Optimised deep k-nearest neighbour's based diabetic retinopathy diagnosis(ODeep-NN) using retinal images

Diabetes mellitus has been regarded as one of the prime health issues in present days, which can often lead to diabetic retinopathy, a complication of the disease that affects the eyes, causing loss of vision. For precisely detecting the condition's existence, clinicians are required to recognise the presence of lesions in colour fundus images, making it an arduous and time-consuming task. To deal with this problem, a lot of work has been undertaken to develop deep learning-based computer-aided diagnosis systems that assist clinicians in making accurate diagnoses of the diseases in medical images. Contrariwise, the basic operations involved in deep learning models lead to the extraction of a bulky set of features, further taking a long period of training to predict the existence of the disease. For effective execution of these models, feature selection becomes an important task that aids in selecting the most appropriate features, with an aim to increase the classification accuracy. This research presents an optimised deep k-nearest neighbours'-based pipeline model in a bid to amalgamate the feature extraction capability of deep learning models with nature-inspired metaheuristic algorithms, further using k-nearest neighbour algorithm for classification. The proposed model attains an accuracy of 97.67 and 98.05% on two different datasets considered, outperforming Resnet50 and AlexNet deep learning models. Additionally, the experimental results also portray an analysis of five different nature-inspired metaheuristic algorithms, considered for feature selection on the basis of various evaluation parameters.

PET brain imaging in neurological disorders

Brain disorders are a series of conditions with damage or loss of neurons, such as Parkinson's disease (PD), Alzheimer's disease (AD), or drug dependence. These individuals have gradual deterioration of cognitive, motor, and other central nervous system functions affected. This degenerative trajectory is intricately associated with dysregulations in neurotransmitter systems. Positron Emission Tomography (PET) imaging, employing radiopharmaceuticals and molecular imaging techniques, emerges as a crucial tool for detecting brain biomarkers. It offers invaluable insights for early diagnosis and distinguishing brain disorders. This article comprehensively reviews the application and progress of conventional and novel PET imaging agents in diagnosing brain disorders. Furthermore, it conducts a thorough analysis on merits and limitations. The article also provides a forward-looking perspective in the future development directions of PET imaging agents for diagnosing brain disorders and proposes potential innovative strategies. It aims to furnish clinicians and researchers with an all-encompassing overview of the latest advancements and forthcoming trends in the utilization of PET imaging for diagnosing brain disorders.

Dosimetric Impact of Delineation and Motion Uncertainties on the Heart and Substructures in Lung Cancer Radiotherapy

AIMS

Delineation variations and organ motion produce difficult-to-quantify uncertainties in planned radiation doses to targets and organs at risk. Similar to manual contouring, most automatic segmentation tools generate single delineations per structure; however, this does not indicate the range of clinically acceptable delineations. This study develops a method to generate a range of automatic cardiac structure segmentations, incorporating motion and delineation uncertainty, and evaluates the dosimetric impact in lung cancer.

MATERIALS AND METHODS

Eighteen cardiac structures were delineated using a locally developed auto-segmentation tool. It was applied to lung cancer planning CTs for 27 curative (planned dose ≥50 Gy) cases, and delineation variations were estimated by using ten mapping-atlases to provide separate substructure segmentations. Motion-related cardiac segmentation variations were estimated by auto-contouring structures on ten respiratory phases for 9/27 cases that had 4D-planning CTs. Dose volume histograms (DVHs) incorporating these variations were generated for comparison.

RESULTS

Variations in mean doses (Dmean), defined as the range in values across ten feasible auto-segmentations, were calculated for each cardiac substructure. Over the study cohort the median variations for delineation uncertainty and motion were 2.20-11.09 Gy and 0.72-4.06 Gy, respectively. As relative values, variations in Dmean were between 18.7%-65.3% and 7.8%-32.5% for delineation uncertainty and motion, respectively. Doses vary depending on the individual planned dose distribution, not simply on segmentation differences, with larger dose variations to cardiac structures lying within areas of steep dose gradient.

CONCLUSION

Radiotherapy dose uncertainties from delineation variations and respiratory-related heart motion were quantified using a cardiac substructure automatic segmentation tool. This predicts the 'dose range' where doses to structures are most likely to fall, rather than single DVH curves. This enables consideration of these uncertainties in cardiotoxicity research and for future plan optimisation. The tool was designed for cardiac structures, but similar methods are potentially applicable to other OARs.

Ultrasound-based bone tracking using cross-correlation enables dynamic measurements of knee kinematics during clinical assessments

Purpose

Measuring joint kinematics in the clinic is important for diagnosing injuries, tracking healing and guiding treatments; however, current methods are limited by accuracy and/or feasibility of widespread clinical adoption. Therefore, the purpose of this study was to develop and validate an ultrasound (US)-based method for measuring knee kinematics during clinical assessments.

Methods

We mimicked four clinical laxity assessments (i.e., anterior, posterior, varus, valgus) on five human cadaver knees using our robotic testing system. We simultaneously collected B-mode cine loops with an US transducer. We computed the errors in kinematics between those measured using our bone-tracking algorithm, which cross-correlated regions of interest across frames of the cine loops, and those measured using optical motion capture with bone pins. Additionally, we conducted studies to determine the effects of loading rate and transducer placement on kinematics measured using our US-based bone tracking.

Results

Pooling the trials at experimental speeds and those downsampled to replicate clinical laxity assessments, the maximum root-mean-square errors of knee kinematics using our bone-tracking algorithm were 2.2 mm and 1.3° for the anterior-posterior and varus-valgus laxity assessments, respectively. Repeated laxity assessments proved to have good-to-excellent repeatability (intraclass correlation coefficients [ICCs] of 0.81-0.99), but ICCs from repositioning the transducer varied more widely, ranging from poor-to-good reproducibility (0.19-0.89).

Conclusion

Our results demonstrate that US is capable of tracking knee kinematics during dynamic movement. Because US is a safe and commonly used imaging modality, when paired with our bone-tracking algorithm, US has the potential to assess dynamic knee kinematics across a wide variety of applications in the clinic.

Level of Evidence

Not applicable.

The neural oscillatory mechanism underlying human brain fingerprint recognition using a portable EEG acquisition device

In recent years, brainprint recognition has emerged as a novel method of personal identity verification. Although studies have demonstrated the feasibility of this technology, some limitations hinder its further development into the society, such as insufficient efficiency (extended wear time for multi-channel EEG cap), complex experimental paradigms (more time in learning and completing experiments), and unclear neurobiological characteristics (lack of intuitive biomarkers and an inability to eliminate the impact of noise on individual differences). Overall, these limitations are due to the incomplete understanding of the underlying neural mechanisms. Therefore, this study aims to investigate the neural mechanisms behind brainwave recognition and simplify the operation process. We recorded prefrontal resting-state EEG data from 40 participants, which is followed up over nine months using a single-channel portable brainwave device. We found that portable devices can effectively and stably capture the characteristics of different subjects in the alpha band (8-13Hz) over long periods, as well as capturing their individual differences (no alpha peak, 1 alpha peak, or 2 alpha peaks). Through correlation analysis, alpha-band activity can reveal the uniqueness of the subjects compared to others within one minute. We further used a descriptive model to dissect the oscillatory and non-oscillatory components in the alpha band, demonstrating the different contributions of fine oscillatory features to individual differences (especially amplitude and bandwidth). Our study validated the feasibility of portable brainwave devices in brainwave recognition and the underlying neural oscillation mechanisms. The fine characteristics of various alpha oscillations will contribute to the accuracy of brainwave recognition, providing new insights for the development of future brainwave recognition technology.

Empowering brain cancer diagnosis: harnessing artificial intelligence for advanced imaging insights

Artificial intelligence (AI) is increasingly being used in the medical field, specifically for brain cancer imaging. In this review, we explore how AI-powered medical imaging can impact the diagnosis, prognosis, and treatment of brain cancer. We discuss various AI techniques, including deep learning and causality learning, and their relevance. Additionally, we examine current applications that provide practical solutions for detecting, classifying, segmenting, and registering brain tumors. Although challenges such as data quality, availability, interpretability, transparency, and ethics persist, we emphasise the enormous potential of intelligent applications in standardising procedures and enhancing personalised treatment, leading to improved patient outcomes. Innovative AI solutions have the power to revolutionise neuro-oncology by enhancing the quality of routine clinical practice.

Micro-environmental personal radio-frequency electromagnetic field exposures in Melbourne: A longitudinal trend analysis

BACKGROUND

A knowledge gap exists regarding longitudinal assessment of personal radio-frequency electromagnetic field (RF-EMF) exposures globally. It is unclear how the change in telecommunication technology over the years translates to change in RF-EMF exposure. This study aims to evaluate longitudinal trends of micro-environmental personal RF-EMF exposures in Australia.

METHODS

The study utilised baseline (2015-16) and follow-up (2022) data on personal RF-EMF exposure (88 MHz-6 GHz) measured across 18 micro-environments in Melbourne. Simultaneous quantile regression analysis was conducted to compare exposure data distribution percentiles, particularly median (P50), upper extreme value (P99) and overall exposure trends. RF-EMF exposures were compared across six exposure source types: mobile downlink, mobile uplink, broadcast, 5G-New Radio, Others and Total (of the aforementioned sources). Frequency-specific exposures measured at baseline and follow-up were compared. Total exposure across different groups of micro-environment types were also compared.

