Physical and Engineering Sciences in Medicine最新文献

In this paper, we proposed a complete study method to achieve accurate aortic dissection diagnosis at the patient level. Based on the CT angiography (CTA) images, a classification model named DAT-DenseNet, which combined the deep attention Transformer module with the DenseNet architecture is proposed. In the first phase, two DAT-DenseNet are combined in parallel. It is used to accurately achieve two classification task at the CTA images. In the second stage, we propose a feature fusion module. It concatenates and fuses the image features output from the two classification models on a patient by patient basis. In the comparison experiments of classification model performance, DAT-DenseNet obtained 92.41 $\%$ accuracy at the image level, which was 2.20 $\%$ higher than the commonly used model. In the comparison experiments of model fusion method, our method obtained 90.83 $\%$ accuracy at the patient level. The experiments showed that DAT-DenseNet model exhibits high performance at the image level. Our feature fusion module achieves the mapping from two classification image features to patient outcomes. It achieves accurate patient classification. The experiments' results in the Discussion section elaborate the details of the experiment and confirmed that the results were reliable.

The current study aimed to predict lymphovascular invasion (LVI) using multiple machine learning algorithms and multi-segmentation positron emission tomography (PET) radiomics in non-small cell lung cancer (NSCLC) patients, offering new avenues for personalized treatment strategies and improving patient outcomes. One hundred and twenty-six patients with NSCLC were enrolled in this study. Various automated and semi-automated PET image segmentation methods were applied, including Local Active Contour (LAC), Fuzzy-C-mean (FCM), K-means (KM), Watershed, Region Growing (RG), and Iterative thresholding (IT) with different percentages of the threshold. One hundred five radiomic features were extracted from each region of interest (ROI). Multiple feature selection methods, including Minimum Redundancy Maximum Relevance (MRMR), Recursive Feature Elimination (RFE), and Boruta, and multiple classifiers, including Multilayer Perceptron (MLP), Logistic Regression (LR), XGBoost (XGB), Naive Bayes (NB), and Random Forest (RF), were employed. Synthetic Minority Oversampling Technique (SMOTE) was also used to determine if it boosts the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). Our results indicated that the combination of SMOTE, IT (with 45% threshold), RFE feature selection and LR classifier showed the best performance (AUC = 0.93, ACC = 0.84, SEN = 0.85, SPE = 0.84) followed by SMOTE, FCM segmentation, MRMR feature selection, and LR classifier (AUC = 0.92, ACC = 0.87, SEN = 1, SPE = 0.84). The highest ACC belonged to the IT segmentation (with 45 and 50% thresholds) alongside Boruta feature selection and the NB classifier without SMOTE (ACC = 0.9, AUC = 0.78 and 0.76, SEN = 0.7, and SPE = 0.94, respectively). Our results indicate that selection of appropriate segmentation method and machine learning algorithm may be helpful in successful prediction of LVI in patients with NSCLC with high accuracy using PET radiomics analysis.

Diabetic foot ulcer (DFU) is a common chronic complication of diabetes. This complication is characterized by the formation of ulcers that are difficult to heal on the skin of the foot. Ulcers can negatively affect patients' quality of life, and improperly treated lesions can result in amputation and even death. Traditionally, the severity and type of foot ulcers are determined by doctors through visual observations and on the basis of their clinical experience; however, this subjective evaluation can lead to misjudgments. In addition, quantitative methods have been developed for classifying and scoring are therefore time-consuming and labor-intensive. In this paper, we propose a reconstruction residual network with a fused spatial-channel attention mechanism (FARRNet) for automatically classifying DFUs. The use of pseudo-labeling and Data augmentation as a pre-processing technique can overcome problems caused by data imbalance and small sample size. The developed model's attention was enhanced using a spatial channel attention (SPCA) module that incorporates spatial and channel attention mechanisms. A reconstruction mechanism was incorporated into the developed residual network to improve its feature extraction ability for achieving better classification. The performance of the proposed model was compared with that of state-of-the-art models and those in the DFUC Grand Challenge. When applied to the DFUC Grand Challenge, the proposed method outperforms other state-of-the-art schemes in terms of accuracy, as evaluated using 5-fold cross-validation and the following metrics: macro-average F1-score, AUC, Recall, and Precision. FARRNet achieved the F1-score of 60.81%, AUC of 87.37%, Recall of 61.04%, and Precision of 61.56%. Therefore, the proposed model is more suitable for use in medical diagnosis environments with embedded devices and limited computing resources. The proposed model can assist patients in initial identifications of ulcer wounds, thereby helping them to obtain timely treatment.

