Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Comparative Study between Artificial Neural Network Performance and Adaptive Neuro-fuzzy Inference Systems in Breast Cancer Diagnosis Depending On Structural Features
دراسة مقارنة بين أداء الشبكات العصبية و نظام الاستدلال العصبي الضبابي المتكيف في تشخيص سرطان الثدي بالاعتماد على السمات البنيوية
2413
2 64
0
(
0
)
Authors
بلسم أحمد عيد( باحث )
Created by
Shamra Editor
Ask ChatGPT about the research
في هذه البحث تم تصميم شبكة عصبية اصطناعية تعتمد على خوارزمية الانتشار الخلفي للخطأ (BPNN) لتشخيص أورام الثدي و كذلك تصميم مصنف للتشخيص باستخدام نظام الاستدلال العصبي الضبابي المتكيف (ANFIS) و قد اعتمدت كلا الدراستين على السمات البنيوية للخزع الموجودة في قاعدة البيانات لصور الثدي لجامعة ويسكونسون في الولايات المتحدة الأميركية” Wisconson Brest Cancer dataset“ في النهاية تم اجراء مقارنة بين الدراستين من أجل التشخيص الحميد و الخبيث للكتل السرطانية لسرطان الثدي حيث حصلت الدراسة الاولى BPNN على دقة %95.95 بينما الدراسة الثانية ANFIS حصلت على دقة 91.9% و هذه النتائج تعتبر هامة جدا و مساعدة إذا ما قورنت بالأبحاث المعتمدة على السمات الشكلية المأخوذة من الصور لأجهزة متنوعة كالماموغراف و الرنين المغناطيسي.
This research aims to produce a diagnosis system for breast cancer by using Neural Network depending on Back Propagation algorithm(BPNN) and Adaptive Neuro Fuzzy Inference System ‘ANFIS’, the both of studies was done using structural features of biopsies in “Wisconson Breast Cancer “data base. In the end a comparison was made between the two studies of malignant- benign classification of breast masses of breast cancer which has accuracy 95,95% with BPNN and 91.9% with ANFIS system, this results can be consider very important if they compared with researches depending on image features that obtained of various devises like mammography, magnetic resonance.
Artificial intelligence review:
Research summary
تقدم هذه الدراسة مقارنة بين أداء الشبكات العصبية الاصطناعية (BPNN) ونظام الاستدلال العصبي الضبابي المتكيف (ANFIS) في تشخيص سرطان الثدي. اعتمدت الدراسة على السمات البنيوية للخزع الموجودة في قاعدة بيانات جامعة ويسكونسن لسرطان الثدي. تم تصميم شبكة عصبية باستخدام خوارزمية الانتشار الخلفي للخطأ (BPNN) ونظام ANFIS لتصنيف الكتل السرطانية إلى حميدة وخبيثة. أظهرت النتائج أن الشبكة العصبية BPNN حققت دقة بنسبة 95.95% بينما حقق نظام ANFIS دقة بنسبة 91.9%. تعتبر هذه النتائج مهمة مقارنة بالأبحاث التي تعتمد على السمات الشكلية المستخرجة من الصور الطبية مثل الماموغرافيا والرنين المغناطيسي. تهدف الدراسة إلى تحسين دقة التشخيص ودعم الأطباء في اتخاذ قرارات علاجية مناسبة.
Critical review
تعتبر الدراسة ذات أهمية كبيرة في مجال تشخيص سرطان الثدي باستخدام تقنيات الذكاء الاصطناعي. ومع ذلك، يمكن الإشارة إلى بعض النقاط التي قد تحتاج إلى تحسين. أولاً، لم يتم توضيح كيفية اختيار السمات البنيوية المستخدمة في التصنيف بشكل كافٍ، مما قد يؤثر على دقة النتائج. ثانياً، لم يتم مناقشة تأثير حجم العينة على أداء المصنفين بشكل مفصل، وهو عامل مهم يجب مراعاته. أخيراً، يمكن تحسين أداء نظام ANFIS من خلال تحسين خوارزمياته واختيار توابع العضوية بشكل أكثر دقة بدلاً من الاعتماد على التجريب.
Questions related to the research
-
ما هي دقة الشبكة العصبية الاصطناعية (BPNN) في تشخيص سرطان الثدي؟
حققت الشبكة العصبية الاصطناعية (BPNN) دقة بنسبة 95.95% في تشخيص سرطان الثدي.
-
ما هي السمات البنيوية التي اعتمدت عليها الدراسة في تصنيف الكتل السرطانية؟
اعتمدت الدراسة على السمات البنيوية التالية: سماكة الأجمة، انتظام حجم الخلية، انتظام شكل الخلية، نسبة الالتصاق الهامشي، حجم ظهارة الخلية الإفرادي، ونسبة تعري نواة الخلية.
-
كيف يمكن تحسين أداء نظام ANFIS في تشخيص سرطان الثدي؟
يمكن تحسين أداء نظام ANFIS من خلال تحسين خوارزمياته واختيار توابع العضوية بشكل أكثر دقة بدلاً من الاعتماد على التجريب.
-
ما هي أهمية هذه الدراسة في مجال تشخيص سرطان الثدي؟
تعتبر هذه الدراسة مهمة لأنها تقدم تقنيات جديدة لتحسين دقة تشخيص سرطان الثدي ودعم الأطباء في اتخاذ قرارات علاجية مناسبة، مما يمكن أن يقلل من معدلات الوفيات الناتجة عن التأخر في الكشف عن المرض.
