In acute ischemic stroke, there is uncertainty regarding the benefit and risk of administering intravenous alteplase before endovascular thrombectomy.

Pancreatic ductal adenocarcinoma (PDAC), the most deadly solid malignancy, is typically detected late and at an inoperable stage. Early or incidental detection is associated with prolonged survival, but screening asymptomatic individuals for PDAC using a single test remains unfeasible due to the low prevalence and potential harms of false positives. Non-contrast computed tomography (CT), routinely performed for clinical indications, offers the potential for large-scale screening, however, identification of PDAC using non-contrast CT has long been considered impossible. Here, we develop a deep learning approach, pancreatic cancer detection with artificial intelligence (PANDA), that can detect and classify pancreatic lesions with high accuracy via non-contrast CT. PANDA is trained on a dataset of 3,208 patients from a single center. PANDA achieves an area under the receiver operating characteristic curve (AUC) of 0.986–0.996 for lesion detection in a multicenter validation involving 6,239 patients across 10 centers, outperforms the mean radiologist performance by 34.1% in sensitivity and 6.3% in specificity for PDAC identification, and achieves a sensitivity of 92.9% and specificity of 99.9% for lesion detection in a real-world multi-scenario validation consisting of 20,530 consecutive patients. Notably, PANDA utilized with non-contrast CT shows non-inferiority to radiology reports (using contrast-enhanced CT) in the differentiation of common pancreatic lesion subtypes. PANDA could potentially serve as a new tool for large-scale pancreatic cancer screening.

Background: Prior studies have investigated the clinical and imaging factors for hemorrhagic transformation (HT), especially symptomatic intracranial hemorrhage (sICH); however, whether alteplase increases the risk of HT after endovascular thrombectomy (EVT) is unknown. This study aimed to assess clinical and imaging features associated with HT, sICH, and parenchymal hematoma (PH) in patients with acute ischemic stroke after EVT, with and without intravenous alteplase in DIRECT-MT (Direct Intraarterial Thrombectomy to Revascularize Acute Ischemic Stroke Patients with Large Vessel Occlusion Efficiently in Chinese Tertiary Hospitals: a Multicenter Randomized Clinical Trial). Methods: The DIRECT-MT trial is a randomized trial of EVT alone versus intravenous thrombolysis combined with EVT. HT, sICH, and PH was evaluated on follow-up computed tomography. Multivariable ordinal logistic regression analysis was used to test the association of stepwise selected determinants with HT, sICH, and PH. Results: In total, 633 patients were analyzed; 261 (41.2%) had HT; 34 (5.4%) had sICH; and 85 (13.4%) had PH. The median age was 69, and 56.7% were men. The median National Institutes of Health Stroke Scale score was 18, and 320 patients were in combination-therapy group. Symptomatic intracranial hemorrhage was associated with higher baseline National Institutes of Health Stroke Scale score (adjusted odds ratio [OR], 1.06 [95% CI, 1.10–1.12]) and higher glucose level at hospital arrival (adjusted OR, 1.14 [95% CI, 1.00–1.29]). No association was found between alteplase treatment and HT, sICH, or PH. The independent predictor of sICH was higher baseline National Institutes of Health Stroke Scale score (adjusted OR, 1.09 [95% CI, 1.01–1.18]) in EVT alone group, and history of anticoagulant drugs (adjusted OR, 3.75 [95% CI, 1.07–13.06]), higher glucose level at hospital arrival (adjusted OR, 1.19 [95% CI, 1.03–1.38]), >3 passes of device (adjusted OR, 4.42 [95% CI, 1.36–14.32]) in combination-therapy group. Conclusions: In DIRECT-MT, independent predictors of sICH were baseline National Institutes of Health Stroke Scale score and glucose level at hospital arrival. Alteplase treatment did not increase the risk of HT, sICH, or PH after EVT. The independent predictor of sICH was different in EVT alone group and combination-therapy group. Registration: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT03469206.

