Diagnostic Image Analysis Research Articles

Systematic Review of Hybrid Vision Transformer Architectures for Radiological Image Analysis.

Vision transformer (ViT)and convolutional neural networks (CNNs) each possess distinct strengths in medical imaging: ViT excels in capturing long-range dependencies through self-attention, while CNNs are adept at extracting local features via spatial convolution filters. While ViT may struggle with capturing detailed local spatial information, critical for tasks like anomaly detection in medical imaging, shallow CNNs often fail to effectively abstract global context. This study aims to explore and evaluate hybrid architectures that integrate ViT and CNN to leverage their complementary strengths for enhanced performance in medical vision tasks, such as segmentation, classification, reconstruction, and prediction. Following PRISMA guideline, a systematic review was conducted on 34 articles published between 2020 and Sept. 2024. These articles proposed novel hybrid ViT-CNN architectures specifically for medical imaging tasks in radiology. The review focused on analyzing architectural variations, merging strategies between ViT and CNN, innovative applications of ViT, and efficiency metrics including parameters, inference time (GFlops), and performance benchmarks. The review identified that integrating ViT and CNN can mitigate the limitations of each architecture offering comprehensive solutions that combine global context understanding with precise local feature extraction. We benchmarked the articles based on architectural variations, merging strategies, innovative uses of ViT, and efficiency metrics (number of parameters, inference time (GFlops), and performance), and derived a ranked list. By synthesizing current literature, this review defines fundamental concepts of hybrid vision transformers and highlights emerging trends in the field. It provides a clear direction for future research aimed at optimizing the integration of ViT and CNN for effective utilization in medical imaging, contributing to advancements in diagnostic accuracy and image analysis. We performed systematic review of hybrid vision transformer architecture using PRISMA guideline and performed thorough comparative analysis to benchmark the architectures.

Management of Cemento-Ossifying Fibroma: A Report on Two Clinical Cases

Cemento-Ossifying Fibroma (COF) is a rare benign tumor of the jaw characterized by the formation of cementum and bone-like tissue, often arising from the periodontal ligament. This article presents two clinical cases that illustrate the complexities of diagnosing and managing COF. The first case involves a 30-year-old male with a painless, progressively enlarging swelling in the left mandible, diagnosed through panoramic radiography and cone-beam computed tomography (CBCT). Surgical intervention included mandibular resection and reconstruction using an iliac graft. The second case features a 26-year-old female presenting with a non-painful swelling in the right mandibular premolar region, which was also confirmed via imaging studies. Complete surgical resection was performed, and histopathological examination validated the diagnosis of COF. Both cases highlight the importance of accurate diagnostic imaging and histological analysis in confirming COF, as well as the need for individualized surgical approaches based on lesion characteristics. Despite its benign nature, COF can lead to significant morbidity due to local invasion and recurrence potential. The article emphasizes that thorough follow-up is essential to monitor for recurrence after surgical management. These cases contribute to the understanding of COF's clinical presentation and reinforce the necessity for a multidisciplinary approach in managing this condition effectively. Further research is needed to explore the underlying pathogenesis and optimize treatment strategies for COF in clinical practice.

Enhancing Laboratory Efficiency: Implementing Custom Image Analysis Tools for Streamlined Pathology Workflows

In the field of pathology, the efficient analysis and interpretation of diagnostic images are critical for timely and accurate decision-making. Traditional manual methods for image analysis are often time-consuming, error-prone, and resource-intensive, leading to delays in diagnosis and increased workloads for pathologists. To address these challenges, this paper explores the development and implementation of custom image analysis tools to streamline pathology workflows. The integration of machine learning (ML) algorithms, computer vision techniques, and automation technologies into laboratory settings has the potential to significantly enhance the speed and accuracy of image processing tasks. This study examines how tailored image analysis solutions can optimize tasks such as tissue segmentation, feature extraction, and classification of abnormal cells. The use of such tools not only improves the diagnostic workflow but also reduces human error, enhances reproducibility, and facilitates real-time analysis. Additionally, the paper discusses the practical considerations for implementing these technologies, including software customization, integration with existing laboratory information systems, and user training. By leveraging the power of custom-built image analysis solutions, pathology laboratories can improve operational efficiency, reduce turnaround times for results, and ultimately enhance patient outcomes. The research provides insights into the future of digital pathology and offers a roadmap for laboratories looking to adopt cutting-edge technologies to stay at the forefront of diagnostic innovation.

