Search

Purpose: This study evaluates the efficacy of two advanced Large Language Models (LLMs), OpenAI's ChatGPT 4 and Google's Gemini Advanced, in providing treatment recommendations for head and neck oncology cases. The aim is to assess their utility in supporting multidisciplinary oncological evaluations and decision-making processes. Methods: This comparative analysis examined the responses of ChatGPT 4 and Gemini Advanced to five hypothetical cases of head and neck cancer, each representing a different anatomical subsite. The responses were evaluated against the latest National Comprehensive Cancer Network (NCCN) guidelines by two blinded panels using the total disagreement score (TDS) and the artificial intelligence performance instrument (AIPI). Statistical assessments were performed using the Wilcoxon signed-rank test and the Friedman test. Results: Both LLMs produced relevant treatment recommendations with ChatGPT 4 generally outperforming Gemini Advanced regarding adherence to guidelines and comprehensive treatment planning. ChatGPT 4 showed higher AIPI scores (median 3 [2–4]) compared to Gemini Advanced (median 2 [2–3]), indicating better overall performance. Notably, inconsistencies were observed in the management of induction chemotherapy and surgical decisions, such as neck dissection. Conclusions: While both LLMs demonstrated the potential to aid in the multidisciplinary management of head and neck oncology, discrepancies in certain critical areas highlight the need for further refinement. The study supports the growing role of AI in enhancing clinical decision-making but also emphasizes the necessity for continuous updates and validation against current clinical standards to integrate AI into healthcare practices fully. [ABSTRACT FROM AUTHOR]

This study aims to compare computed tomography (CT) with magnetic resonance imaging (MRI) of the temporomandibular joint (TMJ) by using texture analysis (TA) to detect condylar bone marrow changes associated with the flattening and erosion of cortical bone. A total of 47 patients from the Dentomaxillofacial Radiology Division at São Paulo State University were evaluated. Images from 250 CT and 250 MRI images were assessed by experienced radiologists employing OnDemand3D software. Texture parameters were extracted with MaZda software (version 4.6), and we focused on regions of interest within the condyles. Statistical analysis revealed significant differences in texture parameters between the affected and control groups. CT images showed higher correlation values in cases of flattening, whereas MRI images demonstrated substantial changes in texture parameters for both flattening and erosion. These findings suggest that the texture analysis of CT and MRI images can effectively detect early and advanced degenerative changes in the TMJ, thus providing valuable insights into the underlying pathophysiology and aiding in early intervention and treatment planning. [ABSTRACT FROM AUTHOR]

To assess the value of 3D multiparametric ultrasound imaging, combining hemodynamic and tissue stiffness quantifications by machine learning, for the prediction of prostate biopsy outcomes. After signing informed consent, 54 biopsy-naïve patients underwent a 3D dynamic contrast-enhanced ultrasound (DCE-US) recording, a multi-plane 2D shear-wave elastography (SWE) scan with manual sweeping from base to apex of the prostate, and received 12-core systematic biopsies (SBx). 3D maps of 18 hemodynamic parameters were extracted from the 3D DCE-US quantification and a 3D SWE elasticity map was reconstructed based on the multi-plane 2D SWE acquisitions. Subsequently, all the 3D maps were segmented and subdivided into 12 regions corresponding to the SBx locations. Per region, the set of 19 computed parameters was further extended by derivation of eight radiomic features per parameter. Based on this feature set, a multiparametric ultrasound approach was implemented using five different classifiers together with a sequential floating forward selection method and hyperparameter tuning. The classification accuracy with respect to the biopsy reference was assessed by a group-k-fold cross-validation procedure, and the performance was evaluated by the Area Under the Receiver Operating Characteristics Curve (AUC). Of the 54 patients, 20 were found with clinically significant prostate cancer (csPCa) based on SBx. The 18 hemodynamic parameters showed mean AUC values varying from 0.63 to 0.75, and SWE elasticity showed an AUC of 0.66. The multiparametric approach using radiomic features derived from hemodynamic parameters only produced an AUC of 0.81, while the combination of hemodynamic and tissue-stiffness quantifications yielded a significantly improved AUC of 0.85 for csPCa detection (p -value < 0.05) using the Gradient Boosting classifier. Our results suggest 3D multiparametric ultrasound imaging combining hemodynamic and tissue-stiffness features to represent a promising diagnostic tool for biopsy outcome prediction, aiding in csPCa localization. [ABSTRACT FROM AUTHOR]

Background: Positional preferences, asymmetry of body position and movements potentially indicate abnormal clinical conditions in infants. However, a lack of standardized nomenclature hinders accurate assessment and documentation of these preferences over time. Video tools offer a safe and reproducible method to analyze and describe infant movement patterns, aiding in physiotherapy management and goal planning. The study aimed to develop an objective classification system for infant movement patterns with particular emphasis on the specific distribution of muscle tension, using methods of computer analysis of video recordings to enhance accuracy and reproducibility in assessments. Methods: The study involved the recording of videos of 51 infants between 6 and 15 weeks of age, born at term, with an Apgar score of at least 8 points. Based on observations of a recording of infant spontaneous movements in the supine position, experts identified postural-motor patterns: symmetry and typical asymmetry linked to the asymmetrical tonic neck reflex. Deviations from the typical postural-motor system were indicated, and subcategories of atypical patterns were distinguished. A computer-based inference system was developed to automatically classify individual patterns. Results: The following division of motor patterns was used: (1) normal patterns, including (a) typical (symmetrical, asymmetrical: variants 1 and 2); and (b) atypical (variants: 1 to 4), (2) positional preference, and (3) abnormal patterns. The proposed automatic classification method achieved an expert decision mapping accuracy of 84%. For atypical patterns, the high reproducibility of the system's results was confirmed. Lower reproducibility, not exceeding 70%, was achieved with typical patterns. Conclusions: Based on the observation of infant spontaneous movements, it is possible to identify movement patterns divided into typical and atypical patterns. Computer-based analysis of infant movement patterns makes it possible to objectify and satisfactorily reproduce diagnostic decisions. [ABSTRACT FROM AUTHOR]

Background: Obstructive sleep apnea (OSA) affects a significant proportion of the global population, with many having moderate or severe forms of the disease. Home Sleep Apnea Testing (HSAT) has become the most common method of diagnosing OSA, replacing in-lab polysomnography. Polysmith software Version 11 by Nihon Kohden allows for the automatic scoring of respiratory events. This study aimed to assess the validity of this technology. Study Objectives: The objective was to assess the accuracy of the Polysmith Software Automatic Scoring Algorithm of HSATs in comparison to that of sleep technicians. Methods: One hundred twenty HSATs were scored by both sleep technicians and Polysmith software. The measured values were the respiratory event index (REI), apneic events, and hypopneic events. Agreement between the two methods was reached by utilizing the Kruskal–Wallis test, Pearson correlation coefficient, and Bland–Altman plot, as well as sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results: The correlation between the REI calculated by the software and technicians proved to be strong overall (r = 0.96, p < 0.0001). The mild OSA group had a moderate correlation (r = 0.45, p = 0.0129). The primary snoring, moderate OSA, and severe OSA groups showed stronger correlations (r = 0.69, p < 0.0001; r = 0.56, p = 0.012; r = 0.71, p < 0.0001). The analysis conducted across all groups demonstrated an average sensitivity of 81%, specificity of 94%, PPV of 82%, and NPV of 94%, with an overall accuracy of 81%. When combining the moderate and severe OSA groups into a single category, the sensitivity was 90%, specificity was 100%, PPV was 100%, and NPV was 91%. Conclusions: OSA can be reliably diagnosed from HSATs with the automated Polysmith software across all OSA disease severity groups, with higher levels of accuracy in moderate/severe OSA and lower levels of accuracy in mild OSA. [ABSTRACT FROM AUTHOR]

