PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “computer vision”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources
PubMed1992

Initial results for automated computational modeling of patient-specific electromagnetic hyperthermia.

Developments in finite-difference time-domain (FD-TD) computational modeling of Maxwell's equations, super-computer technology, and computed tomography (CT) imagery open the possibility of accurate numerical simulation of electromagnetic (EM) wave interactions with specific, complex, biological tissue structures. One application of this technology is in the area of treatment planning for EM hyperthermia. In this paper, we report the first highly automated CT image segmentation and interpolation scheme applied to model patient-specific EM hyperthermia. This novel system is based on sophisticated tools from the artificial intelligence, computer vision, and computer graphics disciplines. It permits CT-based patient-specific hyperthermia models to be constructed without tedious manual contouring on digitizing pads or CRT screens. The system permits in principle near real-time assistance in hyperthermia treatment planning. We apply this system to interpret actual patient CT data, reconstructing a 3-D model of the human thigh from a collection of 29 serial CT images at 10 mm intervals. Then, using FD-TD, we obtain 2-D and 3-D models of EM hyperthermia of this thigh due to a waveguide applicator. We find that different results are obtained from the 2-D and 3-D models, and conclude that full 3-D tissue models are required for future clinical usage.

Computer Simulation↗
PubMed1992

A man-machine vision interface for sensing the environment.

This study describes a computer vision approach for sensing the environment with the intent of helping people with a visual impairment. The principal goal in applying computer vision is to exploit, in an optimal fashion, the information acquired by the camera(s) to yield useful descriptions of the viewed environment. The objective is to seek efficient and reliable guidance cues in order to improve the mobility needs of individuals with a visual impairment. In this research direction, the following problems are identified and addressed: 1) the vision system design; 2) establishment of the mapping principles between the two-dimensional (2-D) camera images and the three-dimensional (3-D) real world; 3) development of appropriate imaging techniques for the interpretation of the 2-D images; and, 4) establishment of a communication link between the vision system and the user. The soundness of this research direction is assessed by means of a theoretical framework and experimental evaluations.

Algorithms↗
PubMed1992

Potential usefulness of computerized nodule detection in screening programs for lung cancer.

RATIONALE AND OBJECTIVE: To alert radiologists to possible nodule locations and subsequently to reduce the number of false-negative diagnoses, the authors are developing a computer-aided diagnostic (CAD) scheme for the detection of lung nodules in digital chest images. METHODS: A computer-vision scheme was applied to photofluorographic films obtained in a mass survey for detection of asymptomatic lung cancer in Japan. Ninety-five patients with abnormal test results who had primary and metastatic lung cancers and 103 patients with normal test results were included. RESULTS: The sensitivity of the computer output was comparable with that of physicians in this mass survey (62%). The computer detected approximately 40% of all nodules missed in the mass survey, but missed 17 true-positive results identified in the mass survey. The CAD scheme produced an average of 15 false-positive findings per image. CONCLUSION: If the number of false-positive results can be significantly reduced, computer-vision schemes such as this may have a role in lung cancer screening programs.

False Positive Reactions↗
PubMed2026

Spectral Transforms as a Tool to Optimize Digital Phenotyping in Biological Images.

Modern livestock breeding has mastered genotyping. Genome-wide association studies, genomic selection, and SNP arrays enable genetic merit prediction at lower cost. However, phenotyping remains the bottleneck, as manual measurement is slow, expensive, subjective, and unable to capture spatial or temporal trait organization. Digital phenotyping via artificial intelligence could resolve this, but deep learning requires thousands of labelled examples, impractical when phenotyping cost itself limits datasets to hundreds of individuals. This creates a paradox: AI could accelerate phenotyping but requires large numbers of samples to train the models. Here, we demonstrate that integrating computer vision with machine learning offers sample-efficient digital phenotyping using eggshell colour as a model system. Rather than learning features from scratch (deep learning), we engineer physically motivated features via Wavelet transforms that decompose images into multi-scale spatial components. Wavelet features captured 14.2 percentage points more variance (R2&#x2009;=&#x2009;0.976 vs. 0.834, p&#x2009;<&#x2009;0.001) than standard colorimetry, with 50% better sample efficiency (achieving at n&#x2009;=&#x2009;60 what colorimetry required n&#x2009;=&#x2009;120). Variance decomposition revealed 77% of discriminative capacity derives from spatial patterns (bands, spots, gradients) invisible to scalar averages. Additionally, we identified "cryptic phenotypes" (3.3%) where spatial patterns contradicted average colour, cases where colorimeters failed but Wavelets succeeded. The underlying principle-that spatial decomposition can recover organizational information lost by scalar averaging-may be applicable to other traits with spatial or temporal structure, such as marbling, dermatitis, or pigmentation rhythms, although whether comparable performance gains would be observed remains to be tested empirically. Hence, for breeding programs implementing genomic selection, computer vision-based digital phenotyping captures complex trait variation without massive training datasets, addressing the bottleneck that increasingly limits genetic progress as genotyping becomes trivial.

