Commercial Artificial Intelligence Research Articles

Evaluation of AI-based Gleason grading algorithms "in the wild"

The biopsy Gleason score is an important prognostic marker for prostate cancer patients. It is, however, subject to substantial variability among pathologists. Artificial intelligence (AI)-based algorithms employing deep learning have shown their ability to match pathologists' performance in assigning Gleason scores, with the potential to enhance pathologists' grading accuracy. The performance of Gleason AI algorithms in research is mostly reported on common benchmark datasets or within public challenges. In contrast, many commercial algorithms are evaluated in clinical studies, for which data is not publicly released. As commercial AI vendors typically do not publish performance on public benchmarks, comparison between research and commercial AI is difficult. The aim of this study is to evaluate and compare the performance of top-ranked public and commercial algorithms using real-world data. We curated a diverse dataset of whole-slide prostate biopsy images through crowdsourcing, containing images with a range of Gleason scores and from diverse sources. Predictions were obtained from five top-ranked public algorithms from the PANDA challenge and from two commercial Gleason grading algorithms. Additionally, ten pathologists evaluated the data set in a reader study. Overall, the pairwise quadratic weighted kappa among pathologists ranged from 0.777 to 0.916. Both public and commercial algorithms showed high agreement with pathologists, with quadratic kappa ranging from 0.617 to 0.900. Commercial algorithms performed on par or outperformed top public algorithms.

Interobserver Agreement and Performance of Concurrent AI Assistance for Radiographic Evaluation of Knee Osteoarthritis.

Background Due to conflicting findings in the literature, there are concerns about a lack of objectivity in grading knee osteoarthritis (KOA) on radiographs. Purpose To examine how artificial intelligence (AI) assistance affects the performance and interobserver agreement of radiologists and orthopedists of various experience levels when evaluating KOA on radiographs according to the established Kellgren-Lawrence (KL) grading system. Materials and Methods In this retrospective observer performance study, consecutive standing knee radiographs from patients with suspected KOA were collected from three participating European centers between April 2019 and May 2022. Each center recruited four readers across radiology and orthopedic surgery at in-training and board-certified experience levels. KL grading (KL-0 = no KOA, KL-4 = severe KOA) on the frontal view was assessed by readers with and without assistance from a commercial AI tool. The majority vote of three musculoskeletal radiology consultants established the reference standard. The ordinal receiver operating characteristic method was used to estimate grading performance. Light kappa was used to estimate interrater agreement, and bootstrapped t statistics were used to compare groups. Results Seventy-five studies were included from each center, totaling 225 studies (mean patient age, 55 years ± 15 [SD]; 113 female patients). The KL grades were KL-0, 24.0% (n = 54); KL-1, 28.0% (n = 63); KL-2, 21.8% (n = 49); KL-3, 18.7% (n = 42); and KL-4, 7.6% (n = 17). Eleven readers completed their readings. Three of the six junior readers showed higher KL grading performance with versus without AI assistance (area under the receiver operating characteristic curve, 0.81 ± 0.017 [SEM] vs 0.88 ± 0.011 [P < .001]; 0.76 ± 0.018 vs 0.86 ± 0.013 [P < .001]; and 0.89 ± 0.011 vs 0.91 ± 0.009 [P = .008]). Interobserver agreement for KL grading among all readers was higher with versus without AI assistance (κ = 0.77 ± 0.018 [SEM] vs 0.85 ± 0.013; P < .001). Board-certified radiologists achieved almost perfect agreement for KL grading when assisted by AI (κ = 0.90 ± 0.01), which was higher than that achieved by the reference readers independently (κ = 0.84 ± 0.017; P = .01). Conclusion AI assistance increased junior readers' radiographic KOA grading performance and increased interobserver agreement for osteoarthritis grading across all readers and experience levels. Published under a CC BY 4.0 license. Supplemental material is available for this article.

Innocence Discovery Lab - Harnessing large language models to surface data buried in wrongful conviction case documents

The recent advent of commercial artificial intelligence (AI), especially in natural language processing (NLP), introduces transformative possibilities for wrongful conviction research. NLP, a pivotal branch of AI that forms the basis for Large Language Models (LLMs), enables computers to interpret human language with a nuanced understanding. This technological advancement is particularly valuable for analyzing the complex language found in case documents associated with wrongful convictions. This paper explores the effectiveness of LLMs in analyzing and extracting data from case documents collected by the Innocence Project New Orleans and the National Registry of Exonerations. The diverse and comprehensive nature of these datasets makes them ideal for assessing the capabilities of LLMs. The findings of this study advance our understanding of how LLMs can be utilized to make wrongful conviction case documents easily accessible by automating the extraction of relevant data.

