Physical and Engineering Sciences in Medicine最新文献

MRI-guided radiotherapy systems enable beam gating by tracking the target on planar, two-dimensional cine images acquired during treatment. This study aims to evaluate how deep-learning (DL) models for target tracking that are trained on data from one fraction can be translated to subsequent fractions. Cine images were acquired for six patients treated on an MRI-guided radiotherapy platform (MRIdian, Viewray Inc.) with an onboard 0.35 T MRI scanner. Three DL models (U-net, attention U-net and nested U-net) for target tracking were trained using two training strategies: (1) uniform training using data obtained only from the first fraction with testing performed on data from subsequent fractions and (2) adaptive training in which training was updated each fraction by adding 20 samples from the current fraction with testing performed on the remaining images from that fraction. Tracking performance was compared between algorithms, models and training strategies by evaluating the Dice similarity coefficient (DSC) and 95% Hausdorff Distance (HD95) between automatically generated and manually specified contours. The mean DSC for all six patients in comparing manual contours and contours generated by the onboard algorithm (OBT) were 0.68 ± 0.16. Compared to OBT, the DSC values improved 17.0 - 19.3% for the three DL models with uniform training, and 24.7 - 25.7% for the models based on adaptive training. The HD95 values improved 50.6 - 54.5% for the models based on adaptive training. DL-based techniques achieved better tracking performance than the onboard, registration-based tracking approach. DL-based tracking performance improved when implementing an adaptive strategy that augments training data fraction-by-fraction.

Dose verification of treatment plans is an essential step in radiotherapy workflows. In this work, we propose a novel method of treatment planning based on nanodosimetric quantity-weighted dose (NQWD), which could realize biological representation using pure physical quantities for biological-oriented carbon ion-beam treatment plans and their direct verification. The relationship between nanodosimetric quantities and relative biological effectiveness (RBE) was studied with the linear least-squares method for carbon-ion radiation fields. Next, under the framework of the matRad treatment planning platform, NQWD was optimized using the existing RBE-weighted dose (RWD) optimization algorithm. The schemes of NQWD-based treatment planning were compared with the RWD treatment plans in term of the microdosimetric kinetic model (MKM). The results showed that the nanodosimetric quantity F_3 - 10 had a good correlation with the radiobiological effect reflected by the relationship between RBE and F_3 - 10. Moreover, the NQWD-based treatment plans reproduced the RWD plans generally. Therefore, F_3 - 10 could be adopted as a radiation quality descriptor for carbon-ion treatment planning. The novel method proposed herein not only might be helpful for rapid physical verification of biological-oriented ion-beam treatment plans with the development of experimental nanodosimetry, but also makes the direct comparison of ion-beam treatment plans in different institutions possible. Thus, our proposed method might be potentially developed to be a new strategy for carbon-ion treatment planning and improve patient safety for carbon-ion radiotherapy.

According to the World Health Organization (WHO), Atrial Fibrillation (AF) is emerging as a global epidemic, which has resulted in a need for techniques to accurately diagnose AF and its various subtypes. While the classification of cardiac arrhythmias with AF is common, distinguishing between AF subtypes is not. Accurate classification of AF subtypes is important for making better clinical decisions and for timely management of the disease. AI techniques are increasingly being considered for image classification and detection in various ailments, as they have shown promising results in improving diagnosis and treatment outcomes. This paper reports the development of a custom 2D Convolutional Neural Network (CNN) model with six layers to automatically differentiate Non-Atrial Fibrillation (Non-AF) rhythm from Paroxysmal Atrial Fibrillation (PAF) and Persistent Atrial Fibrillation (PsAF) rhythms from ECG images. ECG signals were obtained from a publicly available database and segmented into 10-second segments. Applying Constant Q-Transform (CQT) to the segmented ECG signals created a time-frequency depiction, yielding 98,966 images for Non-AF, 16,497 images for PAF, and 52,861 images for PsAF. Due to class imbalance in the PAF and PsAF classes, data augmentation techniques were utilized to increase the number of PAF and PsAF images to match the count of Non-AF images. The training, validation, and testing ratios were 0.7, 0.15, and 0.15, respectively. The training set consisted of 207,828 images, whereas the testing and validation set consisted of 44,538 images and 44,532 images, respectively. The proposed model achieved accuracy, precision, sensitivity, specificity, and F₁ score values of 0.98, 0.98, 0.98, 0.97, and 0.98, respectively. This model has the potential to assist physicians in selecting personalized AF treatment and reducing misdiagnosis.