Using artificial intelligence for bladder cancer detection during cystoscopy and its impact on clinical outcomes: a protocol for a systematic review and meta-analysis

IntroductionCystoscopy has revolutionised the process of diagnosing bladder cancer leading to better categorisation of risk levels and more precise treatment plans. Nonetheless, concerns arise about the lack of uniformity among...

Analysis of Trends in the Use of Artificial Intelligence in Diagnosis and Treatment

AI in healthcare has improved, making diagnostics more accurate and increasing the effectiveness of treatments. The present study discusses the AI trends in diagnostic and therapeutic applications and focuses on the presented practical applications and their effects on patient care. The purpose of this particular review is to focus on the current developments in the implementation of AI in the field of health care, present main use cases and successes, as well as discuss about the issues and concerns in the topic at hand. Previous studies on AI in healthcare with specific consideration of diagnostic image analysis and interpretation, histology and molecular pathology, whole-genome sequencing, and therapeutic decision support are discussed. The selection criteria included papers with data gathered from real-life AI cases and quantitative findings. Study materials were obtained from e-journals, conference papers, and established online sources with descriptive analysis being done on the data collected. A summary of the findings revealed a number of highly impactful subcategories focused on the use of artificial intelligence diagnostic imaging, especially in radiology, pathology, and genomics. The AI applications used in the fields of operations and drug discovery revealed the ability to accurately predict clinical trial outcomes and to create effective treatments. First of all, AI can become a game changer in healthcare by enhancing diagnostics accuracy and treatment outcomes. The future research questions include further developing the methods that explain the AI models’ decisions, protecting the privacy of patient information, and reducing algorithmic bias for better fair healthcare for all. Therefore, better interactions between creators of AI and clinicians and regulatory authorities are pertinent to make sure that the full advantages of AI are realized in clinical practice to advance patient care.

A laminar spray group combustion experiment (LSGCE) with in situ image diagnostic methods and image analysis algorithms.

Spray combustion is important for different engines. The understanding of spray combustion should be further promoted especially in the non-dilute region, and there is lack of well-defined spray experiments. In this study, an experimental platform was developed. Using this platform, a cylindrical quasi-laminar spray can be formed and ignited by a thin and straight hot wire, making it a simple configuration. Two image diagnostic methods were also developed to capture in situ microscopic droplet images and macroscopic droplet-flame images synchronously. Different image analysis algorithms were developed to obtain droplet statistics (diameter, velocity, and number density) and flame information (size, location, and flame propagation speed) from the raw images. The design, diagnostic methods, and image analysis methods are detailedly presented. This experimental platform can cover a wide range of operating conditions, with Gig in a range of 0.01-0.06 and temperature in a range from room temperature to 1400K. In addition, this platform is small in size and is capable of further implanting into a ground-based microgravity facilitaty. The whole experimental system can be applied in spray ignition and combustion studies and can provide legitimate data for further model development.

Innovative Approaches to Clinical Diagnosis: Transfer Learning in Facial Image Classification for Celiac Disease Identification

