Diagnostic use of facial image analysis software in endocrine and genetic disorders: review, current results and future perspectives

Kosilek, Robert P; Frohner, Richard; Würtz, Rolf P.; Berr, Christina M.; Schopohl, Jochen; Reincke, Martín; Schneider, Harald J.

doi:10.1530/eje-15-0429

Cited by 31 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is therefore a current research subject with great potential for medical use. It has previously been shown that this technology can be used to detect acromegaly and various genetic syndromes on facial photographs [13]. Hypothetically, a computer vision algorithm could simultaneously analyze a photograph regarding multiple diseases (e. g., acromegaly, CS, Graves' disease).…”

Section: Discussionmentioning

confidence: 99%

“…Computer vision technology has recently been found to be a promising diagnostic tool for diseases that feature morphological changes of the head and face, such as acromegaly or dysmorphic syndromes [13,14]. In a pilot study from 2013, we reported promising results regarding the use of computer vision technology for the detection of CS in a small and selected female-only sample [15].…”

Section: Introductionmentioning

confidence: 93%

See 1 more Smart Citation

Computer Vision Technology in the Differential Diagnosis of Cushing’s Syndrome

Popp

Kosilek²,

Frohner³

et al. 2019

Exp Clin Endocrinol Diabetes

View full text Add to dashboard Cite

Objective Cushing’s syndrome is a rare disease characterized by clinical features that show morphological similarity with the metabolic syndrome. Distinguishing these diseases in clinical practice is challenging. We have previously shown that computer vision technology can be a potentially useful diagnostic tool in Cushing’s syndrome. In this follow-up study, we addressed the described problem by increasing the sample size and including controls matched by body mass index. Methods We enrolled 82 patients (22 male, 60 female) and 98 control subjects (32 male, 66 female) matched by age, gender and body-mass-index. The control group consisted of patients with initially suspected, but biochemically excluded Cushing’s syndrome. Standardized frontal and profile facial digital photographs were acquired. The images were analyzed using specialized computer vision and classification software. A grid of nodes was semi-automatically placed on disease-relevant facial structures for analysis of texture and geometry. Classification accuracy was calculated using a leave-one-out cross-validation procedure with a maximum likelihood classifier. Results The overall correct classification rates were 10/22 (45.5%) for male patients and 26/32 (81.3%) for male controls, and 34/60 (56.7%) for female patients and 43/66 (65.2%) for female controls. In subgroup analyses, correct classification rates were higher for iatrogenic than for endogenous Cushing’s syndrome. Conclusion Regarding the advanced problem of detecting Cushing’s syndrome within a study sample matched by body mass index, we found moderate classification accuracy by facial image analysis. Classification accuracy is most likely higher in a larger sample with healthy control subjects. Further studies might pursue a more advanced analysis and classification algorithm.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 93%

Computer Vision Technology in the Differential Diagnosis of Cushing’s Syndrome

Popp

Kosilek²,

Frohner³

et al. 2019

Exp Clin Endocrinol Diabetes

View full text Add to dashboard Cite

show abstract

“…The methods described in previous sections are suitable to be applied in other conditions as well. For example, the use of facial imaging has also been applied to evaluate facial abnormalities, using facial features and classifiers to assess conditions such as acromegaly [180], [181] and Cushing's syndrome [181], [182] or craniofacial deformations associated with specific syndromes [13], [136].…”

Section: G Other Conditionsmentioning

confidence: 99%

“…facial morphology abnormalities / characteristics Down syndrome 1 [11], [115], [119]- [122] disturbances in facial expressions depression 2 [161], [162] schizophrenia 4 [15] ADHD 2, 5 [141] acromegaly 1 [180], [181] autism 2,5 [141] craniofacial deformations 1,4 [13], [136] schizophrenia 2,3 [163], [164] fetal alcohol exposure 1, 4 [12], [123]- [131], [135], [136] abnormal heat in orbital area Graves' ophthalmopathy 3 [26], [185] Cornelia de Lange syndrome 1 [116], [133], [134] nonspecific condition (Ophtalmology) 3 [186] Cushing's syndrome 1 [181], [182] other syndromes 1, 4 [117], [133], [134], [136], [137] asymmetry + synkinesis facial nerve dysfunction 1, 2 [86], [88], [89], [104], [105] facial asymmetry facial paralysis 1,5 [83]- [85], [97]- [100],…”

Section: Facial Symptoms Possible Conditions References Facial Symptomentioning

confidence: 99%

A Survey on Computer Vision for Assistive Medical Diagnosis From Faces

Thevenot

López

Hadid

2018

IEEE J. Biomed. Health Inform.

