SNSVM:SqueezeNet-Guided SVM for Breast Cancer Diagnosis

Breast cancer is a major public health concern that affects women worldwide.It is a leading cause of cancer-related deaths among women,and early detection is crucial for successful treatment.Unfortunately,breast cancer can often go undetected until it has reached advanced stages,making it more difficult to treat.Therefore,there is a pressing need for accurate and efficient diagnostic tools to detect breast cancer at an early stage.The proposed approach utilizes SqueezeNet with fire modules and complex bypass to extract informative features from mammography images.The extracted features are then utilized to train a support vector machine(SVM)for mammography image classification.The SqueezeNet-guided SVMmodel,known as SNSVM,achieved promising results,with an accuracy of 94.10% and a sensitivity of 94.30%.A 10-fold cross-validation was performed to ensure the robustness of the results,and the mean and standard deviation of various performance indicators were calculated across multiple runs.This model also outperforms state-of-the-art models in all performance indicators,indicating its superior performance.This demonstrates the effectiveness of the proposed approach for breast cancer diagnosis using mammography images.The superior performance of the proposed model across all indicators makes it a promising tool for early breast cancer diagnosis.This may have significant implications for reducing breast cancer mortality rates.

Inorganic imaging nanoprobes for breast cancer diagnosis

Breast cancer is one of the most prevalent cancers worldwide,and early diagnosis and screening are vital to its successful treatment.Although medical imaging methods can assist in the early detection of breast cancer,imaging methods that are currently used for clinical diagnosis have drawbacks,such as low sensitivity and accuracy.Contrast agents are often used in diagnostic imaging to address these drawbacks.Nanocontrast agents have attracted considerable attention in recent years due to their unique physicochemical characteristics.Among these agents,inorganic nanoprobes have been substantially developed through improvements in synthesis techniques and pairings with other organic molecules.This paper mainly summarizes the specific applications of inorganic nanoprobes in the magnetic resonance imaging,fluorescence imaging,radionuclide imaging,and bimodal/multimodal imaging of breast cancer.

A Novel Method for Diagnosis of Breast Cancer Tumors Based on Random Forest

GLOBOCAN 2020 cancer data shows that female breast cancer has become the most common cancer over lung cancer for the first time. As a disease threatening the life safety of women all over the world, how to improve the accuracy of breast cancer diagnosis and help patients get treatment as early as possible is of great importance. This paper introduces a new random forest-based breast cancer diagnosis method (NRFM), using the average radius, average texture, average circumference and other 30 indicators in the nucleus of breast mass as characteristics, to diagnose the benign and malignant breast cancer. NRFM proposed to randomly miss a certain percentage of breast cancer data, using random forest regression to fill in the experiment proved that using the method proposed in this paper, when the proportion of missing data reached 50%, the accuracy of breast cancer diagnosis will be as high as 96.85%. Experiments show that NRFM is easy to understand, convenient to operate, and has practical application value, which can assist doctors to improve the accuracy of breast cancer diagnosis.

DG-CNN:Introducing Margin Information into Convolutional Neural Networks for Breast Cancer Diagnosis in Ultrasound Images

Although using convolutional neural networks(CNNs)for computer-aided diagnosis(CAD)has made tremendous progress in the last few years,the small medical datasets remain to be the major bottleneck in this area.To address this problem,researchers start looking for information out of the medical datasets.Previous efforts mainly leverage information from natural images via transfer learning.More recent research work focuses on integrating knowledge from medical practitioners,either letting networks resemble how practitioners are trained,how they view images,or using extra annotations.In this paper,we propose a scheme named Domain Guided-CNN(DG-CNN)to incorporate the margin information,a feature described in the consensus for radiologists to diagnose cancer in breast ultrasound(BUS)images.In DG-CNN,attention maps that highlight margin areas of tumors are first generated,and then incorporated via different approaches into the networks.We have tested the performance of DG-CNN on our own dataset(including 1485 ultrasound images)and on a public dataset.The results show that DG-CNN can be applied to different network structures like VGG and ResNet to improve their performance.For example,experimental results on our dataset show that with a certain integrating mode,the improvement of using DG-CNN over a baseline network structure ResNet 18 is 2.17%in accuracy,1.69%in sensitivity,2.64%in specificity and 2.57%in AUC(Area Under Curve).To the best of our knowledge,this is the first time that the margin information is utilized to improve the performance of deep neural networks in diagnosing breast cancer in BUS images.

DIAGNOSTIC AND PROGNOSTIC UTILITY OF SERUM PSA IN BREAST CANCER

Objective To investigate the diagnostic and prognostic value of total and free prostate-specificantigen ( PSA ) in breast cancer women. Methods Using the microparticle enzyme immunoassay system, we measured the concentrations of these markers in the sera of 85 women with breast cancer and in 30 healthy women. Results Free PSA levels were significantly higher in women with breast cancer than healthy women(P <0. 05). The percentage of free PSA predominant subjects was 37. 6% in breast cancer patients and 3. 3% in healthy women. In women with breast cancer,total PSA positivity was 23. 5% and free PSA positivity was 27. 1%. When compared to negatives,total PSA positive patients had a higher percentage of lymph node involvement tumours (P >0. 05). However, patients with predominant free PSA had a higher percentage of early stage than patients with predominant PSA-ACT. Conclusion This study indicate clinical significance of preoperative measurement of serum total and free PSA in diagnosis and prognosis of women with breast cancer. The expression of KLKs is correlated with carcino-genesis of breast cancer.

CACA Guidelines for Holistic Integrative Management of Breast Cancer

Purpose:Breast cancer is now the most common malignant tumor worldwide.About one-fourth of female cancer patients all over the world sufer from breast cancer.And about one in six female cancer deaths worldwide is caused by breast cancer.In terms of absolute numbers of cases and deaths,China ranks frst in the world.The CACA Guidelines for Holistic Integrative Management of Breast Cancer were edited to help improve the diagnosis and comprehensive treatment in China.Methods:The Grading of Recommendations Assessment,Development and Evaluation(GRADE)was used to classify evidence and consensus.Results:The CACA Guidelines for Holistic Integrative Management of Breast Cancer include the epidemiology of breast cancer,breast cancer screening,breast cancer diagnosis,early breast cancer treatment,advanced breast cancer treatment,follow-up,rehabilitation,and traditional Chinese medicine treatment of breast cancer patients.Conclusion:We to standardize the diagnosis and treatment of breast cancer in China through the formulation of the CACA Guidelines.