A growing number of AIs cleared for clinical use is finally available: The AI-assisted Pathologist

As more pathology laboratories are transitioning to a digital workflow, the availability of commercial Artificial Intelligence assistance systems is also increasing. Today nearly 40 such products approved for diagnostic use are available. This article provides an overview of the most widely addressed use cases, including Immunohistochemistry scoring for breast cancer and non-small-cell lung cancer, Gleason grading for prostate cancer, or metastasis detection in lymph nodes. While automation alone already promises an increase in efficiency that may help to bridge the growing gap between supply (pathology work force) and demand (histological testing), this article introduces another category of Artificial Intelligence products that go beyond just mimicking today’s established score. Various Artificial Intelligence are being introduced that detect genetic alterations or stratify risk, directly from the standard hematoxylin &amp; eosin staining. Finally, a brief outlook explains how basic AI models are currently finding their way into computational pathology and promise to further accelerate product developments by decreasing the time-to-model.

Use of a commercial artificial intelligence-based mammography analysis software for improving breast ultrasound interpretations.

To evaluate the use of a commercial artificial intelligence (AI)-based mammography analysis software for improving the interpretations of breast ultrasound (US)-detected lesions. A retrospective analysis was performed on 1109 breasts that underwent both mammography and US-guided breast biopsy. The AI software processed mammograms and provided an AI score ranging from 0 to 100 for each breast, indicating the likelihood of malignancy. The performance of the AI score in differentiating mammograms with benign outcomes from those revealing cancers following US-guided breast biopsy was evaluated. In addition, prediction models for benign outcomes were constructed based on clinical and imaging characteristics with and without AI scores, using logistic regression analysis. The AI software had an area under the receiver operating characteristics curve (AUROC) of 0.79 (95% CI, 0.79-0.82) in differentiating between benign and cancer cases. The prediction models that did not include AI scores (non-AI model), only used AI scores (AI-only model), and included AI scores (integrated model) had AUROCs of 0.79 (95% CI, 0.75-0.83), 0.78 (95% CI, 0.74-0.82), and 0.85 (95% CI, 0.81-0.88) in the development cohort, and 0.75 (95% CI, 0.68-0.81), 0.82 (95% CI, 0.76-0.88), and 0.84 (95% CI, 0.79-0.90) in the validation cohort, respectively. The integrated model outperformed the non-AI model in the development and validation cohorts (p < 0.001 for both). The commercial AI-based mammography analysis software could be a valuable adjunct to clinical decision-making for managing US-detected breast lesions. The commercial AI-based mammography analysis software could potentially reduce unnecessary biopsies and improve patient outcomes. • Breast US has high rates of false-positive interpretations. • A commercial AI-based mammography analysis software could distinguish mammograms having benign outcomes from those revealing cancers after US-guided breast biopsy. • A commercial AI-based mammography analysis software may improve interpretations for breast US-detected lesions.

Usar una herramienta comercial de inteligencia artificial no entrenada para COVID-19 mejora ligeramente la interpretación de las radiografías con neumonía COVID-19, especialmente entre lectores inexpertos

