Search

Cervical cancer is one of the most common malignant tumors among female gynecological diseases. This paper aims to explore the feasibility of utilizing serum Fourier Transform Infrared (FTIR) spectroscopy, combined with machine learning and deep learning algorithms, to efficiently differentiate between healthy individuals, hysteromyoma patients, and cervical cancer patients. In this study, serum samples from 30 groups of hysteromyoma, 36 groups of cervical cancer, and 30 healthy groups were collected and FTIR spectra of each group were recorded. In addition, the raw datasets were averaged according to the number of scans to obtain an average dataset, and the raw datasets were spectrally enhanced to obtain an augmentation dataset, resulting in a total of three sets of data with sizes of 258, 96, and 1806, respectively. Then, the hyperparameters in the four kernel functions of the Support Vector Machine (SVM) model were optimized by grid search and leave-one-out (LOO) cross-validation. The resulting SVM models achieved recognition accuracies ranging from 85.0% to 100.0% on the test set. Furthermore, a one-dimensional convolutional neural network (1D-CNN) demonstrated a recognition accuracy of 75.0% to 90.0% on the test set. It can be concluded that the use of serum FTIR spectroscopy combined with the SVM algorithm for the diagnosis of cervical cancer has important medical significance. [ABSTRACT FROM AUTHOR]

The human's temperature is little known and important to the diagnosis of diseases, according to most researchers and health workers.In ancient medicine, doctors may treat patients with wet mud or slurry clay. The part that would dry up first was considered the diseased part when either of these spread over the body. This can be done today with thermal cameras generating pictures with electromagnetic frequencies. Inflammation and blockage areas that predict cancer without radiation or touch may be detected by thermography. It can be used before any visible symptoms occur as a great advantage in medical testing. Machine learning (ML) is used in this paper as statistical techniques to give software programs the capacity to learn from information without being directly coded. ML can help to do so by learning these thermal scans and identifying suspected areas where a doctor needs to research more. Thermal photography is a comparatively better alternative to other methods that need sophisticated equipment, enabling machines to provide an easier and more effective approach to clinics and hospitals. [ABSTRACT FROM AUTHOR]

Breast cancer is the second popular cause of the women's death. There are some existing techniques for identifying the breast cancer and one of them is mammography screening, for identifying the breast cancer under the age of 40 to 50 years. For medical diagnosis applications such as breast cancer, the recommender system is very helpful. There is a large number of records or datasets available for diagnosis of human diseases. In this article, we have presented an in-depth study of breast cancer predictions to take the remedial actions. Then experiments are carried out in Microsoft Azure on the breast cancer dataset which is available on Kaggle. The training and testing are done on 70% and 30% of the data. The evaluations are conducted by using machine learning algorithms, Locally Deep SVM, Boosted Decision Tree, Averaged Perception, Bayes Point and Decision Forest to predict Breast Cancer. We conducted an experiment on 18 K breast cancer image dataset. A hybrid machine learning algorithm (HMLA) based on decision tree and average perceptron algorithms is proposed. Based on the experimental evaluation, it is analyzed that proposed algorithm has performed well with 98.1% of accuracy and predicting the accurate results with 95.0% of sensitivity and specificity of 99.0% on the Breast Cancer prediction. [ABSTRACT FROM AUTHOR]

Nowadays, breast cancer is a worldwide prevalent disease mostly in females. Consequently, the breast cancer patients are growing rapidly day by day. Therefore, it is quite essential to have some early detection systems which may help patients to know this disease at an early stage. As a result, they can start their medication to curb this fatal disease. In the era of machine learning, various prediction methods have been developed for early diagnosis of this disease. These algorithms use different computational classifiers and also claim good results in some aspects. But, so far, no proper analysis has been done to clarify which computationally intelligent technique is better to detect breast cancer. Therefore, it is required to find the best among the available methods. In this work, the contribution has been made toward the performance evaluation of seven different classification techniques over breast cancer disease datasets. In addition to this, the proper reasons for the superiority of the classifiers have also been explored. [ABSTRACT FROM AUTHOR]