Computer-aided Classification System Research Articles

PolyDSS: computer-aided decision support system for multiclass polyp segmentation and classification using deep learning

Colorectal cancer (CRC) is a malignant condition that affects the colon or rectum, and it is distinguished by abnormal cell growth in these areas. Colon polyps, which are abnormalities, can turn into cancer. To stop the spread of cancer, early polyp detection is essential. The timely removal of polyps without submitting a sample for histology is made possible by computer-assisted polyp classification. In addition to Locally Shared Features (LSF) and ensemble learning majority voting, this paper introduces a computer-aided decision support system named PolyDSS to assist endoscopists in segmenting and classifying various polyp classes using deep learning models like ResUNet and ResUNet++ and transfer learning models like EfficientNet. The PICCOLO dataset is used to train and test the PolyDSS model. To address the issue of class imbalance, data augmentation techniques were used on the dataset. To investigate the impact of each technique on the model, extensive experiments were conducted. While the classification module achieved the highest accuracy of 0.9425 by utilizing the strength of ensemble learning using majority voting, the proposed segmenting module achieved the highest Dice Similarity Coefficient (DSC) of 0.9244 using ResUNet++ and LSF. In conjunction with the Paris classification system, the PolyDSS model, with its significant results, can assist clinicians in identifying polyps early and choosing the best approach to treatment.

Retracted: A Rapid Artificial Intelligence-Based Computer-Aided Diagnosis System for COVID-19 Classification from CT Images.

[This retracts the article DOI: 10.1155/2021/2560388.].

The feasibility of a novel computer-aided classification system for the characterisation and diagnosis of breast masses on ultrasound: a single-centre preliminary test study

To introduce a novel computer-aided classification (CAC) system and investigate the feasibility of characterising and diagnosing breast masses on ultrasound (US). A total of 246 breast masses were included. US features and the final assessment categories of the breast masses were analysed by a radiologist and the CAC system according to the Breast Imaging Reporting and Data System (BI-RADS) lexicon. The CAC system evaluated the BI-RADS assessment from the fusion of multi-view and colour Doppler US images without (SmartBreast) or with combining clinical variables (m-CAC system). The diagnostic performance and agreement of US characteristics between the radiologist and the CAC system were compared. The agreement between the radiologist and the CAC system was substantial for mass shape (κ=0.673), orientation (κ=0.682), margin (κ=0.622), posterior features (κ=0.629), calcifications in a mass (κ=0.709) and vascularity (κ=0.745), fair for echo pattern (κ=0.379), and moderate for BI-RADS assessment (κ=0.575). With BI-RADS 4a as the cut-off value, the specificity (52.5% versus 25%, p<0.0001) and accuracy (73.98% versus 62.6%, p=0.0002) of the m-CAC system were improved without significant loss of sensitivity (94.44% versus 98.41%, p=0.1250) compared with the SmartBreast. The m-CAC system showed similar specificity (52.5% versus 45.83%, p=0.2430) and accuracy (73.98% versus 73.58%, p=1.0000) as the radiologist, but a lower sensitivity (94.44% versus 100%, p=0.0156). The CAC system showed an acceptable agreement with the radiologist for characterisation of breast lesions. It has the potential to mimic the decision-making behaviour of radiologists for the classification of breast lesions.

Support of deep learning to classify vocal fold images in flexible laryngoscopy

PurposeTo collect a dataset with adequate laryngoscopy images and identify the appearance of vocal folds and their lesions in flexible laryngoscopy images by objective deep learning models. MethodsWe adopted a number of novel deep learning models to train and classify 4549 flexible laryngoscopy images as no vocal fold, normal vocal folds, and abnormal vocal folds. This could help these models recognize vocal folds and their lesions within these images. Ultimately, we made a comparison between the results of the state-of-the-art deep learning models, and another comparison of the results between the computer-aided classification system and ENT doctors. ResultsThis study exhibited the performance of the deep learning models by evaluating laryngoscopy images collected from 876 patients. The efficiency of the Xception model was higher and steadier than almost the rest of the models. The accuracy of no vocal fold, normal vocal folds, and vocal fold abnormalities on this model were 98.90 %, 97.36 %, and 96.26 %, respectively. Compared to our ENT doctors, the Xception model produced better results than a junior doctor and was near an expert. ConclusionOur results show that current deep learning models can classify vocal fold images well and effectively assist physicians in vocal fold identification and classification of normal or abnormal vocal folds.