Wavelet transform↗
PubMed2026

AI echo INSIGHT study: A prospective blinded randomized trial of artificial intelligence echocardiogram interpretation.

BACKGROUND: Transthoracic echocardiography (TTE) is the most commonly performed cardiac imaging modality with over 30 million studies annually. Demand for timely expert interpretation continues to outpace capacity, creating diagnostic delays and inter-observer variability that impact patient care. Recent research has suggested computer vision artificial intelligence (AI) models can generate accurate preliminary comprehensive TTE reports, however, prospective evaluation is needed to determine whether AI-assisted TTE interpretation can improve clinician efficiency while preserving diagnostic accuracy. METHODS: AI ECHO INSIGHT is a prospective randomized blinded clinical trial conducted at Kaiser Permanente Northern California that will evaluate 1200 historical TTE studies (1000 consecutive unselected studies plus 200 with moderate or greater valvular disease) interpreted using three workflows: (1) AI-generated preliminary report finalized by a blinded cardiologist (AI-assisted); (2) cardiologist-generated preliminary report finalized by a blinded cardiologist (cardiologist-assisted); and (3) sonographer-generated preliminary report finalized by a blinded cardiologist (sonographer-assisted). The primary outcome is the rate of substantial change between preliminary and final reports, comparing the AI-assisted workflow to the pooled cardiologist-assisted and sonographer-assisted workflows. Secondary outcomes include cardiologist interpretation time for report finalization, superiority testing for diagnostic accuracy, and reporting consistency. CONCLUSION: AI ECHO INSIGHT is a prospective randomized blinded clinical trial evaluating the clinical impact of AI-assisted TTE interpretation on diagnostic accuracy, cardiologist efficiency, and reporting consistency in real-world echocardiography workflows. TRIAL REGISTRATION: ClinicalTrials.gov registration number NCT07229300.

Humans↗
PubMed1992

Artificial vision approach to the understanding of heart motion.

To overcome the major drawbacks of conventional descriptive methods, we have developed a computer vision approach to aid understanding of heart motion from a series of sequential X-ray images. The computation is addressed of local descriptors of the heart pumping function from ventricular contours. Physical constraints are exploited such as spatial smoothness of the displacement field and shape correspondence between ventricular boundaries during the beat. A computational method is proposed for the estimation of the displacement field of the left ventricular boundary. Moreover, the spatial arrangement of the estimated motion field is rendered explicit so that it may be utilized in the medical clinic (or for high-level symbolic processing). This is achieved using a grouping criterion which allows the clustering of contiguous points of the left ventricular outline into curve segments which have homogeneous motion properties.

Algorithms↗
PubMed2025

The role of chromatin state in intron retention: A case study in leveraging large scale deep learning models.

Complex deep learning models trained on very large datasets have become key enabling tools for current research in natural language processing and computer vision. By providing pre-trained models that can be fine-tuned for specific applications, they enable researchers to create accurate models with minimal effort and computational resources. Large scale genomics deep learning models come in two flavors: the first are large language models of DNA sequences trained in a self-supervised fashion, similar to the corresponding natural language models; the second are supervised learning models that leverage large scale genomics datasets from ENCODE and other sources. We argue that these models are the equivalent of foundation models in natural language processing in their utility, as they encode within them chromatin state in its different aspects, providing useful representations that allow quick deployment of accurate models of gene regulation. We demonstrate this premise by leveraging the recently created Sei model to develop simple, interpretable models of intron retention, and demonstrate their advantage over models based on the DNA language model DNABERT-2. Our work also demonstrates the impact of chromatin state on the regulation of intron retention. Using representations learned by Sei, our model is able to discover the involvement of transcription factors and chromatin marks in regulating intron retention, providing better accuracy than a recently published custom model developed for this purpose.

