Multiple Adaptive Neuro-Fuzzy Inference System with Automatic Features Extraction Algorithm for Cervical Cancer Recognition
23 Feb 2014-Computational and Mathematical Methods in Medicine (Hindawi Publishing Corporation)-Vol. 2014, pp 181245-181245
TL;DR: The experimental results prove the capability of the AFE algorithm to be as effective as the manual extraction by human experts, while the proposed MANFIS produces a good classification performance with 94.2% accuracy.
Abstract: To date, cancer of uterine cervix is still a leading cause of cancer-related deaths in women worldwide. The current methods (i.e., Pap smear and liquid-based cytology (LBC)) to screen for cervical cancer are time-consuming and dependent on the skill of the cytopathologist and thus are rather subjective. Therefore, this paper presents an intelligent computer vision system to assist pathologists in overcoming these problems and, consequently, produce more accurate results. The developed system consists of two stages. In the first stage, the automatic features extraction (AFE) algorithm is performed. In the second stage, a neuro-fuzzy model called multiple adaptive neuro-fuzzy inference system (MANFIS) is proposed for recognition process. The MANFIS contains a set of ANFIS models which are arranged in parallel combination to produce a model with multi-input-multioutput structure. The system is capable of classifying cervical cell image into three groups, namely, normal, low-grade squamous intraepithelial lesion (LSIL) and high-grade squamous intraepithelial lesion (HSIL). The experimental results prove the capability of the AFE algorithm to be as effective as the manual extraction by human experts, while the proposed MANFIS produces a good classification performance with 94.2% accuracy.
Citations
More filters
TL;DR: This paper designs and implements the multiple adaptive neuro-fuzzy inference system (MANFIS) architecture-based sensor-actuator (motor) control technique for mobile robot navigation in different two-dimensional environments with the presence of static and moving obstacles.
Abstract: Purpose
This paper aims to design and implement the multiple adaptive neuro-fuzzy inference system (MANFIS) architecture-based sensor-actuator (motor) control technique for mobile robot navigation in different two-dimensional environments with the presence of static and moving obstacles.
Design/methodology/approach
The three infrared range sensors have been mounted on the front, left and right side of the robot, which reads the forward, left forward and right forward static and dynamic obstacles in the environment. This sensor data information is fed as inputs into the MANFIS architecture to generate appropriate speed control commands for right and left motors of the robot. In this study, we have taken one assumption for moving obstacle avoidance in different scenarios the speed of the mobile robot is at least greater than or equal to the speed of moving obstacles and goal.
Findings
Graphical simulations have designed through MATLAB and virtual robot experimentation platform (V-REP) software and experiments have been done on Arduino MEGA 2560 microcontroller-based mobile robot. Simulation and experimental studies demonstrate the effectiveness and efficiency of the proposed MANFIS architecture.
Originality/value
This paper designs and implements MANFIS architecture for mobile robot navigation between a static and moving obstacle in different simulation and experimental environments. Also, the authors have compared this developed architecture to the other navigational technique and found that our developed architecture provided better results in terms of path length in the same environment.
49 citations
TL;DR: Simulation results demonstrated that the proposed fuzzy neural system improves the recognition rate of the designed system and allows enhancing the capability of thedesigned system and efficiently distinguishing healthy individuals.
Abstract: This study presents the design of the recognition system that will discriminate between healthy people and people with Parkinson's disease. A diagnosing of Parkinson's diseases is performed using fusion of the fuzzy system and neural networks. The structure and learning algorithms of the proposed fuzzy neural system (FNS) are presented. The approach described in this paper allows enhancing the capability of the designed system and efficiently distinguishing healthy individuals. It was proved through simulation of the system that has been performed using data obtained from UCI machine learning repository. A comparative study was carried out and the simulation results demonstrated that the proposed fuzzy neural system improves the recognition rate of the designed system.
37 citations
Cites background or methods from "Multiple Adaptive Neuro-Fuzzy Infer..."
