scholarly journals Digital subtraction of temporally sequential mammograms for improved detection and classification of microcalcifications

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Kosmia Loizidou ◽  
Galateia Skouroumouni ◽  
Costas Pitris ◽  
Christos Nikolaou
Keyword(s):  
Breast Imaging ◽  
Contrast Ratio ◽  
Area Under The Curve ◽  
Machine Learning Techniques ◽  
Temporal Subtraction ◽  
Characteristics Analysis ◽  
Tissue Changes ◽  
Sensitivity Specificity ◽  
Changes Over Time

Abstract Background Our aim was to demonstrate that automated detection and classification of breast microcalcifications, according to Breast Imaging Reporting and Data System (BI-RADS) categorisation, can be improved with the subtraction of sequential mammograms as opposed to using the most recent image only. Methods One hundred pairs of mammograms were retrospectively collected from two temporally sequential rounds. Fifty percent of the images included no (BI-RADS 1) or benign (BI-RADS 2) microcalcifications. The remaining exhibited suspicious findings (BI-RADS 4-5) in the recent image. Mammograms cannot be directly subtracted, due to tissue changes over time and breast deformation during mammography. To overcome this challenge, optimised preprocessing, image registration, and postprocessing procedures were developed. Machine learning techniques were employed to eliminate false positives (normal tissue misclassified as microcalcifications) and to classify the true microcalcifications as BI-RADS benign or suspicious. Ninety-six features were extracted and nine classifiers were evaluated with and without temporal subtraction. The performance was assessed by measuring sensitivity, specificity, accuracy, and area under the curve (AUC) at receiver operator characteristics analysis. Results Using temporal subtraction, the contrast ratio improved ~ 57 times compared to the most recent mammograms, enhancing the detection of the radiologic changes. Classifying as BI-RADS benign versus suspicious microcalcifications, resulted in 90.3% accuracy and 0.87 AUC, compared to 82.7% and 0.81 using just the most recent mammogram (p = 0.003). Conclusion Compared to using the most recent mammogram alone, temporal subtraction is more effective in the microcalcifications detection and classification and may play a role in automated diagnosis systems.

scholarly journals Evaluation of cerebral glioma using 3T diffusion kurtosis tensor imaging and the relationship between diffusion kurtosis metrics and tumor cellularity

2017 ◽  
Vol 45 (4) ◽  
pp. 1347-1358 ◽  
Author(s):  
Chong Qi ◽  
Song Yang ◽  
Lanxi Meng ◽  
Huiyuan Chen ◽  
Zhenlan Li ◽  
...  
Keyword(s):  
Mean Diffusivity ◽  
Area Under The Curve ◽  
Tumor Grade ◽  
Superior Performance ◽  
Cerebral Glioma ◽  
Operating Characteristics ◽  
Significant Difference ◽  
Characteristics Analysis ◽  
Sensitivity Specificity ◽  
Diffusion Kurtosis

Purpose To evaluate the clinical utility of diffusion kurtosis tensor imaging in the characterization of cerebral glioma and investigate correlations between diffusion and kurtosis metrics with tumor cellularity. Materials and Methods A group of 163 patients (age: 40.5 ± 11.5 years) diagnosed with cerebral glioma underwent diffusion kurtosis tensor imaging with a 3 T scanner. Diffusion and kurtosis metrics were measured in the solid part of tumors, and their abilities to distinguish between tumor grades was evaluated. In addition, we analyzed correlations between the metrics and tumor cellularity. Results Mean kurtosis (MK) revealed a significant difference between each pair of tumor grades ( P < 0.05) and produced the best performance in a receiver operating characteristics analysis (area under the curve [AUC] = 0.89, sensitivity/specificity = 83.3/90). In contrast, mean diffusivity (MD) revealed a significant difference only for tumor grade II versus IV ( P < 0.05). No significant differences between grades were detected with fractional anisotropy (FA; P > 0.05). Thus, kurtosis metrics exhibited a positive and strong correlation with tumor cellularity, while MD exhibited a negative or weak correlation with tumor cellularity. Conclusion Diffusion kurtosis metrics, particularly MK, demonstrated superior performance in distinguishing cerebral glioma of different grades compared with conventional diffusion metrics, and were closely associated with tumor cellularity.

