Physical and Engineering Sciences in Medicine最新文献

The World Health Organisation 2024 report shows that Cardiovascular Disease (CVD) is the leading cause of death worldwide, estimated at 17.9 million deaths annually, and its mortality is about 32% of all deaths in the world. Of these, about 85% are myocardial infarctions and strokes. This study aims to diagnose heart disorders by providing early medical intervention to reduce the risks of abnormal heart structures. A data-driven model has been developed to achieve the above aim. The CVD and standard Electrocardiogram (ECG) datasets are extracted from PhysioNet in CSV format. This dataset comprises 305 samples of normal heart function, 15 samples of congestive heart failure, 32 samples of intracardiac atrial fibrillation, and 77 samples of supraventricular arrhythmia. The key steps include preprocessing the raw ECG data, extracting the relevant features, and introducing the input to the Machine Learning (ML) model for training. After preprocessing, ECG characteristic features, viz., mean heart interval, RR interval, p-wave amplitude, q-wave amplitude, r-wave amplitude, t-wave amplitude, and the derived features, namely, root mean square of successive difference (RMSSD), mean standard deviation of the normal-to-normal interval (SDDN), are extracted from the ECG signal and implemented using eXplainable Artificial Intelligence (XAI) methods to expound feature contributions. Various ML algorithms, including ensemble (EN), Naive Bayes (NB), and Support Vector Machine (SVM), are implemented for effectiveness. A tenfold cross-validation and performance are assessed using accuracy and recall analysis. Among these four models, SVM outperforms the other models and feature selection, achieving 99.5% accuracy when considering all features, 77% accuracy for the two derived features, and 99.5% accuracy for ECG wave characteristics features. To address the limitations, such as a small dataset and class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is applied to further enhance model performance. This study demonstrates the effectiveness of ML models, notably SVM, in predicting CVD abnormalities based on their ECG characteristics. These results suggest that future research should focus on refining methods to identify key features of ECG wave characteristics, potentially streamlining and speeding up the prediction of CVD in real-time. This work utilises XAI techniques to make the models more transparent, understandable and improve model accuracy of 99.8% for SVM. Furthermore, increasing model transparency with XAI might facilitate quicker clinical adoption for the diagnosis of heart disease.

A prototype Compton camera composed of two high resolution scintillator detectors is presented in this work. The scatterer detector consists of a 21 × 21 gadolinium aluminum gallium garnet (GAGG) crystal array with a crystal size of 0.6 × 0.6 × 2 mm³. The absorber detector consists of a 23 × 23 lutetium yttrium orthosilicate (LYSO) crystal array with a crystal size of 1.0 × 1.0 × 20 mm³. A simple back-projection image reconstruction method was developed. The energy of the scatterer detector was accurately calibrated using the 55, 202, 307 keV gamma-rays from the LYSO natural background and the 511 keV gamma-ray from a ²²Na point source. The scatterer detector provides a performance with all crystals clearly resolved even at an energy window of 30-120 keV and an average crystal energy resolution of 10.4% at 511 keV. The absorber detector provides a performance with all crystals clearly resolved, an average crystal depth of interaction resolution of ~ 2 mm and an average crystal energy resolution of 19.4% at 511 keV. An average spatial resolution of 2.5 mm was obtained and 9 point sources of 3 mm apart were well resolved at an image plane 7.5 mm from the front of the scatterer detector by using the 511 keV gamma-rays from a ²²Na point sources. Furthermore, iterative reconstruction using the maximum-likelihood expectation maximization (MLEM) algorithm achieved a spatial resolution of ~ 1 mm at a plane 7.5 mm from the front of the scatterer detector. Compared with the simple back-projection method, the MLEM reconstruction significantly enhanced the image contrast and effectively suppressed the background artifacts.

