Physical and Engineering Sciences in Medicine最新文献

Autism spectrum disorder (ASD) is one of the major neurological symptoms affecting young children. Most neurological diseases are captured through speech, voice and changes in sbrain activity. Research leading to ASD diagnosis is done in different ways; still, the early ASD diagnosis is a complex task. Various co-occurring situations may hinder Automated ASD detection, and deep learners effectively tackle such issues and create a better design. Here, a novel automated autism detection approach is proposed employing a deep learning technique with the help of brain image. Initially, the brain images are garnered from the standard dataset links. These gathered images are employed for the pre-processing stage, which is accomplished by using contrast enhancement. Subsequently, the most noteworthy deep features are extracted from the image pre-processed using a multi-atlas-based residual network (MResNet). Finally, the detection process is carried out by influencing the adaptive cascaded attention long short term memory with bayesian learning (ACAL-BL), in which some of the hyperparameters are tuned optimally by the random fixed marine predators algorithm (RFMPA). The performance is examined under Python using various factors and contrasted with other classical models and the results show that our ACAL-BL achieved an FPR of 4.5%, representing relative improvements of 52%, 54%, 56%, 58%, and 60% compared to LSTM, CNN, ANN, auto encoder, and LSTM-Bayesian learning, respectively. Thus, the suggested technique has the tendency to exploit the outstanding results that aid clinical practitioners to diagnose the disease earlier.

Lung cancer's lethality underscores the need for accurate, real-time detection methods. While bioimpedance spectroscopy (BIS) detects electrical differences between healthy and malignant tissues, prior studies relied on raw impedance values, limiting diagnostic insight. This study introduces a novel framework using fractional-order circuit modeling to extract physiologically relevant features from lung tissue. Ex-vivo BIS measurements (50 kHz-5 MHz) were performed on 328 resected specimens using a tetrapolar probe. Eight circuit models were fitted to the data, including classical Cole models and a newly proposed Parallel Fractional Cole (PFC) model. Although the Double Cole model achieved the best curve-fitting accuracy (mean NRMSE: 1.95%), features from the PFC model enabled superior classification. A sixth-degree polynomial SVM classifier using PFC-derived parameters distinguished tumorous from healthy tissue with 90.00% accuracy, 93.33% sensitivity, 86.67% specificity, and 0.87 AUC. This demonstrates that fractional-order models with biologically aligned topologies not only have high-fitting accuracy but also enhance diagnostic utility. The PFC model's parallel architecture effectively captures the microstructural heterogeneity of lung tumors, offering a pathway to real-time, non-invasive nodule localization during surgery.

A degenerative disease of the patellofemoral joint cartilage, chondromalacia patella (CMP) often results in anterior knee discomfort and functional disability. Determining the best course of therapy and stopping the progression of the disease depend on an accurate and timely diagnosis. In this work, we provide a deep learning architecture based on transformers for the classification of chondromalacia patella using magnetic resonance imaging (MRI) data. We assessed transformer-based designs including Multi-Axis Vision Transformer (MaxViT), Vision Transformer (ViT), and Swin Transformer in addition to convolutional neural network (CNN) based models like Google Network (GoogLeNet), Residual Network 18 (ResNet18), and Mobile Network v2 (MobileNetV2). We evaluated the models' ability to differentiate between cases of chondromalacia patella and normal cases. With an accuracy of 0.9817, precision of 0.9821, recall of 0.9817, and F1-score of 0.9818, Multi-Axis Vision Transformer outperformed all other models on the testing dataset.