124

View full text Add to dashboard Cite

Automatic medical diagnosis is an emerging center of interest in computer vision as it provides unobtrusive objective information on a patient's condition. The face, as a mirror of health status, can reveal symptomatic indications of specific diseases. Thus, the detection of facial abnormalities or atypical features is at upmost importance when it comes to medical diagnostics. This survey aims to give an overview of the recent developments in medical diagnostics from facial images based on computer vision methods. Various approaches have been considered to assess facial symptoms and to eventually provide further help to the practitioners. However, the developed tools are still seldom used in clinical practice, since their reliability is still a concern due to the lack of clinical validation of the methodologies and their inadequate applicability. Nonetheless, efforts are being made to provide robust solutions suitable for healthcare environments, by dealing with practical issues such as real-time assessment or patients positioning. This survey provides an updated collection of the most relevant and innovative solutions in facial images analysis. The findings show that with the help of computer vision methods, over 30 medical conditions can be preliminarily diagnosed from the automatic detection of some of their symptoms. Furthermore, future perspectives, such as the need for interdisciplinary collaboration and collecting publicly available databases, are highlighted.

show abstract

“…Because changes in appearance due to acromegaly and Cushing’s disease generally occur slowly, they are often overlooked by family members, friends, GPs, and the patients themselves. There is increasing support for the development of automated diagnostic tools that would potentially aid the diagnostic process, including face-recognition software to identify the characteristic physical changes associated with these conditions [ 20 – 22 ], or 3-dimensional cephalometry [ 23 ]. However, such approaches have to date been applied only to limited numbers of subjects in pioneering studies.…”

Section: Difficulties With Diagnosis Of Secreting Pituitary Adenomas mentioning

confidence: 99%

The risks of overlooking the diagnosis of secreting pituitary adenomas

Brue

Castinetti

2016

Orphanet J Rare Dis

View full text Add to dashboard Cite

Secreting pituitary adenomas that cause acromegaly and Cushing’s disease, as well as prolactinomas and thyrotroph adenomas, are uncommon, usually benign, slow-growing tumours. The rarity of these conditions means that their diagnosis is not familiar to most non-specialist physicians. Consequently, pituitary adenomas may be overlooked and remain untreated, and affected individuals may develop serious comorbidities that reduce their quality of life and life expectancy. Because many signs and symptoms of pituitary adenomas overlap with those of other, more common disorders, general practitioners and non-endocrinology specialists need to be aware of the “red flags” suggestive of these conditions. A long duration of active disease in patients with secreting pituitary adenomas is associated with an increased risk of comorbidities and reduced quality of life. Appropriate treatment can lead to disease remission, and, although some symptoms may persist in some patients, treatment usually reduces the incidence and severity of comorbidities and improves quality of life. Therefore, correct, early diagnosis and characterization of a pituitary adenoma is crucial for patients, to trigger timely, appropriate treatment and to optimize outcome. This article provides an overview of the epidemiology of hormonal syndromes associated with pituitary adenomas, discusses the difficulties of and considerations for their diagnosis, and reviews the comorbidities that may develop, but can be prevented, by accurate diagnosis and appropriate treatment. We hope this review will help general practitioners and non-endocrinology specialists to suspect secreting pituitary adenomas and refer patients to an endocrinologist for confirmation of the diagnosis and treatment.

show abstract

Diagnostic use of facial image analysis software in endocrine and genetic disorders: review, current results and future perspectives

Cited by 31 publications

References 18 publications

Computer Vision Technology in the Differential Diagnosis of Cushing’s Syndrome

Computer Vision Technology in the Differential Diagnosis of Cushing’s Syndrome

A Survey on Computer Vision for Assistive Medical Diagnosis From Faces

The risks of overlooking the diagnosis of secreting pituitary adenomas

Contact Info

Product

Resources

About