This study explores the efficacy of texture analysis by using preoperative multi-slice spiral computed tomography (MSCT) to non-invasively determine the grade of cellular differentiation in head and neck squamous cell carcinoma (HNSCC). In a retrospective study, MSCT scans of patients with HNSCC were analyzed and classified based on its histological grade as moderately differentiated, well-differentiated, or poorly differentiated. The location of the tumor was categorized as either in the bone or in soft tissues. Segmentation of the lesion areas was conducted, followed by texture analysis. Eleven GLCM parameters across five different distances were calculated. Median values and correlations of texture parameters were examined in relation to tumor differentiation grade by using Spearman's correlation coefficient and Kruskal–Wallis and Dunn tests. Forty-six patients were included, predominantly female (87%), with a mean age of 66.7 years. Texture analysis revealed significant parameter correlations with histopathological grades of tumor differentiation. The study identified no significant age correlation with tumor differentiation, which underscores the potential of texture analysis as an age-independent biomarker. The strong correlations between texture parameters and histopathological grades support the integration of this technique into the clinical decision-making process. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate the impact of an AI-based software trained to detect cerebral aneurysms on TOF-MRA on the diagnostic performance and reading times across readers with varying experience levels. Methods: One hundred eighty-six MRI studies were reviewed by six readers to detect cerebral aneurysms. Initially, readings were assisted by the CNN-based software mdbrain. After 6 weeks, a second reading was conducted without software assistance. The results were compared to the consensus reading of two neuroradiological specialists and sensitivity (lesion and patient level), specificity (patient level), and false positives per case were calculated for the group of all readers, for the subgroup of physicians, and for each individual reader. Also, reading times for each reader were measured. Results: The dataset contained 54 aneurysms. The readers had no experience (three medical students), 2 years experience (resident in neuroradiology), 6 years experience (radiologist), and 12 years (neuroradiologist). Significant improvements of overall specificity and the overall number of false positives per case were observed in the reading with AI support. For the physicians, we found significant improvements of sensitivity on lesion and patient level and false positives per case. Four readers experienced reduced reading times with the software, while two encountered increased times. Conclusion: In the reading with the AI-based software, we observed significant improvements in terms of specificity and false positives per case for the group of all readers and significant improvements of sensitivity and false positives per case for the physicians. Further studies are needed to investigate the effects of the AI-based software in a prospective setting. [ABSTRACT FROM AUTHOR]

Abstract Background Positional preferences, asymmetry of body position and movements potentially indicate abnormal clinical conditions in infants. However, a lack of standardized nomenclature hinders accurate assessment and documentation of these preferences over time. Video tools offer a safe and reproducible method to analyze and describe infant movement patterns, aiding in physiotherapy management and goal planning. The study aimed to develop an objective classification system for infant movement patterns with particular emphasis on the specific distribution of muscle tension, using methods of computer analysis of video recordings to enhance accuracy and reproducibility in assessments. Methods The study involved the recording of videos of 51 infants between 6 and 15 weeks of age, born at term, with an Apgar score of at least 8 points. Based on observations of a recording of infant spontaneous movements in the supine position, experts identified postural-motor patterns: symmetry and typical asymmetry linked to the asymmetrical tonic neck reflex. Deviations from the typical postural-motor system were indicated, and subcategories of atypical patterns were distinguished. A computer-based inference system was developed to automatically classify individual patterns. Results The following division of motor patterns was used: (1) normal patterns, including (a) typical (symmetrical, asymmetrical: variants 1 and 2); and (b) atypical (variants: 1 to 4), (2) positional preference, and (3) abnormal patterns. The proposed automatic classification method achieved an expert decision mapping accuracy of 84%. For atypical patterns, the high reproducibility of the system’s results was confirmed. Lower reproducibility, not exceeding 70%, was achieved with typical patterns. Conclusions Based on the observation of infant spontaneous movements, it is possible to identify movement patterns divided into typical and atypical patterns. Computer-based analysis of infant movement patterns makes it possible to objectify and satisfactorily reproduce diagnostic decisions.

Study Design An experimental study. Purpose This study aimed to investigate the potential use of artificial neural networks (ANNs) in the detection of odontoid fractures using the Konstanz Information Miner (KNIME) Analytics Platform that provides a technique for computer-assisted diagnosis using radiographic X-ray imaging. Overview of Literature In medical image processing, computer-assisted diagnosis with ANNs from radiographic X-ray imaging is becoming increasingly popular. Odontoid fractures are a common fracture of the axis and account for 10%–15% of all cervical fractures. However, a literature review of computer-assisted diagnosis with ANNs has not been made. Methods This study analyzed 432 open-mouth (odontoid) radiographic views of cervical spine X-ray images obtained from dataset repositories, which were used in developing ANN models based on the convolutional neural network theory. All the images contained diagnostic information, including 216 radiographic images of individuals with normal odontoid processes and 216 images of patients with acute odontoid fractures. The model classified each image as either showing an odontoid fracture or not. Specifically, 70% of the images were training datasets used for model training, and 30% were used for testing. KNIME’s graphic user interface-based programming enabled class label annotation, data preprocessing, model training, and performance evaluation. Results The graphic user interface program by KNIME was used to report all radiographic X-ray imaging features. The ANN model performed 50 epochs of training. The performance indices in detecting odontoid fractures included sensitivity, specificity, F-measure, and prediction error of 100%, 95.4%, 97.77%, and 2.3%, respectively. The model’s accuracy accounted for 97% of the area under the receiver operating characteristic curve for the diagnosis of odontoid fractures. Conclusions The ANN models with the KNIME Analytics Platform were successfully used in the computer-assisted diagnosis of odontoid fractures using radiographic X-ray images. This approach can help radiologists in the screening, detection, and diagnosis of acute odontoid fractures.

Background/purpose: Recently, an artificial intelligence-based computer-assisted diagnosis (AI-CAD) for panoramic radiography was developed to scan the inferior margin of the mandible and automatically evaluate mandibular cortical morphology. The aim of this study was to analyze quantitatively the mandibular cortical morphology using the AI-CAD, especially focusing on underlying diseases and dental status in women over 20 years of age. Materials and methods: 419 patients in women over 20 years of age who underwent panoramic radiography were included in this study. The mandibular cortical morphology was analyzed with an AI-CAD that evaluated the degree of deformation of the mandibular inferior cortex (MIC) and mandibular cortical index (MCI) automatically. Those were analyzed in relation to underlying diseases, such as diabetes, hypertension, dyslipidemia, rheumatism and osteoporosis, and dental status, such as the number of teeth present in the maxilla and mandible. Results: The degree of deformation of MIC in women under 51 years of age (21–50 years; n = 229, 16.0 ± 12.7) was significantly lower than those of over 50 years of age (51–90 years; n = 190, 45.1 ± 23.0), and the MCI was a significant difference for the different age group. Regarding the degree of deformation of MIC and MCI in women over 50 years of age, osteoporosis and number of total teeth present in the maxilla and mandible were significant differences. Conclusion: The results of this study indicated that the mandibular cortical morphology using the AI-CAD is significantly related to osteoporosis and dental status in women over 50 years of age.

