Research Insights & Reviews: Radiology & Imaging Sciences

Projection-Related Bias in the Detection of Thoracic Abnormalities: A Large-Scale Analysis of the NIH ChestX-Ray14 Dataset

2026-08-31T11:36:51+00:00

Chest radiography remains a cornerstone in the diagnosis of thoracic diseases. However, differences in image acquisition—particularly projection type—may influence the apparent prevalence and detectability of radiographic findings. Such differences may represent a potential source of bias in large imaging datasets used for clinical research and artificial intelligence. Importantly, projection type is closely associated with the patient’s condition and may therefore reflect both technical imaging factors and underlying clinical characteristics, including disease severity. A total of 120,120 chest radiographs were available in the dataset. After applying inclusion criteria, 112,104 images were included in the primary analysis. Multivariable logistic regression models were used to assess the association between projection type and the presence of radiographic findings, adjusted for age and sex. Subgroup and interaction analyses were performed to evaluate effect modification by demographic factors. Given the large sample size, emphasis was placed on effect sizes and confidence intervals rather than statistical significance alone. Compared with posteroanterior projection, anteroposterior projection was associated with higher odds of detecting consolidation (aOR 3.27; 95% CI 3.07–3.48), infiltration (aOR 1.90; 95% CI 1.84–1.96), pleural effusion (aOR 1.66; 95% CI 1.60–1.72), atelectasis (aOR 1.63; 95% CI 1.57–1.70), and cardiomegaly (aOR 1.19; 95% CI 1.10–1.28). These associations were consistent across age and sex strata. A significant interaction between projection type and sex was observed for infiltration (p = 0.01). Projection type is associated with substantial differences in the detection of thoracic abnormalities on chest radiographs. These associations should be interpreted with caution, as they likely reflect a combination of technical imaging effects and residual confounding related to patient severity and clinical context. Projection may therefore act as a marker of dataset heterogeneity rather than a purely causal factor. Accounting for projection metadata is therefore essential to improve clinical interpretation and to ensure the robust development and validation of artificial intelligence models.

Artificial Intelligence in Pulmonary Endoscopy: Current Evidence, Limitations, and Future Directions

2026-08-31T11:19:46+00:00

Background: Artificial intelligence (AI) is increasingly applied in pulmonary endoscopy, including diagnostic bronchoscopy, interventional pulmonology and endobronchial imaging. Advances in computer vision, machine learning and robotic systems have expanded the potential for automated lesion detection, navigation to peripheral pulmonary lesions, and real-time procedural support. However, the current evidence base remains heterogeneous, and translational challenges persist. Methods: This review summarizes current applications and developments of AI across white-light bronchoscopy (WLB), image-enhanced bronchoscopy (e.g., narrow-band imaging and autofluorescence imaging), endobronchial ultrasound (EBUS), virtual and robotic bronchoscopies, and workflow optimization and training. The authors also examine the methodological limitations, regulatory considerations, and implementation barriers that affect translation into routine practice. Results: Reported developments include deep learning-based models for mucosal abnormality detection, lymph-node characterization during EBUS-guided transbronchial needle aspiration (EBUS-TBNA), improved lesion localization, and reduction in operator-dependent variability. Additionally, AI-assisted simulation platforms and decision-support tools are reshaping training paradigms. Nevertheless, most studies remain retrospective or single-center, with limited external validation, dataset heterogeneity, unclear model explainability, and incomplete integration into clinical workflows. Conclusions: AI has the potential to support lesion detection, navigation, and training in pulmonary endoscopy. However, robust prospective validation, standardized datasets, transparent model reporting, robust data governance, multidisciplinary collaboration, and careful integration into clinical practice are required before widespread adoption.

An Effective Non-Rigid Registration Approach for Ultrasound Images Based on the Improved Variational Model of Intensity, Local Phase Information and Descriptor Matching

2026-05-16T04:05:13+00:00

Ultrasound images have some limitations, such as low signal-to-noise ratio (SNR), speckle noise, lower dynamic range, blurred boundaries, and shadowing; therefore, ultrasound image registration is an important task for estimating tissue motion and analyzing tissue mechanical properties. In this paper, an effective non-rigid ultrasound image registration method is proposed. By integrating intensity, local phase information, and descriptor matching under a variational framework, we can find and track the non-rigid transformation of each pixel under diffeomorphism between the source and target images based on the warping technique. Experiments using simulation and in vivo ultrasound images of the human carotid artery are conducted to demonstrate the advantages of the proposed algorithm, which will act as an important supplement to current ultrasound image registration.