Background: Celiac disease arises from gluten consumption and shares symptoms with other conditions, leading to delayed diagnoses. Untreated celiac disease heightens the risk of autoimmune disorders, neurological issues, and certain cancers like lymphoma while also impacting skin health due to intestinal disruptions. This study uses facial photos to distinguish individuals with celiac disease from those without. Surprisingly, there is a lack of research involving transfer learning for this purpose despite its benefits such as faster training, enhanced performance, and reduced overfitting. While numerous studies exist on endoscopic intestinal photo classification and a few have explored the link between facial morphology measurements and celiac disease, none have concentrated on diagnosing celiac disease through facial photo classification. Methods: This study sought to apply transfer learning techniques with VGG16 to address a gap in research by identifying distinct facial features that differentiate patients with celiac disease from healthy individuals. A dataset containing a total of 200 facial images of adult individuals with and without celiac condition was utilized. Half of the dataset had a ratio of 70% females to 30% males with celiac condition, and the rest had a ratio of 60% females to 40% males without celiac condition. Among those with celiac condition, 28 were newly diagnosed and 72 had been previously diagnosed, with 25 not adhering to a gluten-free diet and 47 partially adhering to such a diet. Results: Utilizing transfer learning, the model achieved a 73% accuracy in classifying the facial images of the patients during testing, with corresponding precision, recall, and F1 score values of 0.54, 0.56, and 0.52, respectively. The training process involved 50,178 parameters, showcasing the model’s efficacy in diagnostic image analysis. Conclusions: The model correctly classified approximately three-quarters of the test images. While this is a reasonable level of accuracy, it also suggests that there is room for improvement as the dataset contains images that are inherently difficult to classify even for humans. Increasing the proportion of newly diagnosed patients in the dataset and expanding the dataset size could notably improve the model’s efficacy. Despite being the first study in this field, further refinement holds promise for the development of a diagnostic tool for celiac disease using transfer learning in medical image analysis, addressing the lack of prior studies in this area.

Real-World Biomarkers for Pediatric Takayasu Arteritis.

Childhood-onset Takayasu arteritis (TA) is a rare, heterogeneous disease with limited diagnostic markers. Our objective was to identify and classify all candidates for biomarkers of TA diagnosis in children reported in the literature. A systematic literature review (PRISMA) of MEDLINE, EMBASE, Wiley Cochrane Library, ClinicalTrias.gov, and WHO ICTRP for articles related to TA in the pediatric age group between January 2000 and August 2023 was performed. Data on demographics, clinical features, laboratory measurements, diagnostic imaging, and genetic analysis were extracted. We identified 2026 potential articles, of which 52 studies (81% case series) met inclusion criteria. A total of 1067 TA patients were included with a peak onset between 10 and 15 years. Childhood-onset TA predominantly presented with cardiovascular, constitutional, and neurological symptoms. Laboratory parameters exhibited a low sensitivity and specificity. Imaging predominantly revealed involvement of the abdominal aorta and renal arteries, with magnetic resonance angiography (MRA) being the preferred imaging modality. Our review confirms the heterogeneous presentation of childhood-onset TA, posing significant challenges to recognition and timely diagnosis. Collaborative, multinational efforts are essential to better understand the natural course of childhood-onset TA and to identify accurate biomarkers to enhance diagnosis and disease management, ultimately improving patient outcomes.

Application of Photoactive Compounds in Cancer Theranostics: Review on Recent Trends from Photoactive Chemistry to Artificial Intelligence.

According to the World Health Organization (WHO) and the International Agency for Research on Cancer (IARC), the number of cancer cases and deaths worldwide is predicted to nearly double by 2030, reaching 21.7 million cases and 13 million fatalities. The increase in cancer mortality is due to limitations in the diagnosis and treatment options that are currently available. The close relationship between diagnostics and medicine has made it possible for cancer patients to receive precise diagnoses and individualized care. This article discusses newly developed compounds with potential for photodynamic therapy and diagnostic applications, as well as those already in use. In addition, it discusses the use of artificial intelligence in the analysis of diagnostic images obtained using, among other things, theranostic agents.

Rapunzel Syndrome: Diagnostic Challenges and Multidisciplinary Treatment Strategies.

Rapunzel syndrome, a rare yet complex condition, poses diagnostic and therapeutic challenges. Trichobezoars, stemming from trichotillomania and pica, manifest as hair conglomerates within the gastrointestinal tract, often necessitating surgical intervention. This review synthesizes literature on symptomatology, diagnostic methods, and treatment modalities, emphasizing the multidisciplinary approach essential for effective management. Psychological interventions, including cognitive-behavioral therapy, complement surgical measures in addressing underlying psychiatric factors. Diagnostic imaging, endoscopic examinations, and histopathological analysis aid in an accurate diagnosis. Enhanced awareness among healthcare providers regarding the association between psychological disorders and gastrointestinal complications is crucial for timely intervention and improved outcomes in individuals with Rapunzel syndrome.