IntroductionOur objective is to evaluate how useful an artificial intelligence (AI) tool is to chest radiograph readers with various levels of expertise for the diagnosis of COVID-19 pneumonia when the tool has been trained on a non-COVID-19 pneumonia pathology. MethodsData was collected for patients who had previously undergone a chest radiograph and digital tomosynthesis due to suspected COVID-19 pneumonia. The gold standard consisted of the readings of two expert radiologists who assessed the presence and distribution of COVID-19 pneumonia on the images. Six medical students, two radiology trainees, and two other expert thoracic radiologists participated as additional readers. Two radiograph readings and a third supported by the AI Thoracic Care Suite tool were performed. COVID-19 pneumonia distribution and probability were assessed along with the contribution made by AI. Agreement and diagnostic performance were analysed. ResultsThe sample consisted of 113 cases, of which 56 displayed lung opacities, 52.2% were female, and the mean age was 50.70±14.9. Agreement with the gold standard differed between students, trainees, and radiologists. There was a non-significant improvement for four of the six students when AI was used. The use of AI by students did not improve the COVID-19 pneumonia diagnostic performance but it did reduce the difference in diagnostic performance with the more expert radiologists. Furthermore, it had more influence on the interpretation of mild pneumonia than severe pneumonia and normal radiograph findings. AI resolved more doubts than it generated, especially among students (31.30 vs 8.32%), followed by trainees (14.45 vs 5.7%) and radiologists (10.05% vs 6.15%). ConclusionFor expert and lesser experienced radiologists, this commercial AI tool has shown no impact on chest radiograph readings of patients with suspected COVID-19 pneumonia. However, it aided the assessment of inexperienced readers and in cases of mild pneumonia.

Clinical implementation of a commercial synthetic computed tomography solution for radiotherapy treatment of glioblastoma

Background and PurposeMagnetic resonance (MR)-only radiotherapy (RT) workflow eliminates uncertainties due to computed tomography (CT)-MR image registration, by using synthetic CT (sCT) images generated from MR. This study describes the clinical implementation process, from retrospective commissioning to prospective validation stage of a commercial artificial intelligence (AI)-based sCT product. Evaluation of the dosimetric performance of the sCT is presented, with emphasis on the impact of voxel size differences between image modalities. Materials and methodssCT performance was assessed in glioblastoma RT planning. Dose differences for 30 patients in both commissioning and validation cohorts were calculated at various dose-volume-histogram (DVH) points for target and organs-at-risk (OAR). A gamma analysis was conducted on regridded image plans. Quality assurance (QA) guidelines were established based on commissioning phase results. ResultsMean dose difference to target structures was found to be within ± 0.7 % regardless of image resolution and cohort. OARs’ mean dose differences were within ± 1.3 % for plans calculated on regridded images for both cohorts, while differences were higher for plans with original voxel size, reaching up to −4.2 % for chiasma D2% in the commissioning cohort. Gamma passing rates for the brain structure using the criteria 1 %/1mm, 2 %/2mm and 3 %/3mm were 93.6 %/99.8 %/100 % and 96.6 %/99.9 %/100 % for commissioning and validation cohorts, respectively. ConclusionsDosimetric outcomes in both commissioning and validation stages confirmed sCT’s equivalence to CT. The large patient cohort in this study aided in establishing a robust QA program for the MR-only workflow, now applied in glioblastoma RT at our center.

Applications of Deep Learning in Trauma Radiology: A Narrative Review

Diagnostic imaging is essential in modern trauma care for initial evaluation and identifying injuries requiring intervention. Deep learning (DL) has become mainstream in medical image analysis and has shown promising efficacy for classification, segmentation, and lesion detection. This narrative review provides the fundamental concepts for developing DL algorithms in trauma imaging and presents an overview of current progress in each modality. DL has been applied to detect free fluid on Focused Assessment with Sonography for Trauma (FAST), traumatic findings on chest and pelvic X-rays, and computed tomography (CT) scans, identify intracranial hemorrhage on head CT, detect vertebral fractures, and identify injuries to organs like the spleen, liver, and lungs on abdominal and chest CT. Future directions involve expanding dataset size and diversity through federated learning, enhancing model explainability and transparency to build clinician trust, and integrating multimodal data to provide more meaningful insights into traumatic injuries. Though some commercial artificial intelligence products are Food and Drug Administration-approved for clinical use in the trauma field, adoption remains limited, highlighting the need for multi-disciplinary teams to engineer practical, real-world solutions. Overall, DL shows immense potential to improve the efficiency and accuracy of trauma imaging, but thoughtful development and validation are critical to ensure these technologies positively impact patient care.

