scholarly journals Breast Cancer Detection via Global and Local Features using Digital Histology Images

2021 ◽  
Vol 5 (1) ◽  
pp. 1-36
Author(s):  
Ghulam Murtaza ◽  
Ainuddin Wahid Abdul Wahab ◽  
Ghulam Raza ◽  
Liyana Shuib
Keyword(s):  
Breast Cancer ◽  
Extraction Methods ◽  
Medical Test ◽  
Detection Model ◽  
Minimum Number ◽  
To Come ◽  
Global Type ◽  
Global And Local ◽  
Image Modality ◽  
Testing Set

Globally, breast cancer (BC) is the prevailing cause of unusual deaths in women. Breast tumor (BT) is a primary symptom and may lead to BC. Digital histology (DH) image modality is a gold standard medical test for a definite diagnosis of BC. Traditionally, DH images are visually examined by two or more pathologists to come up with a consensus for authentic BC detection which may cause a high error rate. Therefore, researchers had developed automated BC detection models using a machine learning (ML) based approach. Thus, this study aims to develop a BC detection model through ten feature extraction methods which extract both local and global type features from publicly available breast histology dataset. The extracted features are sorted by their weights, which are computed by the neighborhood component analysis method. A feature selection algorithm is developed to find the minimum number of discriminating features, evaluated through seven heterogeneous traditional ML classifiers. The proposed ML-based BC detection model acquired 90% accuracy for the initial testing set using 51 Harris features. Whereas, for the extended testing set, only three Harris features is shown 93% accuracy. The proposed BC detection model can assist the doctor in giving a second opinion.

3D RECONSTRUCTION OF BREAST CANCER FROM MAMMOGRAMS USING VOLUME RENDERING TECHNIQUES

2015 ◽  
Vol 75 (2) ◽  
Author(s):  
Ho Wei Yong ◽  
Abdullah Bade ◽  
Rajesh Kumar Muniandy
Keyword(s):  
Breast Cancer ◽  
3D Reconstruction ◽  
Computational Cost ◽  
Reconstruction Method ◽  
Cancer Model ◽  
Volume Reconstruction ◽  
The Past ◽  
Breast Cancer Model ◽  
Reconstruction Software ◽  
To Come

Over the past thirty years, a number of researchers have investigated on 3D organ reconstruction from medical images and there are a few 3D reconstruction software available on the market. However, not many researcheshave focused on3D reconstruction of breast cancer’s tumours. Due to the method complexity, most 3D breast cancer’s tumours reconstruction were done based on MRI slices dataeven though mammogram is the current clinical practice for breast cancer screening. Therefore, this research will investigate the process of creating a method that will be able to reconstruct 3D breast cancer’s tumours from mammograms effectively.  Several steps were proposed for this research which includes data acquisition, volume reconstruction, andvolume rendering. The expected output from this research is the 3D breast cancer’s tumours model that is generated from correctly registered mammograms. The main purpose of this research is to come up with a 3D reconstruction method that can produce good breast cancer model from mammograms while using minimal computational cost.

scholarly journals Relationship between Clinicopathologic Variables in Breast Cancer Overall Survival Using Biogeography-Based Optimization Algorithm

2019 ◽  
Vol 2019 ◽  
pp. 1-12
Author(s):  
Li-Yeh Chuang ◽  
Guang-Yu Chen ◽  
Sin-Hua Moi ◽  
Fu Ou-Yang ◽  
Ming-Feng Hou ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Overall Survival ◽  
Predictive Accuracy ◽  
Cancer Prognosis ◽  
University Hospital ◽  
Health Concern ◽  
Survival Models ◽  
Survival Prediction ◽  
Prediction Ability ◽  
Minimum Number

Breast cancer is the most common cancer among women and is considered a major public health concern worldwide. Biogeography-based optimization (BBO) is a novel metaheuristic algorithm. This study analyzed the relationship between the clinicopathologic variables of breast cancer using Cox proportional hazard (PH) regression on the basis of the BBO algorithm. The dataset is prospectively maintained by the Division of Breast Surgery at Kaohsiung Medical University Hospital. A total of 1896 patients with breast cancer were included and tracked from 2005 to 2017. Fifteen general breast cancer clinicopathologic variables were collected. We used the BBO algorithm to select the clinicopathologic variables that could potentially contribute to predicting breast cancer prognosis. Subsequently, Cox PH regression analysis was used to demonstrate the association between overall survival and the selected clinicopathologic variables. C-statistics were used to test predictive accuracy and the concordance of various survival models. The BBO-selected clinicopathologic variables model obtained the highest C-statistic value (80%) for predicting the overall survival of patients with breast cancer. The selected clinicopathologic variables included tumor size (hazard ratio [HR] 2.372, p = 0.006), lymph node metastasis (HR 1.301, p = 0.038), lymphovascular invasion (HR 1.606, p = 0.096), perineural invasion (HR 1.546, p = 0.168), dermal invasion (HR 1.548, p = 0.028), total mastectomy (HR 1.633, p = 0.092), without hormone therapy (HR 2.178, p = 0.003), and without chemotherapy (HR 1.234, p = 0.491). This number was the minimum number of discriminators required for optimal discrimination in the breast cancer overall survival model with acceptable prediction ability. Therefore, on the basis of the clinicopathologic variables, the survival prediction model in this study could contribute to breast cancer follow-up and management.