Study Design: An experimental study. Purpose: This study aimed to investigate the potential use of artificial neural networks (ANNs) in the detection of odontoid fractures using the Konstanz Information Miner (KNIME) Analytics Platform that provides a technique for computer-assisted diagnosis using radiographic X-ray imaging. Overview of Literature: In medical image processing, computer-assisted diagnosis with ANNs from radiographic X-ray imaging is becoming increasingly popular. Odontoid fractures are a common fracture of the axis and account for 10%–15% of all cervical fractures. However, a literature review of computer-assisted diagnosis with ANNs has not been made. Methods: This study analyzed 432 open-mouth (odontoid) radiographic views of cervical spine X-ray images obtained from dataset repositories, which were used in developing ANN models based on the convolutional neural network theory. All the images contained diagnostic information, including 216 radiographic images of individuals with normal odontoid processes and 216 images of patients with acute odontoid fractures. The model classified each image as either showing an odontoid fracture or not. Specifically, 70% of the images were training datasets used for model training, and 30% were used for testing. KNIME's graphic user interface-based programming enabled class label annotation, data preprocessing, model training, and performance evaluation. Results: The graphic user interface program by KNIME was used to report all radiographic X-ray imaging features. The ANN model performed 50 epochs of training. The performance indices in detecting odontoid fractures included sensitivity, specificity, F-measure, and prediction error of 100%, 95.4%, 97.77%, and 2.3%, respectively. The model's accuracy accounted for 97% of the area under the receiver operating characteristic curve for the diagnosis of odontoid fractures. Conclusions: The ANN models with the KNIME Analytics Platform were successfully used in the computer-assisted diagnosis of odontoid fractures using radiographic X-ray images. This approach can help radiologists in the screening, detection, and diagnosis of acute odontoid fractures. [ABSTRACT FROM AUTHOR]

Deep learning algorithms have commonly been used for the differential diagnosis between benign and malignant thyroid nodules. The aim of the study described here was to develop an integrated system that combines a deep learning model and a clinical standard Thyroid Imaging Reporting and Data System (TI-RADS) for the simultaneous segmentation and risk stratification of thyroid nodules. Three hundred four ultrasound images from two independent sites with TI-RADS 4 thyroid nodules were collected. The edge connection and Criminisi algorithm were used to remove manually induced markers in ultrasound images. An integrated system based on TI-RADS and a mask region-based convolution neural network (Mask R-CNN) was proposed to stratify subclasses of TI-RADS 4 thyroid nodules and to segment thyroid nodules in the ultrasound images. Accuracy and the precision-recall curve were used to evaluate stratification performance, and the Dice similarity coefficient (DSC) between the segmentation of Mask R-CNN and the radiologist's contour was used to evaluate the segmentation performance of the model. The combined approach could significantly enhance the performance of the proposed integrated system. Overall stratification accuracy of TI-RADS 4 thyroid nodules, mean average precision and mean DSC of the proposed model in the independent test set was 90.79%, 0.8579 and 0.83, respectively. Specifically, stratification accuracy values for TI-RADS 4a, 4b and 4c thyroid nodules were 95.83%, 84.21% and 77.78%, respectively. An integrated system combining TI-RADS and a deep learning model was developed. The system can provide clinicians with not only diagnostic assistance from TI-RADS but also accurate segmentation of thyroid nodules, which improves the applicability of the system in clinical practice. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the improvement of mammography interpretation for novice and experienced radiologists assisted by two commercial AI software. Methods: We compared the performance of two AI software (AI-1 and AI-2) in two experienced and two novice readers for 200 mammographic examinations (80 cancer cases). Two reading sessions were conducted within 4 weeks. The readers rated the likelihood of malignancy (range, 1–7) and the percentage probability of malignancy (range, 0–100%), with and without AI assistance. Differences in AUROC, sensitivity, and specificity were analyzed. Results: Mean AUROC increased in both novice (0.86 to 0.90 with AI-1 [p = 0.005]; 0.91 with AI-2 [p < 0.001]) and experienced readers (0.87 to 0.92 with AI-1 [p < 0.001]; 0.90 with AI-2 [p = 0.004]). Sensitivities increased from 81.3 to 88.8% with AI-1 (p = 0.027) and to 91.3% with AI-2 (p = 0.005) in novice readers, and from 81.9 to 90.6% with AI-1 (p = 0.001) and to 87.5% with AI-2 (p = 0.016) in experienced readers. Specificity did not decrease significantly in both novice (p > 0.999, both) and experienced readers (p > 0.999 with AI-1 and 0.282 with AI-2). There was no significant difference in the performance change depending on the type of AI software (p > 0.999). Conclusion: Commercial AI software improved the diagnostic performance of both novice and experienced readers. The type of AI software used did not significantly impact performance changes. Further validation with a larger number of cases and readers is needed. Clinical relevance statement: Commercial AI software effectively aided mammography interpretation irrespective of the experience level of human readers. Key Points: • Mammography interpretation remains challenging and is subject to a wide range of interobserver variability. • In this multi-reader study, two commercial AI software improved the sensitivity of mammography interpretation by both novice and experienced readers. The type of AI software used did not significantly impact performance changes. • Commercial AI software may effectively support mammography interpretation irrespective of the experience level of human readers. [ABSTRACT FROM AUTHOR]

Adrenal venous sampling (AVS) is the primary method for differentiating between primary aldosterone (PA) subtypes. The aim of study is to develop prediction models for subtyping of patients with PA using computed tomography (CT) radiomics and clinicobiochemical characteristics associated with PA. This study retrospectively enrolled 158 patients with PA who underwent AVS between January 2014 and March 2021. Neural network machine learning models were developed using a two-stage analysis of triple-phase abdominal CT and clinicobiochemical characteristics. In the first stage, the models were constructed to classify unilateral or bilateral PA; in the second stage, they were designed to determine the predominant side in patients with unilateral PA. The final proposed model combined the best-performing models from both stages. The model's performance was evaluated using repeated stratified five-fold cross-validation. We employed paired t-tests to compare its performance with the conventional imaging evaluations made by radiologists, which categorize patients as either having bilateral PA or unilateral PA on one side. In the first stage, the integrated model that combines CT radiomic and clinicobiochemical characteristics exhibited the highest performance, surpassing both the radiomic-alone and clinicobiochemical-alone models. It achieved an accuracy and F1 score of 80.6% ± 3.0% and 74.8% ± 5.2% (area under the receiver operating curve [AUC] = 0.778 ± 0.050). In the second stage, the accuracy and F1 score of the radiomic-based model were 88% ± 4.9% and 81.9% ± 6.2% (AUC = 0.831 ± 0.087). The proposed model achieved an accuracy and F1 score of 77.5% ± 3.9% and 70.5% ± 7.1% (AUC = 0.771 ± 0.046) in subtype diagnosis and lateralization, surpassing the accuracy and F1 score achieved by radiologists' evaluation (p <.05). The proposed machine learning model can predict the subtypes and lateralization of PA. It yields superior results compared to conventional imaging evaluation and has potential to supplement the diagnostic process in PA. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is an impediment of diabetes mellitus, which if not treated early may result in complete loss of vision, even without any preemptive symptoms. DR is caused by high level of glucose in the blood, causing alterations in the microvasculature of retina. However, early screening of diabetic patients through retinal fundus imaging, along with proper diagnosis and treatment can control the prevalence of DR complications. Manual inspection of pathological changes in retinal fundus images is an extremely challenging and tedious task. Therefore, computer-aided diagnosis (CAD) system is an efficient and effective method for early detection of DR and can greatly assist the ophthalmologists. CAD system encompasses DR detection and severity grading that includes detection, classification, localization and segmentation of lesions from the fundus images. Significant contributions have been made in DR severity grading using conventional image processing approaches using hand-engineered features and traditional machine-learning (ML) techniques. In the recent years, significant development of deep learning (DL) methods alleviated by the advancement of hardware computation power and efficient learning algorithms, has triumphed over the traditional ML methods in DR detection and grading tasks. Many researchers have employed the established as well as customized DL models in different DR image repositories and reported their findings. In this paper, we conduct a detailed review of the recent state-of-the-art contributions in the field of DL based DR classification by explaining their methodologies and highlighting their advantages and limitations. A detailed comparative study based on certain statistical parameters has also been conducted to quantitatively evaluate the methods, models and preprocessing techniques. In addition, the challenges in designing an efficient, accurate and robust deep-learning model for DR classification are explored in details to help the future research in this field. [ABSTRACT FROM AUTHOR]