Standardized nomenclature for litigational legal prompting in generative language models

With the increasing availability of commercial Artificial Intelligence, General Language Models (GLMs) have been widely explored in various domains, including law. However, to ensure accurate and standardized legal results, it is crucial to establish a consistent framework for prompting GLMs. This paper presents one of the first instances of such nomenclature, providing a robust framework of “variables” and “clauses” that enhances legal-focused results. The proposed framework was applied in diverse legal scenarios, demonstrating its potential from both client and attorney perspectives. By introducing standardized variables and clauses, legal professionals can effectively communicate with GLMs. This not only improves the accuracy of the generated outcomes but also facilitates collaboration between AI systems and legal experts. With a common framework in place, legal practitioners can leverage AI technology confidently, knowing that the results produced align with established legal principles. Furthermore, the framework serves as a foundation for future research in the field of legal prompting with GLMs, and several avenues for future research are recommended in this paper. This standardization of nomenclature is expected to contribute to the wider adoption and benefit of GLMs in the legal field, leading to more accurate and reliable outcomes.

Types of teacher-AI collaboration in K-12 classroom instruction: Chinese teachers’ perspective

AbstractThe advancing power and capabilities of artificial intelligence (AI) have expanded the roles of AI in education and have created the possibility for teachers to collaborate with AI in classroom instruction. However, the potential types of teacher-AI collaboration (TAC) in classroom instruction and the benefits and challenges of implementing TAC are still elusive. This study, therefore, aimed to explore different types of TAC and the potential benefits and obstacles of TAC through Focus Group Interviews with 30 Chinese teachers. The study found that teachers anticipated six types of TAC, which are thematized as One Teach, One Observe; One Teach, One Assist; Co-teaching in Stations; Parallel Teaching in Online and Offline Classes; Differentiated Teaching; and Team Teaching. While teachers highlighted that TAC could support them in instructional design, teaching delivery, teacher professional development, and lowering grading load, they perceived a lack of explicit and consistent curriculum guidance, the dominance of commercial AI in schools, the absence of clear ethical guidelines, and teachers' negative attitude toward AI as obstacles to TAC. These findings enhance our understanding of how TAC could be structured at school levels and direct the implications for future development and practice to support TAC.

How AI should be used in radiology: assessing ambiguity and completeness of intended use statements of commercial AI products

BackgroundIntended use statements (IUSs) are mandatory to obtain regulatory clearance for artificial intelligence (AI)-based medical devices in the European Union. In order to guide the safe use of AI-based medical devices, IUSs need to contain comprehensive and understandable information. This study analyzes the IUSs of CE-marked AI products listed on AIforRadiology.com for ambiguity and completeness.MethodsWe retrieved 157 IUSs of CE-marked AI products listed on AIforRadiology.com in September 2022. Duplicate products (n = 1), discontinued products (n = 3), and duplicate statements (n = 14) were excluded. The resulting IUSs were assessed for the presence of 6 items: medical indication, part of the body, patient population, user profile, use environment, and operating principle. Disclaimers, defined as contra-indications or warnings in the IUS, were identified and compared with claims.ResultsOf 139 AI products, the majority (n = 78) of IUSs mentioned 3 or less items. IUSs of only 7 products mentioned all 6 items. The intended body part (n = 115) and the operating principle (n = 116) were the most frequently mentioned components, while the intended use environment (n = 24) and intended patient population (n = 29) were mentioned less frequently. Fifty-six statements contained disclaimers that conflicted with the claims in 13 cases.ConclusionThe majority of IUSs of CE-marked AI-based medical devices lack substantial information and, in few cases, contradict the claims of the product.Critical relevance statementTo ensure correct usage and to avoid off-label use or foreseeable misuse of AI-based medical devices in radiology, manufacturers are encouraged to provide more comprehensive and less ambiguous intended use statements.Key points• Radiologists must know AI products’ intended use to avoid off-label use or misuse.• Ninety-five percent (n = 132/139) of the intended use statements analyzed were incomplete.• Nine percent (n = 13) of the intended use statements held disclaimers contradicting the claim of the AI product.• Manufacturers and regulatory bodies must ensure that intended use statements are comprehensive.Graphical

AI regulation in the European Union: examining non-state actor preferences

AbstractAs the development and use of artificial intelligence (AI) continues to grow, policymakers are increasingly grappling with the question of how to regulate this technology. The most far-reaching international initiative is the European Union (EU) AI Act, which aims to establish the first comprehensive, binding framework for regulating AI. In this article, we offer the first systematic analysis of non-state actor preferences toward international regulation of AI, focusing on the case of the EU AI Act. Theoretically, we develop an argument about the regulatory preferences of business actors and other non-state actors under varying conditions of AI sector competitiveness. Empirically, we test these expectations using data from public consultations on European AI regulation. Our findings are threefold. First, all types of non-state actors express concerns about AI and support regulation in some form. Second, there are nonetheless significant differences across actor types, with business actors being less concerned about the downsides of AI and more in favor of lax regulation than other non-state actors. Third, these differences are more pronounced in countries with stronger commercial AI sectors. Our findings shed new light on non-state actor preferences toward AI regulation and point to challenges for policymakers balancing competing interests in society.