RESULTS

For all micro-environmental data, total (median and P99) exposure levels did not significantly change at follow-up. Overall exposure trend of total exposure increased at follow-up. Mobile downlink contributed the highest exposure among all sources showing an increase in median exposure and overall exposure trend. Of seven micro-environment types, five of them showed total exposure levels (median and P99) and overall exposure trend increased at follow-up.

Characterizing Major Depressive Disorder (MDD) using alpha-band activity in resting-state electroencephalogram (EEG) combined with MATRICS Consensus Cognitive Battery (MCCB)

BACKGROUND

The diagnosis of major depressive disorder (MDD) is commonly based on the subjective evaluation by experienced psychiatrists using clinical scales. Hence, it is particularly important to find more objective biomarkers to aid in diagnosis and further treatment. Alpha-band activity (7-13 Hz) is the most prominent component in resting electroencephalogram (EEG), which is also thought to be a potential biomarker. Recent studies have shown the existence of multiple sub-oscillations within the alpha band, with distinct neural underpinnings. However, the specific contribution of these alpha sub-oscillations to the diagnosis and treatment of MDD remains unclear.

METHODS

In this study, we recorded the resting-state EEG from MDD and HC populations in both open and closed-eye state conditions. We also assessed cognitive processing using the MATRICS Consensus Cognitive Battery (MCCB).

RESULTS

We found that the MDD group showed significantly higher power in the high alpha range (10.5-11.5 Hz) and lower power in the low alpha range (7-8.5 Hz) compared to the HC group. Notably, high alpha power in the MDD group is negatively correlated with working memory performance in MCCB, whereas no such correlation was found in the HC group. Furthermore, using five established classification algorithms, we discovered that combining alpha oscillations with MCCB scores as features yielded the highest classification accuracy compared to using EEG or MCCB scores alone.

CONCLUSIONS

Our results demonstrate the potential of sub-oscillations within the alpha frequency band as a potential distinct biomarker. When combined with psychological scales, they may provide guidance relevant for the diagnosis and treatment of MDD.

Computed chest radiography for total body irradiation: image quality and clinical feasibility

Objective.In myeloablative total body irradiation (TBI), lung shielding blocks are used to reduce the dose to the lungs and hence decrease the risk of radiation pneumonitis. Some centers are still using mega-Volt (MV) imaging with dedicated silver halide-based films during simulation and treatment for lung delineation and position verification. However, the availability of these films has recently become an issue. This study examines the clinical performance of a computed radiography (CR) solution in comparison to radiographic films and potential improvement of image quality by filtering and post-processing.Approach.We compared BaFBrI-based CR plates to radiographic films. First, images of an aluminum block were analyzed to assess filter impact on scatter reduction. Secondly, a dedicated image quality phantom was used to assess signal linearity, signal-to-noise ratio (SNR), contrast and spatial resolution. Ultimately, a clinical performance study involving two impartial observers was conducted on an anthropomorphic chest phantom, employing visual grading analysis (VGA). Various filter materials and positions as well as post-processing were examined, and the workflow between CR and film was compared.Main results.CR images exhibited high SNR and linearity but demonstrated lower spatial and contrast resolution when compared to film. However, filtering improved contrast resolution and SNR, while positioning filters inside the cassette additionally enhanced sharpness. Image processing improved VGA scores, while additional filtering also resulted in higher spine visibility scores. CR shortened TBI simulation by over 10 minutes for one patient, alongside a dose reduction by order of 0.1 Gy.Significance.This study highlights potential advantages of shifting from conventional radiographic film to CR for TBI. Overall, CR with the incorporation of processing and filtering proves to be suitable for TBI chest imaging. When compared to radiographic film, CR offers advantages such as reduced simulation time and dose delivery, re-usability of image plates and digital workflow integration.

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

BACKGROUND AND PURPOSE

Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap.

METHODS AND MATERIALS

A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended.

RESULTS

The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated.

CONCLUSION

A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.

MADR-Net: multi-level attention dilated residual neural network for segmentation of medical images

Medical image segmentation has made a significant contribution towards delivering affordable healthcare by facilitating the automatic identification of anatomical structures and other regions of interest. Although convolution neural networks have become prominent in the field of medical image segmentation, they suffer from certain limitations. In this study, we present a reliable framework for producing performant outcomes for the segmentation of pathological structures of 2D medical images. Our framework consists of a novel deep learning architecture, called deep multi-level attention dilated residual neural network (MADR-Net), designed to improve the performance of medical image segmentation. MADR-Net uses a U-Net encoder/decoder backbone in combination with multi-level residual blocks and atrous pyramid scene parsing pooling. To improve the segmentation results, channel-spatial attention blocks were added in the skip connection to capture both the global and local features and superseded the bottleneck layer with an ASPP block. Furthermore, we introduce a hybrid loss function that has an excellent convergence property and enhances the performance of the medical image segmentation task. We extensively validated the proposed MADR-Net on four typical yet challenging medical image segmentation tasks: (1) Left ventricle, left atrium, and myocardial wall segmentation from Echocardiogram images in the CAMUS dataset, (2) Skin cancer segmentation from dermoscopy images in ISIC 2017 dataset, (3) Electron microscopy in FIB-SEM dataset, and (4) Fluid attenuated inversion recovery abnormality from MR images in LGG segmentation dataset. The proposed algorithm yielded significant results when compared to state-of-the-art architectures such as U-Net, Residual U-Net, and Attention U-Net. The proposed MADR-Net consistently outperformed the classical U-Net by 5.43%, 3.43%, and 3.92% relative improvement in terms of dice coefficient, respectively, for electron microscopy, dermoscopy, and MRI. The experimental results demonstrate superior performance on single and multi-class datasets and that the proposed MADR-Net can be utilized as a baseline for the assessment of cross-dataset and segmentation tasks.

Prediction of coronary artery disease based on facial temperature information captured by non-contact infrared thermography

BACKGROUND

Current approaches for initial coronary artery disease (CAD) assessment rely on pretest probability (PTP) based on risk factors and presentations, with limited performance. Infrared thermography (IRT), a non-contact technology that detects surface temperature, has shown potential in assessing atherosclerosis-related conditions, particularly when measured from body regions such as faces. We aim to assess the feasibility of using facial IRT temperature information with machine learning for the prediction of CAD.

METHODS

Individuals referred for invasive coronary angiography or coronary CT angiography (CCTA) were enrolled. Facial IRT images captured before confirmatory CAD examinations were used to develop and validate a deep-learning IRT image model for detecting CAD. We compared the performance of the IRT image model with the guideline-recommended PTP model on the area under the curve (AUC). In addition, interpretable IRT tabular features were extracted from IRT images to further validate the predictive value of IRT information.

RESULTS

A total of 460 eligible participants (mean (SD) age, 58.4 (10.4) years; 126 (27.4%) female) were included. The IRT image model demonstrated outstanding performance (AUC 0.804, 95% CI 0.785 to 0.823) compared with the PTP models (AUC 0.713, 95% CI 0.691 to 0.734). A consistent level of superior performance (AUC 0.796, 95% CI 0.782 to 0.811), achieved with comprehensive interpretable IRT features, further validated the predictive value of IRT information. Notably, even with only traditional temperature features, a satisfactory performance (AUC 0.786, 95% CI 0.769 to 0.803) was still upheld.

CONCLUSION

In this prospective study, we demonstrated the feasibility of using non-contact facial IRT information for CAD prediction.

A transformer-guided cross-modality adaptive feature fusion framework for esophageal gross tumor volume segmentation

BACKGROUND AND OBJECTIVE

Accurate segmentation of esophageal gross tumor volume (GTV) indirectly enhances the efficacy of radiotherapy for patients with esophagus cancer. In this domain, learning-based methods have been employed to fuse cross-modality positron emission tomography (PET) and computed tomography (CT) images, aiming to improve segmentation accuracy. This fusion is essential as it combines functional metabolic information from PET with anatomical information from CT, providing complementary information. While the existing three-dimensional (3D) segmentation method has achieved state-of-the-art (SOTA) performance, it typically relies on pure-convolution architectures, limiting its ability to capture long-range spatial dependencies due to convolution's confinement to a local receptive field. To address this limitation and further enhance esophageal GTV segmentation performance, this work proposes a transformer-guided cross-modality adaptive feature fusion network, referred to as TransAttPSNN, which is based on cross-modality PET/CT scans.

METHODS

Specifically, we establish an attention progressive semantically-nested network (AttPSNN) by incorporating the convolutional attention mechanism into the progressive semantically-nested network (PSNN). Subsequently, we devise a plug-and-play transformer-guided cross-modality adaptive feature fusion model, which is inserted between the multi-scale feature counterparts of a two-stream AttPSNN backbone (one for the PET modality flow and another for the CT modality flow), resulting in the proposed TransAttPSNN architecture.

RESULTS

Through extensive four-fold cross-validation experiments on the clinical PET/CT cohort. The proposed approach acquires a Dice similarity coefficient (DSC) of 0.76 ± 0.13, a Hausdorff distance (HD) of 9.38 ± 8.76 mm, and a Mean surface distance (MSD) of 1.13 ± 0.94 mm, outperforming the SOTA competing methods. The qualitative results show a satisfying consistency with the lesion areas.