scholarly journals Breast Cancer Prognosis Using a Machine Learning Approach

Cancers ◽  
2019 ◽  
Vol 11 (3) ◽  
pp. 328 ◽  
Author(s):  
Patrizia Ferroni ◽  
Fabio Zanzotto ◽  
Silvia Riondino ◽  
Noemi Scarpato ◽  
Fiorella Guadagni ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Progression Free Survival ◽  
Cancer Prognosis ◽  
Prognostic Information ◽  
Random Optimization ◽  
Machine Learning Approach ◽  
Risk Of Progression ◽  
Privacy Issues ◽  
Testing Set

Machine learning (ML) has been recently introduced to develop prognostic classification models that can be used to predict outcomes in individual cancer patients. Here, we report the significance of an ML-based decision support system (DSS), combined with random optimization (RO), to extract prognostic information from routinely collected demographic, clinical and biochemical data of breast cancer (BC) patients. A DSS model was developed in a training set (n = 318), whose performance analysis in the testing set (n = 136) resulted in a C-index for progression-free survival of 0.84, with an accuracy of 86%. Furthermore, the model was capable of stratifying the testing set into two groups of patients with low- or high-risk of progression with a hazard ratio (HR) of 10.9 (p < 0.0001). Validation in multicenter prospective studies and appropriate management of privacy issues in relation to digital electronic health records (EHR) data are presently needed. Nonetheless, we may conclude that the implementation of ML algorithms and RO models into EHR data might help to achieve prognostic information, and has the potential to revolutionize the practice of personalized medicine.

scholarly journals Prediction of Breast Cancer Recurrence Using a Deep Convolutional Neural Network Without Region-of-Interest Labeling

2021 ◽  
Vol 11 ◽  
Author(s):  
Nam Nhut Phan ◽  
Chih-Yi Hsu ◽  
Chi-Cheng Huang ◽  
Ling-Ming Tseng ◽  
Eric Y. Chuang
Keyword(s):  
Breast Cancer ◽  
High Risk ◽  
Risk Score ◽  
High Performance ◽  
Cancer Recurrence ◽  
Region Of Interest ◽  
Gene Signature ◽  
Low Risk ◽  
Breast Cancer Recurrence ◽  
Testing Set

PurposeThe present study aimed to assign a risk score for breast cancer recurrence based on pathological whole slide images (WSIs) using a deep learning model.MethodsA total of 233 WSIs from 138 breast cancer patients were assigned either a low-risk or a high-risk score based on a 70-gene signature. These images were processed into patches of 512x512 pixels by the PyHIST tool and underwent color normalization using the Macenko method. Afterward, out of focus and pixelated patches were removed using the Laplacian algorithm. Finally, the remaining patches (n=294,562) were split into 3 parts for model training (50%), validation (7%) and testing (43%). We used 6 pretrained models for transfer learning and evaluated their performance using accuracy, precision, recall, F1 score, confusion matrix, and AUC. Additionally, to demonstrate the robustness of the final model and its generalization capacity, the testing set was used for model evaluation. Finally, the GRAD-CAM algorithm was used for model visualization.ResultsSix models, namely VGG16, ResNet50, ResNet101, Inception_ResNet, EfficientB5, and Xception, achieved high performance in the validation set with an overall accuracy of 0.84, 0.85, 0.83, 0.84, 0.87, and 0.91, respectively. We selected Xception for assessment of the testing set, and this model achieved an overall accuracy of 0.87 with a patch-wise approach and 0.90 and 1.00 with a patient-wise approach for high-risk and low-risk groups, respectively.ConclusionsOur study demonstrated the feasibility and high performance of artificial intelligence models trained without region-of-interest labeling for predicting cancer recurrence based on a 70-gene signature risk score.

scholarly journals Heterogeneous Graph Convolutional Networks for Android Malware Detection using Callback-Aware Caller-Callee Graphs

2021 ◽  
Author(s):  
Vinayaka K V ◽  
Jaidhar C D
Keyword(s):  
Malware Detection ◽  
Application Programming Interface ◽  
Extraction Methods ◽  
Android Application ◽  
Convolutional Network ◽  
Android Malware ◽  
Detection Model ◽  
Convolutional Networks ◽  
Android Malware Detection ◽  
Ablation Study

