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.

Purpose: To develop and validate a radiomics nomogram for the preoperative prediction of lymph node (LN) metastasis in pancreatic ductal adenocarcinoma (PDAC). Materials and methods: In this retrospective study, 225 patients with surgically resected, pathologically confirmed PDAC underwent multislice computed tomography (MSCT) between January 2014 and January 2017. Radiomics features were extracted from arterial CT scans. The least absolute shrinkage and selection operator method was used to select the features. Multivariable logistic regression analysis was used to develop the predictive model, and a radiomics nomogram was built and internally validated in 45 consecutive patients with PDAC between February 2017 and December 2017. The performance of the nomogram was assessed in the training and validation cohort. Finally, the clinical usefulness of the nomogram was estimated using decision curve analysis (DCA). Results: The radiomics signature, which consisted of 13 selected features of the arterial phase, was significantly associated with LN status (p < 0.05) in both the training and validation cohorts. The multivariable logistic regression model included the radiomics signature and CT-reported LN status. The individualized prediction nomogram showed good discrimination in the training cohort [area under the curve (AUC), 0.75; 95% confidence interval (CI), 0.68–0.82] and in the validation cohort (AUC, 0.81; 95% CI, 0.69–0.94) and good calibration. DCA demonstrated that the radiomics nomogram was clinically useful. Conclusions: The presented radiomics nomogram that incorporates the radiomics signature and CT-reported LN status is a noninvasive, preoperative prediction tool with favorable predictive accuracy for LN metastasis in patients with PDAC.

This study aims to evaluate the utility of calculated computed tomography (CT) attenuation value ratio (AVR) and enhancement pattern in distinguishing pancreatic solid serous cystadenomas (SCAs) from nonfunctional pancreatic neuroendocrine tumors (NF-pNETs). A total of 142 consecutive patients with 22 solid SCAs and 120 NF-pNETs confirmed by pathology were included in this retrospective study. All patients underwent preoperative contrast-enhanced CT and were categorized into 2 groups, solid SCA and NF-pNET groups. Patients with NF-pNETs were matched to patients with solid SCAs via propensity scores. AVR was measured and defined as: attenuation value of tumor/attenuation value of normal pancreas. AVR and enhancement pattern performance were assessed according to the discriminative abilities of patients. After matching, 29 patients were allocated to the NF-pNET group. Before matching, sex, age, and the peak enhanced value phase were significantly different between solid SCA and NF-pNET patients (P < .05). After matching, no significant difference was observed between both groups (P > .05). Solid SCAs AVRs were significantly smaller than NF-pNETs AVRs in all unenhanced, arterial, portal venous, and delayed phases (P < .05). Solid SCAs showed significantly more wash-in and wash-out enhancement patterns than NF-pNETs (P < .05). For unenhanced, arterial, portal venous, and delayed phases, and enhancement pattern, the area under the curve (AUC) values were 0.96, 0.72, 0.80, 0.85, and 0.86, respectively. Low AVR on unenhanced CT and wash-in and wash-out enhancement patterns were useful for differentiating solid SCAs from NF-pNETs and may be useful for clinical decisions, a clearer opinion will be formed with further studies to be conducted with larger patient numbers.

This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement. However, fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging. To deal with this problem, we propose a 3D multi-scale attention VoxelMorph (MA-VoxelMorph) registration network. To alleviate the large deformation problem, a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction, and position-aware axial attention for long-distance dependencies between pixels capture. To further improve the large deformation and fine structure registration results, a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers. Our method was evaluated on four public lung datasets (DIR-Lab dataset, Creatis dataset, Learn2Reg dataset, OASIS dataset) and a local dataset. Results proved that the proposed method achieved better registration performance than current state-of-the-art methods, especially in handling the registration of large deformations and fine structures. It also proved to be fast in 3D image registration, using about 1.5 s, and faster than most methods. Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries.

Background: Currently, there is no fully automated tool available for evaluating the degree of cervical spinal stenosis. The aim of this study was to develop and validate the use of artificial intelligence (AI) algorithms for the assessment of cervical spinal stenosis. Methods: In this retrospective multi-center study, cervical spine magnetic resonance imaging (MRI) scans obtained from July 2020 to June 2023 were included. Studies of patients with spinal instrumentation or studies with suboptimal image quality were excluded. Sagittal T2-weighted images were used. The training data from the Fourth People’s Hospital of Shanghai (Hos. 1) and Shanghai Changzheng Hospital (Hos. 2) were annotated by two musculoskeletal (MSK) radiologists following Kang’s system as the standard reference. First, a convolutional neural network (CNN) was trained to detect the region of interest (ROI), with a second Transformer for classification. The performance of the deep learning (DL) model was assessed on an internal test set from Hos. 2 and an external test set from Shanghai Changhai Hospital (Hos. 3), and compared among six readers. Metrics such as detection precision, interrater agreement, sensitivity (SEN), and specificity (SPE) were calculated. Results: Overall, 795 patients were analyzed (mean age ± standard deviation, 55±14 years; 346 female), with 589 in the training (75%) and validation (25%) sets, 206 in the internal test set, and 95 in the external test set. Four tasks with different clinical application scenarios were trained, and their accuracy (ACC) ranged from 0.8993 to 0.9532. When using a Kang system score of ≥2 as a threshold for diagnosing central cervical canal stenosis in the internal test set, both the algorithm and six readers achieved similar areas under the receiver operating characteristic curve (AUCs) of 0.936 [95% confidence interval (CI): 0.916–0.955], with a SEN of 90.3% and SPE of 93.8%; the AUC of the DL model was 0.931 (95% CI: 0.917–0.946), with a SEN in the external test set of 100%, and a SPE of 86.3%. Correlation analysis comparing the DL method, the six readers, and MRI reports between the reference standard showed a moderate correlation, with R values ranging from 0.589 to 0.668. The DL model produced approximately the same upgrades (9.2%) and downgrades (5.1%) as the six readers. Conclusions: The DL model could fully automatically and reliably assess cervical canal stenosis using MRI scans.