Simulation en dermatologie 1 : consultation d’annonce d’un mélanome

To collect a dataset with adequate laryngoscopy images and identify the appearance of vocal folds and their lesions in flexible laryngoscopy images by objective deep learning models.We adopted a number of novel deep learning models to train and classify 4549 flexible laryngoscopy images as no vocal fold, normal vocal folds, and abnormal vocal folds. This could help these models recognize vocal folds and their lesions within these images. Ultimately, we made a comparison between the results of the state-of-the-art deep learning models, and another comparison of the results between the computer-aided classification system and ENT doctors.This study exhibited the performance of the deep learning models by evaluating laryngoscopy images collected from 876 patients. The efficiency of the Xception model was higher and steadier than almost the rest of the models. The accuracy of no vocal fold, normal vocal folds, and vocal fold abnormalities on this model were 98.90 %, 97.36 %, and 96.26 %, respectively. Compared to our ENT doctors, the Xception model produced better results than a junior doctor and was near an expert.Our results show that current deep learning models can classify vocal fold images well and effectively assist physicians in vocal fold identification and classification of normal or abnormal vocal folds.

An expert system for lesion detection in wireless capsule endoscopy using transfer learning

Wireless Capsule Endoscopic (WCE) is a powerful diagnostic tool that has proven especially useful in imaging the small intestine. Currently its use is limited due to the production of a considerable number of images whose analysis is an extremely time-consuming process. The present work presents the design and implementation of a novel computer-aided diagnosis system for automatic classification of images acquired by the capsule into image with and without lesion. Our expert system is based on the concept of transfer learning which reuses features of pre-trained neural networks needing little data. Two pre-trained deep convolutional neural (ResNet50 and Inception V4) were used for feature extraction. Then, the selected features are combined using the minimum Redundancy Maximum Relevance technique. For the final classifier layer, specific machine learning classifiers that have shown promising results in previous medical images studies were compared. The experiments performed on two standard benchmark datasets demonstrated that our expert system outclass the single deep learning architectures, with an average accuracy in detection lesions of 98.09 % on KID Dataset 2 and 94.48 % on MICCAI 2017. The best results in terms of accuracy and training time were obtained using Support Vector Machine as classifier.

Chest X-Ray Examiner

Abstract: The most common image taken in the medical field for diagnosis of any ailment affecting the chest is chest radiography (Chest X-ray). The most common image taken in the medical field for diagnosis of any ailment affecting the chest or neighboring area is chest radiography (Chest X-ray). The use of this approach has been limited due to a scarcity of qualified radiologists. To address this issue, we are developing a computer-aided diagnosis system for chest X-ray disease classification that employs DNN (Deep Neural Network) Transfer learning. CXE (Chest X-Ray Examiner) is a web-based program that works in conjunction with our machine learning console. The most common image taken in the medical field for diagnosis of any ailment affecting the chest is chest radiography (Chest X-ray). There is a Rest API application that serves as a middleman between our user interface and machine learning applications. We used our machine learning console application produced by ML.NET to train our own model using the Mobile.Net v3 Image categorization method. By obtaining X-Ray images from end users, the Chest X-Ray Examiner (CXE) can classify the chest disease name and forecast the accuracy level of that disease. Keywords: Chest X-ray, DNN, API, ML.NET, Chest X-Ray Examiner

Computer-aided diagnosis system for retinal disorder classification using optical coherence tomography images

The incidence of vision impairment is rapidly increasing. Diagnosis and classifying retinal abnormalities in ophthalmological applications is a significant challenge. Using Optical Coherence Tomography (OCT), the study aims to develop a computer aided diagnosis system for detecting and classifying retinal disorders. Choroidal neovascularization, diabetic macular edema, drusen, and normal cases are the investigated groups. Both deep learning and machine learning are combined to build the system. The SqueezeNet neural network was modified toextract features. The Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), Decision Tree (DT), and Ensemble Model (EM) algorithms were used for disorder classification. The Bayesian optimization technique was also used to determine the best hyperparameters for each model. The model' performance was evaluated through nine criteria using 12,000 OCT images. The results have demonstrated accuracies of 97.39, 97.47, 96.98, and 95.25% for the SVM, K-NN, DT, and EM, respectively. When results are compared to relevant studies in terms of accuracy andtested samples, they show superior performance. As aresult, a novel computer-aided diagnosis system for detecting and classifying retinal diseases has been developed, reducing human error while also saving time.

