Routine computed tomography (CT) quality control (QC) is used to verify adequate image quality, support radiation-dose optimisation, and identify changes in scanner performance. Commonly used test objects include the ACR CT Phantom, the AAPM CT Performance Phantom, and the Catphan 600. The AFISMI CT Phantom is a locally manufacturable, water-filled prototype developed for routine constancy testing. This study provides preliminary single-scanner benchmarking of the AFISMI phantom using the IndoQCT automated analysis platform. The AFISMI phantom comprises a hollow polymethyl methacrylate (PMMA) shell (16 cm diameter and 10 cm length), a nominal 1.0-mm aluminium sheet fixed at 45° for slice-thickness measurement, and acrylic and Teflon inserts. Each phantom was scanned in three separate acquisitions on a Philips Ingenuity 128 CT scanner using 120 kVp, 300 mAs, a 5.0-mm slice thickness, and a 200-mm field of view; each acquisition was analysed independently. IndoQCT assessed uniformity in homogeneous water-filled or water-equivalent regions, Hounsfield unit (HU) accuracy, noise power spectrum (NPS), modulation transfer function (MTF), slice thickness, and signal-difference-to-noise ratio (SDNR). Raw-noise magnitude was not analysed separately because it is not included in the Indonesian national CT Compliance Test protocol used to define the QC scope. Under the tested scan and reconstruction conditions, the AFISMI phantom produced broadly comparable results for uniformity, water CT-number accuracy, MTF, and slice-thickness measurement relative to the commercial reference phantoms. NPS magnitude and shape differed among the phantoms. The AFISMI phantom had a higher mean SDNR than the AAPM phantom under the tested conditions, but this result cannot be used to claim better low-contrast performance because phantom geometry, target contrast, and background materials differed. Scalar outcomes are reported as mean ± standard deviation from three acquisitions and compared descriptively; no inferential statistical tests were performed. The AFISMI phantom and IndoQCT showed feasibility for automated CT constancy measurements under the tested single-scanner conditions. The findings represent preliminary benchmarking rather than independent validation or evidence of comparative advantage. Longitudinal baseline testing, multi-scanner evaluation, production-unit reproducibility assessment, and formal cost analysis are required before broad QA applicability or economic advantage can be established.
Arrhythmia poses a serious threat to human health, necessitating research into automated diagnostic methods. Although advances have been made in arrhythmia classification using deep learning, existing models often suffer from high computational cost and poor interpretability, limiting their clinical applicability. To this end, this paper proposes a lightweight progressive residual convolutional attention network (DResCA). Through the synergistic design of stage-adaptive downsampling and channel attention, this network reduces parameter redundancy while enhancing deep ECG feature extraction. To enhance clinical interpretability, template matching and attention visualization are employed to reveal the key ECG regions underlying the model’s diagnoses. Five-class classification experiments on the MIT-BIH Arrhythmia Database demonstrate that the model achieves 98.35
In stereotactic radiosurgery (SRS) for multiple brain metastases (MBM), there is higher out-of-field (OOF) dose contribution than that experienced in single metastasis. This study seeks to assess the impact of the introduced error in OOF dose in MBM SRS. CyberKnife Off-Centre-Ratios (OCRs) were modified by altering the measured umbra dose by an average 0.3 and 0.6
In this study, the usability of masked stereolithography (MSLA) and fused filament fabrication (FFF) type printers to produce breast phantom is investigated. ABS, PET, PLA+, PVA and TPU-95 A filaments are used on FFF type printer with infill ratios between 70 and 100
Brain tumor localization and type classification in MRI are important tasks in computer-aided medical image analysis. However, achieving competitive localization and classification performance with lightweight models remains challenging because reducing model complexity may weaken feature representation and localization ability. In this paper, we propose YOLO-C2ECASA, a lightweight attention-enhanced object detection framework based on YOLOv11 for three-class tumor localization and classification in tumor-positive MRI images. The present study focuses on glioma, meningioma, and pituitary tumors and does not address tumor-versus-no-tumor screening. The proposed C2ECASA module replaces the original self-attention design with a parameter-efficient spatial-channel attention mechanism. It integrates improved channel attention, lightweight spatial attention, C2-based feature preservation, and adaptive fusion to enhance lesion-relevant feature representation with limited computational cost. The proposed model was compared with representative object detection models. In the single-run comparison with representative object detectors, YOLO-C2ECASA maintained competitive detection performance while requiring only 2.4M parameters, 6.2G FLOPs, a model size of 5.01 MB, and a GPU inference time of 1.9 ms per image. More importantly, across ten independent runs under scratch initialization, YOLO-C2ECASA achieved mean mAP@0.5 and mAP@0.5:0.95 values of 0.930± 0.008 and 0.694± 0.009 . Under pretrained initialization, the corresponding repeated-run results were 0.939± 0.005 and 0.703± 0.007 , respectively. Under CPU-only deployment, YOLO-C2ECASA achieves an inference time of 27.4 ms per image, further demonstrating its feasibility for resource-constrained environments. These results indicate that the proposed model achieves competitive detection performance while maintaining a lower computational cost than the compared detectors. Ablation and repeated-run experiments further demonstrate that the complete C2ECASA configuration achieves the highest average performance among the evaluated configurations while maintaining low computational complexity. Overall, the proposed method provides a favorable accuracy–efficiency trade-off for lightweight brain tumor localization and type classification in tumor-positive MRI images.
