Pixel-by-pixel correction of beam hardening artifacts by bowtie filter in fan-beam CT

Objective. Beam hardening (BH) artifacts in computed tomography (CT) images originate from the polychromatic nature of x-ray photons. In a CT system with a bowtie filter, residual BH artifacts remain when polynomial fits are used. These artifacts lead to worse visuals, reduced contrast, and inaccurate CT numbers. This work proposes a pixel-by-pixel correction (PPC) method to reduce the residual BH artifacts caused by a bowtie filter.Approach. The energy spectrum for each pixel at the detector after the photons pass through the bowtie filter was calculated. Then, the spectrum was filtered through a series of water slabs with different thicknesses. The polychromatic projection corresponding to the thickness of the water slab for each detector pixel could be obtained. Next, we carried out a water slab experiment with a mono energyE= 69 keV to get the monochromatic projection. The polychromatic and monochromatic projections were then fitted with a 2nd-order polynomial. The proposed method was evaluated on digital phantoms in a virtual CT system and phantoms in a real CT machine.Main results. In the case of a virtual CT system, the standard deviation of the line profile was reduced by 23.8%, 37.3%, and 14.3%, respectively, in the water phantom with different shapes. The difference of the linear attenuation coefficients (LAC) in the central and peripheral areas of an image was reduced from 0.010 to 0.003cm-1and 0.007cm-1to 0 in the biological tissue phantom and human phantom, respectively. The method was also validated using CT projection data obtained from Activion16 (Canon Medical Systems, Japan). The difference in the LAC in the central and peripheral areas can be reduced by a factor of two.Significance. The proposed PPC method can successfully remove the cupping artifacts in both virtual and authentic CT images. The scanned object's shapes and materials do not affect the technique.

Development of 2400-2450 MHz Frequency Band RF Energy Harvesting System for Low-Power Device Operation

Recently, there has been an increasing fascination for employing radio frequency (RF) energy harvesting techniques to energize various low-power devices by harnessing the ambient RF energy in the surroundings. This work outlines a novel advancement in RF energy harvesting (RFEH) technology, intending to power portable gadgets with minimal operating power demands. A high-gain receiver microstrip patch antenna was designed and tested to capture ambient RF residue, operating at 2450 MHz. Similarly, a two-stage Dickson voltage booster was developed and employed with the RFEH to transform the received RF signals into useful DC voltage signals. Additionally, an LC series circuit was utilized to ensure impedance matching between the antenna and rectifier, facilitating the extraction of maximum power from the developed prototype. The findings indicate that the developed rectifier attained a peak power conversion efficiency (PCE) of 64% when operating at an input power level of 0 dBm. During experimentation, the voltage booster demonstrated its capability to rectify a minimum input AC signal of only 50 mV, yielding a corresponding 180 mV output DC signal. Moreover, the maximum power of 4.60 µW was achieved when subjected to an input AC signal of 1500 mV with a load resistance of 470 kΩ. Finally, the devised RFEH was also tested in an open environment, receiving signals from Wi-Fi modems positioned at varying distances for evaluation.

Electroencephalogram-Based ConvMixer Architecture for Recognizing Attention Deficit Hyperactivity Disorder in Children

Attention deficit hyperactivity disorder (ADHD) is a neuro-developmental disorder that affects approximately 5-10% of school-aged children worldwide. Early diagnosis and intervention are essential to improve the quality of life of patients and their families. In this study, we propose ConvMixer-ECA, a novel deep learning architecture that combines ConvMixer with efficient channel attention (ECA) blocks for the accurate diagnosis of ADHD using electroencephalogram (EEG) signals. The model was trained and evaluated using EEG recordings from 60 healthy children and 61 children with ADHD. A series of experiments were conducted to evaluate the performance of the ConvMixer-ECA. The results showed that the ConvMixer-ECA performed well in ADHD recognition with 94.52% accuracy. The incorporation of attentional mechanisms, in particular ECA, improved the performance of ConvMixer; it outperformed other attention-based variants. In addition, ConvMixer-ECA outperformed state-of-the-art deep learning models including EEGNet, CNN, RNN, LSTM, and GRU. t-SNE visualization of the output of this model layer validated the effectiveness of ConvMixer-ECA in capturing the underlying patterns and features that separate ADHD from typically developing individuals through hierarchical feature learning. These outcomes demonstrate the potential of ConvMixer-ECA as a valuable tool to assist clinicians in the early diagnosis and intervention of ADHD in children.

Extrinsic Laryngeal Muscle Activity With Different Diameters and Water Depths in a Semi-Occluded Vocal Tract Exercise

PURPOSE

Surface electromyography (sEMG) has been used to evaluate extrinsic laryngeal muscle activity during swallowing and phonation. In the current study, sEMG amplitudes were measured from the infrahyoid and suprahyoid muscles during phonation through a tube submerged in water.

METHOD

The sEMG amplitude values measured from the extrinsic laryngeal muscles and the electroglottographic contact quotient (CQ) were obtained simultaneously from 62 healthy participants (31 men, 31 women) during phonation through a tube at six different depths (2, 4, 7, 10, 15, and 20 cm) while using two tubes with different diameters (1 and 0.5 cm).

RESULTS

With increasing depth, the sEMG amplitude for the suprahyoid muscles increased in men and women. However, sEMG amplitudes for the infrahyoid muscles increased significantly only in men. Tube diameter had a significant effect on the suprahyoid sEMG amplitudes only for men, with higher sEMG amplitudes when phonating with a 1.0-cm tube. CQ values increased with submerged depth for both men and women. Tube diameter affected results such than CQ values were higher for men when using the wider tube and for women with the narrower tube.

CONCLUSIONS

Vocal fold vibratory patterns changed with the depth of tube submersion in water for both men and women, but the patterns of muscle activation differed between the sexes. This suggests that men and women use different strategies when confronted with increased intraoral pressure during semi-occluded vocal tract exercises. In this study, sEMG provided insight into the mechanism for differences between vocally normal individuals and could help detect compensatory muscle activation during tube phonation in water for people with voice disorders.

Perceptions of undergraduate medical students on artificial intelligence in medicine: mixed-methods survey study from Palestine

BACKGROUND

The current applications of artificial intelligence (AI) in medicine continue to attract the attention of medical students. This study aimed to identify undergraduate medical students' attitudes toward AI in medicine, explore present AI-related training opportunities, investigate the need for AI inclusion in medical curricula, and determine preferred methods for teaching AI curricula.

METHODS

This study uses a mixed-method cross-sectional design, including a quantitative study and a qualitative study, targeting Palestinian undergraduate medical students in the academic year 2022-2023. In the quantitative part, we recruited a convenience sample of undergraduate medical students from universities in Palestine from June 15, 2022, to May 30, 2023. We collected data by using an online, well-structured, and self-administered questionnaire with 49 items. In the qualitative part, 15 undergraduate medical students were interviewed by trained researchers. Descriptive statistics and an inductive content analysis approach were used to analyze quantitative and qualitative data, respectively.

RESULTS

From a total of 371 invitations sent, 362 responses were received (response rate = 97.5%), and 349 were included in the analysis. The mean age of participants was 20.38 ± 1.97, with 40.11% (140) in their second year of medical school. Most participants (268, 76.79%) did not receive formal education on AI before or during medical study. About two-thirds of students strongly agreed or agreed that AI would become common in the future (67.9%, 237) and would revolutionize medical fields (68.7%, 240). Participants stated that they had not previously acquired training in the use of AI in medicine during formal medical education (260, 74.5%), confirming a dire need to include AI training in medical curricula (247, 70.8%). Most participants (264, 75.7%) think that learning opportunities for AI in medicine have not been adequate; therefore, it is very important to study more about employing AI in medicine (228, 65.3%). Male students (3.15 ± 0.87) had higher perception scores than female students (2.81 ± 0.86) (p < 0.001). The main themes that resulted from the qualitative analysis of the interview questions were an absence of AI learning opportunities, the necessity of including AI in medical curricula, optimism towards the future of AI in medicine, and expected challenges related to AI in medical fields.

CONCLUSION

Medical students lack access to educational opportunities for AI in medicine; therefore, AI should be included in formal medical curricula in Palestine.

Impact on the estimated dose of different tissue assignment strategies during partial breast irradiations with INTRABEAM

PURPOSE

Partial breast irradiations with electronic brachytherapy or kilovoltage intraoperative radiotherapy devices such as Axxent or INTRABEAM are becoming more common every day. Breast is mainly composed of glandular and adipose tissues, which are not always clearly disentangled in planning breast CTs. In these cases, breast tissues are replaced with an average soft tissue, or even water. However, at kilovoltage energies, this may lead to large differences in the delivered dose, due to the dominance of photoelectric effect. Therefore, the aim of this work was to study the effect on the dose prescribed in breast with the INTRABEAM device using different soft tissue assignment strategies that would replace the adipose and glandular tissues that constitute the breast in cases where these tissues cannot be adequately distinguished in a CT scan.

METHODS AND MATERIALS

Dose was computed with a Monte Carlo code in five patients with a 3 cm diameter INTRABEAM spherical applicator. Tissues within the breast were assigned following six different strategies: one based on the TG-43 recommendations, representing the whole breast as water of unity density, another one also water-based but with CT derived density, and the other four also based on CT-derived densities, using a single tissue resulting from different mixes of glandular and adipose tissues. These were compared against the reference dose computed in an accurately segmented CT, following TG-186 recommendations. Relative differences and dose ratios between the reference and the other tissue assignment strategies were obtained in three regions of interest inside the breast.