While cardiovascular diseases are the leading causes of death in developed countries, detection of cardiac abnormalities can reduce mortality rates, through early and accurate diagnosis. One of the main assets used to help in the diagnosis process is the electrocardiogram (ECG). A free software tool for electrocardiogram analysis and diagnosis is presented. The tool, named ECGDT, allows: (1) to detect beats present on the ECG, both in single and multi-channel levels, (2) to identify beat waves, and (3) to diagnose different cardiac abnormalities. System evaluation was performed in two ways: (1) diagnostic capabilities were tested with Receiver Operating Characteristic (ROC) analysis, and (2) Graphical Software Interface (GUI) aspects, such as attraction, efficiency, or novelty, were evaluated employing User Experience Questionnaire (UEQ) scores. For disease diagnosis, the mean Area Under the ROC Curve (AUC) was 0.821. The system was also capable of detecting 100% of several cardiac abnormalities, such as bradycardia or tachycardia. Related to the GUI, all usability estimators scored values ranged between 2.208 and 2.750 (overall positive evaluations are obtained for values over 0.8). ECGDT could serve as an aid in the diagnosis of different medical abnormalities. In addition, the suitability of the developed interface has been proven. [ABSTRACT FROM AUTHOR]

Background: The growing number of older adults in recent decades has led to more prevalent geriatric diseases, such as strokes and dementia. Therefore, Alzheimer's disease (AD), as the most common type of dementia, has become more frequent too. Background: Objective: The goals of this work are to present state-of-the-art studies focused on the automatic diagnosis and prognosis of AD and its early stages, mainly mild cognitive impairment, and predicting how the research on this topic may change in the future. Methods: Articles found in the existing literature needed to fulfill several selection criteria. Among others, their classification methods were based on artificial neural networks (ANNs), including deep learning, and data not from brain signals or neuroimaging techniques were used. Considering our selection criteria, 42 articles published in the last decade were finally selected. Results: The most medically significant results are shown. Similar quantities of articles based on shallow and deep ANNs were found. Recurrent neural networks and transformers were common with speech or in longitudinal studies. Convolutional neural networks (CNNs) were popular with gait or combined with others in modular approaches. Above one third of the cross-sectional studies utilized multimodal data. Non-public datasets were frequently used in cross-sectional studies, whereas the opposite in longitudinal ones. The most popular databases were indicated, which will be helpful for future researchers in this field. Conclusions: The introduction of CNNs in the last decade and their superb results with neuroimaging data did not negatively affect the usage of other modalities. In fact, new ones emerged. [ABSTRACT FROM AUTHOR]

Purpose: This study aimed to evaluate the utility of large language model (LLM) artificial intelligence tools, Chat Generative Pre-Trained Transformer (ChatGPT) versions 3.5 and 4, in managing complex otolaryngological clinical scenarios, specifically for the multidisciplinary management of odontogenic sinusitis (ODS). Methods: A prospective, structured multidisciplinary specialist evaluation was conducted using five ad hoc designed ODS-related clinical scenarios. LLM responses to these scenarios were critically reviewed by a multidisciplinary panel of eight specialist evaluators (2 ODS experts, 2 rhinologists, 2 general otolaryngologists, and 2 maxillofacial surgeons). Based on the level of disagreement from panel members, a Total Disagreement Score (TDS) was calculated for each LLM response, and TDS comparisons were made between ChatGPT3.5 and ChatGPT4, as well as between different evaluators. Results: While disagreement to some degree was demonstrated in 73/80 evaluator reviews of LLMs' responses, TDSs were significantly lower for ChatGPT4 compared to ChatGPT3.5. Highest TDSs were found in the case of complicated ODS with orbital abscess, presumably due to increased case complexity with dental, rhinologic, and orbital factors affecting diagnostic and therapeutic options. There were no statistically significant differences in TDSs between evaluators' specialties, though ODS experts and maxillofacial surgeons tended to assign higher TDSs. Conclusions: LLMs like ChatGPT, especially newer versions, showed potential for complimenting evidence-based clinical decision-making, but substantial disagreement was still demonstrated between LLMs and clinical specialists across most case examples, suggesting they are not yet optimal in aiding clinical management decisions. Future studies will be important to analyze LLMs' performance as they evolve over time. [ABSTRACT FROM AUTHOR]

Recently, an artificial intelligence-based computer-assisted diagnosis (AI-CAD) for panoramic radiography was developed to scan the inferior margin of the mandible and automatically evaluate mandibular cortical morphology. The aim of this study was to analyze quantitatively the mandibular cortical morphology using the AI-CAD, especially focusing on underlying diseases and dental status in women over 20 years of age. 419 patients in women over 20 years of age who underwent panoramic radiography were included in this study. The mandibular cortical morphology was analyzed with an AI-CAD that evaluated the degree of deformation of the mandibular inferior cortex (MIC) and mandibular cortical index (MCI) automatically. Those were analyzed in relation to underlying diseases, such as diabetes, hypertension, dyslipidemia, rheumatism and osteoporosis, and dental status, such as the number of teeth present in the maxilla and mandible. The degree of deformation of MIC in women under 51 years of age (21–50 years; n = 229, 16.0 ± 12.7) was significantly lower than those of over 50 years of age (51–90 years; n = 190, 45.1 ± 23.0), and the MCI was a significant difference for the different age group. Regarding the degree of deformation of MIC and MCI in women over 50 years of age, osteoporosis and number of total teeth present in the maxilla and mandible were significant differences. The results of this study indicated that the mandibular cortical morphology using the AI-CAD is significantly related to osteoporosis and dental status in women over 50 years of age. [ABSTRACT FROM AUTHOR]

Computer-assisted polyp characterization (computer-aided diagnosis, CADx) facilitates optical diagnosis during colonoscopy. Several studies have demonstrated high sensitivity and specificity of CADx tools in identifying neoplastic changes in colorectal polyps. To implement CADx tools in colonoscopy, there is a need to confirm whether these tools satisfy the threshold levels that are required to introduce optical diagnosis strategies such as “diagnose-and-leave,” “resect-and-discard” or “DISCARD-lite.” In this article, we review the available data from prospective trials regarding the effect of multiple CADx tools and discuss whether they meet these thresholds.

Many genetic syndromes are associated with distinctive facial features. Several computer-assisted methods have been proposed that make use of facial features for syndrome diagnosis. Training supervised classifiers, the most common approach for this purpose, requires large, comprehensive, and difficult to collect databases of syndromic facial images. In this work, we use unsupervised, normalizing flow-based manifold and density estimation models trained entirely on unaffected subjects to detect syndromic 3D faces as statistical outliers. Furthermore, we demonstrate a general, user-friendly, gradient-based interpretability mechanism that enables clinicians and patients to understand model inferences. 3D facial surface scans of 2471 unaffected subjects and 1629 syndromic subjects representing 262 different genetic syndromes were used to train and evaluate the models. The flow-based models outperformed unsupervised comparison methods, with the best model achieving an ROC-AUC of 86.3% on a challenging, age and sex diverse data set. In addition to highlighting the viability of outlier-based syndrome screening tools, our methods generalize and extend previously proposed outlier scores for 3D face-based syndrome detection, resulting in improved performance for unsupervised syndrome detection.

