Australasian Physical and Engineering Sciences in Medicine This is an RSS file. You can use it to subscribe to this data in your favourite RSS reader or to display this data on your own website or blog.

Transfer learning and self-distillation for automated detection of schizophrenia using single-channel EEG and scalogram images
In this study, our main goal is to develop an optimized system that can achieve automatic diagnosis of SZ with minimal input information. To optimize the system, we adopted a strategy of using single-channel EEG signals and integrated knowledge distillation and transfer learning techniques into the model. This approach was designed to improve the performance and efficiency of our proposed method for SZ diagnosis. Additionally, to leverage the pre-trained models effectively, we converted the EEG signals into images using Continuous Wavelet Transform (CWT). This transformation allowed us to harness the capabilities of pre-tr...
Source: Australasian Physical and Engineering Sciences in Medicine - April 23, 2024 Category: Biomedical Engineering Source Type: research

A mechanistic simulation of induced DNA damage in a bacterial cell by X- and gamma rays: a parameter study
AbstractMechanistic Monte Carlo simulations calculating DNA damage caused by ionizing radiation are highly dependent on the simulation parameters. In the present study, using the Geant4-DNA toolkit, the impact of different parameters on DNA damage induced in a bacterial cell by X- and gamma-ray irradiation was investigated. Three geometry configurations, including the simple (without DNA details), the random (a random multiplication of identical DNA segments), and the fractal (a regular replication of DNA segments using fractal Hilbert curves), were simulated. Also, three physics constructors implemented in Geant4-DNA, i.e...
Source: Australasian Physical and Engineering Sciences in Medicine - April 23, 2024 Category: Biomedical Engineering Source Type: research

Resting state EEG assisted imagined vowel phonemes recognition by native and non-native speakers using brain connectivity measures
AbstractCommunication is challenging for disabled individuals, but with advancement of brain-computer interface (BCI) systems, alternative communication systems can be developed. Current BCI spellers, such as P300, SSVEP, and MI, have drawbacks like reliance on external stimuli or conversation irrelevant mental tasks. In contrast to these systems, Imagined speech based BCI systems rely on directly decoding the vowels/words user is thinking, making them more intuitive, user friendly and highly popular among Brain-Computer-Interface (BCI) researchers. However, more research needs to be conducted on how subject-specific chara...
Source: Australasian Physical and Engineering Sciences in Medicine - April 22, 2024 Category: Biomedical Engineering Source Type: research

In vivo EPID-based daily treatment error identification for volumetric-modulated arc therapy in head and neck cancers with a hierarchical convolutional neural network: a feasibility study
AbstractWe proposed a deep learning approach to classify various error types in daily VMAT treatment of head and neck cancer patients based on EPID dosimetry, which could provide additional information to support clinical decisions for adaptive planning. 146 arcs from 42 head and neck patients were analyzed. Anatomical changes and setup errors were simulated in 17,820 EPID images of 99 arcs obtained from 30 patients using in-house software for model training, validation, and testing. Subsequently, 141 clinical EPID images from 47 arcs belonging to the remaining 12 patients were utilized for clinical testing. The hierarchic...
Source: Australasian Physical and Engineering Sciences in Medicine - April 22, 2024 Category: Biomedical Engineering Source Type: research

Comparison of commercial atlas-based automatic segmentation software for prostate radiotherapy treatment planning
This study aims to assess the accuracy of automatic atlas-based contours for various key anatomical structures in prostate radiotherapy treatment planning. The evaluated structures include the bladder, rectum, prostate, seminal vesicles, femoral heads and penile bulb. CT images from 20 patients who underwent intensity-modulated radiotherapy were randomly chosen to create an atlas library. Atlas contours of the seven anatomical structures were generated using four software packages: ABAS, Eclipse, MIM, and RayStation. These contours were then compared to manual delineations performed by oncologists, which served as the grou...
Source: Australasian Physical and Engineering Sciences in Medicine - April 22, 2024 Category: Biomedical Engineering Source Type: research

Study of PRESAGE ® dosimeter for end-to-end 3D radiotherapy verification using an anthropomorphic phantom with bespoke dosimeter insert
This study proves the capability of PRESAGE® and bespoke MAX-HD phantom in conjunction with the 3Dmicro HD-OCT system to measure 3D dose distribution for end-to-end dosimetry verification. (Source: Australasian Physical and Engineering Sciences in Medicine)
Source: Australasian Physical and Engineering Sciences in Medicine - April 18, 2024 Category: Biomedical Engineering Source Type: research

Accuracy of patient-specific CT organ doses from Monte Carlo simulations: influence of CT-based voxel models
In this study, organ dose calculations were performed with ImpactMC for chest and cardiac CT using whole-body and anatomy-specific voxel models to estimate the accuracy of CT organ doses based on the latter model. When the 3D patient mod el is limited to the CT scan range, CT organ doses from Monte Carlo simulations are the most accurate for organs entirely in the field of view. For these organs only the radiation dose related to scatter from the rest of the body is not incorporated. For organs lying partially outside the field of v iew organ doses are overestimated by not accounting for the non-irradiated tissue mass. Thi...
Source: Australasian Physical and Engineering Sciences in Medicine - April 18, 2024 Category: Biomedical Engineering Source Type: research