RESULTS AND CONCLUSIONS

Dose planning in water-based tissues was found inaccurate for breast treatment with INTRABEAM, as it would incur in up to 30% under-prescription of dose. If accurate soft tissue assignments in the breast cannot be safely done, a single-tissue composition of 80% adipose and 20% glandular tissue, or even a 100% adipose tissue, would be recommended to avoid dose under-prescription.

Biomechanical Analysis of Human Gait When Changing Velocity and Carried Loads: Simulation Study with OpenSim

Walking is one of the main activities of daily life and gait analysis can provide crucial data for the computation of biomechanics in many fields. In multiple applications, having reference data that include a variety of gait conditions could be useful for assessing walking performance. However, limited extensive reference data are available as many conditions cannot be easily tested experimentally. For this reason, a musculoskeletal model in OpenSim coupled with gait data (at seven different velocities) was used to simulate seven carried loads and all the combinations between the two parameters. The effects on lower limb biomechanics were measured with torque, power, and mechanical work. The results demonstrated that biomechanics was influenced by both speed and load. Our results expand the previous literature: in the majority of previous work, only a subset of the presented conditions was investigated. Moreover, our simulation approach provides comprehensive data that could be useful for applications in many areas, such as rehabilitation, orthopedics, medical care, and sports.

Hospital Environmental Factors That Influence Peripheral Oxygen Saturation Measurements: A Cross-Sectional Study

Pulse oximetry is a non-invasive, cost-effective, and generally reliable instrument measuring pulse rate and peripheral oxygen saturation (SpO2). However, these measurements can be affected by the patient's internal or external factors, including the type of pulse oximeter device (POD). (1) This study's objective was to identify potential environmental factors that may impact the measurements taken by three PODs. (2) Methods: A descriptive-analytical cross-sectional study was designed. The patients' SpO2 levels were measured using a standard monitor and two PODs owned by the professionals. The measurements were taken on the patients' fingers. Concurrently, we evaluated the surrounding environmental conditions, encompassing temperature, humidity, illuminance, and noise. (3) Results: This study involved 288 adult participants in the sample. For each 20-decibel increment in noise, there was a reduction in SpO2 by an average of 1%, whereas for every additional degree of ambient temperature, SpO2 decreased by an average of 2% (4) Conclusions: Significant correlations between SpO2 and age, as well as with noise and ambient temperature, were observed. No significant differences between oxygen saturation and lighting or humidity were observed. This study was prospectively registered with the Clinical Research Ethics Committee of Gran Canaria at the Dr. Negrín University Hospital, with protocol code 2019-247-1, and approved on 24 May 2019.

Data leakage in deep learning studies of translational EEG

A growing number of studies apply deep neural networks (DNNs) to recordings of human electroencephalography (EEG) to identify a range of disorders. In many studies, EEG recordings are split into segments, and each segment is randomly assigned to the training or test set. As a consequence, data from individual subjects appears in both the training and the test set. Could high test-set accuracy reflect data leakage from subject-specific patterns in the data, rather than patterns that identify a disease? We address this question by testing the performance of DNN classifiers using segment-based holdout (in which segments from one subject can appear in both the training and test set), and comparing this to their performance using subject-based holdout (where all segments from one subject appear exclusively in either the training set or the test set). In two datasets (one classifying Alzheimer's disease, and the other classifying epileptic seizures), we find that performance on previously-unseen subjects is strongly overestimated when models are trained using segment-based holdout. Finally, we survey the literature and find that the majority of translational DNN-EEG studies use segment-based holdout. Most published DNN-EEG studies may dramatically overestimate their classification performance on new subjects.

Cascaded-TOARNet: A cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation

BACKGROUND

Accurate and automated segmentation of thoracic organs-at-risk (OARs) is critical for radiotherapy treatment planning of thoracic cancers. However, this has remained a challenging task for four major reasons: (1) thoracic OARs have diverse morphologies; (2) thoracic OARs have low contrast with the background; (3) boundaries of thoracic OARs are blurry; (4) class imbalance issue caused by small organs.

PURPOSE

To overcome the above challenges and achieve accurate and automated segmentation of thoracic OARs on thoracic CT.

METHODS

A novel cascaded framework based on mixed attention and multiscale information for thoracic OARs segmentation, called Cascaded-TOARNet. This cascaded framework comprises two stages: localization and segmentation. During the localization stage, TOARNet locates each organ to crop the regions of interest (ROIs). During the segmentation stage, TOARNet accurately segments the ROIs, and the segmentation results are merged into a complete result.

RESULTS

We evaluated our proposed method and other common segmentation methods on two public datasets: the AAPM Thoracic Auto-Segmentation Challenge dataset and the Segmentation of Thoracic Organs at Risk (SegTHOR) dataset. Our method demonstrated superior performance, achieving a mean Dice score of 92.6% on the SegTHOR dataset and 90.8% on the AAPM dataset.

CONCLUSIONS

This segmentation method holds great promise as an essential tool for enhancing the efficiency of thoracic radiotherapy planning.

Cardiac indices of driver fatigue across in-lab and on-road studies

Driver fatigue is a major contributor to road accidents. Therefore, driver assistance systems (DAS) that would monitor drivers' states may contribute to road safety. Such monitoring can potentially be achieved with input from ECG indices (e.g., heart rate). We reviewed the empirical literature on responses of cardiac measures to driver fatigue and on detecting fatigue with cardiac indices and classification algorithms. We used meta-analytical methods to explore the pooled effect sizes of different cardiac indices of fatigue, their heterogeneity, and the consistency of their responses across studies. Our large pool of studies (N = 39) allowed us to stratify the results across on-road and simulator studies. We found that despite the large heterogeneity of the effect sizes between the studies, many indices had significant pooled effect sizes across the studies, and more frequently across the on-road studies. We also found that most indices showed consistent responses across both on-road and simulator studies. Regarding the detection accuracy, we found that even on-road classification could have been as accurate as 70% with only 2-min of data. However, we could only find two on-road studies that employed fatigue classification algorithms. Overall, our findings are encouraging with respect to the prospect of using cardiac measures for detecting driver fatigue. Yet, to fully explore this possibility, there is a need for additional on-road studies that would employ a similar set of cardiac indices and detection algorithms, a unified definition of fatigue, and additional levels of fatigue than the two fatigue vs alert states.

Triplet-constrained deep hashing for chest X-ray image retrieval in COVID-19 assessment

Radiology images of the chest, such as computer tomography scans and X-rays, have been prominently used in computer-aided COVID-19 analysis. Learning-based radiology image retrieval has attracted increasing attention recently, which generally involves image feature extraction and finding matches in extensive image databases based on query images. Many deep hashing methods have been developed for chest radiology image search due to the high efficiency of retrieval using hash codes. However, they often overlook the complex triple associations between images; that is, images belonging to the same category tend to share similar characteristics and vice versa. To this end, we develop a triplet-constrained deep hashing (TCDH) framework for chest radiology image retrieval to facilitate automated analysis of COVID-19. The TCDH consists of two phases, including (a) feature extraction and (b) image retrieval. For feature extraction, we have introduced a triplet constraint and an image reconstruction task to enhance discriminative ability of learned features, and these features are then converted into binary hash codes to capture semantic information. Specifically, the triplet constraint is designed to pull closer samples within the same category and push apart samples from different categories. Additionally, an auxiliary image reconstruction task is employed during feature extraction to help effectively capture anatomical structures of images. For image retrieval, we utilize learned hash codes to conduct searches for medical images. Extensive experiments on 30,386 chest X-ray images demonstrate the superiority of the proposed method over several state-of-the-art approaches in automated image search. The code is now available online.

Big data research in nursing: A bibliometric exploration of themes and publications

AIMS

To comprehend the current research hotspots and emerging trends in big data research within the global nursing domain.

DESIGN

Bibliometric analysis.

METHODS

The quality articles for analysis indexed by the science core collection were obtained from the Web of Science database as of February 10, 2023.The descriptive, visual analysis and text mining were realized by CiteSpace and VOSviewer.

RESULTS

The research on big data in the nursing field has experienced steady growth over the past decade. A total of 45 core authors and 17 core journals around the world have contributed to this field. The author's keyword analysis has revealed five distinct clusters of research focus. These encompass machine/deep learning and artificial intelligence, natural language processing, big data analytics and data science, IoT and cloud computing, and the development of prediction models through data mining. Furthermore, a comparative examination was conducted with data spanning from 1980 to 2016, and an extended analysis was performed covering the years from 1980 to 2019. This bibliometric mapping comparison allowed for the identification of prevailing research trends and the pinpointing of potential future research hotspots within the field.

CONCLUSIONS

The fusion of data mining and nursing research has steadily advanced and become more refined over time. Technologically, it has expanded from initial natural language processing to encompass machine learning, deep learning, artificial intelligence, and data mining approach that amalgamates multiple technologies. Professionally, it has progressed from addressing patient safety and pressure ulcers to encompassing chronic diseases, critical care, emergency response, community and nursing home settings, and specific diseases (Cardiovascular diseases, diabetes, stroke, etc.). The convergence of IoT, cloud computing, fog computing, and big data processing has opened new avenues for research in geriatric nursing management and community care. However, a global imbalance exists in utilizing big data in nursing research, emphasizing the need to enhance data science literacy among clinical staff worldwide to advance this field.

CLINICAL RELEVANCE

This study focused on the thematic trends and evolution of research on the big data in nursing research. Moreover, this study may contribute to the understanding of researchers, journals, and countries around the world and generate the possible collaborations of them to promote the development of big data in nursing science.