Simple Summary: Cervical lymph node (LN) metastasis is a critical prognostic factor for patients with head and neck squamous cell carcinoma (HNSCC), rendering accurate diagnosis of LN metastasis crucial for improving patient outcomes. Our study aimed to develop deep learning models for metastatic LN detection using YOLOv7, the fastest single-stage object detection model, on B-mode and power Doppler (D-mode) ultrasonography in patients with HNSCC and investigate their utility in supporting the diagnosis by comparing their performance to that of highly experienced radiologists and less experienced residents. A total of 462 B- and D-mode ultrasound images were used to train, validate, and test the B- and D-mode models, respectively. The detection performances of the B- and D-mode models for metastatic LNs were higher than those of less experienced residents; the performance of the D-mode model was comparable to that of highly experienced radiologists, suggesting that YOLOv7-based models are useful for supporting the diagnosis. Ultrasonography is the preferred modality for detailed evaluation of enlarged lymph nodes (LNs) identified on computed tomography and/or magnetic resonance imaging, owing to its high spatial resolution. However, the diagnostic performance of ultrasonography depends on the examiner's expertise. To support the ultrasonographic diagnosis, we developed YOLOv7-based deep learning models for metastatic LN detection on ultrasonography and compared their detection performance with that of highly experienced radiologists and less experienced residents. We enrolled 462 B- and D-mode ultrasound images of 261 metastatic and 279 non-metastatic histopathologically confirmed LNs from 126 patients with head and neck squamous cell carcinoma. The YOLOv7-based B- and D-mode models were optimized using B- and D-mode training and validation images and their detection performance for metastatic LNs was evaluated using B- and D-mode testing images, respectively. The D-mode model's performance was comparable to that of radiologists and superior to that of residents' reading of D-mode images, whereas the B-mode model's performance was higher than that of residents but lower than that of radiologists on B-mode images. Thus, YOLOv7-based B- and D-mode models can assist less experienced residents in ultrasonographic diagnoses. The D-mode model could raise the diagnostic performance of residents to the same level as experienced radiologists. [ABSTRACT FROM AUTHOR]

Computer-assisted polyp characterization (computer-aided diagnosis, CADx) facilitates optical diagnosis during colonoscopy. Several studies have demonstrated high sensitivity and specificity of CADx tools in identifying neoplastic changes in colorectal polyps. To implement CADx tools in colonoscopy, there is a need to confirm whether these tools satisfy the threshold levels that are required to introduce optical diagnosis strategies such as "diagnose-and-leave," "resect-and-discard" or "DISCARD-lite." In this article, we review the available data from prospective trials regarding the effect of multiple CADx tools and discuss whether they meet these thresholds. [ABSTRACT FROM AUTHOR]

Objective: To utilize hip MRI 3D models for demonstration of location and frequency of impingement during simulated range-of-motion in ischiofemoral impingement (IFI) compared to non-IFI hips. Materials and methods: Sixteen hips (N = 7 IFI, 9 non-IFI) from 8 females were examined with high-resolution MRI. We performed image segmentation and generated 3D bone models and simulated hip range-of-motion and impingement. We examined the frequency and location of bone contact in early external rotation and early extension (0–20°), isolated maximum external rotation, and isolated maximum extension. Frequency and location of impingement at varied combinations of external rotation and extension and areas of simulated bone impingement at early external rotation and extension were compared between IFI and non-IFI. Results: Higher frequency of bony impingement occurred more often in IFI hips at each simulated range-of-motion combination (P < 0.05). Impingement involved the lesser trochanter more often in IFI hips (P < 0.001) and occurred at early degrees of external rotation and extension. In isolated maximum external rotation, only the greater trochanter, intertrochanteric area, or both combined were involved, in 14%, 57%, and 29% in IFI hips. In isolated maximum extension, the lesser trochanter, intertrochanteric area, or both combined were involved in 71%, 14%, and 14% in IFI hips. The simulated area of bone impingement was significantly higher in IFI hips (P = 0.02). Conclusion: Hip MRI 3D models are feasible for simulated range-of-motion and show a higher frequency of extra-articular impingement at early stages of external rotation and extension in IFI compared to non-IFI hips. [ABSTRACT FROM AUTHOR]

Abstract Background Most of superficial soft-tissue masses are benign tumors, and very few are malignant tumors. However, persistent growth, of both benign and malignant tumors, can be painful and even life-threatening. It is necessary to improve the differential diagnosis performance for superficial soft-tissue masses by using deep learning models. This study aimed to propose a new ultrasonic deep learning model (DLM) system for the differential diagnosis of superficial soft-tissue masses. Methods Between January 2015 and December 2022, data for 1615 patients with superficial soft-tissue masses were retrospectively collected. Two experienced radiologists (radiologists 1 and 2 with 8 and 30 years’ experience, respectively) analyzed the ultrasound images of each superficial soft-tissue mass and made a diagnosis of malignant mass or one of the five most common benign masses. After referring to the DLM results, they re-evaluated the diagnoses. The diagnostic performance and concerns of the radiologists were analyzed before and after referring to the results of the DLM results. Results In the validation cohort, DLM-1 was trained to distinguish between benign and malignant masses, with an AUC of 0.992 (95% CI: 0.980, 1.0) and an ACC of 0.987 (95% CI: 0.968, 1.0). DLM-2 was trained to classify the five most common benign masses (lipomyoma, hemangioma, neurinoma, epidermal cyst, and calcifying epithelioma) with AUCs of 0.986, 0.993, 0.944, 0.973, and 0.903, respectively. In addition, under the condition of the DLM-assisted diagnosis, the radiologists greatly improved their accuracy of differential diagnosis between benign and malignant tumors. Conclusions The proposed DLM system has high clinical application value in the differential diagnosis of superficial soft-tissue masses.

This study aims to compare computed tomography (CT) with magnetic resonance imaging (MRI) of the temporomandibular joint (TMJ) by using texture analysis (TA) to detect condylar bone marrow changes associated with the flattening and erosion of cortical bone. A total of 47 patients from the Dentomaxillofacial Radiology Division at São Paulo State University were evaluated. Images from 250 CT and 250 MRI images were assessed by experienced radiologists employing OnDemand3D software. Texture parameters were extracted with MaZda software (version 4.6), and we focused on regions of interest within the condyles. Statistical analysis revealed significant differences in texture parameters between the affected and control groups. CT images showed higher correlation values in cases of flattening, whereas MRI images demonstrated substantial changes in texture parameters for both flattening and erosion. These findings suggest that the texture analysis of CT and MRI images can effectively detect early and advanced degenerative changes in the TMJ, thus providing valuable insights into the underlying pathophysiology and aiding in early intervention and treatment planning.

This study explores the efficacy of texture analysis by using preoperative multi-slice spiral computed tomography (MSCT) to non-invasively determine the grade of cellular differentiation in head and neck squamous cell carcinoma (HNSCC). In a retrospective study, MSCT scans of patients with HNSCC were analyzed and classified based on its histological grade as moderately differentiated, well-differentiated, or poorly differentiated. The location of the tumor was categorized as either in the bone or in soft tissues. Segmentation of the lesion areas was conducted, followed by texture analysis. Eleven GLCM parameters across five different distances were calculated. Median values and correlations of texture parameters were examined in relation to tumor differentiation grade by using Spearman’s correlation coefficient and Kruskal–Wallis and Dunn tests. Forty-six patients were included, predominantly female (87%), with a mean age of 66.7 years. Texture analysis revealed significant parameter correlations with histopathological grades of tumor differentiation. The study identified no significant age correlation with tumor differentiation, which underscores the potential of texture analysis as an age-independent biomarker. The strong correlations between texture parameters and histopathological grades support the integration of this technique into the clinical decision-making process.

Background: Obstructive sleep apnea (OSA) affects a significant proportion of the global population, with many having moderate or severe forms of the disease. Home Sleep Apnea Testing (HSAT) has become the most common method of diagnosing OSA, replacing in-lab polysomnography. Polysmith software Version 11 by Nihon Kohden allows for the automatic scoring of respiratory events. This study aimed to assess the validity of this technology. Study Objectives: The objective was to assess the accuracy of the Polysmith Software Automatic Scoring Algorithm of HSATs in comparison to that of sleep technicians. Methods: One hundred twenty HSATs were scored by both sleep technicians and Polysmith software. The measured values were the respiratory event index (REI), apneic events, and hypopneic events. Agreement between the two methods was reached by utilizing the Kruskal–Wallis test, Pearson correlation coefficient, and Bland–Altman plot, as well as sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results: The correlation between the REI calculated by the software and technicians proved to be strong overall (r = 0.96, p < 0.0001). The mild OSA group had a moderate correlation (r = 0.45, p = 0.0129). The primary snoring, moderate OSA, and severe OSA groups showed stronger correlations (r = 0.69, p < 0.0001; r = 0.56, p = 0.012; r = 0.71, p < 0.0001). The analysis conducted across all groups demonstrated an average sensitivity of 81%, specificity of 94%, PPV of 82%, and NPV of 94%, with an overall accuracy of 81%. When combining the moderate and severe OSA groups into a single category, the sensitivity was 90%, specificity was 100%, PPV was 100%, and NPV was 91%. Conclusions: OSA can be reliably diagnosed from HSATs with the automated Polysmith software across all OSA disease severity groups, with higher levels of accuracy in moderate/severe OSA and lower levels of accuracy in mild OSA.