scholarly journals An Efficient Method for Automated Breast Mass Segmentation and Classification in Digital Mammograms

2021 ◽  
Vol 18 (3) ◽  
Author(s):  
Behrouz Niroomand Fam ◽  
Alireza Nikravanshalmani ◽  
Madjid Khalilian
Keyword(s):  
Breast Imaging ◽  
Wavelet Coefficient ◽  
Automatic Segmentation ◽  
Area Under The Curve ◽  
Histogram Equalization ◽  
Screening Mammography ◽  
Discrete Wavelet ◽  
Mass Detection ◽  
Comparable Performance

Background: Automatic detection and classification of breast masses in mammograms are still challenging tasks. Today, computer-aided diagnosis (CAD) systems are being developed to assist radiologists in interpreting mammograms. Objectives: This study aimed to provide a novel method for automatic segmentation and classification of masses in mammograms to help radiologists make an accurate diagnosis. Materials and Methods: For an efficient mass diagnosis in mammograms, we proposed an automatic scheme to perform both mass detection and classification. First, a combination of several image enhancement algorithms, including contrast-limited adaptive histogram equalization (CLAHE), guided imaging, and median filtering, was investigated to enhance the visual features of breast area and increase the accuracy of segmentation outcomes. Second, the density of discrete wavelet coefficient density (DDWCs), based on the quincunx lifting scheme (QLS), was proposed to find suspicious mass regions or regions of interest (ROIs). Finally, mass lesions that appeared in the mammogram were classified into four categories of benign, probably benign, malignant, and probably malignant, based on the morphological shape. The proposed method was evaluated among 1593 images from the Curated Breast Imaging Subset-Digital Database for Screening Mammography (CBIS-DDSM) dataset. Results: The experimental results revealed that the suspected region localization had 100% sensitivity, with a mean of 6.4 ± 4.5 false positive (FP) detections per image. Moreover, the results showed an overall accuracy of 85.9% and an area under the curve (AUC) of 0.901 for the mass classification algorithm. Conclusion: The present results showed the comparable performance of our proposed method to that of the state-of-the-art methods.

scholarly journals Accuracy of a deep convolutional neural network in the detection of myopic macular diseases using swept-source optical coherence tomography

2019 ◽  
Author(s):  
Takahiro Sogawa ◽  
Hitoshi Tabuchi ◽  
Daisuke Nagasato ◽  
Hiroki Masumoto ◽  
Yasushi Ikuno ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Correct Answer ◽  
High Myopia ◽  
Binary Classification ◽  
Area Under The Curve ◽  
Optical Coherence ◽  
Swept Source ◽  
Study Results ◽  
Sensitivity Specificity

AbstractThis study examined and compared outcomes of deep learning (DL) in identifying swept-source optical coherence tomography (OCT) images without myopic macular lesions [i.e., no high myopia (nHM) vs. high myopia (HM)], and OCT images with myopic macular lesions [e.g., myopic choroidal neovascularization (mCNV) and retinoschisis (RS)]. A total of 796 SS-OCT images were included in the study as follows and analyzed by k-fold cross-validation (k = 5) using DL’s renowned model, Visual Geometry Group-16: nHM, 107 images; HM, 456 images; mCNV, 122 images; and RS, 111 images (n = 796). The binary classification of OCT images with or without myopic macular lesions; the binary classification of HM images and images with myopic macular lesions (i.e., mCNV and RS images); and the ternary classification of HM, mCNV, and RS images were examined. Additionally, sensitivity, specificity, and the area under the curve (AUC) for the binary classifications as well as the correct answer rate for ternary classification were examined.The classification results of OCT images with or without myopic macular lesions were as follows: AUC, 0.983; sensitivity, 0.953; specificity, 0.940. The classification results of HM images and images with myopic macular lesions were as follows: AUC, 0.976; sensitivity, 0.940; specificity, 0.941. The correct answer rate in the ternary classification of HM images, mCNV images, and RS images were as follows: HM images, 93.7%; mCNV images, 82.4%; and RS, 92.3% with mean, 91.4%. Using noninvasive, easy-to-obtain swept-source OCT images, the DL model was able to classify OCT images without myopic macular lesions and OCT images with myopic macular lesions such as mCNV and RS with high accuracy. The study results suggest the possibility of conducting highly accurate screening of ocular diseases using artificial intelligence, which may improve the prevention of blindness and reduce workloads for ophthalmologists.

