Framework for a Computer-Aided Treatment Prediction (CATP) System for Breast Cancer

This study offers a framework for a breast cancer computer-aided treat-ment prediction(CATP)system.The rising death rate among women due to breast cancer is a worldwide health concern that can only be addressed by early diagno-sis and frequent screening.Mammography has been the most utilized breast ima-ging technique to date.Radiologists have begun to use computer-aided detection and diagnosis(CAD)systems to improve the accuracy of breast cancer diagnosis by minimizing human errors.Despite the progress of artificial intelligence(AI)in the medical field,this study indicates that systems that can anticipate a treatment plan once a patient has been diagnosed with cancer are few and not widely used.Having such a system will assist clinicians in determining the optimal treatment plan and avoid exposing a patient to unnecessary hazardous treatment that wastes a significant amount of money.To develop the prediction model,data from 336,525 patients from the SEER dataset were split into training(80%),and testing(20%)sets.Decision Trees,Random Forest,XGBoost,and CatBoost are utilized with feature importance to build the treatment prediction model.The best overall Area Under the Curve(AUC)achieved was 0.91 using Random Forest on the SEER dataset.

Breast cancer awareness among Sudanese females in Omdurman city: 2021

Background:Breast cancer is the most commonly diagnosed malignancy among women worldwide.In contrast to Europe,it generally presents very late in Africa.As with the rest of Africa,it is the most common primary malignancy of females in Sudan and typically presents in stage III or IV disease.This study is intended to analyze the level of breast cancer awareness among women in Sudan.Objective:To assess the level of awareness of breast cancer among Sudanese females and their attitude towards breast changes.Also,to establish possible associations between several variables(education level,age,contact with a breast cancer patient,residence)on awareness.Method:A descriptive cross-sectional community-based study of 385 females in Omdurman city,selected by convenient sampling.An interview-based Arabic version of Breast Cancer Awareness Measure was used.Data were coded and analyzed using Statistical Package for Social Sciences v.20.Results:A total of 385 females were included,of which 38.7%were 20–30 years,47.8%were single,53.8%had a university education,41%of them were currently unemployed,and 54.3%resided in Ummbadda’s locality.When asked about breast cancer’s signs and risk factors,55.06%and 55.8%failed to name any.The cumulative percentage of correct answers of close-ended questions about signs,risk factors and Federal Ministry of Health screening program were 42.8%,30.7%and 44.7%in that order.Only 38.2%knew the right method breast self-examination,and 48.2%of them rarely practiced it.38.2%noticed a change in the breast tissue but didn't visit a doctor.The majority of them,though,said they would see a doctor if they noticed a change in the future.Conclusion:There is a severe lack of awareness of breast cancer among females in Sudanese society.Also,there was a clear ignorant attitude practiced by a significant proportion of the candidates.Recommendations:To address this study’s limitations,further research is to be done.Federal Ministry of Health has to improve its media message and arrange targeted awareness campaigns.

Convolutional neural network for breast cancer diagnosis using diffuse optical tomography

We have developed a computer-aided diagnosis system based on a convolutional neural network that aims to classify breast mass lesions in optical tomographic images obtained using a diffuse optical tomography system,which is suitable for repeated measurements in mass screening.Sixty-three optical tomographic images were collected from women with dense breasts,and a dataset of 12602D gray scale images sliced from these 3D images was built.After image preprocessing and normalization,we tested the network on this dataset and obtained 0.80 specificity,0.95 sensitivity,90.2%accuracy,and 0.94 area under the receiver operating characteristic curve(AUC).Furthermore,a data augmentation method was implemented to alleviate the imbalance between benign and malignant samples in the dataset.The sensitivity,specificity,accuracy,and AUC of the classification on the augmented dataset were 0.88,0.96,93.3%,and 0.95,respectively.

Dual inhibition of EGFR at protein and activity level via combinatorial blocking of PI4KIla as anti-tumor strategy

Our previous studies indicate that phosphatidylinositol 4-kinase Ila can promote the growth of multi-malignant tumors via HER-2/PI3K and MAPK pathways. However, the molecular mechanisms of this pathway and its potential for clinical application remain unknown. In this study, we found that PI4KIla could be an ideal combinatorial target for EGFR treatment via regulating EGFR degradation. Results showed that PI4KIla knockdown reduced EGFR protein level, and the expression of Pi4KIla shows a strong correlation with EGFR in human breast cancer tissues （r= 0.77, P 〈 0.01）. PI4KIla knockdown greatly prolonged the effects and decreased the effective dosage of AG-1478, a specific inhibitor of EGFR. In addition, it significantly enhanced AG1478-induced inhibition of tumor cell survival and strengthened the effect of the EGFR-targeting anti-cancer drug Iressa in xenograft tumor models. Mechanistically, we found that PI4KIla suppression increased EGFR ligand-independent degradation. Quantitative proteomic analysis by stable isotope labeling with amino acids in cell culture （SlLAC） and LC-MS/MS suggested that HsPg0 mediated the effect of PI4KIla on EGFR. Furthermore, we found that combined inhibition of PI4KIla and EGFR suppressed both PI3K/AKT and MAPK/ERK pathways, and resulted in downregulation of multiple oncogenes like PRDX2, FASN, MTA2, ultimately leading to suppression of tumor growth. Therefore, we conclude that combined inhibition of PI4KIla and EGFR exerts a multiple anti-tumor effect. Dual inhibition of EGFR at protein and activity level via combinatorial blocking of PI4KIla presents a novel strategy to combat EGFR-dependent tumors.