MS-PANet: Multi-Scale Spatial Pyramid Attention for Effective Drainage Pipeline Image Dehazing

2026-08-31T11:29:44+00:00

Urban drainage pipelines are crucial for flood control, drainage, and environmental quality. However, fog within pipelines degrades image quality, hindering the identification of damage features such as cracks and leaks. Existing dehazing algorithms struggle with the unique challenges presented by drainage pipelines, such as their cylindrical structure, non-uniform lighting, and multi-scale particulate interference, leading to inadequate feature extraction and weak cross-channel dependency modeling. To address these issues, we propose a novel drainage pipeline image dehazing network based on a pyramid attention mechanism. Specifically, our proposed method incorporates a custom-designed multi-scale spatial pyramid attention (MSPA) module, which combines hierarchical pyramid convolution and spatial pyramid recalibration modules. This enables the dynamic adjustment of multi-scale feature weights and the effective modeling of cross-channel long-range dependencies. Extensive experiments demonstrate that our network achieves superior dehazing performance across diverse underground environments, particularly in synthetic foggy dataset under real pipeline conditions, outperforming state-of-the-art dehazing algorithms. This proposed approach provides a reliable solution for high-precision visual inspection in complex pipeline scenarios.

Management of Complex CNS Tumours: Impact of Multiple Tumour Board Review

2026-08-31T11:10:49+00:00

Background: Patients with malignant or benign central nervous system (CNS) tumours are evaluated for suitability of treatment modality based on multiple clinical and tumour-related factors. To obtain multidisciplinary consensus, a patient’s file and imaging are commonly reviewed by a tumour board (TB). There are three relevant weekly TB venues at our institute—gamma knife stereotactic radiosurgery (SRS) intake rounds, CNS rounds, and stereotactic body radiotherapy (SBRT) rounds—which are attended by non-overlapping clinician teams. We explored the clinical parameters prompting multiple TB reviews in patients with complex CNS tumours.

Methods: Data were retrospectively obtained from electronic medical records. Patients referred for discussion at SRS rounds (November 2017–June 2020) were cross-referenced with those reviewed in CNS rounds and SBRT rounds. The cohort of interest included patients who underwent review at more than one TB for the same indication. Patient, tumour, and treatment factors were abstracted, and descriptive statistics were calculated. A sub-cohort of patients with pre-plans created for both SRS and conventionally fractionated external beam radiotherapy (EBRT) was identified. Dosimetric data were analyzed.

Results: Of 1091 patients, 87 (8.0%) were discussed at more than one TB. 59/87 (67.8%) patients were reviewed at two TBs pertaining to the same CNS lesion and comprised the study cohort. The most common tumour type was meningioma (20/59), and the most common reason for multiple discussions was proximity to optic structures (19/59). After TB discussions, 25/59 patients were seen in consultation by one specialist, 29/59 by two, and 5/59 by none. Overall, the final treatment decisions were conventional EBRT in 21/59; SRS in 18/59; surveillance in 12/59; surgery in 3/59; systemic therapy in 3/59; proton referral in 1/59; and SBRT in 1/59. A total of 20/59 patients were treated with palliative intent. Among all patients who ultimately received radiotherapy, median interval between the first TB discussion and the first RT treatment was 56 days (IQR 7.5–65.5 d). The pre-plan sub-cohort consisted of four patients, all of whom were ultimately treated with conventional EBRT.

Conclusions: Evidence to support optimal treatment for some complex CNS tumours can be limited. Multiple radiotherapy modalities may be equally favourable (or unfavourable) options. Proximity to the optic apparatus and previous CNS irradiation are common reasons for clinical equipoise. Tumour board review is an essential tool in formulating a multidisciplinary care plan; however, attention should be paid to ensuring that subsequent consultations and treatment initiation are not unduly delayed.