CONCLUSIONS

The devised transformer-guided cross-modality adaptive feature fusion module integrates the strengths of PET and CT, effectively enhancing the segmentation performance of esophageal GTV. The proposed TransAttPSNN has further advanced the research of esophageal GTV segmentation.

3D-printed boluses for radiotherapy: influence of geometrical and printing parameters on dosimetric characterization and air gap evaluation

The work investigates the implementation of personalized radiotherapy boluses by means of additive manufacturing technologies. Boluses materials that are currently used need an excessive amount of human intervention which leads to reduced repeatability in terms of dosimetry. Additive manufacturing can solve this problem by eliminating the human factor in the process of fabrication. Planar boluses with fixed geometry and personalized boluses printed starting from a computed tomography scan of a radiotherapy phantom were produced. First, a dosimetric characterization study on planar bolus designs to quantify the effects of print parameters such as infill density and geometry on the radiation beam was made. Secondly, a volumetric quantification of air gap between the bolus and the skin of the patient as well as dosimetric analyses were performed. The optimization process according to the obtained dosimetric and airgap results allowed us to find a combination of parameters to have the 3D-printed bolus performing similarly to that in conventional use. These preliminary results confirm those in the relevant literature, with 3D-printed boluses showing a dosimetric performance similar to conventional boluses with the additional advantage of being perfectly conformed to the patient geometry.

Evaluation of overexposure risk when there is a space between the subject and the couch in computed tomography: a phantom study

The purpose of this study was to investigate the risk of overexposure associated with automatic tube current modulation (ATCM) and automatic couch height positioning compensation mechanism (AHC) in computed tomography (CT) systems, particularly in scenarios involving a gap between the subject and the couch. Results revealed that when AHC was enabled, CT dose index volume (CTDIvol) increased by approximately 10% at 2.5 cm, 20% at 5.0 cm, and 40% at 10.0 cm gaps compared to close contact conditions. While the AHC function ensures consistent exposure doses and image quality regardless of subject positioning relative to the CT gantry isocenter, the study highlights a potential risk of overexposure when a gap exists between the subject and the couch. These findings offer valuable insights for optimizing CT imaging protocols and underscore the importance of carefully considering subject positioning in clinical practice.

Effect of veno-arterial extracorporeal membrane oxygenation lower-extremity cannulation on intra-arterial flow characteristics, oxygen content, and thrombosis risk

PURPOSE

This study aimed to investigate the effects of lower-extremity cannulation on the intra-arterial hemodynamic environment, oxygen content, blood damage, and thrombosis risk under different levels of veno-arterial (V-A) ECMO support.

METHODS

Computational fluid dynamics methods were used to investigate the effects of different levels of ECMO support (ECMO flow ratios supplying oxygen-rich blood 100-40 %). Flow rates and oxygen content in each arterial branch were used to determine organ perfusion. A new thrombosis model considering platelet activation and deposition was proposed to determine the platelet activation and thrombosis risk at different levels of ECMO support. A red blood cell damage model was used to explore the risk of hemolysis.

RESULTS

Our study found that partial recovery of cardiac function improved the intra-arterial hemodynamic environment, with reduced impingement of the intra-arterial flow field by high-velocity blood flow from the cannula, a flow rate per unit time into each arterial branch closer to physiological levels, and improved perfusion in the lower extremities. Partial recovery of cardiac function helps reduce intra-arterial high shear stress and residence time, thereby reducing blood damage. The overall level of hemolysis and platelet activation in the aorta decreased with the gradual recovery of cardiac contraction function. The areas at high risk of thrombosis under V-A ECMO femoral cannulation support were the aortic root and the area distal to the cannula, which moved to the descending aorta when cardiac function recovered to 40-60 %. However, with the recovery of cardiac contraction function, hypoxic blood pumped by the heart is insufficient in supplying oxygen to the front of the aortic arch, which may result in upper extremity hypoxia.

CONCLUSION

We developed a thrombosis risk prediction model applicable to ECMO cannulation and validated the model accuracy using clinical data. Partial recovery of cardiac function contributed to an improvement in the aortic hemodynamic environment and a reduction in the risk of blood damage; however, there is a potential risk of insufficient perfusion of oxygen-rich blood to organs.

All you need is data preparation: A systematic review of image harmonization techniques in Multi-center/device studies for medical support systems

BACKGROUND AND OBJECTIVES

Artificial intelligence (AI) models trained on multi-centric and multi-device studies can provide more robust insights and research findings compared to single-center studies. However, variability in acquisition protocols and equipment can introduce inconsistencies that hamper the effective pooling of multi-source datasets. This systematic review evaluates strategies for image harmonization, which standardizes appearances to enable reliable AI analysis of multi-source medical imaging.

METHODS

A literature search using PRISMA guidelines was conducted to identify relevant papers published between 2013 and 2023 analyzing multi-centric and multi-device medical imaging studies that utilized image harmonization approaches.

RESULTS

Common image harmonization techniques included grayscale normalization (improving classification accuracy by up to 24.42 %), resampling (increasing the percentage of robust radiomics features from 59.5 % to 89.25 %), and color normalization (enhancing AUC by up to 0.25 in external test sets). Initially, mathematical and statistical methods dominated, but machine and deep learning adoption has risen recently. Color imaging modalities like digital pathology and dermatology have remained prominent application areas, though harmonization efforts have expanded to diverse fields including radiology, nuclear medicine, and ultrasound imaging. In all the modalities covered by this review, image harmonization improved AI performance, with increasing of up to 24.42 % in classification accuracy and 47 % in segmentation Dice scores.

CONCLUSIONS

Continued progress in image harmonization represents a promising strategy for advancing healthcare by enabling large-scale, reliable analysis of integrated multi-source datasets using AI. Standardizing imaging data across clinical settings can help realize personalized, evidence-based care supported by data-driven technologies while mitigating biases associated with specific populations or acquisition protocols.

Prediction of histopathologic grades of bladder cancer with radiomics based on MRI: Comparison with traditional MRI

PURPOSE

To compare biparametric magnetic resonance imaging (bp-MRI) radiomics signatures and traditional MRI model for the preoperative prediction of bladder cancer (BCa) grade.

MATERIALS AND METHODS

This retrospective study included 255 consecutive patients with pathologically confirmed 113 low-grade and 142 high-grade BCa. The traditional MRI nomogram model was developed using univariate and multivariate logistic regression by the mean apparent diffusion coefficient (ADC), vesical imaging reporting and data system, tumor size, and the number of tumors. Volumes of interest were manually drawn on T2-weighted imaging (T2WI) and ADC maps by 2 radiologists. Using one-way analysis of variance, correlation, and least absolute shrinkage and selection operator methods to select features. Then, a logistic regression classifier was used to develop the radiomics signatures. Receiver operating characteristic (ROC) analysis was used to compare the diagnostic abilities of the radiomics and traditional MRI models by the DeLong test. Finally, decision curve analysis was performed by estimating the clinical usefulness of the 2 models.

RESULTS

The area under the ROC curves (AUCs) of the traditional MRI model were 0.841 in the training cohort and 0.806 in the validation cohort. The AUCs of the 3 groups of radiomics model [ADC, T2WI, bp-MRI (ADC and T2WI)] were 0.888, 0.875, and 0.899 in the training cohort and 0.863, 0.805, and 0.867 in the validation cohort, respectively. The combined radiomics model achieved higher AUCs than the traditional MRI model. decision curve analysis indicated that the radiomics model had higher net benefits than the traditional MRI model.

CONCLUSION

The bp-MRI radiomics model may help distinguish high-grade and low-grade BCa and outperforming the traditional MRI model. Multicenter validation is needed to acquire high-level evidence for its clinical application.

Alternative muscle synergy patterns of upper limb amputees

Myoelectric hand prostheses are effective tools for upper limb amputees to regain hand functions. Much progress has been made with pattern recognition algorithms to recognize surface electromyography (sEMG) patterns, but few attentions was placed on the amputees' motor learning process. Many potential myoelectric prostheses users could not fully master the control or had declined performance over time. It is possible that learning to produce distinct and consistent muscle activation patterns with the residual limb could help amputees better control the myoelectric prosthesis. In this study, we observed longitudinal effect of motor skill learning with 2 amputees who have developed alternative muscle activation patterns in response to the same set of target prosthetic actions. During a 10-week program, amputee participants were trained to produce distinct and constant muscle activations with visual feedback of live sEMG and without interaction with prosthesis. At the end, their sEMG patterns were different from each other and from non-amputee control groups. For certain intended hand motion, gradually reducing root mean square (RMS) variance was observed. The learning effect was also assessed with a CNN-LSTM mixture classifier designed for mobile sEMG pattern recognition. The classification accuracy had a rising trend over time, implicating potential performance improvement of myoelectric prosthesis control. A follow-up session took place 6 months after the program and showed lasting effect of the motor skill learning in terms of sEMG pattern classification accuracy. The results indicated that with proper feedback training, amputees could learn unique muscle activation patterns that allow them to trigger intended prosthesis functions, and the original motor control scheme is updated. The effect of such motor skill learning could help to improve myoelectric prosthetic control performance.