In linear accelerator-based stereotactic irradiation (STI) for brain metastasis, cone-beam computed tomography (CBCT) image quality is essential for ensuring precise patient setup and tumor localization. However, CBCT images may be degraded by the deviation of the CBCT isocenter from the brain center. This study aims to investigate the effects of the distance from the brain center to the CBCT isocenter (DBI) on the image quality in STI. An anthropomorphic phantom was scanned with varying DBI in right, anterior, superior, and inferior directions. Thirty patients undergoing STI were prospectively recruited. Objective metrics, utilizing regions of interest included contrast-to-noise ratio (CNR) at the centrum semiovale, lateral ventricle, and basal ganglia levels, gray and white matter noise at the basal ganglia level, artifact index (AI), and nonuniformity (NU). Two radiation oncologists assessed subjective metrics. In this phantom study, objective measures indicated a degradation in image quality for non-zero DBI. In this patient study, there were significant correlations between the CNR at the centrum semiovale and lateral ventricle levels (r_s = - 0.79 and - 0.77, respectively), gray matter noise (r_s = 0.52), AI (r_s = 0.72), and NU (r_s = 0.91) and DBI. However, no significant correlations were observed between the CNR at the basal ganglia level, white matter noise, and subjective metrics and DBI (r_s < ± 0.3). Our results demonstrate the effects of DBI on contrast, noise, artifacts in the posterior fossa, and uniformity of CBCT images in STI. Aligning the CBCT isocenter with the brain center can aid in improving image quality.

The brain biomarker of irritable bowel syndrome (IBS) patients is still lacking. The study aims to explore a new technology studying the brain alterations of IBS patients based on multi-source brain data. In the study, a decision-level fusion method based on gradient boosting decision tree (GBDT) was proposed. Next, 100 healthy subjects were used to validate the effectiveness of the method. Finally, the identification of brain alterations and the pain evaluation in IBS patients were carried out by the fusion method based on the resting-state fMRI and DWI for 46 patients and 46 controls selected randomly from 100 healthy subjects. The results showed that the method can achieve good classification between IBS patients and controls (accuracy = 95%) and pain evaluation of IBS patients (mean absolute error = 0.1977). Moreover, both the gain-based and the permutation-based evaluation instead of statistical analysis showed that left cingulum bundle contributed most significantly to the classification, and right precuneus contributed most significantly to the evaluation of abdominal pain intensity in the IBS patients. The differences seem to suggest a probable but unexplored separation about the central regions between the identification and progression of IBS. This finding may provide one new thought and technology for brain alteration related to IBS.

Fetal electrocardiogram (fECG) monitoring is crucial for assessing fetal condition during pregnancy. However, current fECG extraction algorithms are not suitable for wearable devices due to their high computational cost and multi-channel signal requirement. The paper introduces a novel and efficient algorithm called Adaptive Improved Permutation Entropy (AIPE), which can extract fetal QRS from a single-channel abdominal ECG (aECG). The proposed algorithm is robust and computationally efficient, making it a reliable and effective solution for wearable devices. To evaluate the performance of the proposed algorithm, we utilized our clinical data obtained from a pilot study with 10 subjects, each recording lasting 20 min. Additionally, data from the PhysioNet 2013 Challenge bank with labeled QRS complex annotations were simulated. The proposed methodology demonstrates an average positive predictive value ( $+P$ ) of 91.0227%, sensitivity (Se) of 90.4726%, and F1 score of 90.6525% from the PhysioNet 2013 Challenge bank, outperforming other methods. The results suggest that AIPE could enable continuous home-based monitoring of unborn babies, even when mothers are not engaging in any hard physical activities.

