Research on SPDTRS-PNN Based Intelligent Assistant Diagnosis for Breast Cancer

Abstract Background:Breast cancer is the second dangerous cancer in the world. How to identify breast cancer quickly and accurately is of great help to the treatment of breast cancer. Breast cancer data often contains more redundant information. Redundant information makes the breast cancer auxiliary diagnosis less accurate and time-consuming. Dimension reduction algorithm combined with machine learning can solve these problems well. Methods:This paper proposes the single-parameter decision-theoretic rough set (SPDTRS) combined with the probability neural network (PNN) model for breast cancer diagnosis. We structure fifteen models by combining five dimensionality reduction algorithms with three classification algorithms. We compared the accuracy and test time of fifteen models under different parameters or dimensions. We find that when the parameter value of SPDTRS is 2.5, the classification effect of SPDTRS combined with PNN is better. At this point, the number of 30 attributes of the original breast cancer data dropped to 12. Then the SPDTRS-PNN model is further optimized. We compared the accuracy and test time of the model under different SPREAD values in PNN, and established a better SPDTRS-PNN model.Result:We find the parameter value of SPDTRS is 2.5 and the SPREAD value is 0.75, the accuracy of the SPDTRS-PNN model training set is 99.25%, the accuracy of the test set is 97.04%, and the test time is 0.093s.Conclusion:The experimental results show that the SPDTRS-PNN model can improve the accuracy of breast cancer recognition, reduce the time required for diagnosis, and achieve rapid and accurate breast cancer diagnosis.

Download Full-text

Research of Feature Selection Methods to Predict Breast Cancer

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b1268.0982s1119 ◽

2019 ◽

Vol 8 (2S11) ◽

pp. 2353-2355 ◽

Cited By ~ 2

Keyword(s):

Breast Cancer ◽

Feature Selection ◽

Early Stage ◽

Classification Methods ◽

Selection Methods ◽

Breast Cancer Data ◽

Cancer Data ◽

Cancer Breast ◽

Data Mining Approach ◽

The World

Human health is most important than anything in the world, one should take care of it. Among various disease, cancer is the most terrible and deadly disease, so it is necessary to predict such disease in early stage. In this paper different feature selection methods used for feature extraction with different feature classification methods to identify the breast cancer. Breast cancer data is taken from UCI repository and is processed using WEKA tool and proposed techniques are applied to classify data accurately. This study well defines that data mining approach is suitable for predicting breast cancer.

Download Full-text

Loss in working years after a breast cancer diagnosis: A population-based study (Sweden).

Journal of Clinical Oncology ◽

10.1200/jco.2017.35.5_suppl.209 ◽

2017 ◽

Vol 35 (5_suppl) ◽

pp. 209-209

Author(s):

Mats Lambe ◽

Paul Lambert ◽

Irma Fredriksson ◽

Anna Plym

Keyword(s):

Breast Cancer ◽

Cancer Diagnosis ◽

Early Stage ◽

Stage Iv ◽

Population Level ◽

Breast Cancer Diagnosis ◽

Early Stage Disease ◽

Cancer Data ◽

Stage Disease ◽

Working Age

209 Background: More than half of all women with breast cancer are diagnosed during working age. We present a new measure of clinical and public health relevance to estimate the loss in working years after a breast cancer diagnosis. Methods: Women of working age diagnosed with breast cancer between 1997 and 2012 were identified in the Breast Cancer Data Base Sweden (N = 19,661), together with a breast cancer-free comparison cohort (N = 81,303). Women were followed until permanent exit from the labour market (defined as receipt of disability pension, old-age retirement or death) or censoring. Using flexible parametric survival modelling, the loss in working years was calculated as the difference in the remaining years in the work force between women with and women without breast cancer. Results: The loss in working years was most pronounced in women of younger ages and in women with advanced stage disease. Women aged 50 years at diagnosis with stage I disease lost on average 0.6 years (95% CI, 0.4-0.8) of their remaining working time; the corresponding estimates were 1.2 years (1.0-1.5) in stage II, 3.2 years (2.7-3.7) in stage III, and 8.8 years (7.9-9.8) in stage IV disease. Type of treatment was a clear determinant in women with early stage disease, with a higher loss in working years among women treated with axillary surgery, mastectomy and chemotherapy. Conclusions: Our measure provides a new perspective of the burden of breast cancer in women of working age. The modest loss in working years in women with early stage disease is reassuring, although the economic consequences on a population-level are likely to be high given the large number of women diagnosed with breast cancer every year.