...The use of multiple ANFIS structures, in [27], leads to the increase of the number of parameters of the network....
[...]
...Well known ANFIS (adaptive neurofuzzy inference system) structure is used for solving cervical cancer recognition [27], for optimizing the chiller loading [28], and for distinguishing ESES (electrical status epilepticus) and normal EEG (electroencephalography) signals [29]....
[...]
15 Apr 2017
TL;DR: The Adaptive neuro-fuzzy inference system (ANFIS) is a soft computing model based on neural network precision and fuzzy decision-making advantages, which can highly facilitate diagnostic modeling.
Abstract: Introduction: The Adaptive neuro-fuzzy inference system (ANFIS) is a soft computing model based on neural network precision and fuzzy decision-making advantages, which can highly facilitate diagnostic modeling. In this study, this model was used for breast
15 citations
Cites result from "Multiple Adaptive Neuro-Fuzzy Infer..."
...conducted a research with a relatively high precision of 94%, pointing toward the higher quality and precision of the acceptable results of using the adaptive system, compared to those achieved by each assessment system separately [17]....
[...]
TL;DR: Clinically, patients are evaluated in terms of 12 features, including degree of scaling and erythema; presence or absence of defined lesion borders; itching and koebner phenomenon; papule formation; family history; and involvement of the oral mucosa, knees, elbows, and scalp, which are important indices in the differential diagnosis of erythemato-squamous diseases.
Abstract: INTRODUCTION Erythemato-squamous diseases are often encountered in the outpatient departments of dermatology. Initially, the disease appears similar to scaling and erythema. After careful analysis, at the predilection sites (localizations of the skin where the disease manifests), some patients show typical clinical features of the disease, whereas others show typical localizations. In dermatology, the differential diagnosis of erythemato-squamous disease is challenging. Different classes of the disease share the clinical features of scaling and erythema, with very few differences. Erythemato-squamous diseases to be classified include pityriasis rubra pilaris, seborrheic dermatitis, psoriasis, lichen planus, chronic dermatitis, and pityriasis rosea. Clinically, patients are first evaluated in terms of 12 features, including degree of scaling and erythema; presence or absence of defined lesion borders; itching and koebner phenomenon; papule formation; family history; and involvement of the oral mucosa, knees, elbows, and scalp, which are important indices in the differential diagnosis of erythemato-squamous diseases. Scaling and erythema in chronic dermatitis are lesser than those in psoriasis, whereas the koebner phenomenon is found only in psoriasis, pityriasis rosea, and lichen planus. Polygonal papules and itching are observed in lichen planus. However, follicular papules are observed in pityriasis rubra pilaris. Lichen is found at oral mucosa (predilection site) while psoriasis is found within the elbow, scalp and knee. Usually, pityriasis rubra pilaris occurs during childhood. Generally, there is a family history for psoriasis.
13 citations
Cites background or methods from "Multiple Adaptive Neuro-Fuzzy Infer..."
...Adaptive Neuro-Fuzzy Inference System (ANFIS) was applied for feature extraction (8, 9)....
[...]
...Several fuzzy and neural topologies have been explored to solve different classification and feature extraction problems (8-14)....
[...]
TL;DR: A systematic review as mentioned in this paper evaluated the diagnostic performance of artificial intelligence (AI) technologies for the prediction, screening, and diagnosis of cervical cancer and pre-cancerous lesions, and found that the accuracy of the algorithms in predicting cervical cancer varied from 70% to 100%.