Custom-Trained Deep Learning-Based Auto-Segmentation for Male Pelvic Iterative CBCT on C-Arm Linear Accelerators

Purpose: To evaluate the clinical applicability of a commercial artificial intelligence (AI)-driven deep learning auto-segmentation (DLAS) tool on enhanced iterative cone-beam CT (iCBCT) acquisitions for intact prostate and prostate bed treatments. Methods and MaterialsDLAS models were trained using 116 iCBCT datasets with manually delineated organs-at-risk (OARs – bladder, femoral heads, and rectum) and target volumes (intact prostate and prostate bed) adhering to institution-specific contouring guidelines. An additional 25 intact prostate and prostate bed iCBCT datasets were utilized for model testing. Segmentation accuracy relative to a reference structure set was quantified using various geometric comparison metrics and qualitatively evaluated by trained physicists and physicians. These results were compared to those obtained for an additional DLAS-based model trained on planning CT (pCT) datasets and for a deformable image registration (DIR)-based automatic contour propagation method. Results: In most instances, statistically significant differences in the Dice similarity coefficient (DSC), 95% directed Hausdorff distance, and mean surface distance metrics were observed between the models, as the iCBCT-trained DLAS model outperformed the pCT-trained DLAS model and DIR-based method for all OARs and the intact prostate target volume. Mean DSC values for the proposed method were ≥0.90 for these volumes-of-interest. The iCBCT-trained DLAS model demonstrated a relatively suboptimal performance for the prostate bed segmentation, as the mean DSC value was <0.75 for this target contour. Overall, 90% of bladder, 93% of femoral head, 67% of rectum, and 92% of intact prostate contours generated by the proposed method were deemed clinically acceptable based on qualitative scoring, while approximately 63% of prostate bed contours required moderate or major manual editing to adhere to institutional contouring guidelines. Conclusion: The proposed method presents the potential for improved segmentation accuracy and efficiency when compared to the DIR-based automatic contour propagation method as commonly applied in CBCT-based dose evaluation and calculation studies.

The Investigation Related to Application of ChatGPT in Language Teaching

Being one of the foremost commercial artificial intelligence models, ChatGPT has garnered extensive attention and utilization within the education sector. Controversies have also arisen in scholarly circles regarding its potential adverse impacts. This study examines the operational principles of ChatGPT and elucidates its applications across various language teaching scenarios through illustrative instances. In the investigation of ChatGPT-assisted grammar instruction, the role and constraints of ChatGPT's grammar correction for Chinese learners are analyzed. Despite ChatGPT's accuracy in educational settings, it falls short in comprehending the requirements of novice learners. Using it as a self-study tool can leave students confused with difficult knowledge. However, it can significantly improve the teaching efficiency of teachers. In the process of ChatGPT assisted pronunciation teaching, this paper collected survey questionnaires from volunteers and summarized the conclusions. Most volunteers support the effectiveness of ChatGPT in oral teaching. Compared to traditional voice assistants like Siri, ChatGPTs pronunciation is more accurate and its sentences are closer to real humans. This paper provides a summary of ChatGPTs application in the field of language teaching, with a focus on two scenarios. It also discusses the shortcomings of ChatGPT in the current stage of language teaching. The future prospects of ChatGPT in language teaching are still very broad, and with the development of technology, the combination of ChatGPT and language teaching will become even closer.