Download Full-text

Primary gynecological neoplasms and clinical outcomes in patients diagnosed with breast carcinoma

International Journal of Gynecological Cancer ◽

10.1136/ijgc-00009577-200602001-00019 ◽

2006 ◽

Vol 16 (Suppl 1) ◽

pp. 118-122

Author(s):

P. F. Escobar ◽

R. Patrick ◽

L. Rybicki ◽

N. Al-Husaini ◽

C. M. Michener ◽

...

Keyword(s):

Breast Cancer ◽

Clinical Outcomes ◽

Cancer Diagnosis ◽

Ductal Carcinoma ◽

Bilateral Breast Cancer ◽

Breast Cancer Diagnosis ◽

Rank Test ◽

Cancer Data ◽

Synchronous Bilateral Breast Cancer ◽

Gynecological Neoplasms

The purpose of this study was to quantify and describe nonmammary neoplasms (n-MN), particularly gynecological neoplasms, in a patient population previously diagnosed with breast cancer. Data were collected prospectively in our institutional review board–approved registry for patients diagnosed with infiltrating breast cancer or ductal carcinoma in situ. Patients who developed a second, n-MN were identified; neoplastic site, time to development after breast cancer, and clinical outcomes were recorded. FIGO stage was recorded for patients who developed a gynecological neoplasm. Synchronous bilateral breast cancer was defined as a second, contralateral diagnosis made within 12 months of the first and, similarly, synchronous n-MN were defined as those identified within 1 year of a breast cancer diagnosis. Outcome curves were generated using the method of Kaplan and Meier, and compared using the log-rank test. Of 4126 patients diagnosed with breast cancer, 3% developed a n-MN, the majority of which were nongynecological and asynchronous to the initial breast cancer diagnosis. Three percent of patients diagnosed with breast cancer were diagnosed with a second, n-MN. Among patients who developed a n-MN, most developed a nongynecological cancer more than 1 year after the initial breast cancer diagnosis, and their outcomes were significantly worse than those patients who did not develop a n-MN.

Download Full-text

Breast Cancer Diagnosis Using K-means ‎Methodology

Journal of University of Babylon for Pure and Applied Sciences ◽

10.29196/jub.v26i1.348 ◽

2017 ◽

Vol 26 (1) ◽

pp. 9-16

Author(s):

Noor Kadhim Ayoob

Keyword(s):

Breast Cancer ◽

Lung Cancer ◽

Cause Of Death ◽

Cancer Diagnosis ◽

Computer Systems ◽

Breast Cancer Diagnosis ◽

Medical Personnel ◽

Global Database ◽

Disease Research ◽

Cancer Breast

After lung cancer, breast cancer is the second cause of death among women. Due to the seriousness of the disease, research has stepped up to help diagnose this disease by providing medical personnel with a classification based computer systems that determine whether the patient is infected. This research focuses on the use method (K-means) for the diagnosis of breast cancer based on a global database known as (WBCD) dedicated to this purpose. The proposed method has proved its effectiveness in classification and the accuracy of the system is equal to 96.4861%.

Download Full-text

Optimizing breast cancer diagnosis in Kenya: Importance of standardization of technical methodologies for comparative breast cancer data.

Journal of Clinical Oncology ◽

10.1200/jco.2012.30.27_suppl.139 ◽

2012 ◽

Vol 30 (27_suppl) ◽

pp. 139-139

Author(s):

Shahin Sayed ◽

Zahir Moloo ◽

Ronald Wasike ◽

Rajendra R. Chauhan ◽

Sudhir Vinayak ◽

...