Taxonomy of Acute Stroke: Imaging, Processing, and Treatment

Stroke management employs a variety of diagnostic imaging modalities, image processing and analysis methods, and treatment procedures. This work categorizes methods for stroke imaging, image processing and analysis, and treatment, and provides their taxonomies illustrated by a state-of-the-art review. Imaging plays a critical role in stroke management, and the most frequently employed modalities are computed tomography (CT) and magnetic resonance (MR). CT includes unenhanced non-contrast CT as the first-line diagnosis, CT angiography, and CT perfusion. MR is the most complete method to examine stroke patients. MR angiography is useful to evaluate the severity of artery stenosis, vascular occlusion, and collateral flow. Diffusion-weighted imaging is the gold standard for evaluating ischemia. MR perfusion-weighted imaging assesses the penumbra. The stroke image processing methods are divided into non-atlas/template-based and atlas/template-based. The non-atlas/template-based methods are subdivided into intensity and contrast transformations, local segmentation-related, anatomy-guided, global density-guided, and artificial intelligence/deep learning-based. The atlas/template-based methods are subdivided into intensity templates and atlases with three atlas types: anatomy atlases, vascular atlases, and lesion-derived atlases. The treatment procedures for arterial and venous strokes include intravenous and intraarterial thrombolysis and mechanical thrombectomy. This work captures the stateoftheart in stroke management summarized in the form of comprehensive and straightforward taxonomy diagrams. All three introduced taxonomies in diagnostic imaging, image processing and analysis, and treatment are widely illustrated and compared against other state-of-the-art classifications.

The Crucial Role of Interdisciplinary Conferences in Advancing Explainable AI in Healthcare

As artificial intelligence (AI) integrates within the intersecting domains of healthcare and computational biology, developing interpretable models tailored to medical contexts is met with significant challenges. Explainable AI (XAI) is vital for fostering trust and enabling effective use of AI in healthcare, particularly in image-based specialties such as pathology and radiology where adjunctive AI solutions for diagnostic image analysis are increasingly utilized. Overcoming these challenges necessitates interdisciplinary collaboration, essential for advancing XAI to enhance patient care. This commentary underscores the critical role of interdisciplinary conferences in promoting the necessary cross-disciplinary exchange for XAI innovation. A literature review was conducted to identify key challenges, best practices, and case studies related to interdisciplinary collaboration for XAI in healthcare. The distinctive contributions of specialized conferences in fostering dialogue, driving innovation, and influencing research directions were scrutinized. Best practices and recommendations for fostering collaboration, organizing conferences, and achieving targeted XAI solutions were adapted from the literature. By enabling crucial collaborative junctures that drive XAI progress, interdisciplinary conferences integrate diverse insights to produce new ideas, identify knowledge gaps, crystallize solutions, and spur long-term partnerships that generate high-impact research. Thoughtful structuring of these events, such as including sessions focused on theoretical foundations, real-world applications, and standardized evaluation, along with ample networking opportunities, is key to directing varied expertise toward overcoming core challenges. Successful collaborations depend on building mutual understanding and respect, clear communication, defined roles, and a shared commitment to the ethical development of robust, interpretable models. Specialized conferences are essential to shape the future of explainable AI and computational biology, contributing to improved patient outcomes and healthcare innovations. Recognizing the catalytic power of this collaborative model is key to accelerating the innovation and implementation of interpretable AI in medicine.