Brachytherapy at the nanoscale with protein functionalized and intrinsically radiolabeled [169Yb]Yb2O3 nanoseeds

PURPOSE

Classical brachytherapy of solid malignant tumors is an invasive procedure which often results in an uneven dose distribution, while requiring surgical removal of sealed radioactive seed sources after a certain period of time. To circumvent these issues, we report the synthesis of intrinsically radiolabeled and gum Arabic glycoprotein functionalized [169Yb]Yb2O3 nanoseeds as a novel nanoscale brachytherapy agent, which could directly be administered via intratumoral injection for tumor therapy.

METHODS

169Yb (T½ = 32 days) was produced by neutron irradiation of enriched (15.2% in 168Yb) Yb2O3 target in a nuclear reactor, radiochemically converted to [169Yb]YbCl3 and used for nanoparticle (NP) synthesis. Intrinsically radiolabeled NP were synthesized by controlled hydrolysis of Yb3+ ions in gum Arabic glycoprotein medium. In vivo SPECT/CT imaging, autoradiography, and biodistribution studies were performed after intratumoral injection of radiolabeled NP in B16F10 tumor bearing C57BL/6 mice. Systematic tumor regression studies and histopathological analyses were performed to demonstrate therapeutic efficacy in the same mice model.

RESULTS

The nanoformulation was a clear solution having high colloidal and radiochemical stability. Uniform distribution and retention of the radiolabeled nanoformulation in the tumor mass were observed via SPECT/CT imaging and autoradiography studies. In a tumor regression study, tumor growth was significantly arrested with different doses of radiolabeled NP compared to the control and the best treatment effect was observed with ~ 27.8 MBq dose. In histopathological analysis, loss of mitotic cells was apparent in tumor tissue of treated groups, whereas no significant damage in kidney, lungs, and liver tissue morphology was observed.

CONCLUSIONS

These results hold promise for nanoscale brachytherapy to become a clinically practical treatment modality for unresectable solid cancers.

Radiographer training for screening of patients referred for Magnetic Resonance Imaging: A scoping review

INTRODUCTION

Strict safety practices are essential to ensure the safety of patients and staff in Magnetic Resonance Imaging (MRI). Training regarding the fundamentals of MRI safety is well-established and commonly agreed upon. However, more complex aspect of screening patients, such as image review or screening of unconscious patients/patients with communication difficulties is less well discussed. The current UK and USA guidelines do not suggest the use of communication training for MRI staff nor indicate any training to encourage reviewing images in the screening process. This review aims to map the current guidance regarding safety and patient screening training for MRI diagnostic and therapeutic radiographers.

METHODS

A systematic search of PubMed, Trip Medical database and Radiography journal was conducted. Studies were chosen based on the review objectives and pre-determined inclusion/exclusion criteria using the PRISMA-ScR framework.

RESULTS

Twenty-four studies were included in the review, which identified some key concepts including MRI safety training and delivery methods, screening and communication, screening of unconscious or non-ambulatory patients and the use of imaging.

CONCLUSION

Training gaps lie within the more complex elements of screening such as the inclusiveness of question phrasing, particularly to the neurodivergent population, how we teach radiographers to screen unconscious/unresponsive patients and using imaging to detect implants.

IMPLICATIONS FOR PRACTICE

The consequences of incomplete or inaccurate pre-MRI safety screening could be the introduction of unexpected implants into the scanner or forgoing MRI for a less desirable modality. The development of enhanced training programs in implant recognition using imaging and communication could complement existing training.

Harnessing machine learning for EEG signal analysis: Innovations in depth of anaesthesia assessment

Anaesthesia, crucial to surgical practice, is undergoing renewed scrutiny due to the integration of artificial intelligence in its medical use. The precise control over the temporary loss of consciousness is vital to ensure safe, pain-free procedures. Traditional methods of depth of anaesthesia (DoA) assessment, reliant on physical characteristics, have proven inconsistent due to individual variations. In response, electroencephalography (EEG) techniques have emerged, with indices such as the Bispectral Index offering quantifiable assessments. This literature review explores the current scope and frontier of DoA research, emphasising methods utilising EEG signals for effective clinical monitoring. This review offers a critical synthesis of recent advances, specifically focusing on electroencephalography (EEG) techniques and their role in enhancing clinical monitoring. By examining 117 high-impact papers, the review delves into the nuances of feature extraction, model building, and algorithm design in EEG-based DoA analysis. Comparative assessments of these studies highlight their methodological approaches and performance, including clinical correlations with established indices like the Bispectral Index. The review identifies knowledge gaps, particularly the need for improved collaboration for data access, which is essential for developing superior machine learning models and real-time predictive algorithms for patient management. It also calls for refined model evaluation processes to ensure robustness across diverse patient demographics and anaesthetic agents. The review underscores the potential of technological advancements to enhance precision, safety, and patient outcomes in anaesthesia, paving the way for a new standard in anaesthetic care. The findings of this review contribute to the ongoing discourse on the application of EEG in anaesthesia, providing insights into the potential for technological advancement in this critical area of medical practice.

Fatigue at the wheel: A non-visual approach to truck driver fatigue detection by multi-feature fusion

BACKGROUND

Monitoring of long-haul truck driver fatigue state has attracted considerable interest. Conventional fatigue driving detection methods based on the physiological and visual features are scarcely applicable, due to the intrusiveness, reliability, and cost-effectiveness concerns.

METHODS

We elaborately developed a fatigue driving detection method by fusion of non-visual features derived from the customized wristbands, vehicle-mounted equipment, and trip logs. To capture the spatiotemporal information within the sequential data, the bidirectional long short-term memory network with attention mechanism was proposed to determine whether the truck driver was fatigued within a fine-grained episode of one minute. The model was validated using a natural driving dataset with nine truck drivers on real-world roads in Guiyang, China during June and July 2021.

RESULTS

Our approach yielded 99.21 %, 84.44 %, 82.01 %, 99.63 %, and 83.21 % in accuracy, precision, recall, specificity, and F1-score, respectively. Compared with the mainstream visual-based methods, our approach outperformed particularly in terms of precision and recall. Photoplethysmogram stood out as the most important feature for truck driver fatigue state detection. Vehicle load, driving forward angle, cumulative driving time, midnight, and recent working hours were found to be positively associated with the probability of fatigue driving, while the galvanic skin response, vehicle acceleration, current time, and recent rest hours had a negative relationship. Specifically, truck drivers were more likely to fatigue when driving at 20-40 km/h, braking abruptly at 5-10 m/s2, with vehicle loads over 70 tons, and driving more than 100 min consecutively.

CONCLUSIONS

Our study is among the first to harness the natural driving dataset to delve into the real-life fatigue pattern of long-haul truck drivers without disruptions on routine driving tasks. The proposed method holds pragmatic prospects by providing a privacy-preserving, robust, real-time, and non-intrusive technical pathway for truck driver fatigue monitoring.

The impact of patient scoliosis-specific exercises for adolescent idiopathic scoliosis: a systematic review and meta-analysis of randomized controlled trials with subgroup analysis using observational studies

PURPOSE

Adolescent idiopathic scoliosis (AIS) is a common pediatric spinal deformity frequently treated with patient scoliosis-specific exercises (PSSE). The purpose of this study is to perform a systematic review and meta-analysis of randomized controlled trials and sensitivity analysis of observational studies to determine the impact of PSSE on outcomes for AIS.

METHODS

A systematic review and meta-analysis on impact of PSSE for patients with AIS was performed. Databases used included PubMed, CINAHL, MEDLINE, Cochrane, and ScienceDirect database inception to October 2022. Inclusion criteria included use of PSSE, patient population of AIS, and full text.

RESULTS

A total of 26 articles out of 628 initial retrieved met final inclusion criteria (10 randomized controlled trials (RCTs), 16 observational studies). Total included patients (n = 2083) had a frequency weighted mean age of 13.2 ± 0.9 years and a frequency weighted mean follow-up of 14.5 ± 20.0 months. Based on only data from RCTs with direct comparison groups (n = 7 articles), there was a statistically significant but clinically insignificant improvement in Cobb angle of 2.5 degrees in the PSSE group (n = 152) as compared to the control group (n = 148; p = 0.017). There was no statistically significant improvement in Cobb angle when stratified by small curve (< 30 degrees) or large curve (> 30 degrees) with PSSE (p = 0.140 and p = 0.142, respectively). There was no statistically significant improvement in ATR (p = 0.326) or SRS-22 score (p = 0.370).

CONCLUSION

PSSE may not provide any clinically significant improvements in Cobb angle, ATR, or SRS-22 scores in patients with AIS. PSSE did not significantly improve Cobb angle when stratified by curve size.

LEVEL OF EVIDENCE

Level I.

Development of a digital star-shot analysis system for comparing radiation and imaging isocenters of proton treatment machine

PURPOSE

To directly compare the radiation and imaging isocenters of a proton treatment machine, we developed and evaluated a real-time radiation isocenter verification system.

METHODS

The system consists of a plastic scintillator (PI-200, Mitsubishi Chemical Corporation, Tokyo, Japan), an acrylic phantom, a steel ball on the detachable plate, Raspberry Pi 4 (Raspberry Pi Foundation, London, UK) with camera module, and analysis software implemented through a Python-based graphical user interface (GUI). After kV imaging alignment of the steel ball, the imaging isocenter defined as the position of the steel ball was extracted from the optical image. The proton star-shot was obtained by optical camera because the scintillator converted proton beam into visible light. Then the software computed both the minimum circle radius and the radiation isocenter position from the star-shot. And the deviation between the imaging isocenter and radiation isocenter was calculated. We compared our results with measurements obtained by Gafchromic EBT3 film (Ashland, NJ, USA).