Bolus is commonly used to improve dose distributions in radiotherapy in particular if dose to skin must be optimised such as in breast or head and neck cancer. We are documenting four years of experience with 3D printed bolus at a large cancer centre. In addition to this we review the quality assurance (QA) program developed to support it. More than 2000 boluses were produced between Nov 2018 and Feb 2023 using fused deposition modelling (FDM) printing with polylactic acid (PLA) on up to five Raise 3D printers. Bolus is designed in the radiotherapy treatment planning system (Varian Eclipse), exported to an STL file followed by pre-processing. After checking each bolus with CT scanning initially we now produce standard quality control (QC) wedges every month and whenever a major change in printing processes occurs. A database records every bolus printed and manufacturing details. It takes about 3 days from designing the bolus in the planning system to delivering it to treatment. A 'premium' PLA material (Spidermaker) was found to be best in terms of homogeneity and CT number consistency (80 HU +/- 8HU). Most boluses were produced for photon beams (93.6%) with the rest used for electrons. We process about 120 kg of PLA per year with a typical bolus weighing less than 500 g and the majority of boluses 5 mm thick. Print times are proportional to bolus weight with about 24 h required for 500 g material deposited. 3D printing using FDM produces smooth and reproducible boluses. Quality control is essential but can be streamlined.

CT angiography prior to endovascular aortic surgery is the standard non-invasive imaging method for evaluation of aortic dimensions and access sites. A detailed report is crucial to a proper planning. We assessed Artificial Intelligence (AI)-algorithm accuracy to measure vessels diameters at CT prior to transcatheter aortic valve implantation (TAVI). CT scans of 50 patients were included. Two Radiologists with experience in vascular imaging together manually assessed diameters at nine landmark positions according to the American Heart Association guidelines: 450 values were obtained. We implemented TOST (Two One-Sided Test) to determine whether the measurements were equivalent to the values obtained from the AI algorithm. When the equivalence bound was a range of ± 2 mm the test showed equivalence for every point; if the range was equal to ± 1 mm the two measurements were not equivalent in 6 points out of 9 (p-value > 0.05), close to the aortic valve. The time for automatic evaluation (average 1 min 47 s) was significantly lower compared with manual measurements (5 min 41 s) (p < 0.01). In conclusion, our results indicate that AI-algorithms can measure aortic diameters at CT prior to endovascular surgery with high accuracy. AI-assisted reporting promises high efficiency, reduced inter-reader variabilities and time saving. In order to perform optimal TAVI procedure planning aortic root analysis could be improved, including annulus dimensions.

With the rising use of Computed Tomography (CT) in diagnostic radiology, there are concerns regarding radiation exposure to sensitive groups, including pregnant patients. Accurately determining the radiation dose to the fetus during CT scans is essential to balance diagnostic efficacy with patient safety. This study assessed the accuracy of using the female uterus as a surrogate for fetal radiation dose during CT imaging. The study used common CT protocols to encompass various scenarios, including primary beam, scatter, and partial exposure. The computational program NCICT was used to calculate radiation doses for an adult female and a fetus phantom. The study highlighted that using the uterus for dose estimation can result in consistent underestimations of the effective dose, particularly when the fetus lies within the primary radiation beam. These discrepancies may influence clinical decisions, affecting care strategies and perceptions of associated risks. In conclusion, while the female uterus can indicate fetal radiation dose if the fetus is outside the primary beam, it is unreliable when the fetus is within the primary beam. More reliable abdomen/pelvic organs were recommended.

Single plan techniques for multiple brain targets (MBT) stereotactic radiosurgery (SRS) are now routine. Patient specific quality assurance (QA) for MBT poses challenges due to the limited capabilities of existing QA tools which necessitates several plan redeliveries. This study sought to develop an SRS QA phantom that enables flexible MBT patient specific QA in a single delivery, along with complex SRS commissioning. PLA marble and PLA StoneFil materials were selected based on the literature and previous research conducted in our department. The HU numbers were investigated to determine the appropriate percentage infill for skull and soft-tissue equivalence. A Prusa MK3S printer in conjunction with the above-mentioned filaments were used to print the SRS QA phantom. Quality control (QC) was performed on the printed skull, film inserts and plugs for point dose measurements. EBT3 film and point dose measurements were performed using a CC04 ionisation chamber. QC demonstrated that the SRS QA phantom transverse, coronal and sagittal film planes were orthogonal within 0.5°. HU numbers for the skull, film inserts and plugs were 858 ± 20 and 35 ± 12 respectively. Point and EBT3 film dose measurements were within 2.5% and 3%/2 mm 95% gamma pass rate, respectively except one Gross Tumour Volume (GTV) that had a slightly lower gamma pass rate. Dose distributions to five GTVs were measured with EBT3 film in a single plan delivery on CyberKnife. In conclusion, an SRS QA phantom was designed, and 3D printed and its use for performing complex MBT patient specific QA in a single delivery was demonstrated.