Exploring the State of Cancer Imaging Research in Africa

IntroductionThe growing cancer burden in Africa demands urgent action. Medical imaging is crucial for cancer diagnosis and management and is an essential enabler of precision medicine. To understand the readiness for quantitative imaging analysis to support cancer management in Africa, we analyzed the utilization patterns of imaging modalities for cancer research across the continent. MethodsWe retrieved articles by systematically searching PubMed, using a combination of search terms {“Neoplasm”} AND {“Radiology” or “Diagnostic imaging” or “Radiography” or “Interventional Radiology” or “Radiotherapy” or “Radiation Oncology”} AND {Africa∗ or 54 African countries}. Articles describing cancer diagnosis or management in humans with the utilization of imaging were included. Exclusion criteria were review articles, non-English articles, publications before 2000, noncancer diagnoses, and studies conducted outside Africa. ResultsThe analysis of diagnostic imaging in Africa revealed a diverse utilization pattern across different cancer types and regions. The literature search identified 107 publications on cancer imaging in Africa. The studies were carried out in 19 African countries on 12 different cancer types with 6 imaging modalities identified. Most cancer imaging research studies used multiple imaging modalities. Ultrasound was the most used distinct imaging modality and MRI was the least frequently used. Most research studies originated from Nigeria, South Africa, and Egypt. ConclusionWe demonstrate substantial variability in the presence of imaging modalities, widespread utilization of ultrasonography, and limited availability of advanced imaging modalities for cancer research.

Enhancing Healthcare with AI: Diagnostic Imaging and Patient Sentiment Analysis

Enhancing Healthcare with AI: Diagnostic Imaging and Patient Sentiment Analysis

Enhancing Healthcare with AI: Diagnostic Imaging and Patient Sentiment Analysis

Enhancing Healthcare with AI: Diagnostic Imaging and Patient Sentiment Analysis

Enhancing interpretability and accuracy of AI models in healthcare: a comprehensive review on challenges and future directions.

Artificial Intelligence (AI) has demonstrated exceptional performance in automating critical healthcare tasks, such as diagnostic imaging analysis and predictive modeling, often surpassing human capabilities. The integration of AI in healthcare promises substantial improvements in patient outcomes, including faster diagnosis and personalized treatment plans. However, AI models frequently lack interpretability, leading to significant challenges concerning their performance and generalizability across diverse patient populations. These opaque AI technologies raise serious patient safety concerns, as non-interpretable models can result in improper treatment decisions due to misinterpretations by healthcare providers. Our systematic review explores various AI applications in healthcare, focusing on the critical assessment of model interpretability and accuracy. We identify and elucidate the most significant limitations of current AI systems, such as the black-box nature of deep learning models and the variability in performance across different clinical settings. By addressing these challenges, our objective is to provide healthcare providers with well-informed strategies to develop innovative and safe AI solutions. This review aims to ensure that future AI implementations in healthcare not only enhance performance but also maintain transparency and patient safety.

Impact of dental imaging on pregnant women and recommendations for fetal radiation safety: A systematic review.

This study was conducted to investigate the safety of dental imaging in pregnant women with respect to fetal health. Searches were conducted of the PubMed, Scopus, and Web of Science databases in May 2023. The inclusion criteria encompassed cross-sectional and longitudinal studies that focused on the analysis of diagnostic dental imaging in pregnant women, as well as studies utilizing phantoms to simulate imaging examinations. The exclusion criteria consisted of reviews, letters to the editor, book chapters, and abstracts from scientific conferences and seminars. A total of 3,913 articles were identified. Based on a review of the titles and abstracts, 3,892 articles were excluded, leaving 21 articles remaining for full-text review. Of these, 18 were excluded, and 4 additional articles were included as cross-references. Ultimately, 7 articles underwent quantitative-qualitative analysis. Three retrospective studies were focused on pregnant women who underwent dental imaging procedures. The remaining 4 studies utilized female phantoms to simulate imaging examinations and represent the radiation doses absorbed by the uterus or thyroid. Few dental radiology studies have been conducted to determine the safe radiation threshold for pregnant women. Additionally, the reviewed articles did not provide numbers of dental examinations, by type, corresponding to this dose. Dental imaging examinations of pregnant women should not be restricted if clinically indicated. Ultimately, practitioners must be able to justify the examination and should adhere to the "as low as diagnostically acceptable, being indication-oriented and patient-specific" (ALADAIP) principle of radioprotection.