Keyword(s):

Breast Cancer ◽

Cancer Diagnosis ◽

Breast Cancer Diagnosis ◽

Breast Cancers ◽

Cancer Data ◽

Tissue Handling ◽

Study Results ◽

Er Positive ◽

The Difference ◽

Developed World

139 Background: An analysis of 322 cases referred to Aga Khan University, Nairobi, revealed 56% estrogen receptor (ER) positive tumors and 35% prevalence of triple-negative breast cancer (TNBC). Findings were retrospective and limited by inability to control pre-analytical variables that could potentially impact results. Methods: As part of an ongoing prospective study assessing prevalence of TNBC in the three major ethnic groups in Kenya, we gathered a multidisciplinary team from 10 collaborating health facilities around Kenya for an educational workshop. The objectives were to assess baseline capabilities and pre-analytic variables at each center, identify gaps and provide hands-on training in order to ensure accuracy and validity of ER/PR/HER2 prevalence data gathered as part of the study. Results: See table. Breast cancer biopsies ranged from one to 20 per month per center. Diagnosis was predominantly by FNA and ER/PR/HER2 was not routinely performed. Buffered formalin fixative and standardized CAP reporting format was employed only at one center. A survey 3 months following the workshop demonstrated increase in diagnostic core biopsiesby 90%, and uniform use of buffered formalin fixative, and adoption of synoptic reporting. 66 prospective cases of breast cancer from the 10 institutions with patients from different ethnic backgrounds have been subsequently collected and IHC data will be presented. Conclusions: Much has been made of the difference in prevalence of TNBC in Africa as compared to North America, yet little attention has been paid to differences in diagnostic methodologies and basic tissue handling techniques that can potentially alter results. Despite limitations of resources, educational workshops make it possible to improve the practice of breast cancer diagnosis, and thereby enable accurate comparative analysis between breast cancers in the developing and the developed world. [Table: see text]

Download Full-text

An Intelligent Artificial Bee Colony and Adaptive Bacterial Foraging Optimization Scheme for reliable breast cancer diagnosis

Recent Advances in Computer Science and Communications ◽

10.2174/2666255813999200618143705 ◽

2020 ◽

Vol 13 ◽

Author(s):

S. Punitha ◽

A. Amuthan ◽

K. Suresh Joseph

Keyword(s):

Breast Cancer ◽

Cancer Detection ◽

Cancer Diagnosis ◽

Artificial Bee Colony ◽

Breast Cancer Diagnosis ◽

Bacterial Foraging Optimization ◽

Data Set ◽

Cancer Data ◽

Bacterial Foraging ◽

Bee Colony

: Breast cancer is essential to be detected in primitive localized stage for enhancing the possibility of survival since it is considered as the major malediction to the women society around the globe. Most of the intelligent approaches devised for breast cancer necessitates expertise that results in reliable identification of patterns that conclude the presence of oncology cells and determine the possible treatment to the breast cancer patients in order to enhance their survival feasibility. Moreover, the majority of the existing scheme of the literature incurs intensive labor and time, which induces predominant impact over the diagnosis time utilized for detecting breast cancer cells. An Intelligent Artificial Bee Colony and Adaptive Bacterial Foraging Optimization (IABC-ABFO) scheme is proposed for facilitating better rate of local and global searching ability in selecting the optimal features subsets and optimal parameters of ANN considered for breast cancer diagnosis. In the proposed IABC-ABFO approach, the traditional ABC algorithm used for cancer detection is improved by integrating an adaptive bacterial foraging process in the onlooker bee and the employee bee phase that results in an optimal exploitation and exploration. The results investigation of the proposed IABC-ABFO approach facilitated using Wisconsin breast cancer data set confirmed an enhanced mean classification accuracy of 99.52% on par with the existing baseline cancer detection schemes.