Deep Learning↗
PubMed1979

Cerebral color blindness: an acquired defect in hue discrimination.

In contrast to the traditional view that striate visual cortex (area 17) is surrounded by two homogeneous cortical areas (areas 18 and 19), recent studies have shown that mammalian extrastriate visual cortex contains several anatomically and functionally distinct subregions. One such region, the V-4 complex of the rhesus monkey, is highly specialized for the analysis of color information, suggesting that a lesion in a homologous region might produce a defect in color vision while sparing other visual functions. We have studied a patient whose clinical syndrome supports this suggestion: a 44-year-old man with normal color vision suffered two cerebral infarctions that produced first a right and then a left superior homonymous quadrantanopia and also caused prosopagnosia, topographical disorientation, and severely impaired color vision. Computed tomography demonstrated extensive lesions in both inferior occipital lobes in the territories of the lateral branches of the posterior cerebral arteries, involving the lingual and medial occipitotemporal gyri bilaterally; these gyri contain the inferior portion of striate cortex and segments of extrastriate visual cortex. The patient had no difficulty in giving the correct color names associated with common objects presented either verbally or in outline drawings. Standardized testing with the Farnsworth-Munsell 100-hue test, the Nagel anomaloscope, and a method that tests for just-noticeable differences between monochromatic stimuli all showed that the patient's ability to distinguish one color from another was markedly imparied but not totally absent. In contrast, visual acuity, reading, visually guided eye movements, and stereopsis were normal. Cells in the V-4 complex of monkey extrastriate cortex are highly specialized for distinguishing one color from another; the hue discrimination deficit that was demonstrated in this patient with cerebral color blindness indicates that a region or regions with similar function has been damaged.

Adult↗
PubMed2026

The Role of Artificial Intelligence Combined With Digital Cholangioscopy for Indeterminant and Malignant Biliary Strictures: A Systematic Review and Meta-analysis.

BACKGROUND: Current endoscopic retrograde cholangiopancreatography (ERCP) and cholangioscopic-based diagnostic sampling for indeterminant biliary strictures remain suboptimal. Artificial intelligence (AI)-based algorithms by means of computer vision in machine learning have been applied to cholangioscopy in an effort to improve diagnostic yield. The aim of this study was to perform a systematic review and meta-analysis to evaluate the diagnostic performance of AI-based diagnostic performance of AI-associated cholangioscopic diagnosis of indeterminant or malignant biliary strictures. METHODS: Individualized searches were developed in accordance with PRISMA and MOOSE guidelines, and meta-analysis according to Cochrane Diagnostic Test Accuracy working group methodology. A bivariate model was used to compute pooled sensitivity and specificity, likelihood ratio, diagnostic odds ratio, and summary receiver operating characteristics curve (SROC). RESULTS: Five studies (n=675 lesions; a total of 2,685,674 cholangioscopic images) were included. All but one study analyzed a deep learning AI-based system using a convoluted neural network (CNN) with an average image processing speed of 30 to 60 frames per second. The pooled sensitivity and specificity were 95% (95% CI: 85-98) and 88% (95% CI: 76-94), with a diagnostic accuracy (SROC) of 97% (95% CI: 95-98). Sensitivity analysis of CNN studies (4 studies, 538 patients) demonstrated a pooled sensitivity, specificity, and accuracy (SROC) of 95% (95% CI: 82-99), 88% (95% CI: 72-95), and 97% (95% CI: 95-98), respectively. CONCLUSIONS: Artificial intelligence-based machine learning of cholangioscopy images appears to be a promising modality for the diagnosis of indeterminant and malignant biliary strictures.

