predicting long-term functional outcomes in the early stages of the disease is crucial for guiding individualized treatment and optimizing the allocation of medical resources [3].
-
Assessing deep learning artificial intelligence support for detecting elbow fractures in the pediatric emergency department
Elbow fractures are among the most common pediatric injuries, accounting for 15–20 % of all fractures in children [1,2]. Diagnosing these fractures can be particularly challenging due to the complex radiographic appearance of the developing elbow, which features multiple ossification centers that emerge at different stages [3,4]. As a result, identifying fractures often requires recognizing indirect signs, such as the fat pad sign, which suggests joint effusion [5–7]. Accurate diagnosis is criti…