An automated scoring system for cleanliness assessment during video capsule endoscopy (VCE) is presently lacking. The present study focused on developing an approach to automatically assess the cleanliness in VCE frames as per the latest scoring i.e., Korea-Canada (KODA). Initially, an easy-to-use mobile application called artificial intelligence-KODA (AI-KODA) score was developed to collect a multi-label image dataset of twenty-eight patient capsule videos. Three readers (gastroenterology fellows), who had been trained in reading VCE, rated this dataset in a duplicate manner. The labels were saved automatically in real-time. Inter-rater and intra-rater reliability were checked. The developed dataset was then randomly split into train:validate:test ratio of 70:20:10 and 60:20:20. It was followed by a comprehensive benchmarking and evaluation of three multi-label classification tasks using ten machine learning and two deep learning algorithms. Reliability estimation was found to be overall good among the three readers. Overall, random forest classifier achieved the best evaluation metrics, followed by Adaboost, KNeighbours, and Gaussian naive bayes in the machine learning-based classification tasks. Deep learning algorithms outperformed the machine learning-based classification tasks for only VM labels. Thorough analysis indicates that the proposed approach has the potential to save time in cleanliness assessment and is user-friendly for research and clinical use. Further research is required for the improvement of intra-rater reliability of KODA, and the development of automated multi-task classification in this field.

This study aimed to evaluate the impact of radiation dose and focal spot size on the image quality of super-resolution deep-learning reconstruction (SR-DLR) in comparison with iterative reconstruction (IR) and normal-resolution DLR (NR-DLR) algorithms for cardiac CT. Catphan-700 phantom was scanned on a 320-row scanner at six radiation doses (small and large focal spots at 1.4-4.3 and 5.8-8.8 mGy, respectively). Images were reconstructed using hybrid-IR, model-based-IR, NR-DLR, and SR-DLR algorithms. Noise properties were evaluated through plotting noise power spectrum (NPS). Spatial resolution was quantified with task-based transfer function (TTF); Polystyrene, Delrin, and Bone-50% inserts were used for low-, intermediate, and high-contrast spatial resolution. The detectability index (d') was calculated. Image noise, noise texture, edge sharpness of low- and intermediate-contrast objects, delineation of fine high-contrast objects, and overall quality of four reconstructions were visually ranked. Results indicated that among four reconstructions, SR-DLR yielded the lowest noise magnitude and NPS peak, as well as the highest average NPS frequency, TTF_50%, d' values, and visual rank at each radiation dose. For all reconstructions, the intermediate- to high-contrast spatial resolution was maximized at 4.3 mGy, while the lowest noise magnitude and highest d' were attained at 8.8 mGy. SR-DLR at 4.3 mGy exhibited superior noise performance, intermediate- to high-contrast spatial resolution, d' values, and visual rank compared to the other reconstructions at 8.8 mGy. Therefore, SR-DLR may yield superior diagnostic image quality and facilitate radiation dose reduction compared to the other reconstructions, particularly when combined with small focal spot scanning.

The accurate assessment of film results is highly dependent on the methodology and techniques used to process film. This study aims to compare the performance of EBT3 and EBT-XD film for SRS dosimetry using two different film processing methods. Experiments were performed in a solid water slab and an anthropomorphic head phantom. For each experiment, the net optical density of the film was calculated using two different methods; taking the background (initial) optical density from 1) an unirradiated film from the same film lot as the irradiated film (stock to stock (S-S) method), and 2) a scan of the same piece of film taken prior to irradiation (film to film (F-F) method). EBT3 and EBT-XD performed similarly across the suite of experiments when using the green channel only or with triple channel RGB dosimetry. The dosimetric performance of EBT-XD was improved across all colour channels by using an F-F method, particularly for the blue channel. In contrast, EBT3 performed similarly well regardless of the net optical density method used. Across 21 SRS treatment plans, the average per-pixel agreement between EBT3 and EBT-XD films, normalised to the 20 Gy prescription dose, was within 2% and 4% for the non-target (2-10 Gy) and target (> 10 Gy) regions, respectively, when using the F-F method. At doses relevant to SRS, EBT3 provides comparable dosimetric performance to EBT-XD. In addition, an S-S dosimetry method is suitable for EBT3 while an F-F method should be adopted if using EBT-XD.