RESULTS

The minimum circle radii were averaged 0.29 and 0.41 mm while the position deviations from the radiation isocenter to the laser marker were averaged 0.99 and 1.07 mm, for our system and EBT3 film, respectively. Furthermore, the average position difference between the radiation isocenter and imaging isocenter was 0.27 mm for our system. Our system reduced analysis time by 10 min.

CONCLUSIONS

Our system provided automated star-shot analysis with sufficient accuracy, and it is cost-effective alternative to conventional film-based method for radiation isocenter verification.

Assessment of radio frequency fields in the 2.45 GHz band produced by smart home devices

This paper describes the assessment of the electromagnetic fields produced by consumer "smart" devices used to control and monitor everyday equipment and appliances in a modern "smart" home. The assessment is based on the careful measurement of fields produced by a range of such devices in a laboratory environment configured to operate in a condition simulating high user activity. All devices included in this study operate in the 2.4 GHz band utilizing either Wi-Fi or Bluetooth connectivity. Overall results indicate very low levels of electromagnetic fields for all IoT smart devices in terms of human exposure safety standards (typically much less than 1%) with very low duty cycles (also less than 1%) resulting in even lower time-averaged exposure levels. These low levels of exposure, along with rapid reduction of levels with distance from the devices, suggests that the cumulative effect of multiple devices in a "smart" home are not significant.

Dual-TranSpeckle: Dual-pathway transformer based encoder-decoder network for medical ultrasound image despeckling

The majority of existing deep learning-based image denoising algorithms mainly focus on processing the overall image features, ignoring the fine differences between the semantic and pixel features. Hence, we propose Dual-TranSpeckle (DTS), a medical ultrasound image despeckling network built on a dual-path Transformer. The DTS introduces two different paths, named "semantic path" and "pixel path," to facilitate the parallel transfer of feature information within the image. The semantic path passes a global view of the input semantic features, and the image features are passed through a Semantic Block to extract global semantic information from pixel-level features. The pixel path is employed to transmit finer-grained pixel features. Within the dual-path network framework, two essential modules, namely Dual Block and Merge Block, are designed. These leverage the Transformer architecture during the encoding and decoding stages. The Dual Block module facilitates information interaction between the semantic and pixel features by considering the interdependencies across both paths. Meanwhile, the Merge Block module enables parallel transfer of feature information by merging the dual path features, thereby facilitating the self-attention calculations for the overall feature representation. Our DTS is extensively evaluated on two public datasets and one private dataset. The DTS network demonstrates significant enhancements in quantitative evaluation results in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), feature similarity (FSIM), and naturalness image quality evaluator (NIQE). Furthermore, our qualitative analysis confirms that the DTS has significant improvements in despeckling performance, effectively suppressing speckle noise while preserving essential image structures.

Application of convolutional neural networks in medical images: a bibliometric analysis

Background

In the field of medical imaging, the rapid rise of convolutional neural networks (CNNs) has presented significant opportunities for conserving healthcare resources. However, with the wide spread application of CNNs, several challenges have emerged, such as enormous data annotation costs, difficulties in ensuring user privacy and security, weak model interpretability, and the consumption of substantial computational resources. The fundamental challenge lies in optimizing and seamlessly integrating CNN technology to enhance the precision and efficiency of medical diagnosis.

Methods

This study sought to provide a comprehensive bibliometric overview of current research on the application of CNNs in medical imaging. Initially, bibliometric methods were used to calculate the frequency statistics, and perform the cluster analysis and the co-citation analysis of countries, institutions, authors, keywords, and references. Subsequently, the latent Dirichlet allocation (LDA) method was employed for the topic modeling of the literature. Next, an in-depth analysis of the topics was conducted, and the topics in the medical field, technical aspects, and trends in topic evolution were summarized. Finally, by integrating the bibliometrics and LDA results, the developmental trajectory, milestones, and future directions in this field were outlined.

Results

A data set containing 6,310 articles in this field published from January 2013 to December 2023 was complied. With a total of 55,538 articles, the United States led in terms of the citation count, while in terms of the publication volume, China led with 2,385 articles. Harvard University emerged as the most influential institution, boasting an average of 69.92 citations per article. Within the realm of CNNs, residual neural network (ResNet) and U-Net stood out, receiving 1,602 and 1,419 citations, respectively, which highlights the significant attention these models have received. The impact of coronavirus disease 2019 (COVID-19) was unmistakable, as reflected by the publication of 597 articles, making it a focal point of research. Additionally, among various disease topics, with 290 articles, brain-related research was the most prevalent. Computed tomography (CT) imaging dominated the research landscape, representing 73% of the 30 different topics.

Conclusions

Over the past 11 years, CNN-related research in medical imaging has grown exponentially. The findings of the present study provide insights into the field's status and research hotspots. In addition, this article meticulously chronicled the development of CNNs and highlighted key milestones, starting with LeNet in 1989, followed by a challenging 20-year exploration period, and culminating in the breakthrough moment with AlexNet in 2012. Finally, this article explored recent advancements in CNN technology, including semi-supervised learning, efficient learning, trustworthy artificial intelligence (AI), and federated learning methods, and also addressed challenges related to data annotation costs, diagnostic efficiency, model performance, and data privacy.

Novel Technology Allowing Cone Beam Computed Tomography in 6 Seconds: A Patient Study of Comparative Image Quality

PURPOSE

The goal of this study was to evaluate the image quality provided by a novel cone beam computed tomography (CBCT) platform (HyperSight, Varian Medical Systems), a platform with enhanced reconstruction algorithms as well as rapid acquisition times. Image quality was compared with both status quo CBCT for image guidance, and to fan beam CT (FBCT) acquired on a CT simulator (CTsim).

METHODS AND MATERIALS

In a clinical study, 30 individuals were recruited for whom either deep inspiration (DIBH) or deep exhalation breath hold (DEBH) was used during imaging and radiation treatment of tumors involving liver, lung, breast, abdomen, chest wall, and pancreatic sites. All subjects were imaged during breath hold with CBCT on a standard image guidance platform (TrueBeam 2.7, Varian Medical Systems) and FBCT CT (CTsim, GE Optima). HyperSight imaging with both breath hold (HSBH) and free breathing (HSFB) was performed in a single session. The 4 image sets thus acquired were registered and compared using metrics quantifying artifact index, image nonuniformity, contrast, contrast-to-noise ratio, and difference of Hounsfield unit (HU) from CTsim.

RESULTS

HSBH provided less severe artifacts compared with both HSFB and TrueBeam. The severity of artifacts in HSBH images was similar to that in CTsim images, with statistically similar artifact index values. CTsim provided the best image uniformity; however, HSBH provided improved uniformity compared with both HSFB and TrueBeam. CTsim demonstrated elevated contrast compared with HyperSight imaging, but both HSBH and HSFB imaging showed superior contrast-to-noise ratio characteristics compared with TrueBeam. The median HU difference of HSBH from CTsim was within 1 HU for muscle/fat tissue, 12 HU for bone, and 14 HU for lung.

CONCLUSIONS

The HyperSight system provides 6-second CBCT acquisition with image artifacts that are significantly reduced compared with TrueBeam and comparable to those in CTsim FBCT imaging. HyperSight breath hold imaging was of higher quality compared with free breathing imaging on the same system. The median HU value in HyperSight breath hold imaging is within 15 HU of that in CTsim imaging for muscle, fat, bone, and lung tissue types, indicating the utility of image data for direct dose calculation in adaptive workflows.

3D printing technology to produce intraoral stents for head and neck radiotherapy: A scoping review

INTRODUCTION

Radiotherapy remains one of the main treatments for head and neck cancer; however, it is accompanied by acute and chronic adverse effects. Use of three-dimensional (3D) oral stents to modulate radiation intensity to specific target areas have been developed to minimize these adverse effects. This study aimed to present a scoping review of studies published on 3D printing of oral stents and their clinical applicability.

METHODS

MEDLINE/Pubmed, Scopus, Web of Science and CENTRAL Cochrane data bases were searched, studies selected, and data collected by three independent reviewers up to December 2022. The review was conducted based on the Preferred Reporting Items for Systematic Reviews and Meta-analysis-Extension for Scoping Reviews (PRISMA-ScR).

RESULTS

The search resulted in 404 studies and 5 articles fulfilled the eligibility criteria and were considered for this review. Three-dimensional printed intraoral stents were produced for 56 patients with indication for radiotherapy. 3D-printed stents were well-tolerated by all tested patients and demonstrated great reproducibility of maxillomandibular relation, required less time for production and lower cost to manufacture. Two studies showed great protection of healthy tissues with 3D-printed stents during radiotherapy.

CONCLUSIONS

Three-dimensional printing is promising for production of intraoral stents, however, more studies are needed to improve the technique and further investigate the safety and prevention of oral toxicities from radiotherapy.