Characteristics of visual perception of patients’ faces and the formation of “observation” in the process of training cosmetologists

Professional experience assists specialists in processing information more quickly and effectively making precise decisions. Visual expertise, as a crucial component of experience, refers to the capability to rapidly perceive visual information within a specific professional domain, acquired through systematic education, professional development, and practice. Numerous studies utilize eye-tracking methods to analyze the relationship between professional experience and gaze patterns. For instance, experienced dermatologists have developed optimal scanning patterns, allowing them to efficiently allocate attention and accurately identify key diagnostic features within images amidst numerous secondary details. The purpose of this study is to analyze changes in oculomotor patterns after completing the author’s training program for doctors, aimed at versatile aesthetic analytics of the face, building individual treatment protocols and increasing the patient’s adherence to aesthetic medicine in order to assess the possibility of developing observation in the conditions of short-term training. Thirty cosmetic doctors participated in the study, which utilized eye-tracking methods with the Neuroburo program-hardware complex. The study was conducted in two phases – before and after training – with 15 patient facial images exhibiting various dermatological issues presented on a computer screen to the cosmetic doctors. Participants were tasked with identifying signs of dermatological disorders of the patients. Following training, a decrease in the number of fixations, an increase in saccadic amplitude, and a reduction in the overall scanning path length were observed among the cosmetic doctors. These findings indicate a more optimized perception strategy and suggest a more systematic and directed approach to diagnostic image analysis. The results suggest an enhanced global perception ability among the doctors, which may aid in recognizing broader patterns and structures and understanding the wider context and relationships between details.

Physician practice migration and changes in practice style: An empirical analysis of inappropriate diagnostic imaging in primary care

Much interest exists in physicians’ ability and willingness to adapt their practice styles, as research demonstrates that many physicians practice in ways that are not aligned with the best available scientific evidence. We exploit migration patterns of primary care physicians in Massachusetts over a span of 8 years by tracking physician migrations to practice sites comprised of new peers who shared actual physical working space. We examined whether a patient's likelihood of receiving an inappropriate referral for diagnostic imaging, specifically a magnetic resonance imaging (MRI), was associated with a change in the work environment of the referring physician. Study results indicate that migrating physicians changed their practice style for imaging relatively soon after migration in conformance with the average practice style of their new peer group regardless of whether or not the practice style was aligned with evidence‐based standards for diagnostic imaging. To place our results in context, a 1 percentage point difference in average inappropriate MRI referral rates between a migrating physician's new and previous work environment was associated with approximately a 14% change in the probability that a patient received an inappropriate MRI referral. The effect diminished with greater variability in inappropriate MRI referral rates within the new peer group. The results show that physician practice style may deviate from evidence‐based standards and vary markedly among physicians within a work environment. At the same time, physician practice style is also malleable in either direction—more or less likely to deviate from evidence‐based standards in conformance with the average practice style of their new peer group. These results imply that healthcare managers can employ various institutional‐level interventions to influence physician behavior in the direction of evidence‐based practice by including strategies directed towards developing strong peer influence in physicians’ work environments.

Automated Measurement of Vascular Calcification in Femoral Endarterectomy Patients Using Deep Learning.

Atherosclerosis, a chronic inflammatory disease affecting the large arteries, presents a global health risk. Accurate analysis of diagnostic images, like computed tomographic angiograms (CTAs), is essential for staging and monitoring the progression of atherosclerosis-related conditions, including peripheral arterial disease (PAD). However, manual analysis of CTA images is time-consuming and tedious. To address this limitation, we employed a deep learning model to segment the vascular system in CTA images of PAD patients undergoing femoral endarterectomy surgery and to measure vascular calcification from the left renal artery to the patella. Utilizing proprietary CTA images of 27 patients undergoing femoral endarterectomy surgery provided by Prisma Health Midlands, we developed a Deep Neural Network (DNN) model to first segment the arterial system, starting from the descending aorta to the patella, and second, to provide a metric of arterial calcification. Our designed DNN achieved 83.4% average Dice accuracy in segmenting arteries from aorta to patella, advancing the state-of-the-art by 0.8%. Furthermore, our work is the first to present a robust statistical analysis of automated calcification measurement in the lower extremities using deep learning, attaining a Mean Absolute Percentage Error (MAPE) of 9.5% and a correlation coefficient of 0.978 between automated and manual calcification scores. These findings underscore the potential of deep learning techniques as a rapid and accurate tool for medical professionals to assess calcification in the abdominal aorta and its branches above the patella.