Background: The Lyon consensus classifies the evidence of gastroesophageal reflux (GERD) based on endoscopic features and results of pH/impedance monitoring (pH‐MII) including the post‐reflux swallow‐induced peristaltic wave index (PSPWI) and mean nocturnal baseline impedance (MNBI). The Wingate consensus established criteria to reduce inter‐reviewer variability when assessing reflux episodes and PSPWI by impedance. This study aims to assess the influence of the Wingate criteria on the different pH‐MII parameters obtained by automated analysis. Methods: Thirty consecutive pH‐MII off PPI were reviewed according to Wingate criteria. Number of impedance episodes and PSPWI were compared before and after censoring from automatic analysis. Reflux categorization according to Lyon consensus between censored and uncensored data was compared. Pearson correlations between impedance parameters and censored episodes were calculated. Key Results: Censoring the tracings significantly reduced the number of reflux episodes (66 [42–90.25] vs. 44.5 [21.5–61.5], p = 0.0105). Reasons for censoring were as follows: 1/ anterograde episode: 9.5 [6–13], 2/ impedance drop <50%: 1 [0–3], 3/ duration <4 s: 1 [0–2], 4/ <2 distal channels: 2.5 [1–4], and 5/ artifacts: 2 [1–5]. Censored episodes were in majority non‐acid (16.5 [13–26.5] vs. 2 [0–4], p < 0.00001). Censoring altered the categorization of impedance episodes (<40 episodes, 6 vs. 13 for resp. uncensored vs. censored tracings, 40–80 episodes: 13 vs. 13, and >80 episodes: 11 vs. 4, p = 0.0264), but not the symptom index, the symptom association probability, or the categorization according to the Lyon consensus. Nevertheless, individual tracings were affected. The percentage of censored episodes was inversely correlated with the number of acidic impedance episodes (r = −0.62, p = 0.0002). Conclusion and inferences: Manual interpretation of impedance tracings based on the Wingate consensus reduces the number of impedance episodes, impacting on reflux categorization. Acidic reflux episodes are less likely to be censored, harboring a potential at improving automatic pH‐MII analysis. [ABSTRACT FROM AUTHOR]

The purpose of this study was to develop artificial intelligence algorithms that can distinguish between orbital and conjunctival mucosa-associated lymphoid tissue (MALT) lymphomas in pathological images. Tissue blocks with residual MALT lymphoma and data from histological and flow cytometric studies and molecular genetic analyses such as gene rearrangement were procured for 129 patients treated between April 2008 and April 2020. We collected pathological hematoxylin and eosin-stained (HE) images of lymphoma from these patients and cropped 10 different image patches at a resolution of 2048 × 2048 from pathological images from each patient. A total of 990 images from 99 patients were used to create and evaluate machine-learning models. Each image patch of three different magnification rates at ×4, ×20, and ×40 underwent texture analysis to extract features, and then seven different machine-learning algorithms were applied to the results to create models. Cross-validation on a patient-by-patient basis was used to create and evaluate models, and then 300 images from the remaining 30 cases were used to evaluate the average accuracy rate. Ten-fold cross-validation using the support vector machine with linear kernel algorithm was identified as the best algorithm for discriminating between conjunctival mucosa-associated lymphoid tissue and orbital MALT lymphomas, with an average accuracy rate under cross-validation of 85%. There were ×20 magnification HE images that were more accurate in distinguishing orbital and conjunctival MALT lymphomas among ×4, ×20, and ×40. Artificial intelligence algorithms can successfully distinguish HE images between orbital and conjunctival MALT lymphomas. [ABSTRACT FROM AUTHOR]

PURPOSE. This study aimed to investigate whether the accuracy of intraoral scanners is influenced by different scanning strategies in an in vitro setting, through a systematic review and meta-analysis. MATERIALS AND METHODS. This review was conducted in accordance with the PRISMA 2020 standard. The following PICOS approach was used: population, tooth impressions; intervention, the use of intraoral scanners with scanning strategies different from the manufacturer's instructions; control, the use of intraoral scanners following the manufacturers' requirements; outcome, accuracy of intraoral scanners; type of studies,in vitro. A comprehensive literature search was conducted across various databases including Embase, SciELO, PubMed, Scopus, and Web of Science. The inclusion criteria were based on in vitro studies that reported the accuracy of digital impressions using intraoral scanners. Analysis was performed using Review Manager software (version 5.3.5; Cochrane Collaboration, Copenhagen, Denmark). Global comparisons were made using a standardized mean difference based on random-effect models, with a significance level of α = 0.05. RESULTS. The meta-analysis included 15 articles. Digital impression accuracy significantly improved under dry conditions (P< 0.001). Moreover, trueness and precision were enhanced when artificial landmarks were used (P ≤ 0.02) and when an S-shaped pattern was followed (P ≤ 0.01). However, the type of light used did not have a significant impact on the accuracy of the digital intraoral scanners (P ≥ 0.16). CONCLUSION. The accuracy of digital intraoral scanners can be enhanced by employing scanning processes using artificial landmarks and digital impressions under dry conditions. [ABSTRACT FROM AUTHOR]

Background: Most of superficial soft-tissue masses are benign tumors, and very few are malignant tumors. However, persistent growth, of both benign and malignant tumors, can be painful and even life-threatening. It is necessary to improve the differential diagnosis performance for superficial soft-tissue masses by using deep learning models. This study aimed to propose a new ultrasonic deep learning model (DLM) system for the differential diagnosis of superficial soft-tissue masses. Methods: Between January 2015 and December 2022, data for 1615 patients with superficial soft-tissue masses were retrospectively collected. Two experienced radiologists (radiologists 1 and 2 with 8 and 30 years' experience, respectively) analyzed the ultrasound images of each superficial soft-tissue mass and made a diagnosis of malignant mass or one of the five most common benign masses. After referring to the DLM results, they re-evaluated the diagnoses. The diagnostic performance and concerns of the radiologists were analyzed before and after referring to the results of the DLM results. Results: In the validation cohort, DLM-1 was trained to distinguish between benign and malignant masses, with an AUC of 0.992 (95% CI: 0.980, 1.0) and an ACC of 0.987 (95% CI: 0.968, 1.0). DLM-2 was trained to classify the five most common benign masses (lipomyoma, hemangioma, neurinoma, epidermal cyst, and calcifying epithelioma) with AUCs of 0.986, 0.993, 0.944, 0.973, and 0.903, respectively. In addition, under the condition of the DLM-assisted diagnosis, the radiologists greatly improved their accuracy of differential diagnosis between benign and malignant tumors. Conclusions: The proposed DLM system has high clinical application value in the differential diagnosis of superficial soft-tissue masses. [ABSTRACT FROM AUTHOR]

Purpose: To construct a deep learning knowledge distillation framework exploring the utilization of MRI alone or combing with distilled Arthroscopy information for meniscus tear detection.Methods: A database of 199 paired knee Arthroscopy-MRI exams was used to develop a multimodal teacher network and an MRI-based student network, which used residual neural networks architectures. A knowledge distillation framework comprising the multimodal teacher network T and the monomodal student network S was proposed. We optimized the loss functions of mean squared error (MSE) and cross-entropy (CE) to enable the student network S to learn arthroscopic information from the teacher network T through our deep learning knowledge distillation framework, ultimately resulting in a distilled student network ST. A coronal proton density (PD)-weighted fat-suppressed MRI sequence was used in this study. Fivefold cross-validation was employed, and the accuracy, sensitivity, specificity, F1-score, receiver operating characteristic (ROC) curves and area under the receiver operating characteristic curve (AUC) were used to evaluate the medial and lateral meniscal tears detection performance of the models, including the undistilled student model S, the distilled student model ST and the teacher model T.Results: The AUCs of the undistilled student model S, the distilled student model ST, the teacher model T for medial meniscus (MM) tear detection and lateral meniscus (LM) tear detection are 0.773/0.672, 0.792/0.751 and 0.834/0.746, respectively. The distilled student model ST had higher AUCs than the undistilled model S. After undergoing knowledge distillation processing, the distilled student model demonstrated promising results, with accuracy (0.764/0.734), sensitivity (0.838/0.661), and F1-score (0.680/0.754) for both medial and lateral tear detection better than the undistilled one with accuracy (0.734/0.648), sensitivity (0.733/0.607), and F1-score (0.620/0.673).Conclusion: Through the knowledge distillation framework, the student model S based on MRI benefited from the multimodal teacher model T and achieved an improved meniscus tear detection performance.

