Automated Categorisation of Nailfold Capillaroscopy Images

2016 ◽  
pp. 134-145
Author(s):  
Niraj Doshi ◽  
Gerald Schaefer
Keyword(s):  
Early Detection ◽  
Texture Analysis ◽  
Ground Truth ◽  
Experimental Results ◽  
Nailfold Capillaroscopy ◽  
Image Region ◽  
Blood Capillaries ◽  
Non Invasive ◽  
Spectrum Disorders ◽  
Voting Strategy

Nailfold capillaroscopy (NC) is a non-invasive imaging technique employed to assess the condition of blood capillaries in the nailfold. It is particularly useful for early detection of scleroderma spectrum disorders and evaluation of Raynaud's phenomenon. While automated approaches to analysing NC images are relatively rare, they are typically based on extraction and analysis of individual capillaries from the images in order to assign a patient to one of the commonly employed scleroderma patterns. In this chapter, we present a different approach that does not rely on individual capillaries but performs interpretation in a holistic way based on information gathered from an image or a selected image region. In particular, our algorithm employs texture analysis to characterise the underlying patterns, coupled with a classification stage to first identify patterns in fingers, and then, through a voting strategy, reach a decision for a patient. Experimental results on a set of NC images with known ground truth demonstrate the efficacy of the proposed approach.

Computer-Aided Analysis of Nailfold Capillaroscopy Images

2016 ◽  
pp. 146-158
Author(s):  
Niraj Doshi ◽  
Gerald Schaefer
Keyword(s):  
Image Enhancement ◽  
Connective Tissue Diseases ◽  
Noise Removal ◽  
Nailfold Capillaroscopy ◽  
Blood Capillaries ◽  
Rule Based ◽  
Non Invasive ◽  
Computer Aided Analysis ◽  
Computer Aided ◽  
Bilateral Filters

Nailfold capillaroscopy (NC) is a non-invasive imaging technique employed to assess the condition of blood capillaries in the nailfold, and is routinely used for the detection of scleroderma spectral disorders, Raynaud's phenomenon and other connective tissue diseases. In this chapter, we present computer-aided approaches for capillary inspection, in particular focussing on the tasks of image enhancement, binarisation and skeletonisation. We evaluate the performance of a number image enhancement/noise removal techniques for NC images, as a pre-cursor to edge detection aimed at identifying capillaries. Results show that bilateral filters and enhancers provide the best overall image quality. Following noise removal, NC images typically get converted into binary form. For this purpose, we employed a difference-of-Gaussian approach before thresholding. The final stage is that of skeletonisation, which can be effectively performed using a rule-based thinning algorithm. Thus the complete imaging pipeling of pre-processing, binarisation and skeletonisation is represented in this chapter.

scholarly journals Nailfold Capillaroscopy in Systemic Diseases: Short Overview for Internal Medicine

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Alina Dima ◽  
Ioana Berza ◽  
Daniela Nicoleta Popescu ◽  
Magda Ileana Parvu
Keyword(s):  
Systemic Sclerosis ◽  
Connective Tissue ◽  
Lupus Erythematosus ◽  
Connective Tissue Diseases ◽  
Nailfold Capillaroscopy ◽  
Raynaud Phenomenon ◽  
Non Invasive ◽  
Invasive Method ◽  
Spectrum Disorders ◽  
Parallel Fashion

Abstract Nailfold capillaroscopy (NFC) is now one of the main imaging tools in systemic sclerosis and imposed over time as an easy, non-invasive method for the nailfold microvascular bed assessment. In qualitative NFC normal pattern is characterized by homogeneous, parallel fashion arrangement of the last capillaries row as well as by capillaries with hairpin or non-specific variations like tortuous and/ or crossing shape. Nailfold capillaroscopy is strongly recommended for evaluation of all patients with Raynaud phenomenon. Appearance of giant capillaries is chronologically the first finding relevant for scleroderma spectrum disorders development (systemic sclerosis, dermatomyositis, undifferentiated and mixed connective tissue disease). Collapses of the giant loops generate microhemorrhages and further capillary loss with subsequent hypoxia, and neoangiogenesis seen as ramified/ bushy capillaries. Nailfold capillaroscopy is indicated especially in systemic sclerosis, being also included in the classification criteria. Based on these major NFC pathologic findings (giant capillaries, microhemorrhages, avascularity and neoangiogenesis), three evolutive stages were described in systemic sclerosis, namely the early, active, and late scleroderma pattern. In other connective tissue diseases than those scleroderma-related, like systemic lupus erythematosus, psoriatic arthritis, or antiphospholipid syndrome, the interest for capillaroscopy is growing, but the attempts of defining specific characteristics failed until now. Besides qualitative NFC, semiquantitative and quantitative capillaroscopic assessments were proposed for more accurate evaluation. Lately, automated systems are under development. There is still need of more studies to sustain the nailfold capillaroscopy validity as diagnostic and prognostic test.