Abstract: Objective: The likelihood of timely treatment for cervical cancer increases with timely detection of abnormal cervical cells. Automated methods of detecting abnormal cervical cells were established because manual identification requires skilled pathologists and is time consuming and prone to error. The purpose of this systematic review is to evaluate the diagnostic performance of artificial intelligence (AI) technologies for the prediction, screening, and diagnosis of cervical cancer and pre-cancerous lesions. Materials and Methods: Comprehensive searches were performed on three databases: Medline, Web of Science Core Collection (Indexes = SCI-EXPANDED, SSCI, A & HCI Timespan) and Scopus to find papers published until July 2022. Articles that applied any AI technique for the prediction, screening, and diagnosis of cervical cancer were included in the review. No time restriction was applied. Articles were searched, screened, incorporated, and analyzed in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines. Results: The primary search yielded 2538 articles. After screening and evaluation of eligibility, 117 studies were incorporated in the review. AI techniques were found to play a significant role in screening systems for pre-cancerous and cancerous cervical lesions. The accuracy of the algorithms in predicting cervical cancer varied from 70% to 100%. AI techniques make a distinction between cancerous and normal Pap smears with 80–100% accuracy. AI is expected to serve as a practical tool for doctors in making accurate clinical diagnoses. The reported sensitivity and specificity of AI in colposcopy for the detection of CIN2+ were 71.9–98.22% and 51.8–96.2%, respectively. Conclusion: The present review highlights the acceptable performance of AI systems in the prediction, screening, or detection of cervical cancer and pre-cancerous lesions, especially when faced with a paucity of specialized centers or medical resources. In combination with human evaluation, AI could serve as a helpful tool in the interpretation of cervical smears or images.
13 citations
References
More filters
01 May 1993
TL;DR: The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference System implemented in the framework of adaptive networks.
Abstract: The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference system implemented in the framework of adaptive networks. By using a hybrid learning procedure, the proposed ANFIS can construct an input-output mapping based on both human knowledge (in the form of fuzzy if-then rules) and stipulated input-output data pairs. In the simulation, the ANFIS architecture is employed to model nonlinear functions, identify nonlinear components on-line in a control system, and predict a chaotic time series, all yielding remarkable results. Comparisons with artificial neural networks and earlier work on fuzzy modeling are listed and discussed. Other extensions of the proposed ANFIS and promising applications to automatic control and signal processing are also suggested. >
15,085 citations
"Multiple Adaptive Neuro-Fuzzy Infer..." refers background in this paper
...The acronym ANFIS stands for adaptive neuro-fuzzy inference system which is a multi-input, single-output model [51]....
[...]
TL;DR: The drugs orlistat and sibutramine appear beneficial for the treatment of adults with obesity, and metformin for obese patients with type 2 diabetes, and exercise and/or behaviour therapy appear to improve weight loss when added to diet.
Abstract: Objectives To undertake a systematic review of the long-term effects of obesity treatments on body weight, risk factors for disease, and disease. Methods The study encompassed three systematic reviews that examined different aspects of obesity treatments. (1) A systematic review of obesity treatments in adults where the methods of the Cochrane Collaboration were applied and randomised controlled trials (RCTs) with a follow-up of at least 1 year were evaluated. (2) A systematic epidemiological review, where studies were sought on long-term effects of weight loss on morbidity and/or mortality, and examined through epidemiological modelling. (3) A systematic economic review that sought reports with both costs and outcomes of treatment, including recent reports that assessed the cost-effectiveness of pharmaceutical and surgical interventions. A Markov model was also adopted to examine the cost-effectiveness of a low-fat diet and exercise intervention in adults with obesity and impaired glucose tolerance. Results The addition of the drugs orlistat or sibutramine was associated with weight loss and generally improved risk factors, apart from diastolic blood pressure for sibutramine. Metformin was associated with decreased mortality after 10 years in obese people with type 2 diabetes. Low-fat diets were associated with continuing weight loss for 3 years and improvements