Time-domain heart rate dynamics in the prognosis of progressive atherosclerosis

BACKGROUND AND AIM

The regular uptake of a high-fat diet (HFD) with changing lifestyle causes atherosclerosis leading to cardiovascular diseases and autonomic dysfunction. Therefore, the current study aimed to investigate the correlation of autonomic activity to lipid and atherosclerosis markers. Further, the study proposes a support vector machine (SVM) based model in the prediction of atherosclerosis severity.

METHODS AND RESULTS

The Lead-II electrocardiogram and blood markers were measured from both the control and the experiment subjects each week for nine consecutive weeks. The time-domain heart rate variability (HRV) parameters were derived, and the significance level was tested using a one-way Analysis of Variance. The correlation analysis was performed to determine the relation between autonomic parameters and lipid and atherosclerosis markers. The statistically significant time-domain values were used as features of the SVM. The observed results demonstrated the reduced time domain HRV parameters with the increase in lipid and atherosclerosis index markers with the progressive atherosclerosis severity. The correlation analysis revealed a negative association between time-domain HRV parameters with lipid and atherosclerosis parameters. The percentage accuracy increases from 86.58% to 98.71% with the increase in atherosclerosis severity with regular consumption of HFD.

CONCLUSIONS

Atherosclerosis causes autonomic dysfunction with reduced HRV. The negative correlation between autonomic parameters and lipid profile and atherosclerosis indexes marker revealed the potential role of vagal activity in the prognosis of atherosclerosis progression. The support vector machine presented a respectable accuracy in the prediction of atherosclerosis severity from the control group.

A study of polarity effect for various ionization chambers in kilovoltage x-ray beams

BACKGROUND

Ionization chambers play an essential role in dosimetry measurements for kilovoltage (kV) x-ray beams. Despite their widespread use, there is limited data on the absolute values for the polarity correction factors across a range of commonly employed ionization chambers.

PURPOSE

This study aimed to investigate the polarity effects for five different ionization chambers in kV x-ray beams.

METHODS

Two plane-parallel chambers being the Advanced Markus and Roos and three cylindrical chambers; 3D PinPoint, Semiflex and Farmer chamber (PTW, Freiburg, Germany), were employed to measure the polarity correction factors. The kV x-ray beams were produced from an Xstrahl 300 unit (Xstrahl Ltd., UK). All measurements were acquired at 2 cm depth in a PTW-MP1 water tank for beams between 60 kVp (HVL 1.29 mm Al) and 300 kVp (HVL 3.08 mm Cu), and field sizes of 2-10 cm diameter for 30 cm focus-source distance (FSD) and 4 × 4 cm2 - 20 × 20 cm2 for 50 cm FSD. The ionization chambers were connected to a PTW-UNIDOS electrometer, and the polarity effect was determined using the AAPM TG-61 code of practice methodology.

RESULTS

The study revealed significant polarity effects in ionization chambers, especially in those with smaller volumes. For the plane-parallel chambers, the Advanced Markus chamber exhibited a maximum polarity effect of 2.5%, whereas the Roos chamber showed 0.3% at 150 KVp with the 10 cm circular diameter open-ended applicator. Among the cylindrical chambers at the same beam energy and applicator, the Pinpoint chamber exhibited a 3% polarity effect, followed by Semiflex with 1.7%, and Farmer with 0.4%. However, as the beam energy increased to 300 kVp, the polarity effect significantly increased reaching 8.5% for the Advanced Markus chamber and 13.5% for the PinPoint chamber at a 20 × 20 cm2 field size. Notably, the magnitude of the polarity effect increased with both the field size and beam energy, and was significantly influenced by the size of the chamber's sensitive volume.

CONCLUSIONS

The findings demonstrate that ionization chambers can exhibit substantial polarity effects in kV x-ray beams, particularly for those chambers with smaller volumes. Therefore, it is important to account for polarity corrections when conducting relative dose measurements in kV x-ray beams to enhance the dosimetry accuracy and improve patient dose calculations.

Brain waves and landscape settings: emotional responses to attractiveness

Neuro-architecture is a specific branch of architecture that studies how the physical environment can change our mental processes and influence our behaviors. One of the main purposes of this field is to use changes in brain activities as a measure to quantify attractiveness of the landscapes. In this study, we investigated how changes in elements of attractiveness influence ones' emotional perception and present the related pattern of changes in brain activities. Therefore, we implied five elements of attractiveness including mystery, visual openness, landscape or greenness, walkability, and social interaction using the Delphi method. Then, we made changes in each element separately to make the landscape more attractive and assessed their effects on a group of young adults. We used the self-assessment manikin questionnaire to measure the participants' emotional perception while the participants' brain activities were recorded using a 32-channel EEG while exposed to the landscape images. The results showed that changes in attractive elements of the landscape could significantly improve ones' emotional perception of the landscape. In addition, these changes are perceived by changing the oscillatory pattern of brain activities. We hope these findings could shed a light to use of neural markers in measurement of place attractiveness.

Bibliometric Analysis of Scientific Output Growth in the Field of Lung Transplantation

BACKGROUND

 Lung transplantation (LT) has recently emerged as a scientifically validated curative therapeutic modality for patients afflicted with end-stage lung disease. This study aimed to conduct a global bibliometric analysis of research articles on LT between 1983 and 2021.

METHODS

 Employing the Web of Science database, a bibliometric analysis was conducted to assess the expansion of scientific output within the field of LT. We searched specific bibliometric characteristics such as language, and year of publication, first author, institutional affiliation, main publishing journals, and highly cited articles. Additionally, we made comparisons of the most productive countries. The VOSviewer program and the open-source visualization software Biblioshiny (version 2.0) were used to perform the bibliometric analysis.

RESULTS

 We identified 10,467 articles on LT published between 1983 and 2021, of which 94.898% were published in the Science Citation Index Expanded. The articles were from 101 different research areas. The publications were from 81 different countries globally, and mostly from the United States (41.196%), Germany (7.118%), and Canada (6.372%). The Journal of Heart and Lung Transplantation was the most published journal. Four thousand seven hundred and ninety three of the publications were published in the last 10 years with a 78,781 citation number in total. The highest number of publications and citations was in 2021.

CONCLUSION

 The majority of cutting-edge research findings are focused on only a few developed nations, and exchanges with emerging nations are still in their infancy. The United States has a strong, commanding position among the active countries in LT.

An image-based metal artifact reduction technique utilizing forward projection in computed tomography

The projection data generated via the forward projection of a computed tomography (CT) image (FP-data) have useful potentials in cases where only image data are available. However, there is a question of whether the FP-data generated from an image severely corrupted by metal artifacts can be used for the metal artifact reduction (MAR). The aim of this study was to investigate the feasibility of a MAR technique using FP-data by comparing its performance with that of a conventional robust MAR using projection data normalization (NMARconv). The NMARconv was modified to make use of FP-data (FPNMAR). A graphics processing unit was used to reduce the time required to generate FP-data and subsequent processes. The performances of FPNMAR and NMARconv were quantitatively compared using a normalized artifact index (AIn) for two cases each of hip prosthesis and dental fillings. Several clinical CT images with metal artifacts were processed by FPNMAR. The AIn values of FPNMAR and NMARconv were not significantly different from each other, showing almost the same performance between these two techniques. For all the clinical cases tested, FPNMAR significantly reduced the metal artifacts; thereby, the images of the soft tissues and bones obscured by the artifacts were notably recovered. The computation time per image was ~ 56 ms. FPNMAR, which can be applied to CT images without accessing the projection data, exhibited almost the same performance as that of NMARconv, while consuming significantly shorter processing time. This capability testifies the potential of FPNMAR for wider use in clinical settings.

Radiomic Prediction of CCND1 Expression Levels and Prognosis in Low-grade Glioma Based on Magnetic Resonance Imaging

OJECTIVES

Low-grade glioma (LGG) is associated with increased mortality owing to recrudescence and the tendency for malignant transformation. Therefore, it is imperative to discover novel prognostic biomarkers as existing traditional prognostic biomarkers of glioma, including clinicopathological features and imaging examinations, are unable to meet the clinical demand for precision medicine. Accordingly, we aimed to evaluate the prognostic value of cyclin D1 (CCND1) expression levels and construct radiomic models to predict these levels in patients with LGG MATERIALS AND METHODS: A total of 412 LGG cases from The Cancer Genome Atlas (TCGA) were used for gene-based prognostic analysis. Using magnetic resonance imaging (MRI) images stored in The Cancer Imaging Archive with genomic data from TCGA, 149 cases were selected for radiomics feature extraction and model construction. After feature extraction, the radiomic signature was constructed using logistic regression (LR) and support vector machine (SVM) analyses.

RESULTS

CCND1 was identified as a prognosis-related gene with differential expression in tumor and normal samples and plays a role in regulating both the cell cycle and immune response. Landmark analysis revealed that high-expression levels of CCND1 were beneficial for survival (P < 0.05) in advanced LGG. Four optimal radiomics features were selected to construct radiomics models. The performance of LR and SVM achieved areas under the curve of 0.703 and 0.705, as well as 0.724 and 0.726 in the training and validation sets, respectively.