References used
Ebrahim Edriss Ebrahim Ali, Wu Zhi Feng. Breast Cancer Classification using Support Vector Machine and Neural Network. International Journal of Science and Research (IJSR). Vol.5 No. 3, 2016, 1-6
K. A. Mohamed Junaid. Classification Using Two Layer Neural Network Back Propagation Algorithm. Circuits and Systems, Vol.1, No.7, 2016, 1207-1212
Htet Thazin, Tike Thein, Khin Mo. AN APPROACH FOR BREAST CANCER DIAGNOSIS CLASSIFICATION USING NEURAL NETWORK. Advanced Computing: An International Journal (ACIJ), Vol.6, No.1, 2015, 1-11
rate research
Read More
Suspension system is considered one of the most important components of modern
automobiles as it is the responsible for the vehicle’s stability, balance and safety. The
presence of robust controller is very necessary in order to ensure full interac
tion between
suspension components and making accurate decisions at the right time. This paper
proposes to design an Extended Adaptive Neuro Fuzzy Inference System (EANFIS)
controller for suspension system in quarter car model. The proposed controller is used as
decision maker In order to contribute in absorbing shocks caused by bumpy roads, and to
prevent vibrations from reaching the cockpit. Furthermore, it provides stability and
coherence required to reduce the discomfort felt by passengers, which arises from road
roughness, which in turn, improve the road handling. The MATLAB Simulink is used to
simulate the proposed controller with the controlled model and to display the responses of
the controlled model under different types of disturbance. In addition, a comparison
between EANFIS controller, Fuzzy controller and open loop model (passive suspension)
was done with different types of disturbance on order to evaluate the performance of the
proposed model. Controller has shown excelled performance in terms of reducing
displacements, velocity and acceleration.
Evapotranspiration is an important component of the
hydrologic cycle, and the accurate prediction of this parameter is
very important for many water resources applications. Thus, the
aim of this study is prediction of monthly reference
evapotranspiration using Artificial Neural Networks (ANNs) and
fuzzy inference system (FIS).
Accurate estimating and predicting of hydrological phenomena plays an influential role in the development and management of water resources, preparing of future plans according to different scenarios of climate changes. Evapotranspiration is one of t
he major meteorological components of the hydrologic cycle and from the most complex of them, and the accurate prediction of this parameter is very important for many water resources applications.
So, this research goals to prediction of monthly reference evapotranspiration (ET0) at Homs meteostation, in the middle of Syrian Arab Republic, using Artificial Neural Networks (ANNs), and Fuzzy Inference System (FIS), depending on available climatic data, and comparision between the results of these models.
The used data contained 347 monthly values of Air Temperature (T), Relative Humidity (RH), Wind Speed (WS) and Sunshine Hours (SS) (from October 1974 to December 2004). The monthly reference evapotranspiration data were estimated by the Penman Monteith method, which is the proposed method by Food and Agriculture Organization of the United Nations (FAO) as the standard method for the estimation of ET0, and used as outputs of the models.
The results of this study showed that feed forward back propagation Artificial Neural Networks (FFBP-ANNs) pridected successfully the monthly ET0 using climatic data, with low values of root mean square errors (RMSE), and high values of correlation coefficients (R), and showed that the using of the monthly index as an additional input, improves the accurate of prediction of the artificial neural networks models.
Also, the results showed good ability of Fuzzy Inference Models (FIS) in predicting of monthly reference evapotranspiration. Sunshine hours are the most influential single parameter for ET0 prediction (R= 97.71%, RMSE = 18.08 mm/month) during the test period, sunshine hours and wind speed are the most influential optimal combination of two parameters
(R= 98.55%, RMSE = 12.49 mm/month) during the test period.
The results showed high reliability for each of the artificial neural networks and fuzzy inference system with a little preference for artificial neural networks which can add the monthly index in the input layer, and there for improve the presicion of predictions.
This study recommends the using of artificial intelligence techniques in modeling of complex and nonlinear phenomena which related of water resources.
A retrospective study included 25 cases with inflammatory breast cancer. The patients were admitted to AL-Assad University Hospital, Lattakia, Syria (average age 55, and range 49-61 years old). The most common clinical signs and symptoms were: erythe
ma 100%, edema 100%, enlarged axillary nodes 100%, Nipple flattened/inverted 96%, warm Breast 92%, Ridges/thickening of breast 84%, Peau d’orange 88%, painful/tender Breast 88%, and Mass 80%. Mammography findings were: an increase in skin thickness 100%, an increased tissue density in the involved breast 100%, and an asymmetric widening of the sub-cutaneous lymphatic vessels 33.33%. 80% of cases were diagnosed as stage IV. All patients received primary neoadjuvant chemotherapy for three cycles. After that a modified radical breast mastectomy and axillary lymph nodes dissection were performed for all patients. The wound edges were closed primarily after dissecting the skin in 76%, for 4 patients 16% a split-thickness skin grafts were performed, and for 2 patients 8% a Latissimus dorsi pedicled myocutaneous flap was performed.
This study aimed to assessing the relationship between locus of control and
depression among breast cancer patients. The study was carried out in the chemical and
radiational treatment center in Tishreen University Hospital – Latakia, Data collecte
d
from15/12/2015 to 15/2/2016.The sample comprised of 100 breast cancer patients. Three
tools was been used, the first tool (Demographic and Clinical Data Sheet) was been filling
by the researcher, then all patients which participated in the study was asked to answer on
the second tool (Rotter's Locus of control Scale) and the third tool (Beck Inventory Scale
II). This study found that there was significant statistical relation between locus of
controltype and depression degree among breast cancer patients, more than half of breast
cancer patients was had depression, and was had external locus of control. So it is
recommended study theeffect of training program to modify locus of control type on the
incidence average of depression among breast cancer patients.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