The use of artificial intelligence (AI) and robotics in endovascular neurosurgery promises to transform neurovascular care. We present a review of the recently published neurosurgical literature on artificial intelligence and robotics in endovascular neurosurgery to provide insights into the current advances and applications of this technology. The PubMed database was searched for "neurosurgery" OR "endovascular" OR "interventional" AND "robotics" OR "artificial intelligence" between January 2016 and August 2021. A total of 1296 articles were identified, and after applying the inclusion and exclusion criteria, 38 manuscripts were selected for review and analysis. These manuscripts were divided into four categories: 1) robotics and AI for the diagnosis of cerebrovascular pathology, 2) robotics and AI for the treatment of cerebrovascular pathology, 3) robotics and AI for training in neuroendovascular procedures, and 4) robotics and AI for clinical outcome optimization. The 38 articles presented include 23 articles on AI-based diagnosis of cerebrovascular disease, 10 articles on AI-based treatment of cerebrovascular disease, two articles on AI-based training techniques for neuroendovascular procedures, and three articles reporting AI prediction models of clinical outcomes in vascular disorders of the brain. Innovation with robotics and AI focus on diagnostic efficiency, optimizing treatment and interventional procedures, improving physician procedural performance, and predicting clinical outcomes with the use of artificial intelligence and robotics. Experimental studies with robotic systems have demonstrated safety and efficacy in treating cerebrovascular disorders, and novel microcatheterization techniques may permit access to deeper brain regions. Other studies show that pre-procedural simulations increase overall physician performance. Artificial intelligence also shows superiority over existing statistical tools in predicting clinical outcomes. The recent advances and current usage of robotics and AI in the endovascular neurosurgery field suggest that the collaboration between physicians and machines has a bright future for the improvement of patient care. The aim of this work is to equip the medical readership, in particular the neurosurgical specialty, with tools to better understand and apply findings from research on artificial intelligence and robotics in endovascular neurosurgery.

Abstract Background As the first point of contact for patients with health issues, general practitioners (GPs) are frequently confronted with patients presenting with non-specific symptoms of unclear origin. This can result in delayed, prolonged or false diagnoses. To accelerate and improve the diagnosis of diseases, clinical decision support systems would appear to be an appropriate tool. The objective of the project ‘Smart physician portal for patients with unclear disease’ (SATURN) is to employ a user-centered design process based on the requirements analysis presented in this paper to develop an artificial Intelligence (AI)-based diagnosis support system that specifically addresses the needs of German GPs. Methods Requirements analysis for a GP-specific diagnosis support system was conducted in an iterative process with five GPs. First, interviews were conducted to analyze current workflows and the use of digital applications in cases of diagnostic uncertainty (as-is situation). Second, we focused on collecting and prioritizing tasks to be performed by an ideal smart physician portal (to-be situation) in a workshop. We then developed a task model with corresponding user requirements. Results Numerous GP-specific user requirements were identified concerning the tasks and subtasks: performing data entry (open system, enter patient data), reviewing results (receiving and evaluating results), discussing results (with patients and colleagues), scheduling further diagnostic procedures, referring to specialists (select, contact, make appointments), and case closure. Suggested features particularly concerned the process of screening and assessing results: e.g., the system should focus more on atypical patterns of common diseases than on rare diseases only, display probabilities of differential diagnoses, ensure sources and results are transparent, and mark diagnoses that have already been ruled out. Moreover, establishing a means of using the platform to communicate with colleagues and transferring patient data directly from electronic patient records to the system was strongly recommended. Conclusions Essential user requirements to be considered in the development and design of a diagnosis system for primary care could be derived from the analysis. They form the basis for mockup-development and system engineering.

Computed Tomography (CT) is one of the biomedical imaging modalities which are used to confirm COVID-19 cases and/or to identify infected areas in the lung. Therefore, this article aims at assisting this crucial radiological task by proposing squeeze-and-excitation networks (SENets) within the Internet of medical things (IoMT) framework for automated segmentation of COVID-19 infections in lung CT images. The proposed SE block has been directly integrated with deep residual networks to form Seresnets based on U-Net and LinkNet models. Extensive tests were conducted on a public COVID-19 CT dataset including 20 cases and 1800 + annotated slices to evaluate the segmentation results of our proposed method. The proposed Seresnet models showed a good performance with a Dice score of 0.73, structure similarity index of 0.98, enhanced alignment measure of 0.98, and mean absolute error of 0.06. This study demonstrated a new advanced tool for radiologists to achieve automatic segmentation of the COVID-19 infected areas using CT scans. The main prospect of this research work is deploying our proposed IoMT segmentation framework in the medical diagnosis routine of positive COVID-19 patients.

Purpose: To evaluate the stand-alone diagnostic performances of AI-CAD and outcomes of AI-CAD detected abnormalities when applied to the mammographic interpretation workflow. Methods: From January 2016 to December 2017, 6499 screening mammograms of 5228 women were collected from a single screening facility. Historic reads of three radiologists were used as radiologist interpretation. A commercially-available AI-CAD was used for analysis. One radiologist not involved in interpretation had retrospectively reviewed the abnormality features and assessed the significance (negligible vs. need recall) of the AI-CAD marks. Ground truth in terms of cancer, benign or absence of abnormality was confirmed according to histopathologic diagnosis or negative results on the next-round screen. Results: Of the 6499 mammograms, 6282 (96.7%) were in the negative, 189 (2.9%) were in the benign, and 28 (0.4%) were in the cancer group. AI-CAD detected 5 (17.9%, 5 of 28) of the 9 cancers that were intially interpreted as negative. Of the 648 AI-CAD recalls, 89.0% (577 of 648) were marks seen on examinations in the negative group, and 267 (41.2%) of the AI-CAD marks were considered to be negligible. Stand-alone AI-CAD has significantly higher recall rates (10.0% vs. 3.4%, P

Key Clinical Message: Large language models have made artificial intelligence readily available to the general public and potentially have a role in healthcare; however, their use in difficult differential diagnosis is still limited, as demonstrated by a case of necrotizing otitis externa. This case report presents a peculiar case of necrotizing otitis externa (NOE) with skull base involvement which proved diagnostically challenging. The initial patient presentation and the imaging performed on the 78‐year‐old patient suggested a neoplastic rhinopharyngeal lesion and only after several unsuccessful biopsies the patient was transferred to our unit. Upon re‐evaluation of the clinical picture, a clinical hypothesis of NOE with skull base erosion was made and confirmed by identifying Pseudomonas aeruginosa in biopsy specimens of skull base bone and external auditory canal skin. Upon diagnosis confirmation, the patient was treated with culture‐oriented long‐term antibiotics with complete resolution of the disease. Given the complex clinical presentation, we chose to submit a posteriori this NOE case to two large language models (LLM) to test their ability to handle difficult differential diagnoses. LLMs are easily approachable artificial intelligence tools that enable human‐like interaction with the user relying upon large information databases for analyzing queries. The LLMs of choice were ChatGPT‐3 and ChatGPT‐4 and they were requested to analyze the case being provided with only objective clinical and imaging data. [ABSTRACT FROM AUTHOR]