scholarly journals Recognition of the Impulse of Love at First Sight Based on Electrocardiograph Signal

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Jin Zhang ◽  
Guangjie Yuan ◽  
Huan Lu ◽  
Guangyuan Liu
Keyword(s):  
Romantic Relationship ◽  
Area Under The Curve ◽  
Identification Accuracy ◽  
Selection Algorithm ◽  
Forward Selection ◽  
Ecg Signals ◽  
Signal Collection ◽  
The Right ◽  
Sensitivity Specificity

The impulse of love at first sight (ILFS) is a well known but rarely studied phenomenon. Despite the privacy of these emotions, knowing how attractive one finds a partner may be beneficial for building a future relationship in an open society, where partners are accepting each other. Therefore, this study adopted the electrocardiograph (ECG) signal collection method, which has been widely used in wearable devices, to collect signals and conduct corresponding recognition analysis. First, we used photos to induce ILFS and obtained ECG signals from 46 healthy students (24 women and 22 men) in a laboratory. Second, we extracted the time- and frequency-domain features of the ECG signals and performed a nonlinear analysis. We subsequently used a feature selection algorithm and a set of classifiers to classify the features. Combined with the sequence floating forward selection and random forest algorithms, the identification accuracy of the ILFS was 69.07%. The sensitivity, specificity, F1, and area under the curve of the other parameters were all greater than 0.6. The classification of ECG signals according to their characteristics demonstrated that the signals could be recognized. Through the information provided by the ECG signals, it can be determined whether the participant possesses the desire to fall in love, helping to determine the right partner in the fastest time; this is conducive to establishing a romantic relationship.

scholarly journals Analysis of Personality and EEG Features in Emotion Recognition Using Machine Learning Techniques to Classify Arousal and Valence Labels

2020 ◽  
Vol 2 (2) ◽  
pp. 99-124 ◽  
Author(s):  
Laura Alejandra Martínez-Tejada ◽  
Yasuhisa Maruyama ◽  
Natsue Yoshimura ◽  
Yasuharu Koike
Keyword(s):  
Machine Learning ◽  
Personality Traits ◽  
Emotion Recognition ◽  
Area Under The Curve ◽  
Machine Learning Techniques ◽  
Discrete Emotions ◽  
The Mean ◽  
Eeg Features ◽  
Arousal And Valence

We analyzed the contribution of electroencephalogram (EEG) data, age, sex, and personality traits to emotion recognition processes—through the classification of arousal, valence, and discrete emotions labels—using feature selection techniques and machine learning classifiers. EEG traits and age, sex, and personality traits were retrieved from a well-known dataset—AMIGOS—and two sets of traits were built to analyze the classification performance. We found that age, sex, and personality traits were not significantly associated with the classification of arousal, valence and discrete emotions using machine learning. The added EEG features increased the classification accuracies (compared with the original report), for arousal and valence labels. Classification of arousal and valence labels achieved higher than chance levels; however, they did not exceed 70% accuracy in the different tested scenarios. For discrete emotions, the mean accuracies and the mean area under the curve scores were higher than chance; however, F1 scores were low, implying that several false positives and false negatives were present. This study highlights the performance of EEG traits, age, sex, and personality traits using emotion classifiers. These findings could help to understand the traits relationship in a technological and data level for personalized human-computer interactions systems.

scholarly journals Comparison of Convolutional Neural Network Architectures for Classification of Tomato Plant Diseases

