Automatic Approach for Cervical Cancer Detection and Segmentation Using Neural Network Classifier

Abstract

Cervical cancer leads to major death disease in women around the world every year. This cancer can be cured if it is initially screened and giving timely treatment to the patients. This paper proposes a novel methodology for screening the cervical cancer using cervigram images. Oriented Local Histogram Technique (OLHT) is applied on the cervical image to enhance the edges and then Dual Tree Complex Wavelet Transform (DT-CWT) is applied on it to obtain multi resolution image. Then, features as wavelet, Grey Level Co-occurrence Matrix (GLCM), moment invariant and Local Binary Pattern (LBP) features are extracted from this transformed multi resolution cervical image. These extracted features are trained and also tested by feed forward back propagation neural network to classify the given cervical image into normal and abnormal. The morphological operations are applied on the abnormal cervical image to detect and segment the cancer region. The performance of the proposed cervical cancer detection system is analyzed in the terms of sensitivity, specificity, accuracy, positive predictive value, negative predictive value, Likelihood Ratio positive, Likelihood ratio negative, precision, false positive rate and false negative rate. The performance measures for the cervical cancer detection system achieves 97.42% of sensitivity, 99.36% of specificity, 98.29% of accuracy, PPV of 97.28%, NPV of 92.17%, LRP of 141.71, LRN of 0.0936, 97.38 % precision, 96.72% FPR and 91.36% NPR. From the simulation results, the proposed methodology outperforms the conventional methodologies for cervical cancer detection and segmentation process.

Artificial Intelligence in Medical Imaging of the Breast

“…Nindrea RD et al conducted a systematic review of the published ML algorithms for breast cancer risk prediction between January 2000 and May 2018, summarized and compared five ML algorithms including SVM, ANN, decision tree (DT), naive Bayes, and K-nearest neighbor (KNN) algorithms, and confirmed that the SVM algorithm was able to calculate breast cancer risk with better accuracy than other ML algorithms (43). Some studies have shown that the mammography results, risk factors, and clinical findings were analyzed and learned through an ANN combined with cytopathological diagnosis to evaluate the risk of breast cancer for doctors to estimate the probability of malignancy and improve the positive predictive value (PPV) of the decision to perform biopsy (44). Yala A and his team also developed a hybrid DL model that operates on both the full-field mammogram and traditional risk factors, and found that it was more accurate than a current clinical standard, i.e.…”

<p>Progress of Artificial Intelligence in Gynecological Malignant Tumors</p>

“…So far, cervical carcinoma is still the main reason of cancer-related deaths in women around the world. Elayaraja and Suganathi 26 proposed a theory for screening the cervical carcinoma using cervigram image. Oriented local histogram technique (OLHT) was put into use in the image of cervix to enhance the edge, and then dual tree-complex wavelet transform (DT-CWT) was put into use in the enhanced image to obtain the multi-resolution image.…”

“…Creative Commons license and disclaimer available from:( http://creativecommons.org/licenses/by/4.0/legalcode ). 26 Abbreviations: NN, neural network; SVM, support vector machine; QSL, quasi supervised learning. …”

“…Creative Commons license and disclaimer available from:( http://creativecommons.org/licenses/by/4.0/legalcode ). 26 …”

“… 63 In the latest research mentioned in this review, it is found that the application performance of AI in gynecologic oncology at present mostly exceeds the existing methods and models in prognosis and diagnosis 21 , 27 , 29 , 31 , 53 , 54 , 56–60 and it is also superior to the less experienced clinicians, 20 or equivalent to the most experienced clinicians. 22 , 23 , 30 In the comparison of AI itself, it is also found that the performance of the ensemble classifier combining DL and SL is often the best, 28 , 34 DL (ANN, CNN, FFBPNN, and PNN, etc) is often better than SL (CARTs, SVM, and RF, etc), 20 , 21 , 26 , 29 , 57 , 59 but a small part of them are the same 28 or even the opposite. 34 This just reflects the advantages of ensemble classifier and the development trend that DL may even replace SL.…”