Development of a CD163-Targeted PET Radiotracer That Images Resident Macrophages in Atherosclerosis

Tissue-resident macrophages are complementary to proinflammatory macrophages to promote the progression of atherosclerosis. The noninvasive detection of their presence and dynamic variation will be important to the understanding of their role in the pathogenesis of atherosclerosis. The goal of this study was to develop a targeted PET radiotracer for imaging CD163-positive (CD163+) macrophages in multiple mouse atherosclerosis models and assess the potential of CD163 as a biomarker for atherosclerosis in humans. Methods: CD163-binding peptide was identified using phage display and conjugated with a NODAGA chelator for 64Cu radiolabeling ([64Cu]Cu-ICT-01). CD163-overexpressing U87 cells were used to measure the binding affinity of [64Cu]Cu-ICT-01. Biodistribution studies were performed on wild-type C57BL/6 mice at multiple time points after tail vein injection. The sensitivity and specificity of [64Cu]Cu-ICT-01 in imaging CD163+ macrophages upregulated on the surface of atherosclerotic plaques were assessed in multiple mouse atherosclerosis models. Immunostaining, flow cytometry, and single-cell RNA sequencing were performed to characterize the expression of CD163 on tissue-resident macrophages. Human carotid atherosclerotic plaques were used to measure the expression of CD163+ resident macrophages and test the binding specificity of [64Cu]Cu-ICT-01. Results: [64Cu]Cu-ICT-01 showed high binding affinity to U87 cells. The biodistribution study showed rapid blood and renal clearance with low retention in all major organs at 1, 2, and 4 h after injection. In an ApoE-/- mouse model, [64Cu]Cu-ICT-01 demonstrated sensitive and specific detection of CD163+ macrophages and capability for tracking the progression of atherosclerotic lesions; these findings were further confirmed in Ldlr-/- and PCSK9 mouse models. Immunostaining showed elevated expression of CD163+ macrophages across the plaques. Flow cytometry and single-cell RNA sequencing confirmed the specific expression of CD163 on tissue-resident macrophages. Human tissue characterization demonstrated high expression of CD163+ macrophages on atherosclerotic lesions, and ex vivo autoradiography revealed specific binding of [64Cu]Cu-ICT-01 to human CD163. Conclusion: This work reported the development of a PET radiotracer binding CD163+ macrophages. The elevated expression of CD163+ resident macrophages on human plaques indicated the potential of CD163 as a biomarker for vulnerable plaques. The sensitivity and specificity of [64Cu]Cu-ICT-01 in imaging CD163+ macrophages warrant further investigation in translational settings.

Associating Knee Osteoarthritis Progression with Temporal-Regional Graph Convolutional Network Analysis on MR Images

BACKGROUND

Artificial intelligence shows promise in assessing knee osteoarthritis (OA) progression on MR images, but faces challenges in accuracy and interpretability.

PURPOSE

To introduce a temporal-regional graph convolutional network (TRGCN) on MR images to study the association between knee OA progression status and network outcome.

STUDY TYPE

Retrospective.

POPULATION

194 OA progressors (mean age, 62 ± 9 years) and 406 controls (mean age, 61 ± 9 years) from the OA Initiative were randomly divided into training (80%) and testing (20%) cohorts.

FIELD STRENGTH/SEQUENCE

Sagittal 2D IW-TSE-FS (IW) and 3D-DESS-WE (DESS) at 3T.

ASSESSMENT

Anatomical subregions of cartilage, subchondral bone, meniscus, and the infrapatellar fat pad at baseline, 12-month, and 24-month were automatically segmented and served as inputs to form compartment-based graphs for a TRGCN model, which containing both regional and temporal information. The performance of models based on (i) clinical variables alone, (ii) radiologist score alone, (iii) combined features (containing i and ii), (iv) composite TRGCN (combining TRGCN, i and ii), (v) radiomics features, (vi) convolutional neural network based on Densenet-169 were compared.

STATISTICAL TESTS

DeLong test was performed to compare the areas under the ROC curve (AUC) of all models. Additionally, interpretability analysis was done to evaluate the contributions of individual regions. A P value <0.05 was considered significant.

RESULTS

The composite TRGCN outperformed all other models with AUCs of 0.841 (DESS) and 0.856 (IW) in the testing cohort (all P < 0.05). Interpretability analysis highlighted cartilage's importance over other structures (42%-45%), tibiofemoral joint's (TFJ) dominance over patellofemoral joint (PFJ) (58%-67% vs. 12%-37%), and importance scores changes in compartments over time (TFJ vs. PFJ: baseline: 44% vs. 43%, 12-month: 52% vs. 39%, 24-month: 31% vs. 48%).

DATA CONCLUSION

The composite TRGCN, capturing temporal and regional information, demonstrated superior discriminative ability compared with other methods, providing interpretable insights for identifying knee OA progression.

LEVEL OF EVIDENCE: 4

TECHNICAL EFFICACY

Stage 2.

Multi-instance learning based artificial intelligence model to assist vocal fold leukoplakia diagnosis: A multicentre diagnostic study

OBJECTIVE

To develop a multi-instance learning (MIL) based artificial intelligence (AI)-assisted diagnosis models by using laryngoscopic images to differentiate benign and malignant vocal fold leukoplakia (VFL).

METHODS

The AI system was developed, trained and validated on 5362 images of 551 patients from three hospitals. Automated regions of interest (ROI) segmentation algorithm was utilized to construct image-level features. MIL was used to fusion image level results to patient level features, then the extracted features were modeled by seven machine learning algorithms. Finally, we evaluated the image level and patient level results. Additionally, 50 videos of VFL were prospectively gathered to assess the system's real-time diagnostic capabilities. A human-machine comparison database was also constructed to compare the diagnostic performance of otolaryngologists with and without AI assistance.

RESULTS

In internal and external validation sets, the maximum area under the curve (AUC) for image level segmentation models was 0.775 (95 % CI 0.740-0.811) and 0.720 (95 % CI 0.684-0.756), respectively. Utilizing a MIL-based fusion strategy, the AUC at the patient level increased to 0.869 (95 % CI 0.798-0.940) and 0.851 (95 % CI 0.756-0.945). For real-time video diagnosis, the maximum AUC at the patient level reached 0.850 (95 % CI, 0.743-0.957). With AI assistance, the AUC improved from 0.720 (95 % CI 0.682-0.755) to 0.808 (95 % CI 0.775-0.839) for senior otolaryngologists and from 0.647 (95 % CI 0.608-0.686) to 0.807 (95 % CI 0.773-0.837) for junior otolaryngologists.

CONCLUSIONS

The MIL based AI-assisted diagnosis system can significantly improve the diagnostic performance of otolaryngologists for VFL and help to make proper clinical decisions.

Comparison of iterative reconstruction implementations for multislice helical CT

The most mature image reconstruction algorithms in multislice helical computed tomography are based on analytical and iterative methods. Over the past decades, several methods have been developed for iterative reconstructions that improve image quality by reducing noise and artifacts. In the regularization step of iterative reconstruction, noise can be significantly reduced, thereby making low-dose CT. The quality of the reconstructed image can be further improved by using model-based reconstructions. In these reconstructions, the main focus is on modeling the data acquisition process, including the behavior of the photon beams, the geometry of the system, etc. In this article, we propose two model-based reconstruction algorithms using a virtual detector for multislice helical CT. The aim of this study is to compare the effect of using a virtual detector on image quality for the two proposed algorithms with a model-based iterative reconstruction using the original detector model. Since the algorithms are implemented using multiple GPUs, the merging of separately reconstructed volumes can significantly affect image quality. This issue is often referred to as the "long object" problem, for which we also present a solution that plays an important role in the proposed reconstruction processes. The algorithms were evaluated using mathematical and physical phantoms, as well as patient cases. The SSIM, MS-SSIM and L1 metrics were utilized to evaluate the image quality of the mathematical phantom case. To demonstrate the effectiveness of the algorithms, we used the CatPhan 600 phantom. Additionally, anonymized patient scans were used to showcase the improvements in image quality on real scan data.

Developing a Computer Vision Model to Automate Quantitative Measurement of Hip-Knee-Ankle Angle in Total Hip and Knee Arthroplasty Patients

BACKGROUND

Increasing deformity of the lower extremities, as measured by the hip-knee-ankle angle (HKAA), is associated with poor patient outcomes after total hip and knee arthroplasty (THA, TKA). Automated calculation of HKAA is imperative to reduce the burden on orthopaedic surgeons. We proposed a detection-based deep learning (DL) model to calculate HKAA in THA and TKA patients and assessed the agreement between DL-derived HKAAs and manual measurement.

METHODS

We retrospectively identified 1,379 long-leg radiographs (LLRs) from patients scheduled for THA or TKA within an academic medical center. There were 1,221 LLRs used to develop the model (randomly split into 70% training, 20% validation, and 10% held-out test sets); 158 LLRs were considered "difficult," as the femoral head was difficult to distinguish from surrounding tissue. There were 2 raters who annotated the HKAA of both lower extremities, and inter-rater reliability was calculated to compare the DL-derived HKAAs with manual measurement within the test set.

RESULTS

The DL model achieved a mean average precision of 0.985 on the test set. The average HKAA of the operative leg was 173.05 ± 4.54°; the nonoperative leg was 175.55 ± 3.56°. The inter-rater reliability between manual and DL-derived HKAA measurements on the operative leg and nonoperative leg indicated excellent reliability (intraclass correlation (2,k) = 0.987 [0.96, 0.99], intraclass correlation (2, k) = 0.987 [0.98, 0.99, respectively]). The standard error of measurement for the DL-derived HKAA for the operative and nonoperative legs was 0.515° and 0.403°, respectively.

CONCLUSIONS

A detection-based DL algorithm can calculate the HKAA in LLRs and is comparable to that calculated by manual measurement. The algorithm can detect the bilateral femoral head, knee, and ankle joints with high precision, even in patients where the femoral head is difficult to visualize.

Is the sustainability of exposure to non-ionizing electromagnetic radiation possible?

Technological advances imply an increase in artificially generating sources of electromagnetic fields (EMF), therefore, resulting in a permanent exposure of people and the environment (electromagnetic pollution). Inconsistent results have been published considering the evaluated health effects. The purpose of this study was to review scientific literature on EMF to provide a global and retrospective perspective, on the association between human exposure to non-ionizing radiation (NIR, mainly radiofrequency-EMF) and health and environmental effects. Studies on the health effects of 5G radiation exposure have not yet been performed with sufficient statistical power, as the exposure time is still relatively short and also the latency and intensity of exposure to 5G. The safety standards only consider thermal effects, do not contemplate non-thermal effects. We consider relevant to communicate this knowledge to the general public to improve education in this field, and to healthcare professionals to prevent diseases that may result from RF-EMF exposures.