Wireless Capsule Endoscopy (WCE) is a useful method for imaging the intestines painlessly and looking into gastrointestinal tract diseases. The investigation of the enormous dataset produced by the patient's digestive tract WCE imaging takes a lot of time and a unique set of skills from a medical professional. Therefore, there is a strong need for effective analysis techniques that minimize examination times and increase diagnostic accuracy. To address the problem, the authors devise an approach that can automatically analyze WCE images to spot anomalies and help medical professionals make reliable diagnoses. This study adopts CNN based ensemble approach that combines the DenseNet201, MobileNetV2, and EfficientNetB7 model to classify WCE bleeding images. The CNN-based average ensemble model's performance is assessed using a dataset of 1309 bleeding and 1309 non-bleeding images generated by the wireless capsule endoscopy (WCE) tube. The suggested ensemble model achieved an accuracy of 98.74%, with precision, recall, and F1 score of 98.06%, 98.83%, and 98.44%, respectively. The proposed model is also compared with individual model and with custom built CNN model. The findings indicate that the proposed method offers an acceptable alternative and may prove beneficial for healthcare professionals.

This study assessed a high-resolution ionisation chamber-based PTW 1600SRS detector array (array) for beam profile analysis and patient-specific quality assurance (PSQA) in CyberKnife (CK) stereotactic radiosurgery (SRS) and stereotactic body radiotherapy (SBRT). The goal was to determine its suitability for small fields and non-isocentric delivery, which is unique to robotic platforms. Detector performance was examined for dose linearity, reproducibility, beam profiles, output factors, dose-rate dependence, and verification of the Iris collimator field size. Results were benchmarked against diode-based commissioning data. Clinical applicability was tested by retrospectively verifying 20 intracranial SRS and 20 extracranial SBRT plans using gamma analysis with criteria ranging from 3%/3 mm to 1%/1 mm, as well as 4%/1 mm. The detector showed strong dose linearity (R² = 0.999) and stable reproducibility. Beam profiles matched commissioning values within 0.5 mm, and output factors agreed within 2% for most collimators, with a maximum deviation of 3% at 5 mm. Dose-rate variation remained within 2.5% across relevant SADs. Iris collimator field sizes were consistent with reference measurements. Clinical validation achieved high passing rates, all with tolerance limit of > 95%. It enables accurate beam characterization and reliable PSQA in CK treatments. This work provides the first combined evaluation of beam analysis and clinical validation for this detector on a robotic radiosurgery system, supporting its routine use in small-field quality assurance.

High-b-value (b = 2000 s/mm²) diffusion-weighted imaging (DWI) is vital for prostate disease detection and characterization due to superior tumor-to-background contrast, but its direct acquisition is time-consuming, technically demanding, and prone to noise and artifacts, limiting routine clinical use. This study aims to synthesize high-b-value prostate DWI from low-b-value data via a novel deep learning method. A dual low-b-value-driven U-shaped Fusion Generative Adversarial Network (UsFGAN) was proposed, integrating three core components: (1) U-Net-based dedicated subnetworks (with skip connections) for feature extraction from two low-b-values (b = 50/1000 sec/mm²); (2) Swin-Transformer with residual blocks (STRB) to capture local/long-range pixel dependencies; (3) hierarchical fusion network with multiple feature fusion blocks (MFFB) for adaptive multi-scale feature combination. Validation was done on a multi-center dataset of 280 subjects (6440 DWI slices). The proposed method outperformed state-of-the-art models (CycleGAN, Pix2Pix, DiscoGAN): peak signal-to-noise ratio = 36.14 dB, structural similarity index = 0.91, LPIPS = 0.09, FID = 8.87. Synthesized high-b-value DWI achieved 86.3% accuracy in prostate lesion detection. Radiologist qualitative evaluation confirmed synthesized images were comparable to real high-b-value scans in noise suppression, artifact reduction, and diagnostic acceptability. UsFGAN effectively leverages dual low-b-value complementary information to synthesize high-quality high-b-value prostate DWI. It exhibits superior performance and clinical diagnostic value, promising to reduce scan time and improve prostate disease assessment.