Early detection of lato sensu epilepsy: diagnostic and prognostic importance in autism spectrum disorders

2016 ◽  
Vol Ano 6 ◽  
pp. 46-50
Author(s):  
Evelyn Kuczynski
Keyword(s):  
Autism Spectrum Disorders ◽  
Early Detection ◽  
Autism Spectrum ◽  
Prognostic Importance ◽  
Spectrum Disorders

Associar autismo e epilepsia é mais que casual ou aleatório, dado que ocorre um aumento na detecção de epilepsia após a puberdade nos transtornos do espectro do autismo (TEA). Mais frequente entre os menores de 5 anos de idade e em adolescentes, a epilepsia apresenta taxas de até 70% entre os transtornos desintegrativos. Contudo, não há dados suficientes quanto à prevalência de TEA entre indivíduos com epilepsia. Os mais conservadores estabelecem que a prevalência de epilepsia nos TEA é de 1 a 2% mais alta do que na população em geral, caracterizando TEA como fator de risco para o surgimento da epilepsia. Pesquisas se beneficiaram de critérios de diagnóstico mais bem estruturados e universais para os TEA e de uma nova classificação internacional das epilepsias, com melhor identificação e estudo da epilepsia nos subgrupos de TEA. Não mais se questiona a grande associação entre os TEA e a epilepsia. Estabelecer uma relação causa/efeito para a epilepsia e os TEA é tentador. Entretanto, não há evidência de que o tratamento clínico ou cirúrgico da epilepsia modifique o prognóstico dos TEA. Estudos específicos com essa população são necessários para elucidar o real papel da epilepsia nos TEA.

A NOVEL EXTENSIVE EX-VIVO OCT DATABASE FROM MURINE MODELS OF COLORECTAL CANCER

2021 ◽  
Vol 108 (Supplement_3) ◽  
Author(s):  
J Bote ◽  
J F Ortega-Morán ◽  
C L Saratxaga ◽  
B Pagador ◽  
A Picón ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Machine Learning ◽  
Structural Information ◽  
Ex Vivo ◽  
Ground Truth ◽  
Colon Polyps ◽  
Learning Methods ◽  
Non Invasive ◽  
Machine Learning Methods ◽  
In Situ Methods

Abstract INTRODUCTION New non-invasive technologies for improving early diagnosis of colorectal cancer (CRC) are demanded by clinicians. Optical Coherence Tomography (OCT) provides sub-surface structural information and offers diagnosis capabilities of colon polyps, further improved by machine learning methods. Databases of OCT images are necessary to facilitate algorithms development and testing. MATERIALS AND METHODS A database has been acquired from rat colonic samples with a Thorlabs OCT system with 930nm centre wavelength that provides 1.2KHz A-scan rate, 7μm axial resolution in air, 4μm lateral resolution, 1.7mm imaging depth in air, 6mm x 6mm FOV, and 107dB sensitivity. The colon from anaesthetised animals has been excised and samples have been extracted and preserved for ex-vivo analysis with the OCT equipment. RESULTS This database consists of OCT 3D volumes (C-scans) and 2D images (B-scans) of murine samples from: 1) healthy tissue, for ground-truth comparison (18 samples; 66 C-scans; 17,478 B-scans); 2) hyperplastic polyps, obtained from an induced colorectal hyperplastic murine model (47 samples; 153 C-scans; 42,450 B-scans); 3) neoplastic polyps (adenomatous and adenocarcinomatous), obtained from clinically validated Pirc F344/NTac-Apcam1137 rat model (232 samples; 564 C-scans; 158,557 B-scans); and 4) unknown tissue (polyp adjacent, presumably healthy) (98 samples; 157 C-scans; 42,070 B-scans). CONCLUSIONS A novel extensive ex-vivo OCT database of murine CRC model has been obtained and will be openly published for the research community. It can be used for classification/segmentation machine learning methods, for correlation between OCT features and histopathological structures, and for developing new non-invasive in-situ methods of diagnosis of colorectal cancer.

scholarly journals Exploring personalized postoperative non-invasive tissue oximetry in DIEP flap breast reconstruction

2021 ◽  
Author(s):  
Anouk A. M. A. Lindelauf ◽  
Nousjka P. A. Vranken ◽  
Rutger M. Schols ◽  
Esther A. C. Bouman ◽  
Patrick W. Weerwind ◽  
...  
Keyword(s):  
Early Detection ◽  
Breast Reconstruction ◽  
Near Infrared ◽  
Diep Flap ◽  
Baseline Measurement ◽  
Flap Surgery ◽  
Level Of Evidence ◽  
Non Invasive ◽  
Vascular Compromise ◽  
Tissue Oximetry