Study on Gamma sensory flicker for Insomnia

OBJECTIVES

Insomnia has been the subject of much systematic research because it is a risk factor for a variety of diseases. There is some evidence that gamma sensory stimulation therapy has also been demonstrated to improve sleep quality for people with Alzheimer's disease. However, it is unclear whether this method is effective for treating insomnia. The principal objective of this project was to investigate the efficacy and safety of gamma sensory flicker in improving the sleep quality of insomnia patients.

METHODS

Thirty-seven participants with insomnia were recruited for this prospective observational study. For a duration of 8 weeks, participants were exposed to flicker stimulation through a light and sound device.

RESULTS

During the main phase of the study, adherence rates averaged 92.21%. Additionally, no severe adverse events were reported for flicker treatment. Analysis of sleep diaries indicated that 40 Hz flickers can enhance sleep quality by reducing sleep onset latencies, and arousals, and increasing total sleep duration.

CONCLUSIONS

Gamma sensory flicker improves sleep quality in people suffering from insomnia.

Epstein-Barr virus positive gastric cancer: the pathological basis of CT findings and radiomics models prediction

PURPOSE

To analyze the clinicopathologic information and CT imaging features of Epstein-Barr virus (EBV)-positive gastric cancer (GC) and establish CT-based radiomics models to predict the EBV status of GC.

METHODS

This retrospective study included 144 GC cases, including 48 EBV-positive cases. Pathological and immunohistochemical information was collected. CT enlarged LN and morphological characteristics were also assessed. Radiomics models were constructed to predict the EBV status, including decision tree (DT), logistic regression (LR), random forest (RF), and support vector machine (SVM).

RESULTS

T stage, Lauren classification, histological differentiation, nerve invasion, VEGFR2, E-cadherin, PD-L1, and Ki67 differed significantly between the EBV-positive and -negative groups (p = 0.015, 0.030, 0.006, 0.022, 0.028, 0.030, < 0.001, and < 0.001, respectively). CT enlarged LN and large ulceration differed significantly between the two groups (p = 0.019 and 0.043, respectively). The number of patients in the training and validation cohorts was 100 (with 33 EBV-positive cases) and 44 (with 15 EBV-positive cases). In the training cohort, the radiomics models using DT, LR, RF, and SVM yielded areas under the curve (AUCs) of 0.905, 0.771, 0.836, and 0.886, respectively. In the validation cohort, the diagnostic efficacy of radiomics models using the four classifiers were 0.737, 0.722, 0.751, and 0.713, respectively.

CONCLUSION

A significantly higher proportion of CT enlarged LN and a significantly lower proportion of large ulceration were found in EBV-positive GC. The prediction efficiency of radiomics models with different classifiers to predict EBV status in GC was good.

Transfer learning and self-distillation for automated detection of schizophrenia using single-channel EEG and scalogram images

Schizophrenia (SZ) has been acknowledged as a highly intricate mental disorder for a long time. In fact, individuals with SZ experience a blurred line between fantasy and reality, leading to a lack of awareness about their condition, which can pose significant challenges during the treatment process. Due to the importance of the issue, timely diagnosis of this illness can not only assist patients and their families in managing the condition but also enable early intervention, which may help prevent its advancement. EEG is a widely utilized technique for investigating mental disorders like SZ due to its non-invasive nature, affordability, and wide accessibility. In this study, our main goal is to develop an optimized system that can achieve automatic diagnosis of SZ with minimal input information. To optimize the system, we adopted a strategy of using single-channel EEG signals and integrated knowledge distillation and transfer learning techniques into the model. This approach was designed to improve the performance and efficiency of our proposed method for SZ diagnosis. Additionally, to leverage the pre-trained models effectively, we converted the EEG signals into images using Continuous Wavelet Transform (CWT). This transformation allowed us to harness the capabilities of pre-trained models in the image domain, enabling automatic SZ detection with enhanced efficiency. To achieve a more robust estimate of the model's performance, we employed fivefold cross-validation. The accuracy achieved from the 5-s records of the EEG signal, along with the combination of self-distillation and VGG16 for the P4 channel, is 97.81. This indicates a high level of accuracy in diagnosing SZ using the proposed method.

Artificial intelligence in chorioretinal pathology through fundoscopy: a comprehensive review

BACKGROUND

Applications for artificial intelligence (AI) in ophthalmology are continually evolving. Fundoscopy is one of the oldest ocular imaging techniques but remains a mainstay in posterior segment imaging due to its prevalence, ease of use, and ongoing technological advancement. AI has been leveraged for fundoscopy to accomplish core tasks including segmentation, classification, and prediction.

MAIN BODY

In this article we provide a review of AI in fundoscopy applied to representative chorioretinal pathologies, including diabetic retinopathy and age-related macular degeneration, among others. We conclude with a discussion of future directions and current limitations.

SHORT CONCLUSION

As AI evolves, it will become increasingly essential for the modern ophthalmologist to understand its applications and limitations to improve patient outcomes and continue to innovate.

Classification of mental workload using brain connectivity and machine learning on electroencephalogram data

Mental workload refers to the cognitive effort required to perform tasks, and it is an important factor in various fields, including system design, clinical medicine, and industrial applications. In this paper, we propose innovative methods to assess mental workload from EEG data that use effective brain connectivity for the purpose of extracting features, a hierarchical feature selection algorithm to select the most significant features, and finally machine learning models. We have used the Simultaneous Task EEG Workload (STEW) dataset, an open-access collection of raw EEG data from 48 subjects. We extracted brain-effective connectivities by the direct directed transfer function and then selected the top 30 connectivities for each standard frequency band. Then we applied three feature selection algorithms (forward feature selection, Relief-F, and minimum-redundancy-maximum-relevance) on the top 150 features from all frequencies. Finally, we applied sevenfold cross-validation on four machine learning models (support vector machine (SVM), linear discriminant analysis, random forest, and decision tree). The results revealed that SVM as the machine learning model and forward feature selection as the feature selection method work better than others and could classify the mental workload levels with accuracy equal to 89.53% (± 1.36).

Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis

PURPOSE

Fracture detection is one of the most commonly used and studied aspects of artificial intelligence (AI) in medicine. In this systematic review and meta-analysis, we aimed to summarize available literature and data regarding AI performance in fracture detection on plain radiographs and various factors affecting it.

METHODS

We systematically reviewed studies evaluating AI algorithms in detecting bone fractures in plain radiographs, combined their performance using meta-analysis (a bivariate regression approach), and compared it with that of clinicians. We also analyzed the factors potentially affecting algorithm performance using meta-regression.

RESULTS

Our analysis included 100 studies. In 83 studies with confusion matrices, AI algorithms showed a sensitivity of 91.43% and a specificity of 92.12% (Area under the summary receiver operator curve = 0.968). After adjustment and false discovery rate correction, tibia/fibula (excluding ankle) fractures were associated with higher (7.0%, p=0.004) AI sensitivity, while more recent publications (5.5%, p=0.003) and Xception architecture (6.6%, p<0.001) were associated with higher specificity. Clinicians and AI showed similar specificity in fracture identification, although AI leaned to higher sensitivity (7.6%, p=0.07). Radiologists, on the other hand, were more specific than AI overall and in several subgroups, and more sensitive to hip fractures before FDR correction.

CONCLUSIONS

Currently available AI aids could result in a significant improvement in care where radiologists are not readily available. Moreover, identifying factors affecting algorithm performance could guide AI development teams in their process of optimizing their products.

Development of a multi-fusion convolutional neural network (MF-CNN) for enhanced gastrointestinal disease diagnosis in endoscopy image analysis

Gastrointestinal (GI) diseases are prevalent medical conditions that require accurate and timely diagnosis for effective treatment. To address this, we developed the Multi-Fusion Convolutional Neural Network (MF-CNN), a deep learning framework that strategically integrates and adapts elements from six deep learning models, enhancing feature extraction and classification of GI diseases from endoscopic images. The MF-CNN architecture leverages truncated and partially frozen layers from existing models, augmented with novel components such as Auxiliary Fusing Layers (AuxFL), Fusion Residual Block (FuRB), and Alpha Dropouts (αDO) to improve precision and robustness. This design facilitates the precise identification of conditions such as ulcerative colitis, polyps, esophagitis, and healthy colons. Our methodology involved preprocessing endoscopic images sourced from open databases, including KVASIR and ETIS-Larib Polyp DB, using adaptive histogram equalization (AHE) to enhance their quality. The MF-CNN framework supports detailed feature mapping for improved interpretability of the model's internal workings. An ablation study was conducted to validate the contribution of each component, demonstrating that the integration of AuxFL, αDO, and FuRB played a crucial part in reducing overfitting and efficiency saturation and enhancing overall model performance. The MF-CNN demonstrated outstanding performance in terms of efficacy, achieving an accuracy rate of 99.25%. It also excelled in other key performance metrics with a precision of 99.27%, a recall of 99.25%, and an F1-score of 99.25%. These metrics confirmed the model's proficiency in accurate classification and its capability to minimize false positives and negatives across all tested GI disease categories. Furthermore, the AUC values were exceptional, averaging 1.00 for both test and validation sets, indicating perfect discriminative ability. The findings of the P-R curve analysis and confusion matrix further confirmed the robust classification performance of the MF-CNN. This research introduces a technique for medical imaging that can potentially transform diagnostics in gastrointestinal healthcare facilities worldwide.

