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 55 records · Page 3Linked to original sources
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 = 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↗
PubMed1990

A network that learns to recognize three-dimensional objects.

The visual recognition of three-dimensional (3-D) objects on the basis of their shape poses at least two difficult problems. First, there is the problem of variable illumination, which can be addressed by working with relatively stable features such as intensity edges rather than the raw intensity images. Second, there is the problem of the initially unknown pose of the object relative to the viewer. In one approach to this problem, a hypothesis is first made about the viewpoint, then the appearance of a model object from such a viewpoint is computed and compared with the actual image. Such recognition schemes generally employ 3-D models of objects, but the automatic learning of 3-D models is itself a difficult problem. To address this problem in computational vision, we have developed a scheme, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view. A network equivalent to this scheme will thus 'recognize' the object on which it was trained from any viewpoint.

Artificial Intelligence↗
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 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 D (adjusted mean difference 1.33 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↗
PubMed1991

Quantitative light microscopy of combined perfusion and freezing processes.

The rational design of cryopreservation protocols for living tissues demands an understanding of the mechanisms of mass transport between cells and their environment throughout the entire process. We have developed a new microscope stage to enable a specimen to be viewed continuously during a preservation protocol, including the addition and removal of cryoprotective additives and freezing and thawing. The specimen is contained in a sealed chamber having inlet and outlet ports for admitting and collecting perfusate solution, the entire volume of which may be exchanged with a time constant of 1-5 s, depending on the solution viscosity. The temperature of the active area of the stage is regulated by the standard techniques of convection cryomicroscopy over a range in excess of 50 to -100 degrees C. A series of experiments has been performed on this system to measure the osmotic behaviour of rat pancreas islets during the addition and removal of dimethyl sulphoxide at temperatures between 25 and -10 degrees C. The technique involves mounting a single islet onto the low-temperature stage so that it is constrained from lateral movement by a specially sized mesh. Both the system temperature and chemical composition are monitored and controlled simultaneously and independently; as a consequence, virtually any defined cryopreservation protocol may be imposed on the specimen. For making permeability measurements, the bathing medium of the specimen may be changed very rapidly to produce a defined osmotic stress. Alternatively, the specimen may be subcooled to a specific and fixed subzero temperature, at which point ice is nucleated in the extracellular medium, creating a near instantaneous change in composition. The temporal alteration in specimen size is monitored by video microscopy and quantified by computer vision analysis methods. One of several mass transfer models is fitted to the data to estimate the membrane permeability based on the assumption of either transport dominated by the movement of water or simultaneous coupled flows of water and cryoprotective agent.

Animals↗
PubMed1989

Cell locomotion as shape change.

Although a great deal of understanding of blood cell locomotion can be derived from the evaluation of cell paths, cell movement may also be examined by evaluating how the cell changes shape as it moves. In order to understand how a cell changes shape, it is first necessary to be able to quantitatively describe cell shape and cell shape change. A review of current work in computer vision and shape description as applied to blood cells is presented.

Biophysical Phenomena↗
PubMed1986

Volume flow measurement of pulsatile flow by digitised cine angiography.

The validation, by phantom experiments, of a method of measuring volumetric, pulsatile blood flow in vessels of about 4 mm calibre is described. 'Instantaneous' as well as integrated flow is obtained from cine angiograms by digitisation of the images and densitometric analysis in an advanced computer vision analysis system. From 48 frames per second cine, pulsatile flow at any moment between 0 and about 400 ml/min was calculated within about 10 per cent of the electromagnetic flow meter reading. Further improvement is expected. It is proposed to advance to 3D and have the methodology available for clinical use in due course.

Angiography, Digital Subtraction↗
PubMed1988

Giant serpentine aneurysm in a long-term hemodialysis patient.

