Classification of Breast Cancer in Mammograms with Deep Learning Adding a Fifth Class

Breast cancer is one of the diseases of most profound concern, with the most prevalence worldwide, where early detections and diagnoses play the leading role against this disease achieved through imaging techniques such as mammography. Radiologists tend to have a high false positive rate for mammography diagnoses and an accuracy of around 82%. Currently, deep learning (DL) techniques have shown promising results in the early detection of breast cancer by generating computer-aided diagnosis (CAD) systems implementing convolutional neural networks (CNNs). This work focuses on applying, evaluating, and comparing the architectures: AlexNet, GoogLeNet, Resnet50, and Vgg19 to classify breast lesions after using transfer learning with fine-tuning and training the CNN with regions extracted from the MIAS and INbreast databases. We analyzed 14 classifiers, involving 4 classes as several researches have done it before, corresponding to benign and malignant microcalcifications and masses, and as our main contribution, we also added a 5th class for the normal tissue of the mammary parenchyma increasing the correct detection; in order to evaluate the architectures with a statistical analysis based on the received operational characteristics (ROC), the area under the curve (AUC), F1 Score, accuracy, precision, sensitivity, and specificity. We generate the best results with the CNN GoogLeNet trained with five classes on a balanced database with an AUC of 99.29%, F1 Score of 91.92%, the accuracy of 91.92%, precision of 92.15%, sensitivity of 91.70%, and specificity of 97.66%, concluding that GoogLeNet is optimal as a classifier in a CAD system to deal with breast cancer.

Download Full-text

Convolutional Neural Networks for the Segmentation of Microcalcification in Mammography Imaging

Journal of Healthcare Engineering ◽

10.1155/2019/9360941 ◽

2019 ◽

Vol 2019 ◽

pp. 1-9 ◽

Cited By ~ 8

Author(s):

Gabriele Valvano ◽

Gianmarco Santini ◽

Nicola Martini ◽

Andrea Ripoli ◽

Chiara Iacconi ◽

...

Keyword(s):

Breast Cancer ◽

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

False Positive ◽

False Positive Rate ◽

Novel Approach ◽

Positive Rate ◽

Microcalcification Detection ◽

Microcalcification Clusters

Cluster of microcalcifications can be an early sign of breast cancer. In this paper, we propose a novel approach based on convolutional neural networks for the detection and segmentation of microcalcification clusters. In this work, we used 283 mammograms to train and validate our model, obtaining an accuracy of 99.99% on microcalcification detection and a false positive rate of 0.005%. Our results show how deep learning could be an effective tool to effectively support radiologists during mammograms examination.

Download Full-text

Automated covid-19 detection from frontal Chest X-Ray images using Deep Learning: an online feasibility study

10.1101/2020.07.16.20155093 ◽

2020 ◽

Author(s):

Xavier P. Burgos-Artizzu

Keyword(s):

Deep Learning ◽

Bacterial Pneumonia ◽

False Positive Rate ◽

Area Under The Curve ◽

Prospective Clinical Study ◽

Online Data ◽

X Ray ◽

Positive Rate ◽

Chest X Ray ◽

Online Sources

ABSTRACTStudy designto evaluate the performance of Deep Learning methods to detect covid-19 from X-Ray chest imagesMethodsChest X-Ray (CXR) images collected from confirmed covid-19 cases in several different centers and institutions and available online were downloaded and combined together with images of healthy patients and patients suffering from bacterial pneumonia found in other online sources. An AI image-based covid-19 classifier was developed and evaluated on the CXR images downloaded.ResultsSeven different online data sources were combined for a total of N=16,665 patients (3,156 with covid-19, 2,311 with bacterial pneumonia and 11,198 healthy patients). When half of the patients (N=8,331) where used to train the classifier leaving the other half (N=8,334) for validation, the classifier reached an Area Under the Curve (AUC) for covid-19 detection of 98.6% (detection rate of 91.8% at 1.1% false positive rate). Results were similar for other training/validation splits. AUC was close to 90% even when tested on patients from a source not used to train the classifier.ConclusionsComputer aided automatic covid-19 detection from CXR images showed promising results on a large cohort of patients. The classifier will be made available online for its evaluation. These results merit further evaluation through a prospective clinical study.