Smart grading of diabetic retinopathy: an intelligent recommendation-based fine-tuned EfficientNetB0 framework

Diabetic retinopathy is a condition that affects the retina and causes vision loss due to blood vessel destruction. The retina is the layer of the eye responsible for visual processing and nerve signaling. Diabetic retinopathy causes vision loss, floaters, and sometimes blindness; however, it often shows no warning signals in the early stages. Deep learning-based techniques have emerged as viable options for automated illness classification as large-scale medical imaging datasets have become more widely available. To adapt to medical image analysis tasks, transfer learning makes use of pre-trained models to extract high-level characteristics from natural images. In this research, an intelligent recommendation-based fine-tuned EfficientNetB0 model has been proposed for quick and precise assessment for the diagnosis of diabetic retinopathy from fundus images, which will help ophthalmologists in early diagnosis and detection. The proposed EfficientNetB0 model is compared with three transfer learning-based models, namely, ResNet152, VGG16, and DenseNet169. The experimental work is carried out using publicly available datasets from Kaggle consisting of 3,200 fundus images. Out of all the transfer learning models, the EfficientNetB0 model has outperformed with an accuracy of 0.91, followed by DenseNet169 with an accuracy of 0.90. In comparison to other approaches, the proposed intelligent recommendation-based fine-tuned EfficientNetB0 approach delivers state-of-the-art performance on the accuracy, recall, precision, and F1-score criteria. The system aims to assist ophthalmologists in early detection, potentially alleviating the burden on healthcare units.

Generative adversarial network-based synthesis of contrast-enhanced MR images from precontrast images for predicting histological characteristics in breast cancer

Objective. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a sensitive tool for assessing breast cancer by analyzing tumor blood flow, but it requires gadolinium-based contrast agents, which carry risks such as brain retention and astrocyte migration. Contrast-free MRI is thus preferable for patients with renal impairment or who are pregnant. This study aimed to investigate the feasibility of generating contrast-enhanced MR images from precontrast images and to evaluate the potential use of synthetic images in diagnosing breast cancer.Approach. This retrospective study included 322 women with invasive breast cancer who underwent preoperative DCE-MRI. A generative adversarial network (GAN) based postcontrast image synthesis (GANPIS) model with perceptual loss was proposed to generate contrast-enhanced MR images from precontrast images. The quality of the synthesized images was evaluated using the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The diagnostic performance of the generated images was assessed using a convolutional neural network to predict Ki-67, luminal A and histological grade with the area under the receiver operating characteristic curve (AUC). The patients were divided into training (n= 200), validation (n= 60), and testing sets (n= 62).Main results. Quantitative analysis revealed strong agreement between the generated and real postcontrast images in the test set, with PSNR and SSIM values of 36.210 ± 2.670 and 0.988 ± 0.006, respectively. The generated postcontrast images achieved AUCs of 0.918 ± 0.018, 0.842 ± 0.028 and 0.815 ± 0.019 for predicting the Ki-67 expression level, histological grade, and luminal A subtype, respectively. These results showed a significant improvement compared to the use of precontrast images alone, which achieved AUCs of 0.764 ± 0.031, 0.741 ± 0.035, and 0.797 ± 0.021, respectively.Significance. This study proposed a GAN-based MR image synthesis method for breast cancer that aims to generate postcontrast images from precontrast images, allowing the use of contrast-free images to simulate kinetic features for improved diagnosis.

Tinnitus classification based on resting-state functional connectivity using a convolutional neural network architecture

OBJECTIVES

Many studies have investigated aberrant functional connectivity (FC) using resting-state functional MRI (rs-fMRI) in subjective tinnitus patients. However, no studies have verified the efficacy of resting-state FC as a diagnostic imaging marker. We established a convolutional neural network (CNN) model based on rs-fMRI FC to distinguish tinnitus patients from healthy controls, providing guidance and fast diagnostic tools for the clinical diagnosis of subjective tinnitus.

METHODS

A CNN architecture was trained on rs-fMRI data from 100 tinnitus patients and 100 healthy controls using an asymmetric convolutional layer. Additionally, a traditional machine learning model and a transfer learning model were included for comparison with the CNN, and each of the three models was tested on three different brain atlases.

RESULTS

Of the three models, the CNN model outperformed the other two models with the highest area under the curve, especially on the Dos_160 atlas (AUC = 0.944). Meanwhile, the model with the best classification performance highlights the crucial role of the default mode network, salience network, and sensorimotor network in distinguishing between normal controls and patients with subjective tinnitus.

CONCLUSION

Our CNN model could appropriately tackle the diagnosis of tinnitus patients using rs-fMRI and confirmed the diagnostic value of FC as measured by rs-fMRI.

Enhanced lung cancer detection: Integrating improved random walker segmentation with artificial neural network and random forest classifier

Background

Medical image segmentation is a vital yet difficult job because of the multimodality of the acquired images. It is difficult to locate the polluted area before it spreads.

Methods

This research makes use of several machine learning tools, including an artificial neural network as well as a random forest classifier, to increase the system's reliability of pulmonary nodule classification. Anisotropic diffusion filtering is initially used to remove noise from a picture. After that, a modified random walk method is used to get the region of interest inside the lung parenchyma. Finally, the features corresponding to the consistency of the picture segments are extracted using texture-based feature extraction for pulmonary nodules. The final stage is to identify and classify the pulmonary nodules using a classifier algorithm.

Results

The studies employ cross-validation to demonstrate the validity of the diagnosis framework. In this instance, the proposed method is tested using CT scan information provided by the Lung Image Database Consortium. A random forest classifier showed 99.6 percent accuracy rate for detecting lung cancer, compared to a artificial neural network's 94.8 percent accuracy rate.

Conclusions

Due to this, current research is now primarily concerned with identifying lung nodules and classifying them as benign or malignant. The diagnostic potential of machine learning as well as image processing approaches are enormous for the categorization of lung cancer.

Automatic measurement of lower limb alignment in portable devices based on deep learning for knee osteoarthritis

BACKGROUND

For knee osteoarthritis patients, analyzing alignment of lower limbs is essential for therapy, which is currently measured from standing long-leg radiographs of anteroposterior X-ray (LLR) manually. To address the time wasting, poor reproducibility and inconvenience of use caused by existing methods, we present an automated measurement model in portable devices for assessing knee alignment from LLRs.

METHOD

We created a model and trained it with 837 conforming LLRs, and tested it using 204 LLRs without duplicates in a portable device. Both manual and model measurements were conducted independently, then we recorded knee alignment parameters such as Hip knee ankle angle (HKA), Joint line convergence angle (JCLA), Anatomical mechanical angle (AMA), mechanical Lateral distal femoral angle (mLDFA), mechanical Medial proximal tibial angle (mMPTA), and the time required. We evaluated the model's performance compared with manual results in various metrics.

RESULT

In both the validation and test sets, the average mean radial errors were 2.778 and 2.447 (P<0.05). The test results for native knee joints showed that 92.22%, 79.38%, 87.94%, 79.82%, and 80.16% of the joints reached angle deviation<1° for HKA, JCLA, AMA, mLDFA, and mMPTA. Additionally, for joints with prostheses, 90.14%, 93.66%, 86.62%, 83.80%, and 85.92% of the joints reached that. The Chi-square test did not reveal any significant differences between the manual and model measurements in subgroups (P>0.05). Furthermore, the Bland-Altman 95% limits of agreement were less than ± 2° for HKA, JCLA, AMA, and mLDFA, and slightly more than ± 2 degrees for mMPTA.

CONCLUSION

The automatic measurement tool can assess the alignment of lower limbs in portable devices for knee osteoarthritis patients. The results are reliable, reproducible, and time-saving.

Artificial intelligence in the healthcare sector: comparison of deep learning networks using chest X-ray images

Purpose

Artificial intelligence has led to significant developments in the healthcare sector, as in other sectors and fields. In light of its significance, the present study delves into exploring deep learning, a branch of artificial intelligence.

Methods

In the study, deep learning networks ResNet101, AlexNet, GoogLeNet, and Xception were considered, and it was aimed to determine the success of these networks in disease diagnosis. For this purpose, a dataset of 1,680 chest X-ray images was utilized, consisting of cases of COVID-19, viral pneumonia, and individuals without these diseases. These images were obtained by employing a rotation method to generate replicated data, wherein a split of 70 and 30% was adopted for training and validation, respectively.

Results

The analysis findings revealed that the deep learning networks were successful in classifying COVID-19, Viral Pneumonia, and Normal (disease-free) images. Moreover, an examination of the success levels revealed that the ResNet101 deep learning network was more successful than the others with a 96.32% success rate.

Conclusion

In the study, it was seen that deep learning can be used in disease diagnosis and can help experts in the relevant field, ultimately contributing to healthcare organizations and the practices of country managers.

Development of an automatic surgical planning system for high tibial osteotomy using artificial intelligence

BACKGROUND

This study proposed an automatic surgical planning system for high tibial osteotomy (HTO) using deep learning-based artificial intelligence and validated its accuracy. The system simulates osteotomy and measures lower-limb alignment parameters in pre- and post-osteotomy simulations.

METHODS

A total of 107 whole-leg standing radiographs were obtained from 107 patients who underwent HTO. First, the system detected anatomical landmarks on radiographs. Then, it simulated osteotomy and automatically measured five parameters in pre- and post-osteotomy simulation (hip knee angle [HKA], weight-bearing line ratio [WBL ratio], mechanical lateral distal femoral angle [mLDFA], mechanical medial proximal tibial angle [mMPTA], and mechanical lateral distal tibial angle [mLDTA]). The accuracy of the measured parameters was validated by comparing them with the ground truth (GT) values given by two orthopaedic surgeons.