CONCLUSION

Elevated levels of CCND1 expression could impact the prognosis of patients with LGG. MRI-based radiomics, especially the AUC values, can serve as a novel tool for predicting CCND1 expression and understanding the correlation between elevated CCND1 expression and prognosis.

AVAILABILITY OF DATA AND MATERIALS

The datasets analyzed during the current study are available in the TCGA, TCIA, UCSC XENA and GTEx repository, https://portal.gdc.cancer.gov/, https://www.cancerimagingarchive.net/, https://xenabrowser.net/datapages/, https://www.gtexportal.org/home/.

S-WD-EEMD: A hybrid framework for imbalanced sEMG signal analysis in diagnosis of human knee abnormality

The diagnosis of human knee abnormalities using the surface electromyography (sEMG) signal obtained from lower limb muscles with machine learning is a major problem due to the noisy nature of the sEMG signal and the imbalance in data corresponding to healthy and knee abnormal subjects. To address this challenge, a combination of wavelet decomposition (WD) with ensemble empirical mode decomposition (EEMD) and the Synthetic Minority Oversampling Technique (S-WD-EEMD) is proposed. In this study, a hybrid WD-EEMD is considered for the minimization of noises produced in the sEMG signal during the collection, while the Synthetic Minority Oversampling Technique (SMOTE) is considered to balance the data by increasing the minority class samples during the training of machine learning techniques. The findings indicate that the hybrid WD-EEMD with SMOTE oversampling technique enhances the efficacy of the examined classifiers when employed on the imbalanced sEMG data. The F-Score of the Extra Tree Classifier, when utilizing WD-EEMD signal processing with SMOTE oversampling, is 98.4%, whereas, without the SMOTE oversampling technique, it is 95.1%.

AI-Based Metamaterial Design

The use of metamaterials in various devices has revolutionized applications in optics, healthcare, acoustics, and power systems. Advancements in these fields demand novel or superior metamaterials that can demonstrate targeted control of electromagnetic, mechanical, and thermal properties of matter. Traditional design systems and methods often require manual manipulations which is time-consuming and resource intensive. The integration of artificial intelligence (AI) in optimizing metamaterial design can be employed to explore variant disciplines and address bottlenecks in design. AI-based metamaterial design can also enable the development of novel metamaterials by optimizing design parameters that cannot be achieved using traditional methods. The application of AI can be leveraged to accelerate the analysis of vast data sets as well as to better utilize limited data sets via generative models. This review covers the transformative impact of AI and AI-based metamaterial design for optics, acoustics, healthcare, and power systems. The current challenges, emerging fields, future directions, and bottlenecks within each domain are discussed.

Strengthening education and training programmes for medical physics in Asia and the Pacific: the IAEA non-agreement technical cooperation (TC) regional RAS6088 project

This article documents the work conducted in implementing the IAEA non-agreement TC regional RAS6088 project "Strengthening Education and Training Programmes for Medical Physics". Necessary information on the project was collected from the project counterparts via emails for a period of one month, starting from 21st September 2023, and verified at the Final Regional Coordination Meeting in Bangkok, Thailand from 30th October 2023 to 3rd November 2023. Sixty-three participants were trained in 5 Regional Training Courses (RTCs), with 48%, 32% and 20% in radiation therapy, diagnostic radiology, and nuclear medicine, respectively. One RTC was successfully organised to introduce molecular biology as an academic module to participants. Three participating Member States, namely United Arab Emirates (UAE), Nepal and Afghanistan have initiated processes to start the postgraduate master medical physics education programmes by coursework, adopting the IAEA TCS56 Guidelines. UAE has succeeded in completing the process while Nepal and Afghanistan have yet to initiate the programme. The postgraduate master medical physics programmes by coursework were strengthened in Indonesia, Jordan, Malaysia, Pakistan, Syria, and Thailand, along with the national registration of medical physicists. In particular, Thailand has revised 6 postgraduate master medical physics programmes by coursework during the tenure of this project. Home Based Assignment and RTCs have resulted in two publications. In conclusion, the RAS6088 project was found to have achieved its planned outcomes despite challenges faced due to the COVID-19 pandemic. It is proposed that a follow up project be implemented to increase the number of Member States who are better prepared to improve medical physics education and training in the region.

Improving motion management in radiation therapy: findings from a workshop and survey in Australia and New Zealand

Motion management has become an integral part of radiation therapy. Multiple approaches to motion management have been reported in the literature. To allow the sharing of experiences on current practice and emerging technology, the University of Sydney and the New South Wales/Australian Capital Territory branch of the Australasian College of Physical Scientists and Engineers in Medicine (ACPSEM) held a two-day motion management workshop. To inform the workshop program, participants were invited to complete a survey prior to the workshop on current use of motion management techniques and their opinion on the effectiveness of each approach. A post-workshop survey was also conducted, designed to capture changes in opinion as a result of workshop participation. The online workshop was the most well attended ever hosted by the ACPSEM, with over 300 participants and a response to the pre-workshop survey was received from at least 60% of the radiation therapy centres in Australia and New Zealand. Motion management is extensively used in the region with use of deep inspiration breath-hold (DIBH) reported by 98% of centres for left-sided breast treatments and 91% for at least some right-sided breast treatments. Surface guided radiation therapy (SGRT) was the most popular session at the workshop and survey results showed that the use of SGRT is likely to increase. The workshop provided an excellent opportunity for the exchange of knowledge and experience, with most survey respondents indicating that their participation would lead to improvements in the quality of delivery of treatments at their centres.

Design and validation of dual-point time-differentiated photoplethysmogram (2PPG) wearable for cuffless blood pressure estimation

BACKGROUND & OBJECTIVES

Measurement of blood pressure (BP) in ambulatory patients is crucial for at high-risk cardiovascular patients. A non-obtrusive, non-occluding device that continuously measures BP via photoplethysmography will enable long-term ambulatory assessment of BP. The aim of this study is to validate the metasense 2PPG cuffless wearable design for continuous BP estimation without ECG.

METHODS

A customized high-speed electronic optical sensor architecture with laterally spaced reflectance pulse oximetry was designed into a simple unobtrusive low-power wearable in the form of a watch. 78 volunteers with a mean age of 32.72 ± 7.4 years (21 to 64), 51% male, 49% female were recruited with ECG-2PPG signals acquired. The fiducial features of the 2PPG morphologies were then attributed to the estimator. A 9-1 K-fold cross-validation was applied in the ML.

RESULTS

The correlation for PTT-SBP was 0.971 and for PTT-DBP was 0.954. The mean absolute error was 3.167±1.636 mmHg for SBP and 6.4 ± 3.9 mm Hg for DBP. The ambulatory estimate for SBP and DBP for an individual over 3 days with 8-hour recordings was 0.70-0.81 for SBP and 0.42-0.51 for DBP with a ± 2.65 mmHg for SBP and ±2.02 mmHg for DBP. For SBP, 98% of metasense measurements were within 15 mm Hg and for DBP, 91% of metasense measurements were within 10 mmHg CONCLUSIONS: The metasense device provides continuous, non-invasive BP estimations that are comparable to ambulatory BP meters. The portability and unobtrusiveness of this device, as well as the ability to continuously measure BP could one day enable long-term ambulatory BP measurement for precision cardiovascular therapeutic regimens.

Quantification of deformable image registration uncertainties for dose accumulation on head and neck cancer proton treatments

PURPOSE

Head and neck cancer (HNC) patients in radiotherapy require adaptive treatment plans due to anatomical changes. Deformable image registration (DIR) is used in adaptive radiotherapy, e.g. for deformable dose accumulation (DDA). However, DIR's ill-posedness necessitates addressing uncertainties, often overlooked in clinical implementations. DIR's further clinical implementation is hindered by missing quantitative commissioning and quality assurance tools. This study evaluates one pathway for more quantitative DDA uncertainties.

METHODS

For five HNC patients, each with multiple repeated CTs acquired during treatment, a simultaneous-integrated boost (SIB) plan was optimized. Recalculated doses were warped individually using multiple DIRs from repeated to reference CTs, and voxel-by-voxel dose ranges determined an error-bar for DDA. Followed by evaluating, a previously proposed early-stage DDA uncertainty estimation method tested for lung cancer, which combines geometric DIR uncertainties, dose gradients and their directional dependence, in the context of HNC.

RESULTS

Applying multiple DIRs show dose differences, pronounced in high dose gradient regions. The patient with largest anatomical changes (-13.1 % in ROI body volume), exhibited 33 % maximum uncertainty in contralateral parotid, with 54 % of voxels presenting an uncertainty >5 %. Accumulation over multiple CTs partially mitigated uncertainties. The estimation approach predicted 92.6 % of voxels within ±5 % to the reference dose uncertainty across all patients.

CONCLUSIONS

DIR variations impact accumulated doses, emphasizing DDA uncertainty quantification's importance for HNC patients. Multiple DIR dose warping aids in quantifying DDA uncertainties. An estimation approach previously described for lung cancer was successfully validated for HNC, for SIB plans, presenting different dose gradients, and for accumulated treatments.