2020 ◽  
Vol 10 (4) ◽  
pp. 1245 ◽  
Author(s):  
Valeria Maeda-Gutiérrez ◽  
Carlos E. Galván-Tejada ◽  
Laura A. Zanella-Calzada ◽  
José M. Celaya-Padilla ◽  
Jorge I. Galván-Tejada ◽  
...  
Keyword(s):  
Operating Characteristic ◽  
Area Under The Curve ◽  
Plant Diseases ◽  
Fine Tuning ◽  
Network Architectures ◽  
Tomato Plants ◽  
Tomato Diseases ◽  
Sensitivity Specificity

Tomato plants are highly affected by diverse diseases. A timely and accurate diagnosis plays an important role to prevent the quality of crops. Recently, deep learning (DL), specifically convolutional neural networks (CNNs), have achieved extraordinary results in many applications, including the classification of plant diseases. This work focused on fine-tuning based on the comparison of the state-of-the-art architectures: AlexNet, GoogleNet, Inception V3, Residual Network (ResNet) 18, and ResNet 50. An evaluation of the comparison was finally performed. The dataset used for the experiments is contained by nine different classes of tomato diseases and a healthy class from PlantVillage. The models were evaluated through a multiclass statistical analysis based on accuracy, precision, sensitivity, specificity, F-Score, area under the curve (AUC), and receiving operating characteristic (ROC) curve. The results present significant values obtained by the GoogleNet technique, with 99.72% of AUC and 99.12% of sensitivity. It is possible to conclude that this significantly success rate makes the GoogleNet model a useful tool for farmers in helping to identify and protect tomatoes from the diseases mentioned.

scholarly journals A Curriculum Learning Strategy to Enhance the Accuracy of Classification of Various Lesions in Chest-PA X-ray Screening for Pulmonary Abnormalities

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Beomhee Park ◽  
Yongwon Cho ◽  
Gaeun Lee ◽  
Sang Min Lee ◽  
Young-Hoon Cho ◽  
...  
Keyword(s):  
Healthy Subjects ◽  
Learning Strategy ◽  
Image Interpretation ◽  
Area Under The Curve ◽  
Regional Patterns ◽  
X Ray ◽  
Disease Patterns ◽  
Sensitivity Specificity ◽  
Pulmonary Abnormalities

Abstract We evaluated the efficacy of a curriculum learning strategy using two steps to detect pulmonary abnormalities including nodule[s], consolidation, interstitial opacity, pleural effusion, and pneumothorax with chest-PA X-ray (CXR) images from two centres. CXR images of 6069 healthy subjects and 3417 patients at AMC and 1035 healthy subjects and 4404 patients at SNUBH were obtained. Our approach involved two steps. First, the regional patterns of thoracic abnormalities were identified by initial learning of patch images around abnormal lesions. Second, Resnet-50 was fine-tuned using the entire images. The network was weakly trained and modified to detect various disease patterns. Finally, class activation maps (CAM) were extracted to localise and visualise the abnormal patterns. For average disease, the sensitivity, specificity, and area under the curve (AUC) were 85.4%, 99.8%, and 0.947, respectively, in the AMC dataset and 97.9%, 100.0%, and 0.983, respectively, in the SNUBH dataset. This curriculum learning and weak labelling with high-scale CXR images requires less preparation to train the system and could be easily extended to include various diseases in actual clinical environments. This algorithm performed well for the detection and classification of five disease patterns in CXR images and could be helpful in image interpretation.

A Brief Survey on Text Classification Using Various Machine Learning Techniques

2018 ◽  
Vol 8 (1) ◽  
pp. 14
Author(s):  
Padmavathi .S ◽  
M. Chidambaram
Keyword(s):  
Machine Learning ◽  
Text Classification ◽  
Fixed Number ◽  
Machine Learning Techniques ◽  
Online Information ◽  
Rule Based ◽  
Learning Techniques ◽  
Machine Learning Approach ◽  
Rule Based Approach

Text classification has grown into more significant in managing and organizing the text data due to tremendous growth of online information. It does classification of documents in to fixed number of predefined categories. Rule based approach and Machine learning approach are the two ways of text classification. In rule based approach, classification of documents is done based on manually defined rules. In Machine learning based approach, classification rules or classifier are defined automatically using example documents. It has higher recall and quick process. This paper shows an investigation on text classification utilizing different machine learning techniques.