<pre> The popularity of the Android Operating System in the smartphone market has given rise to lots of Android malware. To accurately detect these malware, many of the existing works use machine learning and deep learning-based methods, in which feature extraction methods were used to extract fixed-size feature vectors using the files present inside the Android Application Package (APK). Recently, Graph Convolutional Network (GCN) based methods applied on the Function Call Graph (FCG) extracted from the APK are gaining momentum in Android malware detection, as GCNs are effective at learning tasks on variable-sized graphs such as FCG, and FCG sufficiently captures the structure and behaviour of an APK. However, the FCG lacks information about callback methods as the Android Application Programming Interface (API) is event-driven. This paper proposes enhancing the FCG to eFCG (enhanced-FCG) using the callback information extracted using Android Framework Space Analysis to overcome this limitation. Further, we add permission - API method relationships to the eFCG. The eFCG is reduced using node contraction based on the classes to get R-eFCG (Reduced eFCG) to improve the generalisation ability of the Android malware detection model. The eFCG and R-eFCG are then given as the inputs to the Heterogeneous GCN models to determine whether the APK file from which they are extracted is malicious or not. To test the effectiveness of eFCG and R-eFCG, we conducted an ablation study by removing their various components. To determine the optimal neighbourhood size for GCN, we experimented with a varying number of GCN layers and found that the Android malware detection model using R-eFCG with all its components with four convolution layers achieved maximum accuracy of 96.28%.</pre>

scholarly journals Heterogeneous Graph Convolutional Networks for Android Malware Detection using Callback-Aware Caller-Callee Graphs

2021 ◽  
Author(s):  
Vinayaka K V ◽  
Jaidhar C D
Keyword(s):  
Malware Detection ◽  
Application Programming Interface ◽  
Extraction Methods ◽  
Android Application ◽  
Convolutional Network ◽  
Android Malware ◽  
Detection Model ◽  
Convolutional Networks ◽  
Android Malware Detection ◽  
Ablation Study

<pre> The popularity of the Android Operating System in the smartphone market has given rise to lots of Android malware. To accurately detect these malware, many of the existing works use machine learning and deep learning-based methods, in which feature extraction methods were used to extract fixed-size feature vectors using the files present inside the Android Application Package (APK). Recently, Graph Convolutional Network (GCN) based methods applied on the Function Call Graph (FCG) extracted from the APK are gaining momentum in Android malware detection, as GCNs are effective at learning tasks on variable-sized graphs such as FCG, and FCG sufficiently captures the structure and behaviour of an APK. However, the FCG lacks information about callback methods as the Android Application Programming Interface (API) is event-driven. This paper proposes enhancing the FCG to eFCG (enhanced-FCG) using the callback information extracted using Android Framework Space Analysis to overcome this limitation. Further, we add permission - API method relationships to the eFCG. The eFCG is reduced using node contraction based on the classes to get R-eFCG (Reduced eFCG) to improve the generalisation ability of the Android malware detection model. The eFCG and R-eFCG are then given as the inputs to the Heterogeneous GCN models to determine whether the APK file from which they are extracted is malicious or not. To test the effectiveness of eFCG and R-eFCG, we conducted an ablation study by removing their various components. To determine the optimal neighbourhood size for GCN, we experimented with a varying number of GCN layers and found that the Android malware detection model using R-eFCG with all its components with four convolution layers achieved maximum accuracy of 96.28%.</pre>

scholarly journals Multi-Scale Deep Neural Network for Mitosis Detection in Breast Cancer Histological Images

2017 ◽  
Author(s):  
Boqian Wu ◽  
Binwen Fan ◽  
Qiao Xiao ◽  
Tasleem Kausar ◽  
Wenfeng Wang
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Training Sample ◽  
Detection Accuracy ◽  
Training Strategy ◽  
Detection Model ◽  
Multi Scale ◽  
Mitosis Detection ◽  
Training Samples ◽  
Image Analyze

Accurate assessment of the breast cancer deterioration degree plays a crucial role in making medical plan, and the important basis for degree assessment is the number of mitoses in a given area of the pathological image. We utilized deep multi-scale fused fully convolutional neural network (MFF-CNN) combing with conditional random felid (CRF) to detect mitoses in hematoxylin and eosin stained histology image. Analyze the characteristics of mitotic detection ----scale invariance and sparsity, as well as the difficulties ---- small amount of data , inconsistent image staining and sample class unbalanced. Based on this, mitotic detection model is designed. In this paper, a tissue-based staining equalization method is used, and to establish an effective training sample set, we select training samples by using CNN. A mitotic detection model fusing multi-level and multi-scale features and context information was designed, and the corresponding training strategy was made to reduce over-fitting. As preliminarily validated on the public 2014 ICPR MITOSIS data, our method achieves a better performance in term of detection accuracy than ever recorded for this dataset.

Sign in / Sign up

Export Citation Format

Share Document