Dataset Information

Quantifying frequency content in cross-sectional retinal scans of diabetics vs. controls.

ABSTRACT:

Purpose

To examine subtle differences in the structure of diabetic vs. control retinas.

Methods

Spectral-domain optical coherence tomography (SD-OCT) images were compared for the retinas of 33 diabetic subjects who did not have clinical evidence of diabetic macular edema and age-matched controls, with central macular thicknesses of 275 and 276 microns, respectively. Cross-sectional retinal images through the fovea, called B-scans, were analyzed for spatial frequency content. The B-scans were processed to remove and smooth the portions of the retinal image not within regions of interest in the retina. The remaining retinal images were then quantified using a Fast Fourier Transform (FFT) approach that provided amplitude as a function of spatial frequency.

Results

The FFT analysis showed that diabetic retinas had spatial frequency content with significantly higher power compared to control retinas particularly for a deeper fundus layer at mid-range spatial frequencies, ranging from p = 0.0030 to 0.0497 at 16.8 to 18.2 microns/cycle. There was lower power at higher spatial frequencies, ranging from p = 0.0296 and 0.0482 at 27.4 and 29.0 microns/cycle. The range of mid-range frequencies corresponds to the sizes of small blood vessel abnormalities and hard exudates. Retinal thickness did not differ between the two groups.

Conclusions

Diabetic retinas, although not thicker than controls, had subtle but quantifiable pattern changes in SD-OCT images particularly in deeper fundus layers. The size range and distribution of this pattern in diabetic eyes were consistent with small blood vessel abnormalities and leakage of lipid and fluid. Feature-based biomarkers may augment retinal thickness criteria for management of diabetic eye complications, and may detect early changes.

SUBMITTER: Papay JA

PROVIDER: S-EPMC8213050 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Retinal imaging helps to detect retinal and cardiovascular abnormalities. Among these abnormalities, Diabetic Macular Edema (DME) and Age Related Macular Degeneration (AMD), both are frequent retinal degenerative diseases leading to blindness. Content based retinal OCT scan retrieval process makes use of characteristic features to retrieve similar Optical Coherent Tomography (OCT) scans, index-wise, from a database with minimal human intervention. A number of existing methods take care of segmentation and identification of retinal landmarks and pathologies from OCT volumes. As per the literature survey, till date, no papers are there which deal with the retrieval of retinal OCT scans. In this work, we propose a retrieval system for retinal OCT scans which extracts feature maps of both query and database samples from the layer of deep convolutional neural network and compares for their similarity. The Twin network comparison approach exploits deep features without the resource, space and computation exhaustive network training phase. Most of the techniques involving deep network implementation suffer from the drawbacks of data augmentation and resizing. These requirements have been eliminated automatically as part of the Twin network implementation procedure. The system successfully retrieves retinas with similar symptoms from the database of differently affected and unaffected OCT scans. We evaluated different variations of retrieval performances like AMD-Normal, DME-Normal, AMD-DME, AMD-DME-Normal, etc. Execution time optimization has also been achieved as the network used is comparatively shallow and network training is not required. The system retrieves similar scans from a dataset of abnormal and normal OCT scans with a mean average precision of 0.7571 and mean reciprocal rank of 0.9050. Considering all possible variations of retrieval, we achieved overall mean average precision and mean reciprocal rank of 0.631167 and 0.829607, respectively which are also quite notable with rank thresholds of 3, 5 and 7. Experiments show that the method is noticeably successful in retrieving similar OCT volumes. Per image mean average retrieval time is 8.3 sec. Automatic retrieval of retinal OCT volumes for the presence of a particular ailment can help ophthalmologists in the mass screening process. Supplementary Information The online version contains supplementary material available at 10.1007/s12046-021-01701-5.

Project description:Surgeons usually witness only the limb-threatening stages of infected, closed pedal puncture wounds in diabetics. Given that this catastrophic outcome often represents failure of conservative management of pre-infected wounds, some suggest consideration of invasive intervention (coring or laying-open) for pre-infected wounds in hope of preventing contamination from evolving into infection, there being no evidence based guidelines. However, an invasive pre-emptive approach is only justifiable if the probability of progression to catastrophic infection is very high. Literature search revealed no prior studies on the natural history of closed pedal puncture wounds in diabetics.A survey was conducted via an interviewer-administered questionnaire on 198 adult diabetics resident in the parish of St. James, Jamaica. The sample was selected using a purposive technique designed to mirror the social gradient and residential distribution of the target population and is twice the number needed to detect a prevalence of puncture wounds of 14% with a range of 7-21% in a random sample of the estimated adult diabetic population.The prevalence of a history of at least one closed pedal puncture wound since diagnosis of diabetes was 25.8% (CI; 19.6-31.9%). The only modifiable variable associated at the 5% level of significance with risk of pedal puncture wound, after adjustment by multivariable logistic regression, was site of interview/paying status, a variable substantially reflective of income more so than quality-of-care.Of 77 reported episodes of closed pedal puncture wound among 51 participants, 45.4% healed without medical intervention, 27.3% healed after non-surgical treatment by a doctor and 27.3% required surgical intervention ranging from debridement to below-knee amputation. Anesthetic foot (failure to feel the puncture) and sole of the forefoot as site of puncture were the variables significantly associated with risk of requiring surgical intervention.That 72.7% of wounds healed either spontaneously or after non-surgical treatment means that routine, non-selective surgical intervention for pre-infected closed pedal puncture wounds in diabetics is not justifiable. However the subset of patients with an anesthetic foot and a wound on the sole of the forefoot should be marked for intensive surveillance and early surgical intervention if infection occurs.

Project description:Multiple sclerosis (MS) is an inflammatory disorder of the central nervous system. By combining longitudinal MRI-based brain morphometry and brain age estimation using machine learning, we tested the hypothesis that MS patients have higher brain age relative to chronological age than healthy controls (HC) and that longitudinal rate of brain aging in MS patients is associated with clinical course and severity. Seventy-six MS patients [71% females, mean age 34.8 years (range 21-49) at inclusion] were examined with brain MRI at three time points with a mean total follow up period of 4.4 years (±0.4 years). We used additional cross-sectional MRI data from 235 HC for case-control comparison. We applied a machine learning model trained on an independent set of 3,208 HC to estimate individual brain age and to calculate the difference between estimated and chronological age, termed brain age gap (BAG). We also assessed the longitudinal change rate in BAG in individuals with MS. MS patients showed significantly higher BAG (4.4 ± 6.6 years) compared to HC (Cohen's D = 0.69, p = 4.0 × 10-6). Longitudinal estimates of BAG in MS patients showed high reliability and suggested an accelerated rate of brain aging corresponding to an annual increase of 0.41 (SE = 0.15) years compared to chronological aging (p = 0.008). Multiple regression analyses revealed higher rate of brain aging in patients with more brain atrophy (Cohen's D = 0.86, p = 4.3 × 10-15) and increased white matter lesion load (WMLL) (Cohen's D = 0.55, p = 0.015). On average, patients with MS had significantly higher BAG compared to HC. Progressive brain aging in patients with MS was related to brain atrophy and increased WMLL. No significant clinical associations were found in our sample, future studies are warranted on this matter. Brain age estimation is a promising method for evaluation of subtle brain changes in MS, which is important for predicting clinical outcome and guide choice of intervention.