Reader bias in breast cancer screening related to cancer prevalence and artificial intelligence decision support—a reader study

ObjectivesThe aim of our study was to examine how breast radiologists would be affected by high cancer prevalence and the use of artificial intelligence (AI) for decision support.Materials and methodThis reader study was based on selection of screening mammograms, including the original radiologist assessment, acquired in 2010 to 2013 at the Karolinska University Hospital, with a ratio of 1:1 cancer versus healthy based on a 2-year follow-up. A commercial AI system generated an exam-level positive or negative read, and image markers. Double-reading and consensus discussions were first performed without AI and later with AI, with a 6-week wash-out period in between. The chi-squared test was used to test for differences in contingency tables.ResultsMammograms of 758 women were included, half with cancer and half healthy. 52% were 40–55 years; 48% were 56–75 years. In the original non-enriched screening setting, the sensitivity was 61% (232/379) at specificity 98% (323/379). In the reader study, the sensitivity without and with AI was 81% (307/379) and 75% (284/379) respectively (p < 0.001). The specificity without and with AI was 67% (255/379) and 86% (326/379) respectively (p < 0.001). The tendency to change assessment from positive to negative based on erroneous AI information differed between readers and was affected by type and number of image signs of malignancy.ConclusionBreast radiologists reading a list with high cancer prevalence performed at considerably higher sensitivity and lower specificity than the original screen-readers. Adding AI information, calibrated to a screening setting, decreased sensitivity and increased specificity.Clinical relevance statementRadiologist screening mammography assessments will be biased towards higher sensitivity and lower specificity by high-risk triaging and nudged towards the sensitivity and specificity setting of AI reads. After AI implementation in clinical practice, there is reason to carefully follow screening metrics to ensure the impact is desired.Key Points• Breast radiologists’ sensitivity and specificity will be affected by changes brought by artificial intelligence.• Reading in a high cancer prevalence setting markedly increased sensitivity and decreased specificity.• Reviewing the binary reads by AI, negative or positive, biased screening radiologists towards the sensitivity and specificity of the AI system.Graphical abstract

Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction.

Background Multiple commercial artificial intelligence (AI) products exist for assessing radiographs; however, comparable performance data for these algorithms are limited. Purpose To perform an independent, stand-alone validation of commercially available AI products for bone age prediction based on hand radiographs and lung nodule detection on chest radiographs. Materials and Methods This retrospective study was carried out as part of Project AIR. Nine of 17 eligible AI products were validated on data from seven Dutch hospitals. For bone age prediction, the root mean square error (RMSE) and Pearson correlation coefficient were computed. The reference standard was set by three to five expert readers. For lung nodule detection, the area under the receiver operating characteristic curve (AUC) was computed. The reference standard was set by a chest radiologist based on CT. Randomized subsets of hand (n = 95) and chest (n = 140) radiographs were read by 14 and 17 human readers, respectively, with varying experience. Results Two bone age prediction algorithms were tested on hand radiographs (from January 2017 to January 2022) in 326 patients (mean age, 10 years ± 4 [SD]; 173 female patients) and correlated strongly with the reference standard (r = 0.99; P < .001 for both). No difference in RMSE was observed between algorithms (0.63 years [95% CI: 0.58, 0.69] and 0.57 years [95% CI: 0.52, 0.61]) and readers (0.68 years [95% CI: 0.64, 0.73]). Seven lung nodule detection algorithms were validated on chest radiographs (from January 2012 to May 2022) in 386 patients (mean age, 64 years ± 11; 223 male patients). Compared with readers (mean AUC, 0.81 [95% CI: 0.77, 0.85]), four algorithms performed better (AUC range, 0.86-0.93; P value range, <.001 to .04). Conclusions Compared with human readers, four AI algorithms for detecting lung nodules on chest radiographs showed improved performance, whereas the remaining algorithms tested showed no evidence of a difference in performance. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Omoumi and Richiardi in this issue.

The use of artificial intelligence in orthodontics

The application of Artificial Intelligence (AI) in orthodontics is very diverse and ranges from the identification of anatomical and pathological structures of the human dentition to support complex decision-making in orthodontic treatment planning. Its application has grown significantly in recent years, as reflected by the exponential increase in the number of scientific publications on the integration of artificial intelligence into everyday clinical practice. In many cases, AI can be seen as a valuable tool whose algorithms help dentists and clinicians analyze data from multiple sources of information. The purpose of this paper was to analyze current views on the use of artificial intelligence techniques and models in orthodontics based on a literature review. The scientific publications of various scientometric databases (PubMed, Scopus, Google Scolar, Web of Science, etc.) over the past 5 years were processed. Artificial intelligence is one of the most promising tools due to its high accuracy and efficiency. Given the current scientific dynamics in the field of AI, it can be assumed that AI will become an integral part of diagnostics and treatment planning in the near future. Practicing dentists will be able to use it as an additional tool to reduce their workload. However, this requires close cooperation of commercial AI products with the scientific community, further research, including randomized clinical trials, to test and integrate this concept in dental practice. Modern artificial intelligence is excellent at utilizing structured knowledge and gaining insights from huge amounts of data. However, it is not able to create associations like the human brain and is only partially capable of making complex decisions in a clinical situation. In turn, the efficiency of AI is achieved only when unbiased training data and a properly designed and trained algorithm are used. Keywords: dentistry, diagnostic, machine learning, cephalometry.