Download Full-text

Ascertaining an efficient eligibility cut-off for extended Medicare items for eating disorders

Australasian Psychiatry ◽

10.1177/10398562211028632 ◽

2021 ◽

pp. 103985622110286

Author(s):

Tracey Wade ◽

Jamie-Lee Pennesi ◽

Yuan Zhou

Keyword(s):

Eating Disorders ◽

Eating Disorder ◽

False Positive Rate ◽

Area Under The Curve ◽

Rate Sensitivity ◽

True Positive Rate ◽

Eating Disorder Examination Questionnaire ◽

Eating Disorder Examination ◽

Positive Rate ◽

The Relationship

Objective: Currently eligibility for expanded Medicare items for eating disorders (excluding anorexia nervosa) require a score ⩾ 3 on the 22-item Eating Disorder Examination-Questionnaire (EDE-Q). We compared these EDE-Q “cases” with continuous scores on a validated 7-item version of the EDE-Q (EDE-Q7) to identify an EDE-Q7 cut-off commensurate to 3 on the EDE-Q. Methods: We utilised EDE-Q scores of female university students ( N = 337) at risk of developing an eating disorder. We used a receiver operating characteristic (ROC) curve to assess the relationship between the true-positive rate (sensitivity) and the false-positive rate (1-specificity) of cases ⩾ 3. Results: The area under the curve showed outstanding discrimination of 0.94 (95% CI: .92–.97). We examined two specific cut-off points on the EDE-Q7, which included 100% and 87% of true cases, respectively. Conclusion: Given the EDE-Q cut-off for Medicare is used in conjunction with other criteria, we suggest using the more permissive EDE-Q7 cut-off (⩾2.5) to replace use of the EDE-Q cut-off (⩾3) in eligibility assessments.

Download Full-text

IoT Botnet Anomaly Detection Using Unsupervised Deep Learning

Electronics ◽

10.3390/electronics10161876 ◽

2021 ◽

Vol 10 (16) ◽

pp. 1876

Author(s):

Ioana Apostol ◽

Marius Preda ◽

Constantin Nila ◽

Ion Bica

Keyword(s):

Deep Learning ◽

Detection System ◽

False Positive Rate ◽

Empirical Evaluation ◽

Learning Approaches ◽

Promising Alternative ◽

Positive Rate ◽

Unsupervised Deep Learning ◽

Attack Surface ◽

Iot Devices

The Internet of Things has become a cutting-edge technology that is continuously evolving in size, connectivity, and applicability. This ecosystem makes its presence felt in every aspect of our lives, along with all other emerging technologies. Unfortunately, despite the significant benefits brought by the IoT, the increased attack surface built upon it has become more critical than ever. Devices have limited resources and are not typically created with security features. Lately, a trend of botnet threats transitioning to the IoT environment has been observed, and an army of infected IoT devices can expand quickly and be used for effective attacks. Therefore, identifying proper solutions for securing IoT systems is currently an important and challenging research topic. Machine learning-based approaches are a promising alternative, allowing the identification of abnormal behaviors and the detection of attacks. This paper proposes an anomaly-based detection solution that uses unsupervised deep learning techniques to identify IoT botnet activities. An empirical evaluation of the proposed method is conducted on both balanced and unbalanced datasets to assess its threat detection capability. False-positive rate reduction and its impact on the detection system are also analyzed. Furthermore, a comparison with other unsupervised learning approaches is included. The experimental results reveal the performance of the proposed detection method.

Download Full-text

Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system

Scientific Reports ◽

10.1038/s41598-021-95653-9 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Chiaki Kuwada ◽

Yoshiko Ariji ◽

Yoshitaka Kise ◽

Takuma Funakoshi ◽

Motoki Fukuda ◽

...

Keyword(s):

Deep Learning ◽

Cleft Palate ◽

Panoramic Radiography ◽

False Positive Rate ◽

Normal Subjects ◽

Learning System ◽

Panoramic Radiographs ◽

Positive Rate ◽

Aided Diagnosis

AbstractAlthough panoramic radiography has a role in the examination of patients with cleft alveolus (CA), its appearances is sometimes difficult to interpret. The aims of this study were to develop a computer-aided diagnosis system for diagnosing the CA status on panoramic radiographs using a deep learning object detection technique with and without normal data in the learning process, to verify its performance in comparison to human observers, and to clarify some characteristic appearances probably related to the performance. The panoramic radiographs of 383 CA patients with cleft palate (CA with CP) or without cleft palate (CA only) and 210 patients without CA (normal) were used to create two models on the DetectNet. The models 1 and 2 were developed based on the data without and with normal subjects, respectively, to detect the CAs and classify them into with or without CP. The model 2 reduced the false positive rate (1/30) compared to the model 1 (12/30). The overall accuracy of Model 2 was higher than Model 1 and human observers. The model created in this study appeared to have the potential to detect and classify CAs on panoramic radiographs, and might be useful to assist the human observers.