RESULTS

All absolute errors of the system were within 1.5° or 1.5%. All inter-rater correlation confidence (ICC) values between the system and GT showed good reliability (>0.80). Excellent reliability was observed in the HKA (0.99) and WBL ratios (>0.99) for the pre-osteotomy simulation. The intra-rater difference of the system exhibited excellent reliability with an ICC value of 1.00 for all lower-limb alignment parameters in pre- and post-osteotomy simulations. In addition, the measurement time per radiograph (0.24 s) was considerably shorter than that of an orthopaedic surgeon (118 s).

CONCLUSION

The proposed system is practically applicable because it can measure lower-limb alignment parameters accurately and quickly in pre- and post-osteotomy simulations. The system has potential applications in surgical planning systems.

CovMediScanX: A medical imaging solution for COVID-19 diagnosis from chest X-ray images

INTRODUCTION

Radiologists have extensively employed the interpretation of chest X-rays (CXR) to identify visual markers indicative of COVID-19 infection, offering an alternative approach for the screening of infected individuals. This research article presents CovMediScanX, a deep learning-based framework designed for a rapid and automated diagnosis of COVID-19 from CXR scan images.

METHODS

The proposed approach encompasses gathering and preprocessing CXR image datasets, training deep learning-based custom-made Convolutional Neural Network (CNN), pre-trained and hybrid transfer learning models, identifying the highest-performing model based on key evaluation metrics, and embedding this model into a web interface called CovMediScanX, designed for radiologists to detect the COVID-19 status in new CXR images.

RESULTS

The custom-made CNN model obtained a remarkable testing accuracy of 94.32% outperforming other models. CovMediScanX, employing the custom-made CNN underwent evaluation with an independent dataset also. The images in the independent dataset are sourced from a scanning machine that is entirely different from those used for the training dataset, highlighting a clear distinction of datasets in their origins. The evaluation outcome highlighted the framework's capability to accurately detect COVID-19 cases, showcasing encouraging results with a precision of 73% and a recall of 84% for positive cases. However, the model requires further enhancement, particularly in improving its detection of normal cases, as evidenced by lower precision and recall rates.

CONCLUSION

The research proposes CovMediScanX framework that demonstrates promising potential in automatically identifying COVID-19 cases from CXR images. While the model's overall performance on independent data needs improvement, it is evident that addressing bias through the inclusion of diverse data sources during training could further enhance accuracy and reliability.

Unveiling the hidden struggle of healthcare students as second victims through a systematic review

BACKGROUND

When healthcare students witness, engage in, or are involved in an adverse event, it often leads to a second victim experience, impacting their mental well-being and influencing their future professional practice. This study aimed to describe the efforts, methods, and outcomes of interventions to help students in healthcare disciplines cope with the emotional experience of being involved in or witnessing a mistake causing harm to a patient during their clerkships or training.

METHODS

This systematic review followed the PRISMA guidelines and includes the synthesis of eighteen studies, published in diverse languages from 2011 to 2023, identified from the databases MEDLINE, EMBASE, SCOPUS and APS PsycInfo. PICO method was used for constructing a research question and formulating eligibility criteria. The selection process was conducted through Rayyan. Titles and abstracts of were independently screened by two authors. The critical appraisal tools of the Joanna Briggs Institute was used to assess the risk of bias of the included studies.

RESULTS

A total of 1354 studies were retrieved, 18 met the eligibility criteria. Most studies were conducted in the USA. Various educational interventions along with learning how to prevent mistakes, and resilience training were described. In some cases, this experience contributed to the student personal growth. Psychological support in the aftermath of adverse events was scattered.

CONCLUSION

Ensuring healthcare students' resilience should be a fundamental part of their training. Interventions to train them to address the second victim phenomenon during their clerkships are scarce, scattered, and do not yield conclusive results on identifying what is most effective and what is not.

3D amide proton transfer-weighted imaging may be useful for diagnosing early-stage breast cancer: a prospective monocentric study

BACKGROUND

We investigated the value of three-dimensional amide proton transfer-weighted imaging (3D-APTWI) in the diagnosis of early-stage breast cancer (BC) and its correlation with the immunohistochemical characteristics of malignant lesions.

METHODS

Seventy-eight women underwent APTWI and dynamic contrast-enhanced (DCE)-MRI. Pathological results were categorized as either benign (n = 43) or malignant (n = 37) lesions. The parameters of APTWI and DCE-MRI were compared between the benign and malignant groups. The diagnostic value of 3D-APTWI was evaluated using the area under the receiver operating characteristic curve (ROC-AUC) to establish a diagnostic threshold. Pearson's correlation was used to analyze the correlation between the magnetization transfer asymmetry (MTRasym) and immunohistochemical characteristics.

RESULTS

The MTRasym and time-to-peak of malignancies were significantly lower than those of benign lesions (all p < 0.010). The volume transfer constant, rate constant, and wash-in and wash-out rates of malignancies were all significantly greater than those of benign lesions (all p < 0.010). ROC-AUCs of 3D-APTWI, DCE-MRI, and 3D-APTWI+DCE to differential diagnosis between early-stage BC and benign lesions were 0.816, 0.745, and 0.858, respectively. Only the difference between AUCAPT+DCE and AUCDCE was significant (p < 0.010). When a threshold of MTRasym for malignancy for 2.42%, the sensitivity and specificity of 3D-APTWI for BC diagnosis were 86.5% and 67.6%, respectively; MTRasym was modestly positively correlated with pathological grade (r = 0.476, p = 0.003) and Ki-67 (r = 0.419, p = 0.020).

CONCLUSIONS

3D-APTWI may be used as a supplementary method for patients with contraindications of DCE-MRI. MTRasym can imply the proliferation activities of early-stage BC.

RELEVANCE STATEMENT

3D-APTWI can be an alternative diagnostic method for patients with early-stage BC who are not suitable for contrast injection.

KEY POINTS

• 3D-APTWI reflects the changes in the microenvironment of early-stage breast cancer. • Combined 3D-APTWI is superior to DCE-MRI alone for early-stage breast cancer diagnosis. • 3D-APTWI improves the diagnostic accuracy of early-stage breast cancer.

Continuous glucose monitoring for the routine care of type 2 diabetes mellitus

Although continuous glucose monitoring (CGM) devices are now considered the standard of care for people with type 1 diabetes mellitus, the uptake among people with type 2 diabetes mellitus (T2DM) has been slower and is focused on those receiving intensive insulin therapy. However, increasing evidence now supports the inclusion of CGM in the routine care of people with T2DM who are on basal insulin-only regimens or are managed with other medications. Expanding CGM to these groups could minimize hypoglycaemia while allowing efficient adaptation and escalation of therapies. Increasing evidence from randomized controlled trials and observational studies indicates that CGM is of clinical value in people with T2DM on non-intensive treatment regimens. If further studies confirm this finding, CGM could soon become a part of routine care for T2DM. In this Perspective we explore the potential benefits of widening the application of CGM in T2DM, along with the challenges that must be overcome for the evidence-based benefits of this technology to be delivered for all people with T2DM.

2.5D UNet with context-aware feature sequence fusion for accurate esophageal tumor semantic segmentation

Segmenting esophageal tumor from computed tomography (CT) sequence images can assist doctors in diagnosing and treating patients with this malignancy. However, accurately extracting esophageal tumor features from CT images often present challenges due to their small area, variable position, and shape, as well as the low contrast with surrounding tissues. This results in not achieving the level of accuracy required for practical applications in current methods. To address this problem, we propose a 2.5D context-aware feature sequence fusion UNet (2.5D CFSF-UNet) model for esophageal tumor segmentation in CT sequence images. Specifically, we embed intra-slice multiscale attention feature fusion (Intra-slice MAFF) in each skip connection of UNet to improve feature learning capabilities, better expressing the differences between anatomical structures within CT sequence images. Additionally, the inter-slice context fusion block (Inter-slice CFB) is utilized in the center bridge of UNet to enhance the depiction of context features between CT slices, thereby preventing the loss of structural information between slices. Experiments are conducted on a dataset of 430 esophageal tumor patients. The results show an 87.13% dice similarity coefficient, a 79.71% intersection over union and a 2.4758 mm Hausdorff distance, which demonstrates that our approach can improve contouring consistency and can be applied to clinical applications.

Verification of neuronavigated TMS accuracy using structured-light 3D scans

Objective.To investigate the reliability and accuracy of the manual three-point co-registration in neuronavigated transcranial magnetic stimulation (TMS). The effect of the error in landmark pointing on the coil placement and on the induced electric and magnetic fields was examined.Approach.The position of the TMS coil on the head was recorded by the neuronavigation system and by 3D scanning for ten healthy participants. The differences in the coil locations and orientations and the theoretical error values for electric and magnetic fields between the neuronavigated and 3D scanned coil positions were calculated. In addition, the sensitivity of the coil location on landmark accuracy was calculated.Main results.The measured distances between the neuronavigated and 3D scanned coil locations were on average 10.2 mm, ranging from 3.1 to 18.7 mm. The error in angles were on average from two to three degrees. The coil misplacement caused on average a 29% relative error in the electric field with a range from 9% to 51%. In the magnetic field, the same error was on average 33%, ranging from 10% to 58%. The misplacement of landmark points could cause a 1.8-fold error for the coil location.Significance.TMS neuronavigation with three landmark points can cause a significant error in the coil position, hampering research using highly accurate electric field calculations. Including 3D scanning to the process provides an efficient method to achieve a more accurate coil position.