Classification of melanoma images using 2D multifractal detrended cross-correlation analysis

Skin cancer is a common human malignant tumor and melanoma is one of the most fatal diseases in skin cancer. There exists a high degree of visual similarity between melanoma and non-melanoma. In addition, the acquisition and labeling of skin cancer images need relevant medical knowledge, therefore, it is difficult to obtain natural images. These problems make it difficult to distinguish between melanoma and non-melanoma. How to extract the high-dimensional features of skin cancer images is the main problem to improve the classification performance of skin cancer images. For this purpose, we propose a new computer-aided classification system with a two-dimensional (2D) multifractal detrended fluctuation analysis (MF-DCCA) method and classifier combination. The proposed 2D MF-DCCA is expanded by the 2D MF-DFA and we aim to change the distribution of the generalized Hurst exponents calculated by the original 2D MF-DFA, making the image features represented by the generalized Hurst exponents calculated by 2D MF-DCCA are more significant. Therefore, we take the generalized Hurst exponents calculated by the two methods into the classifier and evaluate their classification performance. The classification metrics, such as Accuracy (Acc), Sensitivity (Sen), and Specificity (Spe) of two classifiers, show that the features extracted by MF-DCCA are better than those by MF-DFA. In addition, among the two classifiers such as the SVM and k-NN, the k-NN performs best in Acc and Spe with [Formula: see text] and [Formula: see text], respectively. The k-NN performs better than SVM in the classification Sen with [Formula: see text].

Computer-Aided Classification Framework of Parkinsonian Disorders Using 11C-CFT PET Imaging.

PurposeTo investigate the usefulness of a novel computer-aided classification framework for the differential diagnosis of parkinsonian disorders (PDs) based on 11C-methyl-N-2β-carbomethoxy-3β-(4-fluorophenyl)-tropanel (11C-CFT) positron emission tomography (PET) imaging.MethodsPatients with different forms of PDs—including Parkinson's disease (PD), multiple system atrophy (MSA) and progressive supranuclear palsy (PSP)—underwent dopamine transporter (DAT) imaging with 11C-CFT PET. A novel multistep computer-aided classification framework—consisting of magnetic resonance imaging (MRI)-assisted PET segmentation, feature extraction and prediction, and automatic subject classification—was developed. A random forest method was used to assess the diagnostic relevance of different regions to the classification process. Finally, the performance of the computer-aided classification system was tested using various training strategies involving patients with early and advanced disease stages.ResultsAccuracy values for identifying PD, MSA, and PSP were 85.0, 82.2, and 89.7%, respectively—with an overall accuracy of 80.4%. The caudate and putamen provided the highest diagnostic relevance to the proposed classification framework, whereas the contribution of midbrain was negligible. With the exception of sensitivity for diagnosing PSP, the strategy comprising both early and advanced disease stages performed better in terms of sensitivity, specificity, positive predictive value, and negative predictive value within each PDs subtype.ConclusionsThe proposed computer-aided classification framework based on 11C-CFT PET imaging holds promise for improving the differential diagnosis of PDs.

A Rapid Artificial Intelligence-Based Computer-Aided Diagnosis System for COVID-19 Classification from CT Images.

The excessive number of COVID-19 cases reported worldwide so far, supplemented by a high rate of false alarms in its diagnosis using the conventional polymerase chain reaction method, has led to an increased number of high-resolution computed tomography (CT) examinations conducted. The manual inspection of the latter, besides being slow, is susceptible to human errors, especially because of an uncanny resemblance between the CT scans of COVID-19 and those of pneumonia, and therefore demands a proportional increase in the number of expert radiologists. Artificial intelligence-based computer-aided diagnosis of COVID-19 using the CT scans has been recently coined, which has proven its effectiveness in terms of accuracy and computation time. In this work, a similar framework for classification of COVID-19 using CT scans is proposed. The proposed method includes four core steps: (i) preparing a database of three different classes such as COVID-19, pneumonia, and normal; (ii) modifying three pretrained deep learning models such as VGG16, ResNet50, and ResNet101 for the classification of COVID-19-positive scans; (iii) proposing an activation function and improving the firefly algorithm for feature selection; and (iv) fusing optimal selected features using descending order serial approach and classifying using multiclass supervised learning algorithms. We demonstrate that once this method is performed on a publicly available dataset, this system attains an improved accuracy of 97.9% and the computational time is almost 34 (sec).

Classification of large-scale image database of various skin diseases using deep learning.

The purpose of this study was to develop a deep learning-based computer-aided diagnosis system for skin disease classification using photographic images of patients. The targets are 59 skin diseases, including localized and diffuse diseases captured by photographic cameras, resulting in highly diverse images in terms of the appearance of the diseases or photographic conditions. ResNet-18 is used as a baseline model for classification and is reinforced by metric learning to boost generalization in classification by avoiding the overfitting of the training data and increasing the reliability of CADx for dermatologists. Patient-wise classification is performed by aggregating the inference vectors of all the input patient images. The experiment using 70,196 images of 13,038 patients demonstrated that classification accuracy was significantly improved by both metric learning and aggregation, resulting in patient accuracies of 0.579 for Top-1, 0.793 for Top-3, and 0.863 for Top-5. The McNemar test showed that the improvements achieved by the proposed method were statistically significant. This study presents a deep learning-based classification of 59 skin diseases using multiple photographic images of a patient. The experimental results demonstrated that the proposed classification reinforced by metric learning and aggregation of multiple input images was effective in the classification of patients with diverse skin diseases and imaging conditions.