Abstract Early detection of vascular compromise after autologous breast reconstruction is crucial to enable timely re-exploration for flap salvage. Several studies proposed non-invasive tissue oximetry for early identification of ischemia of deep inferior epigastric perforator (DIEP) flaps. The present study aimed to explore the utility of non-invasive tissue oximetry following DIEP flap surgery using a personalized oxygenation threshold. Methods Patients undergoing immediate/delayed DIEP flap surgery were included in this prospective observational study. DIEP flap tissue oxygenation (StO2) was monitored continuously using near-infrared spectroscopy. A baseline measurement was performed by positioning one sensor at the marked position of the major inferior epigastric perforator on the abdomen. A new sensor was positioned postoperatively on the transplanted tissue. In unilateral procedures, postoperative StO2 values of the native breast were also obtained. Measurements were continued for 24 h. Results Thirty patients (42 flaps) were included. Fourteen patients (46.7%) had an uncomplicated postoperative course. A minor complication was observed in thirteen patients; in five patients, at least one major complication occurred, requiring re-exploration. Median StO2 readings were significantly lower in patients with major complications compared to uncomplicated cases. In fourteen unilateral DIEP flap procedures, StO2 values of the native breast were similar to the preoperative baseline measurement (92%; p = 0.452). Conclusions Non-invasive tissue oximetry following DIEP flap surgery could aid in early detection of vascular compromise. StO2 values of the native breast and abdominal wall preoperatively can be used interchangeably and can serve as personalized reference value. Level of evidence: Level IV, diagnostic / prognostic study.

INTEGRATING FUZZY C-MEANS AND MAHALANOBIS METRIC CLASSIFICATION FOR EXUDATE DETECTION IN COLOR FUNDUS IMAGING

2015 ◽  
Vol 15 (05) ◽  
pp. 1550085 ◽  
Author(s):  
MADHURI TASGAONKAR ◽  
MADHURI KHAMBETE
Keyword(s):  
Diabetic Retinopathy ◽  
Early Detection ◽  
Ground Truth ◽  
Vital Role ◽  
Detection Accuracy ◽  
Fuzzy C Means ◽  
Fundus Imaging ◽  
Imaging Detection ◽  
Retinal Structure

Diabetes affects retinal structure of a diabetic patient by generating various lesions. Early detection of these lesions can avoid the loss of vision. Automation of detection process can be made easily feasible to masses by the use of fundus imaging. Detection of exudates is significant in diabetic retinopathy (DR) as they are earlier signs and can cause blindness. Finding the exact location as well as correct number of exudates play vital role in the overall treatment of a patient. This paper presents an algorithm for automatic detection of exudates for DR. The algorithm combines the advantages of supervised and unsupervised techniques. It uses fuzzy-C means (FCM) segmentation on coarse level and mahalanobis metric for finer classification of segmented pixels. Mahalanobis criterion gives significance to most relevant features and thus proves a better classifier. The results are validated using DIARETDB0 and DIARETDB1 databases and the ground truth provided with it. This evaluation provided 95.77% detection accuracy.

scholarly journals Multianalyte Tests for the Early Detection of Cancer: Speedbumps and Barriers

2007 ◽  
Vol 2 ◽  
pp. 117727190700200 ◽  
Author(s):  
Michael A. Tainsky ◽  
Madhumita Chatterjee ◽  
Nancy K. Levin ◽  
Sorin Draghici ◽  
Judith Abrams
Keyword(s):  
Early Detection ◽  
Tumor Antigens ◽  
Early Stage ◽  
False Negative ◽  
Clinical Intervention ◽  
Screening Tests ◽  
Molecular Event ◽  
Non Invasive ◽  
In Vitro Diagnostic

It has become very clear that a single molecular event is inadequate to accurately predict the biology (or pathophysiology) of cancer. Furthermore, using any single molecular event as a biomarker for the early detection of malignancy may not comprehensively identify the majority of individuals with that disease. Therefore, the fact that technologies have arisen that can simultaneously detect several, possibly hundreds, of biomarkers has propelled the field towards the development of multianalyte-based in vitro diagnostic early detection tests for cancer using body fluids such as serum, plasma, sputum, saliva, or urine. These multianalyte tests may be based on the detection of serum autoantibodies to tumor antigens, the presence of cancer-related proteins in serum, or the presence of tumor-specific genomic changes that appear in plasma as free DNA. The implementation of non-invasive diagnostic approaches to detect early stage cancer may provide the physician with evidence of cancer, but the question arises as to how the information will affect the pathway of clinical intervention. The confirmation of a positive result from an in vitro diagnostic cancer test may involve relatively invasive procedures to establish a true cancer diagnosis. If in vitro diagnostic tests are proven to be both specific, i.e. rarely produce false positive results due to unrelated conditions, and sufficiently sensitive, i.e. rarely produce false negative results, then such screening tests offer the potential for early detection and personalized therapeutics using multiple disease-related targets with convenient and non-invasive means. Here we discuss the technical and regulatory barriers inherent in development of clinical multianalyte biomarker assays.