Discriminating Malignancy in Thyroid Nodules: The Nomogram Versus the Kwak and ACR TI-RADS

2020 ◽  
Vol 163 (6) ◽  
pp. 1156-1165
Author(s):  
Juan Xiao ◽  
Qiang Xiao ◽  
Wei Cong ◽  
Ting Li ◽  
Shouluan Ding ◽  
...  
Keyword(s):  
Thyroid Nodules ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Diagnostic Study ◽  
Diagnostic Efficiency ◽  
Training Set ◽  
Multivariable Logistic Regression Model ◽  
Predictive Values ◽  
Validation Set ◽  
Sensitivity Specificity

Objective To develop an easy-to-use nomogram for discrimination of malignant thyroid nodules and to compare diagnostic efficiency with the Kwak and American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI-RADS). Study Design Retrospective diagnostic study. Setting The Second Hospital of Shandong University. Subjects and Methods From March 2017 to April 2019, 792 patients with 1940 thyroid nodules were included into the training set; from May 2019 to December 2019, 174 patients with 389 nodules were included into the validation set. Multivariable logistic regression model was used to develop a nomogram for discriminating malignant nodules. To compare the diagnostic performance of the nomogram with the Kwak and ACR TI-RADS, the area under the receiver operating characteristic curve, sensitivity, specificity, and positive and negative predictive values were calculated. Results The nomogram consisted of 7 factors: composition, orientation, echogenicity, border, margin, extrathyroidal extension, and calcification. In the training set, for all nodules, the area under the curve (AUC) for the nomogram was 0.844, which was higher than the Kwak TI-RADS (0.826, P = .008) and the ACR TI-RADS (0.810, P < .001). For the 822 nodules >1 cm, the AUC of the nomogram was 0.891, which was higher than the Kwak TI-RADS (0.852, P < .001) and the ACR TI-RADS (0.853, P < .001). In the validation set, the AUC of the nomogram was also higher than the Kwak and ACR TI-RADS ( P < .05), each in the whole series and separately for nodules >1 or ≤1 cm. Conclusions When compared with the Kwak and ACR TI-RADS, the nomogram had a better performance in discriminating malignant thyroid nodules.

S-CCCapsule: Pneumonia detection in chest X-ray images using skip-connected convolutions and capsule neural network

2021 ◽  
pp. 1-25
Author(s):  
Kwabena Adu ◽  
Yongbin Yu ◽  
Jingye Cai ◽  
Victor Dela Tattrah ◽  
James Adu Ansere ◽  
...  
Keyword(s):  
Neural Network ◽  
Human Error ◽  
Medical Center ◽  
Confusion Matrix ◽  
Area Under The Curve ◽  
Dynamic Routing ◽  
Sigmoid Function ◽  
Radiological Society ◽  
Chest X Ray ◽  
Sensitivity Specificity

The squash function in capsule networks (CapsNets) dynamic routing is less capable of performing discrimination of non-informative capsules which leads to abnormal activation value distribution of capsules. In this paper, we propose vertical squash (VSquash) to improve the original squash by preventing the activation values of capsules in the primary capsule layer to shrink non-informative capsules, promote discriminative capsules and avoid high information sensitivity. Furthermore, a new neural network, (i) skip-connected convolutional capsule (S-CCCapsule), (ii) Integrated skip-connected convolutional capsules (ISCC) and (iii) Ensemble skip-connected convolutional capsules (ESCC) based on CapsNets are presented where the VSquash is applied in the dynamic routing. In order to achieve uniform distribution of coupling coefficient of probabilities between capsules, we use the Sigmoid function rather than Softmax function. Experiments on Guangzhou Women and Children’s Medical Center (GWCMC), Radiological Society of North America (RSNA) and Mendeley CXR Pneumonia datasets were performed to validate the effectiveness of our proposed methods. We found that our proposed methods produce better accuracy compared to other methods based on model evaluation metrics such as confusion matrix, sensitivity, specificity and Area under the curve (AUC). Our method for pneumonia detection performs better than practicing radiologists. It minimizes human error and reduces diagnosis time.

Sign in / Sign up

Export Citation Format

Share Document