This guideline has been prepared by the ACPSEM to provide a standardised quality assurance program to be used within General X-ray imaging environments. The guideline includes the responsibilities of various multidisciplinary team members within medical imaging facilities. It must be noted that the listed tests and testing frequencies are not intended to replace or become regulatory requirements. Implementing a quality assurance program as outlined in this position paper is there to ensure best practice for imaging facilities by providing a framework to establish and monitor correct equipment performance. The current document has been produced through an extensive review of current international practices and local experience within the Australasian healthcare environment. Due to the constant evolution of digital radiographic equipment, there is no current consensus in international quality assurance guidelines as they continue to be adapted and updated. This document describes the current state of the use of digital General X-ray equipment in the Australasian environment and provides recommendations of test procedures that may be best suited for the current medical imaging climate in Australasia. Due to the everchanging developments in the medical imaging environment and the ability of new technologies to perform more complex tasks it is believed that in the future this document will be further reviewed in the hopes of producing a more globally agreed upon standard quality assurance program. Any such adjustments that are deemed to be necessary to Version 1.0 of this document will be provided in electronic format on the ACPSEM website with a notification to all parties involved in the use of digital General X-ray equipment. This guideline does not provide detailed methodologies for all the quality control tests recommended as it is it is expected that the professionals implementing aspects of this quality assurance program have the working knowledge and access to appropriate resources to develop testing methodologies appropriate for their local imaging environment.

This study compared twice-refocused spin-echo sequence (TRSE) and Stejskal-Tanner sequence (ST) to evaluate their respective effects on the image quality of magnetic resonance (MR) diffusion-weighted imaging in the presence of radiofrequency (RF) shielding effect of titanium mesh in cranioplasty. A 1.5-T MR scanner with a Head/Neck coil 20 channels and a phantom simulating the T2 and apparent diffusion coefficient (ADC) value of the human brain were used. Imaging was performed with and without titanium mesh placed on the phantom in TRSE and ST, and normalized absolute average deviation (NAAD), Dice similarity coefficient (DSC), and ADC values were calculated. The NAAD values were significantly lower for TRSE than for ST in the area below the titanium mesh, and the drop rates due to titanium mesh were 14.1% for TRSE and 9.8% for ST. The DSC values were significantly lower for TRSE than for ST. The ADC values were significantly higher for TRSE than for ST without titanium mesh. The ADC values showed no significant difference between TRSE and ST with titanium mesh. The ST had a lower RF shielding effect of titanium mesh than the TRSE.

Surgical excision is the most effective treatment of skin carcinomas (basal cell carcinoma or squamous cell carcinoma). Preoperative assessment of tumoral margins plays a decisive role for a successful result. The aim of this work was to evaluate the possibility that hyperspectral imaging could become a valuable tool in solving this problem. Hyperspectral images of 11 histologically diagnosed carcinomas (six basal cell carcinomas and five squamous cell carcinomas) were acquired prior clinical evaluation and surgical excision. The hyperspectral data were then analyzed using a newly developed method for delineating skin cancer tumor margins. This proposed method is based on a segmentation process of the hyperspectral images into regions with similar spectral and spatial features, followed by a machine learning-based data classification process resulting in the generation of classification maps illustrating tumor margins. The Spectral Angle Mapper classifier was used in the data classification process using approximately 37% of the segments as the training sample, the rest being used for testing. The receiver operating characteristic was used as the method for evaluating the performance of the proposed method and the area under the curve as a metric. The results revealed that the performance of the method was very good, with median AUC values of 0.8014 for SCCs, 0.8924 for BCCs, and 0.8930 for normal skin. With AUC values above 0.89 for all types of tissue, the method was considered to have performed very well. In conclusion, hyperspectral imaging can become an objective aid in the preoperative evaluation of carcinoma margins.

Workforce modelling for Radiation Oncology Medical Physicists (ROMPs) is evolving and challenging, prompting the development of the 2021 Australasian College of Physical Scientists and Engineers in Medicine (ACPSEM) ROMP Workforce (ARW) Model. In the exploration of this model at Sir Charles Gairdner Hospital, a comprehensive productivity exercise was conducted to obtain a detailed breakdown of ROMP time at a granular level. The results provide valuable insights into ROMP activities and enabled an evaluation of ARW Model calculations. The findings also capture the changing ROMP role as evidenced by an increasing involvement in consultation and advisory tasks with other professionals in the field. They also suggest that CyberKnife QA time requirements in the data utilised by the model may need to be revised. This study emphasises features inherent in the model, that need to be understood if the model is to be applied correctly.