in risk factors, as well as prevention of type 2 diabetes and improved control of hypertension. Insufficient evidence was available to demonstrate the benefits of low calorie or very low calorie diets. The addition of an exercise or behaviour programme to diet was associated with improved weight loss and risk factors for at least 1 year. Studies combining low-fat diets, exercise and behaviour therapy suggested improved hypertension and cardiovascular disease. Family therapy was associated with improved weight loss for 2 years compared to individual therapy. There was insufficient evidence to conclude that individual therapy was more beneficial than group therapy. Weight lost more quickly (within 1 year), from the epidemiology review, may be more beneficial with respect to the risk of mortality. The effects of intentional weight loss need further investigation. Weight loss from surgical and non-surgical interventions for people suffering from obesity was associated with decreased risk of development of diabetes, and a reduction in low-density lipoprotein cholesterol, total cholesterol and blood pressure, in the long term. Targeting high-risk individuals with drugs or surgery was likely to result in a cost per additional life-year or quality-adjusted life-year (QALY) of no more than 13,000 British pounds. There was also suggestive evidence of cost saving from treatment of people with type 2 diabetes with metformin. Targeting surgery on people with severe obesity and impaired glucose tolerance was likely to be more cost-effective at 2329 British pounds per additional life-year. Economic modelling over 6 years for diet and exercise for people with impaired glucose tolerance was associated with a high initial cost per additional QALY, but by the sixth year the cost per QALY was 13,389 British pounds. Results did not include cost savings from diseases other than diabetes, and therefore may be conservative. Conclusions The drugs orlistat and sibutramine appear beneficial for the treatment of adults with obesity, and metformin for obese patients with type 2 diabetes. Exercise and/or behaviour therapy appear to improve weight loss when added to diet. Low-fat diets with exercise, or with exercise and behaviour therapy are associated with the prevention of type 2 diabetes and hypertension. Long-term weight loss in epidemiological studies was associated with reduced risk of type 2 diabetes, and may be beneficial for cardiovascular disease. Low-fat diets and exercise interventions in individuals at risk of obesity-related illness are of comparable cost to drug treatments. Long-term pragmatic RCTs of obesity treatments in populations with obesity-related illness or at high risk of developing such illness are needed (to include an evaluation of risk factors, morbidity, quality of life and economic evaluations). Drug trials that include dietary advice, plus exercise and/or behaviour therapy are also needed. Research exploring effective types of exercise, diet or behaviour and also interventions to prevent obesity in adults is required.
983 citations
TL;DR: Most evidence supports the use of intravenous aminobisphosphonates in breast cancer patients where fractures are prevented, and economic modelling showed that for acute hypercalcaemia, drugs with the longest cumulative duration of normocalcaemia were most cost-effective.
Abstract: Objectives: To identify evidence for the role of bisphosphonates in malignancy for the treatment of hypercalcaemia, prevention of skeletal morbidity and use in the adjuvant setting. To perform an economic review of current literature and model the cost effectiveness of bisphosphonates in the treatment of hypercalcaemia and prevention of skeletal morbidity Data sources: Electronic databases (1966-June 2001). Cochrane register. Pharmaceutical companies. Experts in the field. Handsearching of abstracts and leading oncology journals (1999-2001). Review methods: Two independent reviewers assessed studies for inclusion, according to predetermined criteria, and extracted relevant data. Overall event rates were pooled in a meta-analysis, odds ratios ( OR) were given with 95% confidence intervals (CI). Where data could not be combined, studies were reported individually and proportions compared using chi- squared analysis. Cost and cost-effectiveness were assessed by a decision analytic model comparing different bisphosphonate regimens for the treatment of hypercalcaemia; Markov models were employed to evaluate the use of bisphosphonates to prevent skeletal-related events (SRE) in patients with breast cancer and multiple myeloma. Results: For acute hypercalcaemia of malignancy, bisphosphonates normalised serum calcium in >70% of patients within 2-6 days. Pamidronate was more effective than control, etidronate, mithramycin and low-dose clodronate, but equal to high dose clodronate, in achieving normocalcaemia. Pamidronate