3-Way hybrid analysis using clinical and magnetic resonance imaging for early diagnosis of Alzheimer's disease

Alzheimer's is a progressive neurodegenerative disorder that leads to cognitive impairment and ultimately death. To select the most effective treatment options, it is crucial to diagnose and classify the disease early, as current treatments can only delay its progression. However, previous research on Alzheimer's disease (AD) has had limitations, such as inaccuracies and reliance on a small, unbalanced binary dataset. In this study, we aimed to evaluate the early stages of AD using three multiclass datasets: OASIS, EEG, and ADNI MRI. The research consisted of three phases: pre-processing, feature extraction, and classification using hybrid learning techniques. For the OASIS and ADNI MRI datasets, we computed the mean RGB value and used an averaging filter to enhance the images. We balanced and augmented the dataset to increase its size. In the case of the EEG dataset, we applied a band-pass filter for digital filtering to reduce noise and also balanced the dataset using random oversampling. To extract and classify features, we utilized a hybrid technique consisting of four algorithms: AlexNet-MLP, AlexNet-ETC, AlexNet-AdaBoost, and AlexNet-NB. The results showed that the AlexNet-ETC hybrid algorithm achieved the highest accuracy rate of 95.32% for the OASIS dataset. In the case of the EEG dataset, the AlexNet-MLP hybrid algorithm outperformed other approaches with the highest accuracy of 97.71%. For the ADNI MRI dataset, the AlexNet-MLP hybrid algorithm achieved an accuracy rate of 92.59%. Comparing these results with the current state of the art demonstrates the effectiveness of our findings.

Seizure detection using nonlinear measures over EEG frequency bands and deep learning classifiers

Epilepsy is a brain disorder that causes patients to suffer from convulsions, which affects their behavior and way of life. Epilepsy can be detected with electroencephalograms (EEGs), which record brain neural activity. Traditional approaches for detecting epileptic seizures from an EEG signal are time-consuming and annoying. To supersede these traditional methods, a myriad of automated seizure detection frameworks based on machine learning techniques have recently been developed. Feature extraction and classification are the two essential phases for seizure detection. The classifier assigns the proper class label after feature extraction lowers the input pattern space while maintaining useful features. This paper proposes a new feature extraction method based on calculating nonlinear features from the most relevant EEG frequency bands. The EEG signal is first decomposed into smaller time segments from which a vector of nonlinear features is computed and supplied to machine learning (ML) and deep learning (DL) classifiers. Experiments on the Bonn dataset reveals an accuracy of 99.7% reached in classifying normal and ictal EEG signals; and an accuracy of 98.8% in the discrimination of ictal and interictal EEG signals. Furthermore, a performance of 100% is achieved on the Hauz Khas dataset. The classification results of the proposed approach were compared to those from published state of the art techniques. Our results are equivalent to or better than some recent studies appeared in the literature.

Systematic review and meta-analysis of deep learning applications in computed tomography lung cancer segmentation

BACKGROUND

Accurate segmentation of lung tumors on chest computed tomography (CT) scans is crucial for effective diagnosis and treatment planning. Deep Learning (DL) has emerged as a promising tool in medical imaging, particularly for lung cancer segmentation. However, its efficacy across different clinical settings and tumor stages remains variable.

METHODS

We conducted a comprehensive search of PubMed, Embase, and Web of Science until November 7, 2023. We assessed the quality of these studies by using the Checklist for Artificial Intelligence in Medical Imaging and the Quality Assessment of Diagnostic Accuracy Studies-2 tools. This analysis included data from various clinical settings and stages of lung cancer. Key performance metrics, such as the Dice similarity coefficient, were pooled, and factors affecting algorithm performance, such as clinical setting, algorithm type, and image processing techniques, were examined.

RESULTS

Our analysis of 37 studies revealed a pooled Dice score of 79 % (95 % CI: 76 %-83 %), indicating moderate accuracy. Radiotherapy studies had a slightly lower score of 78 % (95 % CI: 74 %-82 %). A temporal increase was noted, with recent studies (post-2022) showing improvement from 75 % (95 % CI: 70 %-81 %). to 82 % (95 % CI: 81 %-84 %). Key factors affecting performance included algorithm type, resolution adjustment, and image cropping. QUADAS-2 assessments identified ambiguous risks in 78 % of studies due to data interval omissions and concerns about generalizability in 8 % due to nodule size exclusions, and CLAIM criteria highlighted areas for improvement, with an average score of 27.24 out of 42.

CONCLUSION

This meta-analysis demonstrates DL algorithms' promising but varied efficacy in lung cancer segmentation, particularly higher efficacy noted in early stages. The results highlight the critical need for continued development of tailored DL models to improve segmentation accuracy across diverse clinical settings, especially in advanced cancer stages with greater challenges. As recent studies demonstrate, ongoing advancements in algorithmic approaches are crucial for future applications.

An automated approach for predicting HAMD-17 scores via divergent selective focused multi-heads self-attention network

This study introduces the Divergent Selective Focused Multi-heads Self-Attention Network (DSFMANet), an innovative deep learning model devised to automatically predict Hamilton Depression Rating Scale-17 (HAMD-17) scores in patients with depression. This model introduces a multi-branch structure for sub-bands and artificially configures attention focus factors on various branches, resulting in distinct attention distributions for different sub-bands. Experimental results demonstrate that when DSFMANet processes sub-band data, its performance surpasses current benchmarks in key metrics such as mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). This success is particularly evident in terms of MSE and MAE, where the performance of sub-band data is significantly superior, highlighting the model's potential in accurately predicting HAMD-17 scores. Concurrently, the experiment also compared the model's performance with sub-band and full-band data, affirming the superiority of the selective focus attention mechanism in electroencephalography (EEG) signal processing. DSFMANet, when utilizing sub-band data, exhibits higher data processing efficiency and reduced model complexity. The findings of this study underscore the significance of employing deep learning models based on sub-band analysis in depression diagnosis. The DSFMANet model not only effectively enhances the accuracy of depression diagnosis but also offers valuable research directions for similar applications in the future. This deep learning-based automated approach can effectively ascertain the HAMD-17 scores of patients with depression, thus offering more accurate and reliable support for clinical decision-making.

Probabilistic U-Net model observer for the DDC method in CT scan protocol optimization

Optimizing complex imaging procedures within Computed Tomography, considering both dose and image quality, presents significant challenges amidst rapid technological advancements and the adoption of machine learning (ML) methods. A crucial metric in this context is the Difference-Detailed Curve, which relies on human observer studies. However, these studies are labor-intensive and prone to both inter- and intra-observer variability. To tackle these issues, a ML-based model observer utilizing the U-Net architecture and a Bayesian methodology is proposed. In order to train a model observer unaffected by the spatial arrangement of low-contrast objects, the image preprocessing incorporates a Gaussian Process-based noise model. Additionally, gradient-weighted class activation mapping is utilized to gain insights into the model observer's decision-making process. By training on data from a diverse group of observers, well-calibrated probabilistic predictions that quantify observer variability are achieved. Leveraging the principles of Beta regression, the Bayesian methodology is used to derive a model observer performance metric, effectively gauging the model observer's strength in terms of an 'effective number of observers'. Ultimately, this framework enables to predict the DDC distribution by applying thresholds to the inferred probabilities (Part of this work has been presented at: Stocker D, Sommer C, Gueng S, Stäuble J, Özden I, Griessinger J, Weyland M S, Lutters G, Scheidegger S (2023). Probabilistic U-Net Model Observer for the DDC Method in CT Scan Protocol Optimization. The 56th SSRMP Annual Meeting 2023, November 30. - December 1., 2023, Luzern, Switzerland).

Identifying Diagnostic Biomarkers for Autism Spectrum Disorder From Higher-order Interactions Using the PED Algorithm

In the field of neuroimaging, more studies of abnormalities in brain regions of the autism spectrum disorder (ASD) usually focused on two brain regions connected, and less on abnormalities of higher-order interactions of brain regions. To explore the complex relationships of brain regions, we used the partial entropy decomposition (PED) algorithm to capture higher-order interactions by computing the higher-order dependencies of all three brain regions (triads). We proposed a method for examining the effect of individual brain regions on triads based on the PED and surrogate tests. The key triads were discovered by analyzing the effects. Further, the hypergraph modularity maximization algorithm revealed the higher-order brain structures, of which the link between right thalamus and left thalamus in ASD was more loose compared with the typical control (TC). Redundant key triad (left cerebellum crus 1 and left precuneus and right inferior occipital gyrus) exhibited a discernible attenuation in interaction in ASD, while the synergistic key triad (right cerebellum crus 1 and left postcentral gyrus and left lingual gyrus) indicated a notable decline. The results of classification model further confirmed the potential of the key triads as diagnostic biomarkers.

A novel fusion of genetic grey wolf optimization and kernel extreme learning machines for precise diabetic eye disease classification

In response to the growing number of diabetes cases worldwide, Our study addresses the escalating issue of diabetic eye disease (DED), a significant contributor to vision loss globally, through a pioneering approach. We propose a novel integration of a Genetic Grey Wolf Optimization (G-GWO) algorithm with a Fully Convolutional Encoder-Decoder Network (FCEDN), further enhanced by a Kernel Extreme Learning Machine (KELM) for refined image segmentation and disease classification. This innovative combination leverages the genetic algorithm and grey wolf optimization to boost the FCEDN's efficiency, enabling precise detection of DED stages and differentiation among disease types. Tested across diverse datasets, including IDRiD, DR-HAGIS, and ODIR, our model showcased superior performance, achieving classification accuracies between 98.5% to 98.8%, surpassing existing methods. This advancement sets a new standard in DED detection and offers significant potential for automating fundus image analysis, reducing reliance on manual examination, and improving patient care efficiency. Our findings are crucial to enhancing diagnostic accuracy and patient outcomes in DED management.