Humans↗
PubMedDate not supplied

Improvement in specificity of ultrasonography for diagnosis of breast tumors by means of artificial intelligence.

A set of ultrasonograms of lesions from 200 patients between the ages of 14 and 93 years who underwent mammography followed by ultrasonographic examination and excisional biopsy has been studied with computer vision techniques to improve the ultrasonographic specificity of the diagnosis. Selected features representing the texture of the lesion were calculated and then classified by an artificial neural network. This network was biased toward correctly classifying all the malignant cases at the expense of some misclassification of the benign cases. The network diagnosed the malignant cases with 100% sensitivity and 40% specificity (compared with 0% specificity for the radiologists diagnosing the same set of cases in the breast imaging setting), and tests performed with a leave-one-out technique indicate that the network will generalize well to new cases. This suggests that methods based on neural network classification of texture features show promise for potentially decreasing the number of unnecessary biopsies by a significant amount in patients with sonographically identifiable lesions.

Adolescent↗
PubMed2026

Automated CEAP Classification of Venous Duplex Reports Using Multimodal Artificial Intelligence.

OBJECTIVE: To develop and internally validate a prototype multimodal artificial intelligence system for automated CEAP (Clinical, Etiological, Anatomical and Pathophysiological) classification of venous duplex ultrasound (VDUS) reports, integrating natural language processing of free-text components with computer vision analysis of hand-drawn anatomical diagrams. METHODS: Single centre retrospective observational study using routinely collected clinical data. One thousand consecutive venous duplex ultrasound reports from Cambridge University Hospitals NHS Foundation Trust, UK (July 2024 - May 2025) were labelled according to the CEAP classification, excluding the Etiological component, which could not be reliably determined from duplex reports alone. Transfer learning was applied using ClinicalBERT for text and MobileNetV3 for diagrammatic data. Clinical classes were predicted from request line text. Text- and image-based pathophysiological models were developed for four anatomical territories (Great Saphenous Vein, Small Saphenous Vein, Deep system, Perforators), combined using late fusion with probability averaging. RESULTS: The clinical CEAP model achieved accuracy of 0.91, macro-F1 of 0.82, and macro-AUC of 0.98. Pathophysiological prediction varied, with text models broadly outperforming image models. Fusion yielded heterogeneous benefits, improving SSV performance but reducing Deep system accuracy. The performance of the final pathophysiological CEAP fusion models varied across anatomical territories: accuracy ranged from 0.70-0.92 and macro-AUC from 0.80-0.92. CONCLUSION: This study demonstrates the feasibility of automated CEAP classification from VDUS reports. Despite class imbalance affecting minority class predictions, the strong discriminatory performance validates this multimodal ML model for extracting clinically meaningful information from real-world data. This approach offers potential, pending external validation, to streamline vascular services through automated triage and guideline-compliant decision making.

Artificial intelligence↗
PubMed2026

Effectiveness of an AI-based home exercise app for rehabilitation of rotator cuff-related shoulder pain: A randomized controlled trial.

BACKGROUND: Rotator cuff-related shoulder pain contributes to disability and healthcare use. Although therapeutic exercise is first-line treatment, limited supervision and adherence may reduce its effectiveness; digital rehabilitation with real-time feedback may address these limitations. OBJECTIVES: To evaluate the effectiveness of adding a digital rehabilitation program to standard physiotherapy on pain, function, fear-avoidance beliefs, and healthcare utilization. DESIGN: Single-center, assessor-blinded, randomized controlled trial with two parallel groups. METHOD: Forty-six adults (mean age 59 years) with rotator cuff-related shoulder pain were randomized to 12 weeks of conventional physiotherapy or physiotherapy plus an AI-based digital rehabilitation program using computer vision for real-time feedback and performance monitoring. Outcomes were assessed at baseline and at 2, 4, and 12 weeks. Pain intensity (NPRS) was primary outcome; secondary outcomes included upper limb function (QuickDASH), fear-avoidance beliefs (FABQ), and post-intervention healthcare utilization. Analyses followed an intention-to-treat approach. RESULTS: Pain reduction exceeded the MCID (1.3) at 4 and 12 weeks. Between-group differences favoured the intervention at Weeks 2 and 4 (MD -0.7; 95% CI -1.13 to -0.14 and MD -1.01; 95% CI -1.8 to -0.2, respectively). Upper limb function improved more at Week 4 (MD -7.3; 95% CI -12.3 to -2.2). FABQ scores decreased more at Week 12 (MD -7.6; 95% CI -14 to -0.5). Fewer participants in the experimental group required post-intervention healthcare (3 vs 10; p&#x202f;=&#x202f;0.02). CONCLUSION: Adding AI-based home exercise app to conventional treatment improve pain and may improve function and reduce healthcare utilization in rotator cuff-related shoulder pain.