Download Full-text

Epileptic Seizure Prediction Using Deep Transformer Model

International Journal of Neural Systems ◽

10.1142/s0129065721500581 ◽

2021 ◽

Author(s):

Abhijeet Bhattacharya ◽

Tanmay Baweja ◽

S. P. K. Karri

Keyword(s):

Signal Processing ◽

Deep Learning ◽

False Positive Rate ◽

Superior Performance ◽

Seizure Prediction ◽

Advantages And Disadvantages ◽

Positive Rate ◽

Benchmark Datasets ◽

Automated Screening ◽

Transformer Model

The electroencephalogram (EEG) is the most promising and efficient technique to study epilepsy and record all the electrical activity going in our brain. Automated screening of epilepsy through data-driven algorithms reduces the manual workload of doctors to diagnose epilepsy. New algorithms are biased either towards signal processing or deep learning, which holds subjective advantages and disadvantages. The proposed pipeline is an end-to-end automated seizure prediction framework with a Fourier transform feature extraction and deep learning-based transformer model, a blend of signal processing and deep learning — this imbibes the potential features to automatically identify the attentive regions in EEG signals for effective screening. The proposed pipeline has demonstrated superior performance on the benchmark dataset with average sensitivity and false-positive rate per hour (FPR/h) as 98.46%, 94.83% and 0.12439, 0, respectively. The proposed work shows great results on the benchmark datasets and a big potential for clinics as a support system with medical experts monitoring the patients.

Download Full-text

Considerations on the region of interest in the ROC space

Statistical Methods in Medical Research ◽

10.1177/09622802211060515 ◽

2021 ◽

pp. 096228022110605

Author(s):

Luigi Lavazza ◽

Sandro Morasca

Keyword(s):

Receiver Operating Characteristic ◽

Operating Characteristic ◽

False Positive Rate ◽

Area Under The Curve ◽

Region Of Interest ◽

True Positive Rate ◽

True Positive ◽

Receiver Operating Characteristic Curves ◽

Positive Rate ◽

Receiver Operating

Receiver Operating Characteristic curves have been widely used to represent the performance of diagnostic tests. The corresponding area under the curve, widely used to evaluate their performance quantitatively, has been criticized in several respects. Several proposals have been introduced to improve area under the curve by taking into account only specific regions of the Receiver Operating Characteristic space, that is, the plane to which Receiver Operating Characteristic curves belong. For instance, a region of interest can be delimited by setting specific thresholds for the true positive rate or the false positive rate. Different ways of setting the borders of the region of interest may result in completely different, even opposing, evaluations. In this paper, we present a method to define a region of interest in a rigorous and objective way, and compute a partial area under the curve that can be used to evaluate the performance of diagnostic tests. The method was originally conceived in the Software Engineering domain to evaluate the performance of methods that estimate the defectiveness of software modules. We compare this method with previous proposals. Our method allows the definition of regions of interest by setting acceptability thresholds on any kind of performance metric, and not just false positive rate and true positive rate: for instance, the region of interest can be determined by imposing that [Formula: see text] (also known as the Matthews Correlation Coefficient) is above a given threshold. We also show how to delimit the region of interest corresponding to acceptable costs, whenever the individual cost of false positives and false negatives is known. Finally, we demonstrate the effectiveness of the method by applying it to the Wisconsin Breast Cancer Data. We provide Python and R packages supporting the presented method.

Download Full-text

Breast cancer detection using deep convolutional neural networks and support vector machines

PeerJ ◽

10.7717/peerj.6201 ◽

2019 ◽

Vol 7 ◽

pp. e6201 ◽

Cited By ~ 48

Author(s):

Dina A. Ragab ◽

Maha Sharkas ◽

Stephen Marshall ◽

Jinchang Ren

Keyword(s):