Commercially available artificial intelligence tools for fracture detection: the evidence.

Missed fractures are a costly healthcare issue, not only negatively impacting patient lives, leading to potential long-term disability and time off work, but also responsible for high medicolegal disbursements that could otherwise be used to improve other healthcare services. When fractures are overlooked in children, they are particularly concerning as opportunities for safeguarding may be missed. Assistance from artificial intelligence (AI) in interpreting medical images may offer a possible solution for improving patient care, and several commercial AI tools are now available for radiology workflow implementation. However, information regarding their development, evidence for performance and validation as well as the intended target population is not always clear, but vital when evaluating a potential AI solution for implementation. In this article, we review the range of available products utilizing AI for fracture detection (in both adults and children) and summarize the evidence, or lack thereof, behind their performance. This will allow others to make better informed decisions when deciding which product to procure for their specific clinical requirements.

Criteria for implementing artificial intelligence systems in reproductive medicine.

This review article discusses the integration of artificial intelligence (AI) in assisted reproductive technology and provides key concepts to consider when introducing AI systems into reproductive medicine practices. The article highlights the various applications of AI in reproductive medicine and discusses whether to use commercial or in-house AI systems. This review also provides criteria for implementing new AI systems in the laboratory and discusses the factors that should be considered when introducing AI in the laboratory, including the user interface, scalability, training, support, follow-up, cost, ethics, and data quality. The article emphasises the importance of ethical considerations, data quality, and continuous algorithm updates to ensure the accuracy and safety of AI systems.

Artificial Intelligence in BI-RADS Categorization of Breast Lesions on Ultrasound: Can We Omit Excessive Follow-ups and Biopsies?

Artificial intelligence (AI) systems have been increasingly applied to breast ultrasonography. They are expected to decrease the workload of radiologists and to improve diagnostic accuracy. The aim of this study is to evaluate the performance of an AI system for the BI-RADS category assessment in breast masses detected on breast ultrasound. MATERIALSAND METHODS: A total of 715 masses detected in 530 patients were analyzed. Three breast imaging centers of the same institution and ninebreast radiologists participated in this study. Ultrasound was performed by one radiologist who obtained two orthogonal views of each detected lesion. These images were retrospectively reviewed by a second radiologist blinded to the patient's clinical data. A commercial AI system evaluated images. The level of agreement between the AI system and the two radiologists and their diagnostic performance were calculated according to dichotomic BI-RADS category assessment. This study included 715 breast masses. Of these, 134 (18.75%) were malignant, and 581 (81.25%) were benign. In discriminating benign and probably benign from suspicious lesions, the agreement between AI and the first and second radiologists was moderate statistically. The sensitivity and specificity of radiologist 1, radiologist 2, and AI were calculated as 98.51% and 80.72%, 97.76% and 75.56%, and 98.51% and 65.40%, respectively. For radiologist 1, the positive predictive value (PPV) was 54.10%, the negative predictive value (NPV) was 99.58%, and the accuracy was 84.06%. Radiologist 2 achieved a PPV of 47.99%, NPV of 99.32%, and accuracy of 79.72%. The AI system exhibited a PPV of 39.64%, NPV of 99.48%, and accuracy of 71.61%. Notably, none of the lesions categorized as BI-RADS 2 by AI were malignant, while 2 of the lesions classified as BI-RADS 3 by AI were subsequently confirmed as malignant. By considering AI-assigned BI-RADS 2 as safe, we could potentially avoid 11% (18 out of 163) of benign lesion biopsies and 46.2% (110 out of 238) of follow-ups. AI proves effective in predicting malignancy. Integrating it into the clinical workflow has the potential to reduce unnecessary biopsies and short-term follow-ups, which, in turn, can contribute to sustainability in healthcare practices.