A long-term hemodialysis patient with a giant intracranial vascular channel, which has been called a giant serpentine aneurysm, is presented. A 50-year-old man with an eight-year history of hemodialysis treatment was admitted because of headache, nausea and double vision. Computed tomographic scans and nuclear magnetic resonance revealed intracranial abnormal shadow. The left vertebral arteriography showed that the distal portion of the left vertebral artery was dilated to 17 mm in diameter. The basilar artery showed a large tortuous vascular channel and globular aneurysms over 25 mm in diameter. This giant serpentine aneurysm is a rather rare disease. To our knowledge, it has not been reported as a complication in a hemodialysis patient, although fourteen cases have been reported in the literature. In our case, several conditions such as long-term hypertension, hyperlipidemia, hypercalcemia, atherosclerosis and abnormal blood flow due to arteriovenous fistula for hemodialysis treatment might be considered to play a role in the formation of the giant serpentine aneurysms.

Basilar Artery↗
PubMed1988

Color vision testing with a computer graphics system: preliminary results.

We report a method for computer enhancement of color vision tests. In our graphics system 256 colors are selected from a much larger range and displayed on a screen divided into 768 x 288 pixels. Eight-bit digital-to-analogue converters drive a high quality monitor with separate inputs to the red, green, and blue amplifiers and calibrated gun chromaticities. The graphics are controlled by a PASCAL program written for a personal computer, which calculates the values of the red, green, and blue signals and specifies them in Commité Internationale d'Eclairage X, Y, and Z fundamentals, so changes in chrominance occur without changes in luminance. The system for measuring color contrast thresholds with gratings is more than adequate in normal observers. In patients with mild retinal damage in whom other tests of visual function are normal, this method of testing color vision shows specific increases in contrast thresholds along tritan color-confusion lines. By the time the Hardy-Rand-Rittler and Farnsworth-Munsell 100-hue tests disclose abnormalities, gross defects in color contrast threshold can be seen with our system.

Adult↗
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↗
PubMed1985

Application of a computable model of human spatial vision to phase discrimination.

We have used a computable model of human spatial vision to make predictions for phase-discrimination experiments. This model is being developed to deal with a broad range of problems in vision and was not specifically formulated to deal with phase discrimination. In the model, cross correlation of the stimuli with an array of sensors produces feature vectors that are operated on by a position-uncertain ideal observer to simulate detection and discrimination experiments. In this report the stimuli are compound sinusoidal gratings composed of a fundamental and a higher-frequency component added in various phases. We compare model predictions with three key results from the literature: the effect of the contrast of the fundamental on phase discrimination, threshold phase difference as a function of the fundamental frequency, and the contrast required for phase discrimination as a function of the frequency ratio of the two grating components. In the first two cases, the predictions capture the main features of the data, although quantitative discrepancies remain. In the third case, the model fails, and this failure suggests additional restrictions on the combination of information across sensors.

Discrimination Learning↗
PubMedDate not supplied

A computational approach to medical imaging.

Notwithstanding the progress in medical imaging by means of computer-based techniques, several problems still remain unsolved in this field. In particular, a unified approach for the treatment of biological complexity and variability is lacking. Moreover, perceptive and cognitive aspects of medical vision play an important role in a computational approach to medical imaging and must be carefully considered. The recent developments of Computer Vision and Artificial Intelligence suggest that such a computational approach is feasible. As a consequence, symbolic representations of the clinical information contained in the images as well as adequate processing techniques are necessary. In this way the treatment of uncertainty and the qualitative analysis are made possible. Moreover, due to the intrinsic homogeneity of symbolic representations, the comparison of different image sources, signals and clinical data is attainable. In the paper, the basic principles of Computer Vision are summarized and the need of a specific computational theory for medical vision is emphasized. Afterwards, the main characteristics of integrated systems for computational imaging in medicine, are described. Some examples relative to the imaging of the cardiovascular system are also given. Although the development of artificial vision systems in biomedicine is still an area of research, very promising perspectives are opened by a computational approach.

Artificial Intelligence↗