Breast Cancer ◽

Breast Imaging ◽

Input Data ◽

Data Augmentation ◽

Area Under The Curve ◽

Screening Mammography ◽

Support Vector ◽

Svm Classifier ◽

Deep Convolutional Neural Networks ◽

Cad System

It is important to detect breast cancer as early as possible. In this manuscript, a new methodology for classifying breast cancer using deep learning and some segmentation techniques are introduced. A new computer aided detection (CAD) system is proposed for classifying benign and malignant mass tumors in breast mammography images. In this CAD system, two segmentation approaches are used. The first approach involves determining the region of interest (ROI) manually, while the second approach uses the technique of threshold and region based. The deep convolutional neural network (DCNN) is used for feature extraction. A well-known DCNN architecture named AlexNet is used and is fine-tuned to classify two classes instead of 1,000 classes. The last fully connected (fc) layer is connected to the support vector machine (SVM) classifier to obtain better accuracy. The results are obtained using the following publicly available datasets (1) the digital database for screening mammography (DDSM); and (2) the Curated Breast Imaging Subset of DDSM (CBIS-DDSM). Training on a large number of data gives high accuracy rate. Nevertheless, the biomedical datasets contain a relatively small number of samples due to limited patient volume. Accordingly, data augmentation is a method for increasing the size of the input data by generating new data from the original input data. There are many forms for the data augmentation; the one used here is the rotation. The accuracy of the new-trained DCNN architecture is 71.01% when cropping the ROI manually from the mammogram. The highest area under the curve (AUC) achieved was 0.88 (88%) for the samples obtained from both segmentation techniques. Moreover, when using the samples obtained from the CBIS-DDSM, the accuracy of the DCNN is increased to 73.6%. Consequently, the SVM accuracy becomes 87.2% with an AUC equaling to 0.94 (94%). This is the highest AUC value compared to previous work using the same conditions.

Download Full-text

Smart Spotting of Pulmonary TB Cavities Using CT Images

Computational and Mathematical Methods in Medicine ◽

10.1155/2013/864854 ◽

2013 ◽

Vol 2013 ◽

pp. 1-12 ◽

Cited By ~ 2

Author(s):

V. Ezhil Swanly ◽

L. Selvam ◽

P. Mohan Kumar ◽

J. Arokia Renjith ◽

M. Arunachalam ◽

...

Keyword(s):

False Positive Rate ◽

Mean Shift ◽

Gradient Vector Flow ◽

Computer Aided Detection ◽

Cad System ◽

High Infection ◽

Positive Rate ◽

Shift Model ◽

Automatic Technique ◽

Inverse Coefficient

One third of the world’s population is thought to have been infected with mycobacterium tuberculosis (TB) with new infection occurring at a rate of about one per second. TB typically attacks the lungs. Indication of cavities in upper lobes of lungs shows the high infection. Traditionally, it has been detected manually by physicians. But the automatic technique proposed in this paper focuses on accurate detection of disease by computed tomography (CT) using computer-aided detection (CAD) system. The various steps of the detection process include the following: (i) image preprocessing, which is done by techniques such as resizing, masking, and Gaussian smoothening, (ii) image egmentation that is implemented by using mean-shift model and gradient vector flow (GVF) model, (iii) feature extraction that can be achieved by Gradient inverse coefficient of variation and circularity measure, and (iv) classification using Bayesian classifier. Experimental results show that its perfection of detecting cavities is very accurate in low false positive rate (FPR).

Download Full-text

Application of Deep Learning to Detect Ground Deformation in InSAR Data

10.5194/egusphere-egu2020-4146 ◽

2020 ◽

Author(s):

Pui Anantrasirichai ◽

Juliet Biggs ◽

Fabien Albino ◽

David Bull

Keyword(s):

Deep Learning ◽

False Positive ◽

Data Augmentation ◽

Ground Deformation ◽

Signal To Noise Ratio ◽

Matrix Completion ◽

False Positive Rate ◽

Synthetic Approach ◽

Positive Rate ◽

Machine Learning Applications

<p>Satellite interferometric synthetic aperture radar (InSAR)&#160;can be used for&#160;measuring&#160;surface&#160;deformation for a variety of applications. Recent satellite&#160;missions,&#160;such as Sentinel-1,&#160;produce&#160;a large amount of data, meaning that visual inspection is impractical. Here we use deep learning, which has proved successful at object detection, to overcome this problem. Initially we present the use of convolutional neural networks (CNNs) for detecting&#160;rapid deformation events, which we test on a global dataset of over 30,000 wrapped interferograms at 900 volcanoes. We compare two potential training datasets: data augmentation applied to archive examples and synthetic models. Both are able to detect true positive results, but the data augmentation approach has a false positive rate of 0.205% and the synthetic approach has a false positive rate of 0.036%. &#160;Then, I will present an enhanced technique for measuring slow, sustained deformation over a range of scales from volcanic unrest to urban sources of deformation such as coalfields. By rewrapping cumulative time series, the detection&#160;performance&#160;is improved when the deformation rate is slow, as more fringes are generated without altering the signal to noise ratio. We adapt the method to use persistent scatterer InSAR data, which is sparse in nature, &#160;by using spatial interpolation methods such as modified matrix completion Finally,&#160;future perspectives for machine learning applications&#160;on InSAR data will be&#160;discussed.</p>

Download Full-text