Radiotherapy dosimetry in composite and modulated fields remains complex, especially when using small field ionization chambers in the second part of the Alfonso et al. formalism. This study investigates the response of the IBA- CC 01 ionization chamber in machine-specific reference, one static field of, and clinical IMRT step-and-shoot composite fields for a 6 MV flattening-filter-free (FFF) TrueBeam STx ^® photon beam. A previously validated BEAMnrc model of the TrueBeam linac was used to generate high-statistics phase-space files, which were then combined with an egs_chamber model of the IBA-CC01 to calculate absorbed dose to water and detector response in static and composite fields. Latent variance was evaluated at three fixed points (central, off-axis, and peripheral) across several IMRT step-and-shoot fields, showing that the detector's latent variance remains below 0.2% and is largely independent of the detector's position. Radiochromic film measurements using Gafchromic EBT4 in a solid water phantom, following AAPM TG-235, validated the Monte Carlo simulation of the plan-class-specific reference fields. For these, off-axis ratio profiles from film and Monte Carlo agree within a few percent in the high-dose region, and a gamma analysis with 3.5%/2.5 mm criteria (global) yielded passing rates of 97% and 95% for cross-planes and in-plane profiles, respectively. Monte Carlo-derived correction factors for the IBA-CC01 in IMRT step-and-shoot composite fields are close to one and, within a mean absolute difference of less than 1.5%, align with the small field correction factors reported in IAEA-AAPM TRS 483 for static fields of similar size. These findings suggest that, for the 6 MV FFF TrueBeam beam and the IMRT step-and-shoot fields examined here, the IBA-CC01 functions effectively as a practical field detector for relative dosimetry and for calculating detector-specific correction factors in composite fields. In contrast, absolute reference dosimetry should still rely on reference-class ionization chambers under conventional reference conditions.

Radiation dosimetry is essential in the optimisation and justification of medical imaging procedures. However, the complexity of modern imaging equipment often surpasses the capabilities of standard dose calculation software, necessitating the use of commercially available dosimetry phantoms, which are often prohibitively expensive. This study aimed to develop a cost-effective, 3D-printed newborn-equivalent dosimetry phantom for measuring organ and whole-body effective doses. Several Polylactic Acid (PLA)-based filaments were investigated for tissue equivalency through Hounsfield-value analysis via micro-CT (40-70 kVp) and clinical CT (70-140 kVp) measurements. Standard PLA at 93% (ρ = 1.14 g/cm³) and 26% (ρ = 0.41 g/cm³) infill density was selected for soft tissue and lung, respectively, while StoneFil composite PLA (FormFutura) at 81% (ρ = 1.21 g/cm³) infill was chosen for bone. The phantom was modelled on a modified Cristy and Eckerman newborn design, with 21 sections generated using MATLAB and printed on a Bambu Lab X1 Carbon 3D printer. A total of 186 thermoluminescent dosimeter (TLD) capsules were embedded in the phantom, and TLD measurements from whole-body 60 kVp radiographs were compared with Monte Carlo (PCXMC 2.0) simulations for validation. The phantom demonstrated accurate dosimetry for the radiographic exposure, with average organ doses closely matching the simulated exposure, and the effective dose (ICRP 103) within 2% of the simulation. The phantom required 135 h to print, with a material cost of A$165. This study successfully developed and validated a cost-effective dosimetry phantom for paediatric radiography, with the potential to print larger phantoms for older children. Future work will explore the phantom's application in other X-ray imaging modalities.

Real-time Image-guided Radiotherapy (IGRT) technologies aim to track intra-fractional tumour motion during delivery of high radiation doses to tumours. For the development and safe implementation of real-time IGRT technologies into the clinic, there is a need for robust and repeatable quality assurance (QA) devices. Motivated by this need, this work presents the development and characterisation of a novel time-synchronised motion platform designed for QA purposes of real-time IGRT technologies that perform combined internal and external patient motion monitoring. The Internal-External Robotic Actuator (IntERAct) QA device was developed to integrate a 6-degree-of-freedom (6DoF) robotic arm with a 1-degree-of-freedom (1DoF) motion actuator, which replicate 6DoF internal tumour and 1DoF external surface movements, respectively. The IntERAct device was validated by performing tests which replicated patient-measured lung and liver motion traces on the 6DoF and 1DoF platforms. The device synchronised the internal and external motions to within 0.1 s with under two-millimetre geometric accuracy. The full details of the IntERAct device have been compiled into an open-source repository on GitHub for the medical physics community to use: https://github.com/Image-X-Institute/IntERAct .