Stability of radiomic features from positron emission tomography images: a phantom study comparing advanced reconstruction algorithms and ordered subset expectation maximization
In this study, we compared the repeatability and reproducibility of radiomic features obtained from positron emission tomography (PET) images according to the reconstruction algorithm used —advanced reconstruction algorithms, such as HYPER iterative (IT), HYPER deep learning reconstruction (DLR), and HYPER deep progressive reconstruction (DPR), or traditional Ordered Subset Expectation Maximization (OSEM)—to understand the potential variations and implications of using advanced re construction techniques in PET-based radiomics. We used a heterogeneous phantom with acrylic spherical beads (4- or 8-mm diameter) filled wi...
Source: Australasian Physical and Engineering Sciences in Medicine - April 16, 2024 Category: Biomedical Engineering Source Type: research

Ex vivo, in vivo and in silico studies of corneal biomechanics: a systematic review
AbstractHealthy cornea guarantees the refractive power of the eye and the protection of the inner components, but injury, trauma or pathology may impair the tissue shape and/or structural organization and therefore its material properties, compromising its functionality in the ocular visual process. It turns out that biomechanical research assumes an essential role in analysing the morphology and biomechanical response of the cornea, preventing pathology occurrence, and improving/optimising treatments. In this review,ex vivo, in vivo andin silico methods for the corneal mechanical characterization are reported. Experimenta...
Source: Australasian Physical and Engineering Sciences in Medicine - April 10, 2024 Category: Biomedical Engineering Source Type: research

A low-cost phantom design for evaluating spine SABR calculations in the presence of prosthetic vertebral stabilization
We present an initial design for a low-cost phantom to evaluate spine stereotactic ablative radiotherapy (SABR) in the presence of prosthetic vertebral stabilization. The phantom is modular, allowing the prosthetic at the centre of the phantom to be removed by exchanging the central block. It also includes space to insert ion chamber and film. The agreement of the RayStation TPS (v8.0B) collapsed cone convolution (CCC) calculation and measurement was determined for phantom versions with and without prosthetic. There was little to no change in the agreement between the measured and calculated dose when introducing metallic ...
Source: Australasian Physical and Engineering Sciences in Medicine - April 4, 2024 Category: Biomedical Engineering Source Type: research

Are deep learning classification results obtained on CT scans fair and interpretable?
AbstractFollowing the great success of various deep learning methods in image and object classification, the biomedical image processing society is also overwhelmed with their applications to various automatic diagnosis cases. Unfortunately, most of the deep learning-based classification attempts in the literature solely focus on the aim of extreme accuracy scores, without considering interpretability, or patient-wise separation of training and test data. For example, most lung nodule classification papers using deep learning randomly shuffle data and split it into training, validation, and test sets, causing certain image...
Source: Australasian Physical and Engineering Sciences in Medicine - April 4, 2024 Category: Biomedical Engineering Source Type: research

On the accuracy of sequence methods for baroreflex sensitivity estimation
AbstractIn the absence of a true gold standard for non-invasive baroreflex sensitivity estimation, it is difficult to quantify the accuracy of the variety of techniques used. A popular family of methods, usually entitled ‘sequence methods’ involves the extraction of (apparently) correlated sequences from blood pressure and RR-interval data and the subsequent fitting of a regression line to the data. This paper discusses the accuracy of sequence methods from a system identification perspective, using both data ge nerated from a known mathematical model and spontaneous baroreflex data. It is shown that sequence methods c...
Source: Australasian Physical and Engineering Sciences in Medicine - April 2, 2024 Category: Biomedical Engineering Source Type: research

PE-Ynet: a novel attention-based multi-task model for pulmonary embolism detection using CT pulmonary angiography (CTPA) scan images
In this study, a novel attention-based multi-task model is proposed for PE segmentation and detection from Computed Tomography Pulmonary Angiography (CTPA) images. A Y-Net architecture is used to implement this model, which facilitates segmentation and classification jointly, improving performance and efficiency. It is leveraged with Multi Head Attention (MHA), which allows the model to focus on important regions of the image while suppressing irrelevant information, improving the accuracy of the segmentation and detection tasks. The proposed PE-YNet model is tested with two public datasets, achieving a maximum mean detect...
Source: Australasian Physical and Engineering Sciences in Medicine - March 28, 2024 Category: Biomedical Engineering Source Type: research

Estimation of organ and effective doses of CBCT scans of radiotherapy using size-specific field of view (FOV): a Monte Carlo study
This study aimed to investigate the influence of using fixed and patient-specific FOVs on the patient dose. Monte Carlo simulations were performed to simulate kV beams of the imaging system integrated into Truebeam linear accelerator using BEAMnrc code. Organ and size-specific effective doses resulting from chest and pelvis scanning protocols were estimated with DOSXYZnrc code using a phantom library developed by the National Cancer Institute (NCI) of the US. The library contains 193 (100 male and 93 female) mesh-type computational human adult phantoms, and it covers a large ratio of patient sizes with heights and weights ...
Source: Australasian Physical and Engineering Sciences in Medicine - March 27, 2024 Category: Biomedical Engineering Source Type: research

A novel textile-based UWB patch antenna for breast cancer imaging
In this study, a novel textile-based ultrawideband (UWB) microstrip patch antenna was designed and modeled to work in the 2 –11.6 GHz frequency range and a simulation was used to test its performance in early breast cancer detection. The antenna was designed with an overall size of 31*31 mm\(^2\) using a denim substrate and 100% metal polyamide-based fabric with copper, silver, and nickel to provide comfort for the wearer. The designed antenna was tested in four numerical breast models. The models ranged from simple tumor-free to complex models with small tumors. The size, structure, and position of the tumor were modifi...
Source: Australasian Physical and Engineering Sciences in Medicine - March 26, 2024 Category: Biomedical Engineering Source Type: research