Making Use of Artificial Intelligence-Generated Synthetic Tympanic Membrane Images.
Ontology highlight
ABSTRACT:
SUBMITTER: Suresh K
PROVIDER: S-EPMC10064279 | biostudies-literature | 2023 Jun
REPOSITORIES: biostudies-literature
Publications
Making Use of Artificial Intelligence-Generated Synthetic Tympanic Membrane Images.
Suresh Krish K Cohen Michael S MS Hartnick Christopher J CJ Bartholomew Ryan A RA Lee Daniel J DJ Crowson Matthew G MG
JAMA otolaryngology-- head & neck surgery 20230601 6
Similar Datasets
Project description:BackgroundGiven the public's tendency to overestimate the capability of artificial intelligence (AI) in surgical outcomes for plastic surgery, this study assesses the accuracy of AI-generated images for breast augmentation and reduction, aiming to determine if AI technology can deliver realistic expectations and can be useful in a surgical context.MethodsWe used AI platforms GetIMG, Leonardo, and Perchance to create pre- and postsurgery images of breast augmentation and reduction. Board-certified plastic surgeons and plastic surgery residents evaluated these images using 11 metrics and divided them into 2 categories: realism and clinical value. Statistical analysis was conducted using analysis of variance and Tukey honestly significant difference post hoc tests. Images of the nipple-areolar complex were excluded due to AI's nudity restrictions.ResultsGetIMG (mean ± SD) (realism: 3.83 ± 0.81, clinical value: 3.13 ± 0.62), Leonardo (realism: 3.30 ± 0.69, clinical value: 2.94 ± 0.47), and Perchance (realism: 2.68 ± 0.77, clinical value: 2.88 ± 0.44) showed comparable realism and clinical value scores with no significant difference (P > 0.05). In specific metrics, GetIMG outperformed significantly in surgical relevance compared with the other models (P values: 0.02 and 0.03). Healing and scarring prediction is the metric that underperformed across models (2.25 ± 1.11 P ≤ 0.03). Panelists found some images "cartoonish" with unrealistic skin, indicating AI origin.ConclusionsThe AI models showed similar performance, with some images accurately predicting postsurgical outcomes, particularly breast size and volume in a bra. Despite this promise, the absence of detailed nipple-areola complex visualization is a significant limitation. Until these features and consistent representations of various body types and skin tones are achievable, the authors advise using actual patient photographs for consultations.
| S-EPMC11661769 | biostudies-literature
Project description:BackgroundArtificial intelligence (AI) in medical imaging diagnostics has huge potential, but human judgement is still indispensable. We propose an AI-aided teaching method that leverages generative AI to train students on many images while preserving patient privacy.MethodsA web-based course was designed using 600 synthetic ultra-widefield (UWF) retinal images to teach students to detect disease in these images. The images were generated by stable diffusion, a large generative foundation model, which we fine-tuned with 6285 real UWF images from six categories: five retinal diseases (age-related macular degeneration, glaucoma, diabetic retinopathy, retinal detachment and retinal vein occlusion) and normal. 161 trainee orthoptists took the course. They were evaluated with two tests: one consisting of UWF images and another of standard field (SF) images, which the students had not encountered in the course. Both tests contained 120 real patient images, 20 per category. The students took both tests once before and after training, with a cool-off period in between.ResultsOn average, students completed the course in 53 min, significantly improving their diagnostic accuracy. For UWF images, student accuracy increased from 43.6% to 74.1% (p<0.0001 by paired t-test), nearly matching the previously published state-of-the-art AI model's accuracy of 73.3%. For SF images, student accuracy rose from 42.7% to 68.7% (p<0.0001), surpassing the state-of-the-art AI model's 40%.ConclusionSynthetic images can be used effectively in medical education. We also found that humans are more robust to novel situations than AI models, thus showcasing human judgement's essential role in medical diagnosis.
| S-EPMC11503156 | biostudies-literature
Project description:ImportanceSurgeons make complex, high-stakes decisions under time constraints and uncertainty, with significant effect on patient outcomes. This review describes the weaknesses of traditional clinical decision-support systems and proposes that artificial intelligence should be used to augment surgical decision-making.ObservationsSurgical decision-making is dominated by hypothetical-deductive reasoning, individual judgment, and heuristics. These factors can lead to bias, error, and preventable harm. Traditional predictive analytics and clinical decision-support systems are intended to augment surgical decision-making, but their clinical utility is compromised by time-consuming manual data management and suboptimal accuracy. These challenges can be overcome by automated artificial intelligence models fed by livestreaming electronic health record data with mobile device outputs. This approach would require data standardization, advances in model interpretability, careful implementation and monitoring, attention to ethical challenges involving algorithm bias and accountability for errors, and preservation of bedside assessment and human intuition in the decision-making process.Conclusions and relevanceIntegration of artificial intelligence with surgical decision-making has the potential to transform care by augmenting the decision to operate, informed consent process, identification and mitigation of modifiable risk factors, decisions regarding postoperative management, and shared decisions regarding resource use.
