Lung cancer stands as the primary cause of cancer-related mortality, with non-small cell lung cancer (NSCLC) accounting for 85 % of cases [1,2]. In addition to the conventional pattern of lung cancer invasion, typically involving myofibroblast stroma, lymphovascular or pleural invasion, the spread through air spaces (STAS) has been officially defined as an unconventional mechanism [3–5]. Recently, the 9th edition of the TNM classification of lung cancer proposed to introduce STAS as a histologic…
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.
-
Robustness of radiomic features in photon-counting CT: Impact of radiation dose and virtual monoenergetic reconstructions compared to dual-energy CT
To evaluate the impact of Virtual Monoenergetic Image (VMI) reconstructions and radiation dose on radiomic feature reproducibility in photon-counting CT (PCCT) and compare its performance with dual-energy CT (DE-CT).
-
Changes in microvessel density in normal-appearing white matter in relation to cerebral small vessel disease: A cohort study
Cerebral small vessel disease (cSVD)-related white matter hyperintensities of presumed vascular origin (WMH) are a common occurrence on brain imaging with uncertain effects on normal-appearing white matter (WM). cSVD is an arteriopathy affecting cerebral arteries, arterioles, venules, and capillaries [1]. A common manifestation of cSVD in magnetic resonance imaging (MRI) are WMH [2–5], which are linked to a plethora of other diseases [6–8]. Areas of severe WMH themselves exhibit axonal loss, dem…
-
Earlier discharge from follow-up for lung cancer screening using artificial intelligence in computed tomography
Lung cancer is the leading cause of cancer death worldwide. Effective screening and early detection are critical in reducing mortality. Artificial intelligence (AI) methods have been proved useful in the diagnosis of pulmonary nodules and early diagnosis of lung cancer. However, the implementation of lung cancer screening and frequent detection of incidental pulmonary nodules lead to more computed tomography scans resulting in increased costs. Therefore, determining the cost-effectiveness of AI …
-
Interpretable combined models for predicting treatment response and hematologic toxicity in locally advanced gastric cancer treated with PD-1 blockade and neoadjuvant chemotherapy
Gastric cancer (GC) remained a significant global health concern, which ranked fifth in terms of incidence and fourth in mortality globally among malignant tumors [1]. In China, the incidence and mortality of gastric cancer ranked second among malignant tumors, and the incidence rate is increasing [2]. Surgery remains the main treatment for GC, but radical gastrectomy is only suitable for early-stage GC. Most GC patients are diagnosed with locally advanced gastric cancer (LAGC), with high recurr…
-
Deep learning model using CT images for longitudinal prediction of benign and malignant ground-glass nodules
Lung cancer continues to be the foremost cause of global cancer deaths, particularly in China [1,2]. Early-stage lung cancer often presents as small pulmonary nodules. Improvements in high-resolution computed tomography (CT) and the broad adoption of low-dose CT screening have significantly enhanced the detection rates of GGNs[3,4]. GGNs exhibit a higher likelihood of malignancy than solid nodules[5,6]; nonetheless, a substantial proportion are histopathologically confirmed as benign[7]. Clinica…
-
The role of neuroimaging in brain death diagnosis: a review of radiological protocols and the need for standardization
For hundreds of years, the death of an individual has been identified with the permanent cessation of breathing and cardiac activity. The first clinical definition of brain death, described as coma, dates to 1959, when Mollaret and Goulon reported a personal experience of 23 patients in deep coma, a reactive without brainstem function and subjected to artificial ventilation [1]. After the first cardiac transplant performed by Christian Barnard in 1967, the culture of organ donation began to be p…
-
Multimodal deep learning for predicting unsuccessful recanalization in refractory large vessel occlusion
Acute ischemic stroke due to large vessel occlusion (LVO) is a severe neurological emergency requiring fast and effective treatment. Endovascular therapy (EVT) is currently the most effective treatment, achieving successful reperfusion in up to 80–85 % of cases [1–3]. However, in patients with intracranial atherosclerotic disease (ICAD), complete recanalization is more difficult to achieve without rescue treatments such as angioplasty and stenting, leading to worse outcomes [4]. Independently fr…
-
Radiologists and Billing: Accountability Without Control
Looking for an enlightened approach to billing isn’t easy amid a sea of third-party payor excuses, absurd addendum requests and CT headers seemingly etched in stone.