Digital Subtraction Angiography of Cerebral Arteries: Influence of Cranial Dimensions on X-ray Tube Performance

(1) Background. Digital subtraction angiography (DSA) is indispensable for diagnosing cerebral aneurysms due to its superior imaging precision. However, optimizing X-ray parameters is crucial for accurate diagnosis, with X-ray tube settings significantly influencing image quality. Understanding the relationship between skull dimensions and X-ray parameters is pivotal for tailoring imaging protocols to individual patients. (2) Methods. A retrospective analysis of DSA data from a single center was conducted, involving 251 patients. Cephalometric measurements and statistical analyses were performed to assess correlations between skull dimensions and X-ray tube parameters (voltage and current). (3) Results. The study revealed significant correlations between skull dimensions and X-ray tube parameters, highlighting the importance of considering individual anatomical variations. Gender-based differences in X-ray parameters were observed, emphasizing the need for personalized imaging protocols. (4) Conclusions. Personalized approaches to DSA imaging, integrating individual anatomical variations and gender-specific differences, are essential for optimizing diagnostic outcomes. While this study provides valuable insights, further research across multiple centers and diverse imaging equipment is warranted to validate these findings.

Cardiac substructure delineation in radiation therapy - A state-of-the-art review

Delineation of cardiac substructures is crucial for a better understanding of radiation-related cardiotoxicities and to facilitate accurate and precise cardiac dose calculation for developing and applying risk models. This review examines recent advancements in cardiac substructure delineation in the radiation therapy (RT) context, aiming to provide a comprehensive overview of the current level of knowledge, challenges and future directions in this evolving field. Imaging used for RT planning presents challenges in reliably visualising cardiac anatomy. Although cardiac atlases and contouring guidelines aid in standardisation and reduction of variability, significant uncertainties remain in defining cardiac anatomy. Coupled with the inherent complexity of the heart, this necessitates auto-contouring for consistent large-scale data analysis and improved efficiency in prospective applications. Auto-contouring models, developed primarily for breast and lung cancer RT, have demonstrated performance comparable to manual contouring, marking a significant milestone in the evolution of cardiac delineation practices. Nevertheless, several key concerns require further investigation. There is an unmet need for expanding cardiac auto-contouring models to encompass a broader range of cancer sites. A shift in focus is needed from ensuring accuracy to enhancing the robustness and accessibility of auto-contouring models. Addressing these challenges is paramount for the integration of cardiac substructure delineation and associated risk models into routine clinical practice, thereby improving the safety of RT for future cancer patients.

Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures

Automatic classification of colon and lung cancer images is crucial for early detection and accurate diagnostics. However, there is room for improvement to enhance accuracy, ensuring better diagnostic precision. This study introduces two novel dense architectures (D1 and D2) and emphasizes their effectiveness in classifying colon and lung cancer from diverse images. It also highlights their resilience, efficiency, and superior performance across multiple datasets. These architectures were tested on various types of datasets, including NCT-CRC-HE-100K (set of 100,000 non-overlapping image patches from hematoxylin and eosin (H&E) stained histological images of human colorectal cancer (CRC) and normal tissue), CRC-VAL-HE-7K (set of 7180 image patches from N = 50 patients with colorectal adenocarcinoma, no overlap with patients in NCT-CRC-HE-100K), LC25000 (Lung and Colon Cancer Histopathological Image), and IQ-OTHNCCD (Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases), showcasing their effectiveness in classifying colon and lung cancers from histopathological and Computed Tomography (CT) scan images. This underscores the multi-modal image classification capability of the proposed models. Moreover, the study addresses imbalanced datasets, particularly in CRC-VAL-HE-7K and IQ-OTHNCCD, with a specific focus on model resilience and robustness. To assess overall performance, the study conducted experiments in different scenarios. The D1 model achieved an impressive 99.80 % accuracy on the NCT-CRC-HE-100K dataset, with a Jaccard Index (J) of 0.8371, a Matthew's Correlation Coefficient (MCC) of 0.9073, a Cohen's Kappa (Kp) of 0.9057, and a Critical Success Index (CSI) of 0.8213. When subjected to 10-fold cross-validation on LC25000, the D1 model averaged (avg) 99.96 % accuracy (avg J, MCC, Kp, and CSI of 0.9993, 0.9987, 0.9853, and 0.9990), surpassing recent reported performances. Furthermore, the ensemble of D1 and D2 reached 93 % accuracy (J, MCC, Kp, and CSI of 0.7556, 0.8839, 0.8796, and 0.7140) on the IQ-OTHNCCD dataset, exceeding recent benchmarks and aligning with other reported results. Efficiency evaluations were conducted in various scenarios. For instance, training on only 10 % of LC25000 resulted in high accuracy rates of 99.19 % (J, MCC, Kp, and CSI of 0.9840, 0.9898, 0.9898, and 0.9837) (D1) and 99.30 % (J, MCC, Kp, and CSI of 0.9863, 0.9913, 0.9913, and 0.9861) (D2). In NCT-CRC-HE-100K, D2 achieved an impressive 99.53 % accuracy (J, MCC, Kp, and CSI of 0.9906, 0.9946, 0.9946, and 0.9906) with training on only 30 % of the dataset and testing on the remaining 70 %. When tested on CRC-VAL-HE-7K, D1 and D2 achieved 95 % accuracy (J, MCC, Kp, and CSI of 0.8845, 0.9455, 0.9452, and 0.8745) and 96 % accuracy (J, MCC, Kp, and CSI of 0.8926, 0.9504, 0.9503, and 0.8798), respectively, outperforming previously reported results and aligning closely with others. Lastly, training D2 on just 10 % of NCT-CRC-HE-100K and testing on CRC-VAL-HE-7K resulted in significant outperformance of InceptionV3, Xception, and DenseNet201 benchmarks, achieving an accuracy rate of 82.98 % (J, MCC, Kp, and CSI of 0.7227, 0.8095, 0.8081, and 0.6671). Finally, using explainable AI algorithms such as Grad-CAM, Grad-CAM++, Score-CAM, and Faster Score-CAM, along with their emphasized versions, we visualized the features from the last layer of DenseNet201 for histopathological as well as CT-scan image samples. The proposed dense models, with their multi-modality, robustness, and efficiency in cancer image classification, hold the promise of significant advancements in medical diagnostics. They have the potential to revolutionize early cancer detection and improve healthcare accessibility worldwide.

Contribution to pulmonary diseases diagnostic from X-ray images using innovative deep learning models

Pulmonary disease identification and characterization are among the most intriguing research topics of recent years since they require an accurate and prompt diagnosis. Although pulmonary radiography has helped in lung disease diagnosis, the interpretation of the radiographic image has always been a major concern for doctors and radiologists to reduce diagnosis errors. Due to their success in image classification and segmentation tasks, cutting-edge artificial intelligence techniques like machine learning (ML) and deep learning (DL) are widely encouraged to be applied in the field of diagnosing lung disorders and identifying them using medical images, particularly radiographic ones. For this end, the researchers are concurring to build systems based on these techniques in particular deep learning ones. In this paper, we proposed three deep-learning models that were trained to identify the presence of certain lung diseases using thoracic radiography. The first model, named "CovCXR-Net", identifies the COVID-19 disease (two cases: COVID-19 or normal). The second model, named "MDCXR3-Net", identifies the COVID-19 and pneumonia diseases (three cases: COVID-19, pneumonia, or normal), and the last model, named "MDCXR4-Net", is destined to identify the COVID-19, pneumonia and the pulmonary opacity diseases (4 cases: COVID-19, pneumonia, pulmonary opacity or normal). These models have proven their superiority in comparison with the state-of-the-art models and reached an accuracy of 99,09 %, 97.74 %, and 90,37 % respectively with three benchmarks.

Optimizing scan time and bayesian penalized likelihood reconstruction algorithm in copper-64 PET/CT imaging: a phantom study

Objectives: The aim of this study was to evaluate Cu-64 PET phantom image quality using Bayesian Penalized Likelihood (BPL) and Ordered Subset Expectation Maximum with point-spread function modeling (OSEM-PSF) reconstruction algorithms. In the BPL, the regularization parameterβwas varied to identify the optimum value for image quality. In the OSEM-PSF, the effect of acquisition time was evaluated to assess the feasibility of shortened scan duration.Methods: A NEMA IEC PET body phantom was filled with known activities of water soluble Cu-64. The phantom was imaged on a PET/CT scanner and was reconstructed using BPL and OSEM-PSF algorithms. For the BPL reconstruction, variousβvalues (150, 250, 350, 450, and 550) were evaluated. For the OSEM-PSF algorithm, reconstructions were performed using list-mode data intervals ranging from 7.5 to 240 s. Image quality was assessed by evaluating the signal to noise ratio (SNR), contrast to noise ratio (CNR), and background variability (BV).Results: The SNR and CNR were higher in images reconstructed with BPL compared to OSEM-PSF. Both the SNR and CNR increased with increasingβ, peaking atβ= 550. The CNR for allβ, sphere sizes and tumor-to-background ratios (TBRs) satisfied the Rose criterion for image detectability (CNR > 5). BPL reconstructed images withβ= 550 demonstrated the highest improvement in image quality. For OSEM-PSF reconstructed images with list-mode data duration ≥ 120 s, the noise level and CNR were not significantly different from the baseline 240 s list-mode data duration.Conclusions: BPL reconstruction improved Cu-64 PET phantom image quality by increasing SNR and CNR relative to OSEM-PSF reconstruction. Additionally, this study demonstrated scan time can be reduced from 240 to 120 s when using OSEM-PSF reconstruction while maintaining similar image quality. This study provides baseline data that may guide future studies aimed to improve clinical Cu-64 imaging.