| S-EPMC7286802 | biostudies-literature
Project description:PurposeDeveloping robust artificial intelligence (AI) models for medical image analysis requires large quantities of diverse, well-chosen data that can prove challenging to collect because of privacy concerns, disease rarity, or diagnostic label quality. Collecting image-based datasets for retinopathy of prematurity (ROP), a potentially blinding disease, suffers from these challenges. Progressively growing generative adversarial networks (PGANs) may help, because they can synthesize highly realistic images that may increase both the size and diversity of medical datasets.DesignDiagnostic validation study of convolutional neural networks (CNNs) for plus disease detection, a component of severe ROP, using synthetic data.ParticipantsFive thousand eight hundred forty-two retinal fundus images (RFIs) collected from 963 preterm infants.MethodsRetinal vessel maps (RVMs) were segmented from RFIs. PGANs were trained to synthesize RVMs with normal, pre-plus, or plus disease vasculature. Convolutional neural networks were trained, using real or synthetic RVMs, to detect plus disease from 2 real RVM test datasets.Main outcome measuresFeatures of real and synthetic RVMs were evaluated using uniform manifold approximation and projection (UMAP). Similarities were evaluated at the dataset and feature level using Fréchet inception distance and Euclidean distance, respectively. CNN performance was assessed via area under the receiver operating characteristic curve (AUC); AUCs were compared via bootstrapping and Delong's test for correlated receiver operating characteristic curves. Confusion matrices were compared using McNemar's chi-square test and Cohen's κ value.ResultsThe CNN trained on synthetic RVMs showed a significantly higher AUC (0.971; P = 0.006 and P = 0.004) and classified plus disease more similarly to a set of 8 international experts (κ = 0.922) than the CNN trained on real RVMs (AUC = 0.934; κ = 0.701). Real and synthetic RVMs overlapped, by plus disease diagnosis, on the UMAP manifold, showing that synthetic images spanned the disease severity spectrum. Fréchet inception distance and Euclidean distances suggested that real and synthetic RVMs were more dissimilar to one another than real RVMs were to one another, further suggesting that synthetic RVMs were distinct from the training data with respect to privacy considerations.ConclusionsSynthetic datasets may be useful for training robust medical AI models. Furthermore, PGANs may be able to synthesize realistic data for use without protected health information concerns.
| S-EPMC9560638 | biostudies-literature
Project description:PurposeTo provide a summary of the research advances on ocular images-based artificial intelligence on systemic diseases.MethodsNarrative literature review.ResultsOcular images-based artificial intelligence has been used in a variety of systemic diseases, including endocrine, cardiovascular, neurological, renal, autoimmune, and hematological diseases, and many others. However, the studies are still at an early stage. The majority of studies have used AI only for diseases diagnosis, and the specific mechanisms linking systemic diseases to ocular images are still unclear. In addition, there are many limitations to the research, such as the number of images, the interpretability of artificial intelligence, rare diseases, and ethical and legal issues.ConclusionWhile ocular images-based artificial intelligence is widely used, the relationship between the eye and the whole body should be more clearly elucidated.
| S-EPMC10197476 | biostudies-literature
Project description:BackgroundGadolinium-based contrast agents (GBCAs) are usually employed for glioma diagnosis. However, GBCAs raise safety concerns, lead to patient discomfort and increase costs. Parametric maps offer a potential solution by enabling quantification of subtle tissue changes without GBCAs, but they are not commonly used in clinical practice due to the need for specifically targeted sequences. This work proposes to predict post-contrast T1-weighted enhancement without GBCAs from pre-contrast conventional weighted images through synthetic parametric maps computed with generative artificial intelligence (deep learning).MethodsIn this retrospective study, three datasets have been employed: (I) a proprietary dataset with 15 glioma patients (hereafter, GLIOMA dataset); (II) relaxometry maps from 5 healthy volunteers; and (III) UPenn-GBM, a public dataset with 493 glioblastoma patients. A deep learning method for synthesizing parametric maps from only two conventional weighted images is proposed. Particularly, we synthesize longitudinal relaxation time (T1), transversal relaxation time (T2), and proton density (PD) maps. The deep learning method is trained in a supervised manner with the GLIOMA dataset, which comprises weighted images and parametric maps obtained with magnetic resonance image compilation (MAGiC). Thus, MAGiC maps were used as references for the training. For testing, a leave-one-out scheme is followed. Finally, the synthesized maps are employed to predict T1-weighted enhancement without GBCAs. Our results are compared with those obtained by MAGiC; specifically, both the maps obtained with MAGiC and the synthesized maps are used to distinguish between healthy and abnormal tissue (ABN) and, particularly, tissues with and without T1-weighted enhancement. The generalization capability of the method was also tested on two additional datasets (healthy volunteers and the UPenn-GBM).ResultsParametric maps synthesized with deep learning obtained similar performance compared to MAGiC for discriminating normal from ABN (sensitivities: 88.37% vs. 89.35%) and tissue with and without T1-weighted enhancement (sensitivities: 93.26% vs. 87.29%) on the GLIOMA dataset. These values were comparable to those obtained on UPenn-GBM (sensitivities of 91.23% and 81.04% for each classification).ConclusionsOur results suggest the feasibility to predict T1-weighted-enhanced tissues from pre-contrast conventional weighted images using deep learning for the synthesis of parametric maps.