Humans↗
PubMed2026

Repeated low-level red-light therapy for improving asthenopic symptoms and accommodation in presbyopia.

BACKGROUND: To assess the short-term effectiveness of repeated low-level red light (RLRL) therapy in relieving asthenopia and enhancing accommodation in presbyopia. METHODS: This randomized, parallel-group, double-masked clinical trial enrolled adults with presbyopia and self-reported asthenopia. Participants were allocated using computer-generated randomization and randomly assigned at a 1:1 ratio to RLRL or sham groups. Blinding included participants, examiners, assessors, and statisticians. The primary outcome was the change from baseline in the Computer Vision Syndrome Questionnaire (CVS-Q) score at day 31. Secondary outcomes were the change in accommodative amplitude (AA), Near Activity Visual Questionnaire (NAVQ) score, habitual near visual acuity, near-addition power, accommodative facility, positive and negative relative accommodation, binocular cross-cylinder response, and accommodative convergence-to-accommodation ratio. Continuous outcomes were analyzed using linear mixed-effects models. RESULTS: Sixty-four of 66 randomized participants (aged 41-62&#x2009;years) completed the 1-month trial. At day 31, RLRL showed greater improvement than sham in CVS-Q score (adjusted mean difference, -1.75 points; 95% CI, -3.10 to -0.39), binocular AA (1.09 D; 95% CI, 0.37 to 1.82), and NAVQ score (-8.07 points; 95% CI, -14.17 to -1.97). The effect on AA was most pronounced in a subgroup of eyes with baseline amplitude >2.0&#x2009;D (adjusted mean difference 1.33&#x2009;D; 95% CI 0.32-2.34). Other measures did not differ between groups at each visit. No treatment-related adverse events were reported. Adherence was similar between groups (mean compliance: 98.2% vs 97.5%). CONCLUSIONS: Short-term treatment with RLRL significantly reduced asthenopic symptoms and improved accommodative amplitude in individuals with presbyopia.Trial registration: NCT06745661 (registered December 8, 2024).

Humans↗
PubMed1976

Bicycle-pedal model for the first step in the vision process.

Computer simulation of the molecular dynamics of retinal during its photoisomerisation inside a restrictive active site gives a detailed model for the sequence of events in the first step of the vision process. It is proposed that the prelumirhodopsin intermediate contains a strained all-trans retinal molecule produced directly and rapidly from the 11-cis, 12-s-trans conformation in rhodopsin by a bicycle-pedal isomerisation. The model reproduces the main experimental observations and explains how the protein makes the photoisomerisation path unique.

Binding Sites↗
PubMed1992

Computational aspects of motion perception in natural and artificial vision systems.

In this paper a computational scheme for motion perception in artificial and natural vision systems is described. The scheme is motivated by a mathematical analysis in which first-order spatial properties of optical flow, such as singular points and elementary components of optical flow, are shown to be salient features for the computation and analysis of visual motion. The fact that different methods for the computation of optical flow produce similar results is explained in terms of the simple spatial structure of the image motion of rigid bodies. Singular points and elementary flow components are used to compute motion parameters, such as time-to-collision and angular velocity, and also to segment the visual field into areas which correspond to different motions. Then a number of biological implications are discussed. Electrophysiological findings suggest that the brain perceives visual motion by detecting and analysing optical flow components. However, the cortical neurons, which seem to detect elementary flow components, are not able to extract these components from more complex flows. A simple model for the organization of the receptive field of these cells, which is consistent with anatomical and electrophysiological data, is described at the end of the paper.

Artificial Intelligence↗