Automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems
Introduction
The differential diagnosis of erythemato-squamous diseases is a difficult problem in dermatology. The diseases in this group are psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis and pityriasis rubra pilaris. They all share the clinical features of erythema and scaling with very few differences [1]. This is where fuzzy set theory plays an important role in dealing with uncertainty when making decisions in medical applications. Fuzzy sets have attracted the growing attention and interest in modern information technology, production technique, decision making, pattern recognition, diagnostics, data analysis, etc. [2], [3], [4]. Neuro-fuzzy systems are fuzzy systems which use artificial neural networks (ANNs) theory in order to determine their properties (fuzzy sets and fuzzy rules) by processing data samples. Neuro-fuzzy systems harness the power of the two paradigms: fuzzy logic and ANNs, by utilizing the mathematical properties of ANNs in tuning rule-based fuzzy systems that approximate the way man processes information. A specific approach in neuro-fuzzy development is the adaptive neuro-fuzzy inference system (ANFIS), which has shown significant results in modelling nonlinear functions. In ANFIS, the membership function parameters are extracted from a data set that describes the system behavior. The ANFIS learns features in the data set and adjusts the system parameters according to a given error criterion [5], [6]. Successful implementations of ANFIS in biomedical engineering have been reported for classification [7], [8] and data analysis [9].
In this study, a new approach based on ANFIS was presented for the detection of erythemato-squamous diseases. The six ANFIS classifiers were used to detect the six erythemato-squamous diseases when 34 features defining six disease indications were used as inputs. Each of the ANFIS classifier was trained so that they are likely to be more accurate for one type of erythemato-squamous disease than the other diseases. The predictions of the six ANFIS classifiers were combined by the seventh ANFIS classifier. The dermatology database investigated in this study consisted of 358 cases of erythemato-squamous diseases compiled by Güvenir et al. [1]. The proposed ANFIS model was then evaluated and performances of the ANFIS model were reported. We were able to achieve significant improvement in accuracy by applying ANFIS model compared to the stand-alone neural networks. Finally, some conclusions were drawn concerning the impacts of features on the detection of erythemato-squamous diseases.
Section snippets
Differential diagnosis of erythemato-squamous diseases
The erythemato-squamous diseases are psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis and pityriasis rubra pilaris. These diseases are frequently seen in the outpatient dermatology departments. Since they all share the clinical features of erythema and scaling with slight variations, the differential diagnosis of erythemato-squamous diseases is difficult. At first sight, all the diseases look very much alike with the erythema and scaling. When inspected more
Architecture of ANFIS
The ANFIS is a fuzzy Sugeno model put in the framework of adaptive systems to facilitate learning and adaptation [5], [6]. Such framework makes the ANFIS modeling more systematic and less reliant on expert knowledge. To present the ANFIS architecture, two fuzzy if–then rules based on a first order Sugeno model are considered
Rule 1: If (x is A1) and (y is B1) then (f1=p1x+q1y+r1).
Rule 2: If (x is A2) and (y is B2) then (f2=p2x+q2y+r2),
where x and y are the inputs, Ai and Bi are the fuzzy sets, fi
Results and discussion
The collection of well-distributed, sufficient, and accurately measured input data is the basic requirement to obtain an accurate model. In the data set, the family history feature has a value of 1 if any of the erythemato-squamous diseases have been observed in the family, otherwise it has a value of zero. The age feature simply represents the age of the patient. Every other feature (clinical and histopathological) was given a degree in the range 0–3. Here, 0 indicates that the feature was not
Conclusion
This paper presented a new application of ANFIS model for the detection of erythemato-squamous diseases. We chose fuzzy logic in the present study due to the uncertainty in differential diagnosis of erythemato-squamous diseases, which is a result of imprecise boundaries among the six erythemato-squamous diseases. Using fuzzy logic enabled us to use this uncertainty in the classifiers designs and consequently to increase the credibility of the systems outputs. The six ANFIS classifiers were used
Acknowledgements
This study has been supported by the State Planning Organization of Turkey (Project No: 2003K 120470, Project name: Biomedical signal acquisition, processing and imaging)
İnan Güler graduated from Erciyes University in 1981. He took his M.S. Degree from Middle East Technical University in 1985, and his Ph.D. Degree from İstanbul Technical University in 1990, all in Electronic Engineering. He is a professor at Gazi University where he is Head of Department. His areas of interest include biomedical systems, biomedical signal processing, biomedical instrumentation, electronic circuit design, neural network, and artificial intelligence. He has written more than 100
References (10)
- et al.
Learning differential diagnosis of erythemato-squamous diseases using voting feature intervals
Artif. Intell. Med.
(1998) - et al.
An introduction to fuzzy systems
Clin. Chim. Acta
(1998) - et al.
Fuzzy diagnosis
Artif. Intell. Med.
(1999) - et al.
Obtaining interpretable fuzzy classification rules from medical data
Artif. Intell. Med.
(1999) - et al.
Automatic detection of distorted plethysmogram pulses in neonates and paediatric patients using an adaptive-network-based fuzzy inference system
Artif. Intell. Med.
(2002)
Cited by (109)
Biophysical and ultrasonographic changes in lichen planus compared with uninvolved skin
2019, International Journal of Women's DermatologyCitation Excerpt :Basal layer damage and melanin incontinence are characteristic pathologic features of LP. A study on the automatic detection of erythemato-squamous diseases using adaptive neuro-fuzzy inference systems showed that melanin incontinence was a diagnostic feature for LP (Übeylı and Guler, 2005). A high-frequency ultrasound is a simple noninvasive method to evaluate skin thickness and echo-density (Firooz et al., 2017).
A novel hybrid intelligent system with missing value imputation for diabetes diagnosis
2018, Alexandria Engineering JournalCitation Excerpt :Abawajy et al. [11] presented a method for identifying cardiovascular autonomic neuropathy category in diabetic data with missing values. Recently, the researchers [12–15] have focused on fuzzy modeling as a proper technique for diagnosing disease. In Ref. [12], a fuzzy classifier named ARTMAP-IC neural network for medical diagnosis is proposed.
Diseases diagnosis using fuzzy logic methods: A systematic and meta-analysis review
2018, Computer Methods and Programs in BiomedicineSkin Diseases Detection Using LBP and WLD: An Ensembling Approach
2024, SN Computer ScienceSkin Disease Detection using Image Processing and Machine Learning
2023, Research Square
İnan Güler graduated from Erciyes University in 1981. He took his M.S. Degree from Middle East Technical University in 1985, and his Ph.D. Degree from İstanbul Technical University in 1990, all in Electronic Engineering. He is a professor at Gazi University where he is Head of Department. His areas of interest include biomedical systems, biomedical signal processing, biomedical instrumentation, electronic circuit design, neural network, and artificial intelligence. He has written more than 100 articles on biomedical engineering.
Elif Derya Übeylı graduated from Çukurova University in 1996. She took her M.S. Degree in 1998, all in electronic engineering. She took her Ph.D. Degree from Gazi University, electronics and computer technology. She is a research assistant at the Department of Electronics and Computer Education at Gazi University. Her areas of interest are biomedical signal processing, neural network, and artificial intelligence.