To estimate the influence of various loss functions on the performance of deep learning (DL) models for dose prediction in intensity-modulated radiotherapy (IMRT) for prostate cancer. A retrospective dataset comprising 110 prostate cancer patients was utilized. DL model was trained using various loss functions: mean absolute error (MAE), mean squared error (MSE), and combinations of MAE with predefined domain-specific knowledge, including dose-volume histogram (DVH) loss and moment loss function. The planned target volume (PTV) and dosimetric metrics for organs at risk (OARs) were used to assess the model's performance. A one-way analysis of variance (ANOVA) was applied to perform statistical comparisons between the clinical and predicted plans. In terms of dose deviations for OARs and PTV, the model trained with MAE plus moment loss performed better than models trained with MAE + DVH loss, MSE, or MAE. The MAE ± standard deviation (SD) between clinical and predicted dose distributions in the test cohort were (1.76 ± 0.5) Gy, (1.78 ± 0.5) Gy, (1.93 ± 0.6) Gy, and (2.02 ± 0.4) Gy for MAE + moment, MAE + DVH, MSE, and MAE models, respectively. Compared to the ground truth plans, the accuracy of all predicted plans was clinically acceptable. This study highlights how important loss function choice is to the optimization of DL-based prostate IMRT dose prediction models. The performance of the model is greatly improved by incorporating domain-specific knowledge into the loss function, which supports the possible practical application of such models for more precise and personalized radiation planning.

A treatment planning system (TPS) is responsible for calculating the radiation dose for patients undergoing brachytherapy. However, to verify TPS dose accuracy of intracavitary brachytherapy, which feature particularly steep and complex dose gradients, 3D-printed phantoms made of polylactic acid (PLA) can be used. A study was designed to create an in-house phantom for verification of gynecological brachytherapy measurement using a radiophotoluminescent glass dosimeters (RPLGDs) and to evaluate the dosimetric differences between measurement and calculation by the treatment planning system under clinical conditions.An in-house phantom holder was designed to move the axis of the holder to the rectum point that differs according to the patient's anatomy. The holder of the applicator was designed for various types of applicators in intracavitary brachytherapy. This clinical study was used to quantify variations between the calculated and measured dose for 6 plans at various points in the phantom, which included point A, point B, the bladder point, and the rectum points.The RPLGDs demonstrated a linear dose response up to 10 Gy, excellent angular dependence, and an associated uncertainty of 3.3% (k  =  1). In the clinical case, the dose differences between the measured and calculated values at Point A, Point B, bladder, and rectum were +1.99  ±  1.11%, 1.01  ±  0.02 Gy, and 0.10 Gy, +4.42 ± 2.56%. and + 3.53  ± 1.44%, respectively.Dosimetry with RPLGDs using the 3D printed in-house phantom can accurately verify delivered dose in intracavitary brachytherapy for quality assurance purposes.

The demand for bedside radiography is increasing due to critical clinical needs, including infection control and the limited mobility of severely ill patients. However, radiation dose adjustment in these settings remains heavily reliant on the expertise and experience of radiographers. To address this issue, a novel flat panel detector (FPD) integrated with an automatic exposure control (AEC) system has been developed. This study aims to experimentally evaluate the fundamental performance of this system and clarify its clinical utility, including its potential limitations. The dependency of the AEC performance on object thickness and tube voltage was investigated using acrylic phantoms. To simulate clinical scenarios, the AEC response was examined using a chest phantom. Additionally, the effects of source-to-image distance and oblique X-ray incidence on the AEC performance were also evaluated using a quality-control test device. Our results elucidated the behavior of the exposure index (EI) and image quality under varying tube voltage and object thickness. In clinical conditions, the introduction of the AEC system significantly reduced EI, confirming its potential for effective dose management. Multiple factors were identified that influence both the AEC response and image quality, such as sensor positioning, imaging distance, and beam angle. These findings demonstrate that the AEC-equipped FPD system maintains consistent image quality while effectively reducing the radiation dose under various simulated imaging conditions. Our results also underscore the importance of accounting for environmental factors that affect dose control and image characteristics, highlighting the need for practical adjustment in routine clinical operation.