scholarly journals Early screening and diagnosis of autism spectrum disorders in Vietnam: A population-based cross-sectional survey

2021 ◽  
Author(s):  
Le Thi Vui ◽  
Duong Minh Duc ◽  
Nguyen Thuy Quynh ◽  
Nguyen Thi Huong Giang ◽  
Vu Thi Thanh Mai ◽  
...  
Keyword(s):  
Autism Spectrum Disorders ◽  
Early Detection ◽  
Public Health Problem ◽  
Population Based ◽  
Autism Spectrum ◽  
Urban Setting ◽  
Cross Sectional ◽  
Middle Income ◽  
Middle Income Countries ◽  
Spectrum Disorders

Background: Early detection of autism spectrum disorders (ASDs) is essential given the under-reported cases in low- and middle-income countries. This first national representative survey was conducted to explore the prevalence of ASDs amongst 18 and 30 months in seven provinces in Vietnam.Design and Method: During 2017- 2018, a national cross-sectional and population-based survey for autism spectrum disorder (ASD) amongst 40,243 children aged 18 to 30 months was conducted in 7 provinces representing the socio-economic regions of Vietnam. M-CHAT was used to screen children and then confirmed by diagnostic assessment using DSM-IV criteria.Results: The prevalence of ASDs amongst children aged 18 and 30 months in Vietnam was high (0.758% or 1 in 132 children). Urban setting, male gender, and hereditable genes were associated with ASD prevalence.Conclusion: ASDs amongst children aged 18 and 30 months in Vietnam tend to be increasing and are similar to this rate in other middle-income countries but lower than that in Western countries. This under-recognized public health problem amongst children should be addressed by early detection and intervention for families with affected children.

scholarly journals Clinical relevance of combining Thermography with Nailfold Capillaroscopy to improve differentiation between primary and secondary Raynaud’s Phenomenon

2021 ◽  
pp. 39-48
Author(s):  
Yumiko Vreeburg ◽  
Laura van Vugt ◽  
Sabrina Simonnet ◽  
Daphne Valk ◽  
Gus Schardijn ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Vascular Function ◽  
Raynaud’S Phenomenon ◽  
Challenge Test ◽  
Raynaud's Phenomenon ◽  
Nailfold Capillaroscopy ◽  
Invasive Technique ◽  
Microvascular Damage ◽  
Non Invasive ◽  
Age Related

Objectives: Early microvascular damage and dysfunction are clinically mirrored in Raynaud’s phenomenon (RP). Currently, nailfold capillaroscopy (NC) is applied to differentiate between primary RP (PRP) and secondary RP (PRP), associated with connective tissue disease. However, abnormal morphology can also be caused due to age-related changes and cardiovascular disease. Thermography (TG) is a non-invasive technique which enables quantification of cutaneous vascular function. An approach using both NC and TG could improve the differentiation between PRP and SRP. Methods: Thirty RP patients (PRP, n = 21; SRP, n = 9) underwent nailfold capillaroscopy and thermography. Morphologic features were scored and patients were categorized according to the guidelines of EULAR Study group on Microcirculation in Rheumatic Diseases. TG of the hand was performed before, directly and ten minutes after a cold challenge test. Baseline images and rewarming curves were analyzed. Results: Capillary abnormalities with NC were found in all SRP patients (9/9) and in 48% (10/21) of PRP patients. Out of 10 PRP patients with altered capillary morphology, 9 (90%) had a cardiovascular disease. For all patients mean temperature was significantly higher 10 minutes after cold induction than before (p < 0,01). The gradient of the rewarming curve was significantly lower in patients with SRP compared to PRP patients (p = 0.015). Conclusions: Nailfold capillaroscopy and thermography can reliably be used to measure microvascular damage and dysfunction. Additional thermography can assist in differentiating between PRP and SRP, especially in elderly patients or in presence of a cardiovascular disease. Keywords: Raynaud’s phenomenon; Nailfold capillaroscopy; Thermography

Sign in / Sign up

Export Citation Format

Share Document