Logistic Regression and Artificial Neural Network: A Comparative Study in Diagnosing Breast Cancer

Breast tumor is a common problem in gynecology. A reliable test for preoperative discrimination between benign and malignant breast tumor is highly helpful for clinicians in culling the malignant cells through felicitous treatment for patients. This paper is carried out to generate and estimate both logistic regression technique and Artificial Neural Network (ANN) technique to predict the malignancy of breast tumor, utilizing Wisconsin Diagnosis Breast Cancer Database (WDBC). Our aim in this Paper is: (i) to compare the diagnostic performance of both methods in distinguishing between malignant and benign patterns, (ii) to truncate the number of benign cases sent for biopsy utilizing the best model as an auxiliary implement, and (iii) to authenticate the capability of each model to recognize incipient cases as an expert system.

A Benign and Malignant Breast Tumor Classification Method via Efficiently Combining Texture and Morphological Features on Ultrasound Images

The classification of benign and malignant based on ultrasound images is of great value because breast cancer is an enormous threat to women’s health worldwide. Although both texture and morphological features are crucial representations of ultrasound breast tumor images, their straightforward combination brings little effect for improving the classification of benign and malignant since high-dimensional texture features are too aggressive so that drown out the effect of low-dimensional morphological features. For that, an efficient texture and morphological feature combing method is proposed to improve the classification of benign and malignant. Firstly, both texture (i.e., local binary patterns (LBP), histogram of oriented gradients (HOG), and gray-level co-occurrence matrixes (GLCM)) and morphological (i.e., shape complexities) features of breast ultrasound images are extracted. Secondly, a support vector machine (SVM) classifier working on texture features is trained, and a naive Bayes (NB) classifier acting on morphological features is designed, in order to exert the discriminative power of texture features and morphological features, respectively. Thirdly, the classification scores of the two classifiers (i.e., SVM and NB) are weighted fused to obtain the final classification result. The low-dimensional nonparameterized NB classifier is effectively control the parameter complexity of the entire classification system combine with the high-dimensional parametric SVM classifier. Consequently, texture and morphological features are efficiently combined. Comprehensive experimental analyses are presented, and the proposed method obtains a 91.11% accuracy, a 94.34% sensitivity, and an 86.49% specificity, which outperforms many related benign and malignant breast tumor classification methods.

Case Report:Granular Cell Tumor In Breast

Granular cell tumor (GCT) of the breast is an unusual neoplasm, tipically benign, it represents between 5-6% of all GCT cases. These tumors are more common in middle-aged premenopausal women with a greater predilection African American race. Nevertheless, there are also cases described in men , , . Almost all of them are favorable, the malignant cases are uncommon (only 1-3%). Sometimes it could be clinically and radiologically confused with a malignant breast tumor; so it's very important to make a differential diagnosis. The choice therapy is an extensive local extirpation with free margins, without the need for adjuvant chemotherapy or radiotherapy. Our case is a 61-year-old woman with a GCT, and three years ago a history of breast carcinoma in the same breast.

Nanorobots as sensors for cancer microenvironment

Malignant cancer cells constantly interact with their surrounding environment and migrate by remodeling the local extracellular matrix (ECM). A quantitative understanding of the remodeled ECM can provide new insights into the process of metastasis. Cells suspended in 3D matrices can mimic many of the physicochemical and mechanical properties of tumors in vivo. Our system is designed to approximate the in vivo histopathological milieu of a malignant breast tumor. Nanorobots can be effective tools for studying cellular biophysics and probing the local rheology of biological systems. Here we demonstrate how magnetically actuated helical nanorobots can probe a 3D tissue co-culture consisting of both cancerous and non-cancerous cells. We find that nanorobots adhere preferentially near cancer cells due to the distinct charge conditions of the cancer-sculpted ECM. The spatial extent of the remodeled ECM was measured to be approximately 40 μm for all cells. However, quantitative measurements showed the adhesive force to increase with metastatic ability of the cell lines. We hypothesized and experimentally confirmed that specific sialic acid linkages related to cancer-secreted ECM may be a major contributing factor in determining this adhesive behavior. Cell-line specific anisotropy in sialic acid distribution was also discovered by nanorobots. These findings can lead to promising applications in cancer diagnosis and quantification of cancer aggression.

Nanorobots Sense Local Physiochemical Heterogeneities of Tumor Matrisome

The dissemination of cancer is brought about by continuous interaction of malignant cells with their surrounding tissue microenvironment. Understanding and quantifying the remodeling of local extracellular matrix (ECM) by invading cells can therefore provide fundamental insights into the dynamics of cancer dissemination. In this paper, we use an active and untethered nanomechanical tool, realized as magnetically driven nanorobots, to locally probe a 3D tissue culture microenvironment consisting of cancerous and non-cancerous epithelia, embedded within reconstituted basement membrane (rBM) matrix. Our assay is designed to mimic the in vivo histopathological milieu of a malignant breast tumor. We find that nanorobots preferentially adhere to the ECM near cancer cells: this is due to the distinct charge conditions of the cancer-remodeled ECM. Surprisingly, quantitative measurements estimate that the adhesive force increases with the metastatic ability of cancer cell lines, while the spatial extent of the remodeled ECM was measured to be approximately 40 μm for all cancer cell lines studied here. We hypothesized and experimentally confirmed that specific sialic acid linkages specific to cancer-secreted ECM may be a major contributing factor in determining this adhesive behavior. The findings reported here can lead to promising applications in cancer diagnosis, quantification of cancer aggression, in vivo drug delivery applications, and establishes the tremendous potential of magnetic nanorobots for fundamental studies of cancer biomechanics.

Nanorobots Sense Local Physiochemical Heterogeneities of Tumor Matrisome

The dissemination of cancer is brought about by continuous interaction of malignant cells with their surrounding tissue microenvironment. Understanding and quantifying the remodeling of local extracellular matrix (ECM) by invading cells can therefore provide fundamental insights into the dynamics of cancer dissemination. In this paper, we use an active and untethered nanomechanical tool, realized as magnetically driven nanorobots, to locally probe a 3D tissue culture microenvironment consisting of cancerous and non-cancerous epithelia, embedded within reconstituted basement membrane (rBM) matrix. Our assay is designed to mimic the in vivo histopathological milieu of a malignant breast tumor. We find that nanorobots preferentially adhere to the ECM near cancer cells: this is due to the distinct charge conditions of the cancer-remodeled ECM. Surprisingly, quantitative measurements estimate that the adhesive force increases with the metastatic ability of cancer cell lines, while the spatial extent of the remodeled ECM was measured to be approximately 40 μm for all cancer cell lines studied here. We hypothesized and experimentally confirmed that specific sialic acid linkages specific to cancer-secreted ECM may be a major contributing factor in determining this adhesive behavior. The findings reported here can lead to promising applications in cancer diagnosis, quantification of cancer aggression, in vivo drug delivery applications, and establishes the tremendous potential of magnetic nanorobots for fundamental studies of cancer biomechanics.