Download Full-text

Consolidation of Cancer Registry and Administrative Claims Data on Cancer Diagnosis and Treatment in the US Military Health System

JCO Clinical Cancer Informatics ◽

10.1200/cci.20.00043 ◽

2020 ◽

pp. 906-917

Author(s):

Yvonne L. Eaglehouse ◽

Amie B. Park ◽

Matthew W. Georg ◽

Derek W. Brown ◽

Jie Lin ◽

...

Keyword(s):

Breast Cancer ◽

Cancer Registry ◽

Cancer Diagnosis ◽

Claims Data ◽

Breast Cancer Diagnosis ◽

Data Sources ◽

Diagnosis And Treatment ◽

Administrative Claims ◽

Military Health ◽

Cancer Data

PURPOSE Linked cancer registry and medical claims data have increased the capacity for cancer research. However, few efforts have described methods to select information between data sources, which may affect data use. We developed a systematic process to evaluate and consolidate cancer diagnosis and treatment information between the linked Department of Defense Central Cancer Registry (CCR) and Military Health System Data Repository (MDR) administrative claims database, called Military Cancer Epidemiology Data System (MilCanEpi). METHODS MilCanEpi contains information on cancer diagnosis and treatment of patients receiving care from 1998 to 2014. We used an iterative process guided by knowledge of data features, current literature, and logical comparisons between the CCR and MDR data to evaluate and consolidate cancer diagnosis and treatment received (yes or no) and their dates. We applied the processes to breast cancer data as an example. Agreement between diagnosis and treatment dates in the two data sources was evaluated using Cohen’s κ with 95% CIs. RESULTS In MilCanEpi, we identified 15,965 patients with a breast cancer diagnosis and 15,145 patients who underwent breast cancer surgery; 97.9% and 84.1% of patients had records in both CCR and MDR for diagnosis and surgery, respectively. Exact agreement was 13.7% for diagnosis dates (Cohen’s κ = 0.14; 95% CI, 0.13 to 0.14) and 68.9% for surgery dates (Cohen’s κ = 0.69; 95% CI, 0.68 to 0.70) between the two data sources. After applying systematic processes, 98.1% of patients with a breast cancer diagnosis and 99.7% of patients with surgery had information selected for analytic data sets. CONCLUSION The developed processes resulted in high consolidation rates of breast cancer data in MilCanEpi and may serve as a data selection template for other tumor sites and linked data sources.

Download Full-text

Conserved Self Pattern Recognition Algorithm with Novel Detection Strategy Applied to Breast Cancer Diagnosis

Journal of Artificial Evolution and Applications ◽

10.1155/2009/130498 ◽

2009 ◽

Vol 2009 ◽

pp. 1-12 ◽

Cited By ~ 2

Author(s):

Senhua Yu ◽

Dipankar Dasgupta

Keyword(s):

Breast Cancer ◽

Pattern Recognition ◽

Cancer Diagnosis ◽

Breast Cancer Diagnosis ◽

Recognition Algorithm ◽

Performance Measure ◽

Pattern Recognition Algorithm ◽

Cancer Data ◽

Detection Strategy ◽

Clinical Breast

This paper presents a novel approach based on an improved Conserved Self Pattern Recognition Algorithm to analyze cytological characteristics of breast fine-needle aspirates (FNAs) for clinical breast cancer diagnosis. A novel detection strategy by coupling domain knowledge and randomized methods is proposed to resolve conflicts on anomaly detection between two types of detectors investigated in our earlier work on Conserved Self Pattern Recognition Algorithm (CSPRA). The improved CSPRA is applied to detect the malignant cases using clinical breast cancer data collected by Dr. Wolberg (1990), and the results are evaluated for performance measure (detection rate and false alarm rate). Results show that our approach has promising performance on breast cancer diagnosis and great potential in the area of clinical diagnosis. Effects of parameters setting in the CSPRA are discussed, and the experimental results are compared with the previous works.

Download Full-text