Mechanisms of Action in FLASH Radiotherapy: A Comprehensive Review of Physicochemical and Biological Processes on Cancerous and Normal Cells

The advent of FLASH radiotherapy (FLASH-RT) has brought forth a paradigm shift in cancer treatment, showcasing remarkable normal cell sparing effects with ultra-high dose rates (>40 Gy/s). This review delves into the multifaceted mechanisms underpinning the efficacy of FLASH effect, examining both physicochemical and biological hypotheses in cell biophysics. The physicochemical process encompasses oxygen depletion, reactive oxygen species, and free radical recombination. In parallel, the biological process explores the FLASH effect on the immune system and on blood vessels in treatment sites such as the brain, lung, gastrointestinal tract, skin, and subcutaneous tissue. This review investigated the selective targeting of cancer cells and the modulation of the tumor microenvironment through FLASH-RT. Examining these mechanisms, we explore the implications and challenges of integrating FLASH-RT into cancer treatment. The potential to spare normal cells, boost the immune response, and modify the tumor vasculature offers new therapeutic strategies. Despite progress in understanding FLASH-RT, this review highlights knowledge gaps, emphasizing the need for further research to optimize its clinical applications. The synthesis of physicochemical and biological insights serves as a comprehensive resource for cell biology, molecular biology, and biophysics researchers and clinicians navigating the evolution of FLASH-RT in cancer therapy.

Gafchromic EBT3 film provides equivalent dosimetric performance to EBT-XD film for stereotactic radiosurgery dosimetry

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.

Effective relax acquisition: a novel approach to classify relaxed state in alpha band EEG-based transformation

A relaxed state is essential for effective hypnotherapy, a crucial component of mental health treatments. During hypnotherapy sessions, neurologists rely on the patient's relaxed state to introduce positive suggestions. While EEG is a widely recognized method for detecting human emotions, analyzing EEG data presents challenges due to its multi-channel, multi-band nature, leading to high-dimensional data. Furthermore, determining the onset of relaxation remains challenging for neurologists. This paper presents the Effective Relax Acquisition (ERA) method designed to identify the beginning of a relaxed state. ERA employs sub-band sampling within the Alpha band for the frequency domain and segments the data into four-period groups for the time domain analysis. Data enhancement strategies include using Window Length (WL) and Overlapping Shifting Windows (OSW) scenarios. Dimensionality reduction is achieved through Principal Component Analysis (PCA) by prioritizing the most significant eigenvector values. Our experimental results indicate that the relaxed state is predominantly observable in the high Alpha sub-band, particularly within the fourth period group. The ERA demonstrates high accuracy with a WL of 3 s and OSW of 0.25 s using the KNN classifier (90.63%). These findings validate the effectiveness of ERA in accurately identifying relaxed states while managing the complexity of EEG data.

Modeling the cortical response elicited by wrist manipulation via a nonlinear delay differential embedding

Regarding motor processes, modeling healthy people's brains is essential to understand the brain activity in people with motor impairments. However, little research has been undertaken when external forces disturb limbs, having limited information on physiological pathways. Therefore, in this paper, a nonlinear delay differential embedding model is used to estimate the brain response elicited by externally controlled wrist movement in healthy individuals. The aim is to improve the understanding of the relationship between a controlled wrist movement and the generated cortical activity of healthy people, helping to disclose the underlying mechanisms and physiological relationships involved in the motor event. To evaluate the model, a public database from the Delft University of Technology is used, which contains electroencephalographic recordings of ten healthy subjects while wrist movement was externally provoked by a robotic system. In this work, the cortical response related to movement is identified via Independent Component Analysis and estimated based on a nonlinear delay differential embedding model. After a cross-validation analysis, the model performance reaches 90.21% ± 4.46% Variance Accounted For, and Correlation 95.14% ± 2.31%. The proposed methodology allows to select the model degree, to estimate a general predominant operation mode of the cortical response elicited by wrist movement. The obtained results revealed two facts that had not previously been reported: the movement's acceleration affects the cortical response, and a common delayed activity is shared among subjects. Going forward, identifying biomarkers related to motor tasks could aid in the evaluation of rehabilitation treatments for patients with upper limbs motor impairments.

The value of linear and non-linear quantitative EEG analysis in paediatric epilepsy surgery: a machine learning approach

Epilepsy surgery is effective for patients with medication-resistant seizures, however 20-40% of them are not seizure free after surgery. Aim of this study is to evaluate the role of linear and non-linear EEG features to predict post-surgical outcome. We included 123 paediatric patients who underwent epilepsy surgery at Bambino Gesù Children Hospital (January 2009-April 2020). All patients had long term video-EEG monitoring. We analysed 1-min scalp interictal EEG (wakefulness and sleep) and extracted 13 linear and non-linear EEG features (power spectral density (PSD), Hjorth, approximate entropy, permutation entropy, Lyapunov and Hurst value). We used a logistic regression (LR) as feature selection process. To quantify the correlation between EEG features and surgical outcome we used an artificial neural network (ANN) model with 18 architectures. LR revealed a significant correlation between PSD of alpha band (sleep), Mobility index (sleep) and the Hurst value (sleep and awake) with outcome. The fifty-four ANN models gave a range of accuracy (46-65%) in predicting outcome. Within the fifty-four ANN models, we found a higher accuracy (64.8% ± 7.6%) in seizure outcome prediction, using features selected by LR. The combination of PSD of alpha band, mobility and the Hurst value positively correlate with good surgical outcome.

Accurate object localization facilitates automatic esophagus segmentation in deep learning

BACKGROUND

Currently, automatic esophagus segmentation remains a challenging task due to its small size, low contrast, and large shape variation. We aimed to improve the performance of esophagus segmentation in deep learning by applying a strategy that involves locating the object first and then performing the segmentation task.

METHODS

A total of 100 cases with thoracic computed tomography scans from two publicly available datasets were used in this study. A modified CenterNet, an object location network, was employed to locate the center of the esophagus for each slice. Subsequently, the 3D U-net and 2D U-net_coarse models were trained to segment the esophagus based on the predicted object center. A 2D U-net_fine model was trained based on the updated object center according to the 3D U-net model. The dice similarity coefficient and the 95% Hausdorff distance were used as quantitative evaluation indexes for the delineation performance. The characteristics of the automatically delineated esophageal contours by the 2D U-net and 3D U-net models were summarized. Additionally, the impact of the accuracy of object localization on the delineation performance was analyzed. Finally, the delineation performance in different segments of the esophagus was also summarized.

RESULTS

The mean dice coefficient of the 3D U-net, 2D U-net_coarse, and 2D U-net_fine models were 0.77, 0.81, and 0.82, respectively. The 95% Hausdorff distance for the above models was 6.55, 3.57, and 3.76, respectively. Compared with the 2D U-net, the 3D U-net has a lower incidence of delineating wrong objects and a higher incidence of missing objects. After using the fine object center, the average dice coefficient was improved by 5.5% in the cases with a dice coefficient less than 0.75, while that value was only 0.3% in the cases with a dice coefficient greater than 0.75. The dice coefficients were lower for the esophagus between the orifice of the inferior and the pulmonary bifurcation compared with the other regions.

CONCLUSION

The 3D U-net model tended to delineate fewer incorrect objects but also miss more objects. Two-stage strategy with accurate object location could enhance the robustness of the segmentation model and significantly improve the esophageal delineation performance, especially for cases with poor delineation results.

Development of shielding evaluation and management program for O-ring type linear accelerators

The shielding parameters can vary depending on the geometrical structure of the linear accelerators (LINAC), treatment techniques, and beam energies. Recently, the introduction of O-ring type linear accelerators is increasing. The objective of this study is to evaluate the shielding parameters of new type of linac using a dedicated program developed by us named ORSE (O-ring type Radiation therapy equipment Shielding Evaluation). The shielding evaluation was conducted for a total of four treatment rooms including Elekta Unity, Varian Halcyon, and Accuray Tomotherapy. The developed program possesses the capability to calculate transmitted dose, maximum treatable patient capacity, and shielding wall thickness based on patient data. The doses were measured for five days using glass dosimeters to compare with the results of program. The IMRT factors and use factors obtained from patient data showed differences of up to 65.0% and 33.8%, respectively, compared to safety management report. The shielding evaluation conducted in each treatment room showed that the transmitted dose at every location was below 1% of the dose limit. The results of program and measurements showed a maximum difference of 0.003 mSv/week in transmitted dose. The ORSE program allows for the shielding evaluation results to the clinical environment of each institution based on patient data.