| S-EPMC11744120 | biostudies-literature
Project description: Not available
| S-EPMC11581642 | biostudies-literature
Project description:ImportanceThe emergence and promise of generative artificial intelligence (AI) represent a turning point for health care. Rigorous evaluation of generative AI deployment in clinical practice is needed to inform strategic decision-making.ObjectiveTo evaluate the implementation of a large language model used to draft responses to patient messages in the electronic inbox.Design, setting, and participantsA 5-week, prospective, single-group quality improvement study was conducted from July 10 through August 13, 2023, at a single academic medical center (Stanford Health Care). All attending physicians, advanced practice practitioners, clinic nurses, and clinical pharmacists from the Divisions of Primary Care and Gastroenterology and Hepatology were enrolled in the pilot.InterventionDraft replies to patient portal messages generated by a Health Insurance Portability and Accountability Act-compliant electronic health record-integrated large language model.Main outcomes and measuresThe primary outcome was AI-generated draft reply utilization as a percentage of total patient message replies. Secondary outcomes included changes in time measures and clinician experience as assessed by survey.ResultsA total of 197 clinicians were enrolled in the pilot; 35 clinicians who were prepilot beta users, out of office, or not tied to a specific ambulatory clinic were excluded, leaving 162 clinicians included in the analysis. The survey analysis cohort consisted of 73 participants (45.1%) who completed both the presurvey and postsurvey. In gastroenterology and hepatology, there were 58 physicians and APPs and 10 nurses. In primary care, there were 83 physicians and APPs, 4 nurses, and 8 clinical pharmacists. The mean AI-generated draft response utilization rate across clinicians was 20%. There was no change in reply action time, write time, or read time between the prepilot and pilot periods. There were statistically significant reductions in the 4-item physician task load score derivative (mean [SD], 61.31 [17.23] presurvey vs 47.26 [17.11] postsurvey; paired difference, -13.87; 95% CI, -17.38 to -9.50; P < .001) and work exhaustion scores (mean [SD], 1.95 [0.79] presurvey vs 1.62 [0.68] postsurvey; paired difference, -0.33; 95% CI, -0.50 to -0.17; P < .001).Conclusions and relevanceIn this quality improvement study of an early implementation of generative AI, there was notable adoption, usability, and improvement in assessments of burden and burnout. There was no improvement in time. Further code-to-bedside testing is needed to guide future development and organizational strategy.
| S-EPMC10955355 | biostudies-literature
Project description: Not available
| S-EPMC6710912 | biostudies-literature
Project description:Synthetic biology plays a pivotal role in improving crop traits and increasing bioproduction through the use of engineering principles that purposefully modify plants through "design, build, test, and learn" cycles, ultimately resulting in improved bioproduction based on an input genetic circuit (DNA, RNA, and proteins). Crop synthetic biology is a new tool that uses circular principles to redesign and create innovative biological components, devices, and systems to enhance yields, nutrient absorption, resilience, and nutritional quality. In the digital age, artificial intelligence (AI) has demonstrated great strengths in design and learning. The application of AI has become an irreversible trend, with particularly remarkable potential for use in crop breeding. However, there has not yet been a systematic review of AI-driven synthetic biology pathways for plant engineering. In this review, we explore the fundamental engineering principles used in crop synthetic biology and their applications for crop improvement. We discuss approaches to genetic circuit design, including gene editing, synthetic nucleic acid and protein technologies, multi-omics analysis, genomic selection, directed protein engineering, and AI. We then outline strategies for the development of crops with higher photosynthetic efficiency, reshaped plant architecture, modified metabolic pathways, and improved environmental adaptability and nutrient absorption; the establishment of trait networks; and the construction of crop factories. We propose the development of SMART (self-monitoring, adapted, and responsive technology) crops through AI-empowered synthetic biotechnology. Finally, we address challenges associated with the development of synthetic biology and offer potential solutions for crop improvement.
| S-EPMC11897457 | biostudies-literature