prolongs ( doubles) the median time to relapse compared with clodronate or etidronate. For prevention of skeletal morbidity, bisphosphonates compared with placebo, significantly reduced the OR for fractures (OR [95% CI], vertebral, 0.69 [0.57-0.84], non-vertebral, 0.65 [0.54-0.79], combined, 0.65 [0.55-0.78]) radiotherapy 0.67 [0.57-0.79] and hypercalcaemia 0.54 [0.36-0.81] but not orthopaedic surgery 0.70 [0.46-1.05] or spinal cord compression 0.71 [0.47-1.08]. However, reduction in orthopaedic surgery was significant in studies that lasted over a year 0.59 [0.39-0.88]. Bisphosphonates significantly increased the time to first SRE but did not affect survival. Subanalyses were performed for disease groups, drugs and route of administration. Most evidence supports the use of intravenous aminobisphosphonates. For adjuvant use of bisphosphonates, Clodronate, given to patients with primary operable breast cancer and no metastatic disease, significantly reduced the number of patients developing bone metastases. This benefit was not maintained once regular administration had been discontinued. Two trials reported significant survival advantages in the treated groups. Bisphosphonates reduce the number of bone metastases in patients with both early and advanced breast cancer. Bisphosphonates are well tolerated with a low incidence of side-effects. Economic modelling showed that for acute hypercalcaemia, drugs with the longest cumulative duration of normocalcaemia were most cost-effective. Zoledronate 4 mg was the most costly, but most cost-effective treatment. For skeletal morbidity, Markov models estimated that the overall cost of bisphosphonate therapy to prevent an SRE was pound250 and pound1500 per event for patients with breast cancer and multiple myeloma, respectively. Bisphosphonate treatment is sometimes cost-saving in breast cancer patients where fractures are prevented. Conclusions: High dose aminobisphosphonates are most effective for the treatment of acute hypercalcaemia and delay time to relapse. Bisphosphonates significantly reduce SREs and delay the time to first SRE in patients with bony metastatic disease but do not affect survival. Benefit is demonstrated after administration for at least 6-12 months. The greatest body of evidence supports the use of intravenous aminobisphosphonates. Further evidence is required to support use in the adjuvant setting.
566 citations
01 Jan 2012
TL;DR: The neuro fuzzy system is applied to predict the rock Young's modulus to overcome the limitation of ANN and fuzzy logic and endow with high performance of predictive neuro-fuzzy system to make use for prediction of complex rock parameter.
Abstract: The engineering properties of the rocks have the most vital role in planning of rock excavation and construction for optimum utilization of earth resources with greater safety and least damage to surroundings. The design and construction of structure is influenced by physico-mechanical properties of rock mass. Young's modulus provides insight about the magnitude and characteristic of the rock mass deformation due to change in stress field. The determination of the Young's modulus in laboratory is very time consuming and costly. Therefore, basic rock properties like point load, density and water absorption have been used to predict the Young's modulus. Point load, density and water absorption can be easily determined in field as well as laboratory and are pertinent properties to characterize a rock mass. The artificial neural network (ANN), fuzzy inference system (FIS) and neuro fuzzy are promising techniques which have proven to be very reliable in recent years. In, present study, neuro fuzzy system is applied to predict the rock Young's modulus to overcome the limitation of ANN and fuzzy logic. Total 85 dataset were used for training the network and 10 dataset for testing and validation of network rules. The network performance indices correlation coefficient, mean absolute percentage error (MAPE), root mean square error (RMSE), and variance account for (VAF) are found to be 0.6643, 7.583, 6.799, and 91.95 respectively, which endow with high performance of predictive neuro-fuzzy system to make use for prediction of complex rock parameter.
339 citations
"Multiple Adaptive Neuro-Fuzzy Infer..." refers methods in this paper
...One of most common tools is ANFIS which combined both fuzzy logic and neural network [49, 50]....
[...]
Book•
18 Jun 1995TL;DR: System design scene constraints image acquisition image preprocessing image understanding image analysis pattern classification applications and case studies visual inspection robotic vision and control.
Abstract: System design scene constraints image acquisition image preprocessing image understanding image analysis pattern classification applications and case studies visual inspection robotic vision and control.
191 citations