Lung cancer is often a fatal disease. To minimize patient mortality, the ability to identify the nodule malignancy stage from computed tomography (CT) lung scans is critical. Most existing methods rely exclusively on deep learning (DL) networks. However, duplicated structures and insufficient training data make DL-based malignancy diagnosis from CT images time-consuming and imprecise. Additionally, the features that DL networks use to make decisions cannot be recognized. In response to these challenges in previous work, we built an end-to-end conventional machine learning (ML) model called 'NoduleDiag' to classify cancerous CT images and their malignancy stage based on the nodule characteristics observable in CT images that radiologists typically prefer for diagnosis. We also prepared a fully automatic pulmonary nodule segmentation model for implementation during the final stage of diagnosis (after disease-stage identification) and added it to our classification framework as immense practical assistance to radiologists and medical personnel. To the best of our knowledge, this work will be the first all in one computer-assisted diagnosis (CAD) framework with lung cancer classification, automatic malignancy-stage identification and nodule segmentation screening together using conventional ML approaches. Our proposed model classifies nodule malignancy on a scale of 1–5. It achieves 99.65% accuracy, 99.64% sensitivity, 99.76% precision, 99.9% specificity, and 99.91% negative predictive value (NPV) with XGBoost. Our segmentation model uses DeepLabv3+ (weights initialized by ResNet-18), achieving a 99.86% global accuracy, mean boundary F1 (BF) score of 0.976, 0.715 mean IoU and 0.997 weighted IoU. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate and compare the measurement accuracy of two different computer-aided diagnosis (CAD) systems regarding artificial pulmonary nodules and assess the clinical impact of volumetric inaccuracies in a phantom study. Methods: In this phantom study, 59 different phantom arrangements with 326 artificial nodules (178 solid, 148 ground-glass) were scanned at 80 kV, 100 kV, and 120 kV. Four different nodule diameters were used: 5 mm, 8 mm, 10 mm, and 12 mm. Scans were analyzed by a deep-learning (DL)–based CAD and a standard CAD system. Relative volumetric errors (RVE) of each system vs. ground truth and the relative volume difference (RVD) DL–based vs. standard CAD were calculated. The Bland–Altman method was used to define the limits of agreement (LOA). The hypothetical impact on LungRADS classification was assessed for both systems. Results: There was no difference between the three voltage groups regarding nodule volumetry. Regarding the solid nodules, the RVE of the 5-mm-, 8-mm-, 10-mm-, and 12-mm-size groups for the DL CAD/standard CAD were 12.2/2.8%, 1.3/ − 2.8%, − 3.6/1.5%, and − 12.2/ − 0.3%, respectively. The corresponding values for the ground-glass nodules (GGN) were 25.6%/81.0%, 9.0%/28.0%, 7.6/20.6%, and 6.8/21.2%. The mean RVD for solid nodules/GGN was 1.3/ − 15.2%. Regarding the LungRADS classification, 88.5% and 79.8% of all solid nodules were correctly assigned by the DL CAD and the standard CAD, respectively. 14.9% of the nodules were assigned differently between the systems. Conclusions: Patient management may be affected by the volumetric inaccuracy of the CAD systems and hence demands supervision and/or manual correction by a radiologist. Key Points: • The DL-based CAD system was more accurate in the volumetry of GGN and less accurate regarding solid nodules than the standard CAD system. • Nodule size and attenuation have an effect on the measurement accuracy of both systems; tube voltage has no effect on measurement accuracy. • Measurement inaccuracies of CAD systems can have an impact on patient management, which demands supervision by radiologists. [ABSTRACT FROM AUTHOR]

Background: Nail diseases are malformations that appear on the nail plate and are classified according to their own signs and symptoms that may be related to other medical conditions. Although most nail diseases have distinct symptoms, making a differential diagnosis of nail problems can be challenging for medical experts. Method: One early diagnosis method for any dermatological disease is designing an image analysis system based on artificial intelligence (AI) techniques. This article implemented a novel model using a publicly available nail disease dataset to determine the occurrence of three common types of nail diseases. Two classification models based on transfer learning using visual geometry group (VGGNet) were utilized to detect and classify nail diseases from images. Result and Finding: The experimental design results showed good accuracy: VGG16 had a score of 94% accuracy and VGG19 had a 93% accuracy rate. These findings suggest that computer-aided diagnostic systems based on transfer learning can be used to identify multiple-lesion nail diseases. [ABSTRACT FROM AUTHOR]

Radiographic examination is essential for diagnosing spinal disorders, and the measurement of spino-pelvic parameters provides important information for the diagnosis and treatment planning of spinal sagittal deformities. While manual measurement methods are the golden standard for measuring parameters, they can be time consuming, inefficient, and rater dependent. Previous studies that have used automatic measurement methods to alleviate the downsides of manual measurements showed low accuracy or could not be applied to general films. We propose a pipeline for automated measurement of spinal parameters by combining a Mask R-CNN model for spine segmentation with computer vision algorithms. This pipeline can be incorporated into clinical workflows to provide clinical utility in diagnosis and treatment planning. A total of 1807 lateral radiographs were used for the training (n = 1607) and validation (n = 200) of the spine segmentation model. An additional 200 radiographs, which were also used for validation, were examined by three surgeons to evaluate the performance of the pipeline. Parameters automatically measured by the algorithm in the test set were statistically compared to parameters measured manually by the three surgeons. The Mask R-CNN model achieved an average precision at 50% intersection over union (AP50) of 96.2% and a Dice score of 92.6% for the spine segmentation task in the test set. The mean absolute error values of the spino-pelvic parameters measurement results were within the range of 0.4° (pelvic tilt) to 3.0° (lumbar lordosis, pelvic incidence), and the standard error of estimate was within the range of 0.5° (pelvic tilt) to 4.0° (pelvic incidence). The intraclass correlation coefficient values ranged from 0.86 (sacral slope) to 0.99 (pelvic tilt, sagittal vertical axis). [ABSTRACT FROM AUTHOR]

Background: As the first point of contact for patients with health issues, general practitioners (GPs) are frequently confronted with patients presenting with non-specific symptoms of unclear origin. This can result in delayed, prolonged or false diagnoses. To accelerate and improve the diagnosis of diseases, clinical decision support systems would appear to be an appropriate tool. The objective of the project 'Smart physician portal for patients with unclear disease' (SATURN) is to employ a user-centered design process based on the requirements analysis presented in this paper to develop an artificial Intelligence (AI)-based diagnosis support system that specifically addresses the needs of German GPs. Methods: Requirements analysis for a GP-specific diagnosis support system was conducted in an iterative process with five GPs. First, interviews were conducted to analyze current workflows and the use of digital applications in cases of diagnostic uncertainty (as-is situation). Second, we focused on collecting and prioritizing tasks to be performed by an ideal smart physician portal (to-be situation) in a workshop. We then developed a task model with corresponding user requirements. Results: Numerous GP-specific user requirements were identified concerning the tasks and subtasks: performing data entry (open system, enter patient data), reviewing results (receiving and evaluating results), discussing results (with patients and colleagues), scheduling further diagnostic procedures, referring to specialists (select, contact, make appointments), and case closure. Suggested features particularly concerned the process of screening and assessing results: e.g., the system should focus more on atypical patterns of common diseases than on rare diseases only, display probabilities of differential diagnoses, ensure sources and results are transparent, and mark diagnoses that have already been ruled out. Moreover, establishing a means of using the platform to communicate with colleagues and transferring patient data directly from electronic patient records to the system was strongly recommended. Conclusions: Essential user requirements to be considered in the development and design of a diagnosis system for primary care could be derived from the analysis. They form the basis for mockup-development and system engineering. [ABSTRACT FROM AUTHOR]