This work presents a preliminary study using an opto-mechatronic system to measure the refractive index and thermo-optical behavior of blood plasma. The setup employs a 650 nm laser and a displacement sensor on a linear actuator to detect beam deviation through small fluid volumes. Using water-based fluids with different glucose levels, a linear decreasing trend in refractive index with temperature was observed. Furthermore, plasma samples with different glucose concentrations were evaluated across a temperature range. One sample, corresponding to a markedly elevated glucose level, exhibited a dual thermo-optical response that suggests a transition to a different optical regime influenced by complex biomolecular composition. To contextualize these findings, numerical modeling under high irradiance was incorporated as a conceptual framework to explore how thermo-optical properties may evolve under stronger light-matter interactions. The simulations indicate that both glucose concentration and molecular polarizability can modulate the thermo-optical coefficient under nonlinear conditions. Rather than demonstrating molecular specificity, these results serve as initial evidence that optical parameters are sensitive to plasma composition and may guide future studies aimed at establishing selective, light-based biochemical analysis.

Congestive heart failure (CHF) is a cardiovascular disease that poses a serious threat to human health. Electrocardiogram (ECG) signals can be used to detect heart diseases such as CHF. However, the low amplitude and short duration of ECG signals severely affected CHF detection. This paper proposes a CHF detection method based on Gramian angular summation field (GASF) and two-dimensional multiscale permutation-ratio entropy (MPRE2D). First, ECG signals are preprocessed and converted into ECG images using the GASF algorithm. GASF can convert one-dimensional ECG signals into two-dimensional coded images containing important information. Then, the two-dimensional permutation-ratio entropy and MPRE2D algorithms are introduced to measure the irregularity and complexity of ECG images. Finally, the MPRE2D features of the image are extracted and the feature vectors are classified using a support vector machine. The classification accuracy is 99.46%, sensitivity 99.36%, specificity 99.63% and F1-score 99.56% on the normal sinus rhythm database and congestive heart failure database. Computer simulations show that the methods based on GASF and MPRE2D provide an effective method for CHF detection. This method can accurately detect patients with CHF using only 2 s of ECG signals length. It not only provides valuable references for clinical doctors to assess and treat CHF, but also offers clinically significant results for CHF risk assessment.

To evaluate ThinkQA (TQA), a collapsed cone convolution-based secondary dose check, as an alternative to MU2net (Clarkson-based, point-dose) for online adaptive planning on the Elekta Unity 1.5 T MR-Linac at Townsville University Hospital. Commissioning followed MPPG 5.b tests. The reference-dose agreement, magnetic-field modelling, directional dependence, output factors, off-axis points, heterogeneous slab geometries and calculation properties were assessed. Nine step-and-shoot IMRT plans (courtesy of Elekta) and 226 retrospectively analysed adapted fractions (prostate and pelvic nodes; planning target volumes 1.9-170.0 cm³) were compared between TQA and Monaco by gamma analysis (global 10.0% threshold; 2.0%/2.0 mm, 3.0%/2.0 mm). At 10.0 cm depth under TQA reference conditions, the mean absolute point-dose difference versus Monaco was 0.4%. TQA reproduced models the magnetic-field-induced cross-plane asymmetry with close agreement to Monaco. Directional dependence differences were ≤  ± 1.2% except when traversing the couch (± 1.8%). Output factors agreed within ≤ 1.0% (SSD 133.5 cm) and ≤ 2.0% (SSD 138.5 cm). In 226 clinical fractions, 3.0%/2.0 mm (global) yielded 93.0% passes in the high-dose region and 100.0% in other regions; 2.0%/2.0 mm yielded 25% high-dose passes. TQA results were available within about 1 min post Monaco export. TQA provides accurate, rapid, volumetric secondary dose verification for Unity, improves agreement with Monaco, and reduces console time by eliminating dose point re-selection. A 3.0%/2.0 mm global gamma criterion is a clinical acceptance level, with tighter criteria reserved for targeted investigations.