Objective Although certain morphological features depicted by high resolution, multi-contrast magnetic resonance imaging (hrMRI) have been shown to be different between culprit and non-culprit middle cerebral artery (MCA) atherosclerotic lesions, the incremental value of hrMRI to define culprit lesions over stenosis has not been assessed. Methods Patients suspected with MCA stenosis underwent hrMRI. Lumen and outer wall were segmented to calculate stenosis, plaque burden (PB), volume (PV), length (PL) and minimum luminal area (MLA). Results Data from 165 lesions (112 culprit and 53 non-culprit) in 139 individuals were included. Culprit lesions were larger and longer with a narrower lumen and increased PB compared with non-culprit lesions. More culprit lesions showed contrast enhancement. Both PB and MLA were better indicators than stenosis in differentiating lesion types (AUC were 0.649, 0.732 and 0.737 for stenosis, PB and MLA, respectively). Combinations of PB, MLA and stenosis could improve positive predictive value (PPV) and specificity significantly. An optimal combination of stenosis ≥ 50 %, PB ≥ 77 % and MLA ≤ 2.0 mm² produced a PPV = 85.7 %, negative predictive value = 54.1 %, sensitivity = 69.6 %, specificity = 75.5 %, and accuracy = 71.5 %. Conclusions hrMRI plaque imaging provides incremental information to luminal stenosis in identifying culprit lesions. Key points • High resolution MRI provides incremental information in defining culprit MCA atherosclerotic lesions. • Both plaque burden and minimum luminal area are better indicators than stenosis. • An optimal combination includes stenosis ≥ 50 %, PB ≥ 77 % and MLA ≤ 2.0 mm ² .

Purpose The aim of this study was to evaluate retrospectively ¹⁸F-FDG PET/CT findings of inflammatory myofibroblastic tumor (IMT) and their correlation with the pathologic findings. Patients and Methods FDG PET/CT findings were reviewed in 5 patients with IMT and 1 patient with spindle cell sarcoma transformed from IMT. PET/CT scans were performed in all 6 patients before surgery. Follow-up FDG PET/CT scan was performed in 1 patient. The location, size, maximal standardized uptake value (SUV_max), and pathologic findings of the tumors were reviewed. The correlation between the FDG uptake and pathologic findings were analyzed. Results A total of 10 lesions were detected in all 6 patients. The tumor locations were liver (n = 3), retroperitoneum (n = 2), spleen (n = 1), lung (n = 1), and bone (n = 3). Seven IMTs and 1 spindle cell sarcoma transformed from IMT were confirmed by pathology. The mean SUV_max of the pathologically proven tumors was 10.9 ± 5.5, with a high variability of SUV_max among tumors ranging from 3.3 to 20.8. The tumors (n = 7) with high cellularity had stronger FDG uptake, while the tumors (n = 1) with low cellularity had relatively low FDG uptake. The tumors with nuclear atypia and relatively high proliferative index had very strong FDG uptake, while those with low proliferative index or negative Ki-67 staining had relatively lower FDG uptake. One small tumor with abundant plasma cells showed high FDG uptake, while 1 large tumor with focal inflammatory cell infiltrate showed lower FDG uptake. One patient developed local recurrences and distant metastases revealed by the second FDG PET/CT scan 7 months after resection. Conclusions FDG uptake in IMTs varied from low to high FDG uptake, which may be due to tumor cellularity, biological behaviors of the tumor cells, the composition and the proportion of inflammatory cells, and the extent of activation of the inflammatory cells. FDG PET/CT may be useful for detection of the primary tumors, local recurrences, and distant metastases.

Interpretation of 18F-FDG PET/CT studies in breast is challenging owing to nonspecific FDG uptake in various benign and malignant conditions. Benign conditions include breast changes in pregnancy and lactation, gynecomastia, mastitis, fat necrosis, fibroadenoma, intraductal papilloma, and atypical ductal hyperplasia. Among malignancies, invasive ductal carcinoma and invasive lobular carcinoma are common histological types of breast carcinoma. Rarely, other unusual histological types of breast carcinomas (eg, intraductal papillary carcinoma, invasive micropapillary carcinoma, medullary carcinoma, mucinous carcinoma, and metaplastic carcinoma), lymphoma, and metastasis can be the causes. Knowledge of a wide spectrum of hypermetabolic breast lesions on FDG PET/CT is essential in accurate reading of FDG PET/CT. The purpose of this atlas article is to demonstrate features of various breast lesions encountered at our institution, both benign and malignant, which can result in hypermetabolism on FDG PET/CT imaging.