Attention mechanism and mixup data augmentation for classification of COVID-19 Computed Tomography images

The Coronavirus disease is quickly spreading all over the world and the emergency situation is still out of control. Latest achievements of deep learning algorithms suggest the use of deep Convolutional Neural Network to implement a computer-aided diagnostic system for automatic classification of COVID-19 CT images. In this paper, we propose to employ a feature-wise attention layer in order to enhance the discriminative features obtained by convolutional networks. Moreover, the original performance of the network has been improved using the mixup data augmentation technique. This work compares the proposed attention-based model against the stacked attention networks, and traditional versus mixup data augmentation approaches. We deduced that feature-wise attention extension, while outperforming the stacked attention variants, achieves remarkable improvements over the baseline convolutional neural networks. That is, ResNet50 architecture extended with a feature-wise attention layer obtained 95.57% accuracy score, which, to best of our knowledge, fixes the state-of-the-art in the challenging COVID-CT dataset.

Multi-objective techniques for feature selection and classification in digital mammography

Feature selection is a crucial stage in the design of a computer-aided classification system for breast cancer diagnosis. The main objective of the proposed research design is to discover the use of multi-objective particle swarm optimization (MOPSO) and Nondominated sorting genetic algorithm-III (NSGA-III) for feature selection in digital mammography. The Pareto-optimal fronts generated by MOPSO and NSGA-III for two conflicting objective functions are used to select optimal features. An artificial neural network (ANN) is used to compute the fitness of objective functions. The importance of features selected by MOPSO and NSGA-III are assessed using artificial neural networks. The experimental results show that MOPSO based optimization is superior to NSGA-III. MOPSO achieves high accuracy with a 55% feature reduction. MOPSO based feature selection and classification deliver an efficiency of 97.54% with 98.22% sensitivity, 96.82% specificity, 0.9508 Cohen’s kappa coefficient, and area under curve AZ= 0.983 ± 0.003.

A CNN based framework for classification of Alzheimer’s disease

In the current decade, advances in health care are attracting widespread interest due to their contributions to people longer surviving and fitter lives. Alzheimer’s disease (AD) is the commonest neurodegenerative and dementing disease. The monetary value of caring for Alzheimer’s disease patients is involved to rise dramatically. The necessity of having a computer-aided system for early and accurate AD classification becomes crucial. Deep-learning algorithms have notable advantages rather than machine learning methods. Many recent research studies that have used brain MRI scans and convolutional neural networks (CNN) achieved promising results for the diagnosis of Alzheimer’s disease. Accordingly, this study proposes a CNN based end-to-end framework for AD-classification. The proposed framework achieved 99.6%, 99.8%, and 97.8% classification accuracies on Alzheimer’s disease Neuroimaging Initiative (ADNI) dataset for the binary classification of AD and Cognitively Normal (CN). In multi-classification experiments, the proposed framework achieved 97.5% classification accuracy on the ADNI dataset.

Novel system in vitro of classifying oral carcinogenesis based on feature extraction for gray-level co-occurrence matrix using scanned laser pico projector.

Oral cancer is among the top 10 causes of death due to cancer worldwide. The prognosis for oral cancer patients is not good, with a 5-year survival rate of only 50%. Earlier and more precise classification will help clinicians make a diagnosis and patients survive. With the advancement of technology, computer-aided detection methods are used to help clinicians form therapy strategies. Gray-level co-occurrence matrix (GLCM) feature extraction of images describing the spatial distribution of gray levels is widely used in medical imaging analysis. Scanned laser pico projector (SLPP) has advantages such as high intensity, directivity, coherence, and mono-color with low bandwidth. In this study, GLCM feature extraction and SLPP reflex images were combined to make a small, non-staining, noninvasive classification system. According to the various image characteristics in oral carcinogenesis, SLPP reflex images better define the borders and three-dimensional structures and provide effective GLCM features such as contrast, energy, and homogeneity to classify carcinogenesis in dysplastic oral keratinocyte (DOK) and normal oral keratinocyte (NOK) cells. Moreover, it also reliably classifies highly metastatic (HSC-3) and tongue cancer (CAL-27) cells. A promising computer-aided classification system for oral cancer was developed to build a reliable intraoral examination system for in situ computer-aided diagnosis in normal clinics.

Automatic computer-aided diagnosis system for mass detection and classification in mammography

Mammography is currently the most powerful technique for early detection of breast cancer. To assist radiologists to better interpret mammogram images, computer-aided detection and diagnosis (CAD) systems have been proposed. This paper proposes a complete CAD system for mass detection and diagnosis, which consists of four steps. The first step consists of the preprocessing where the image is enhanced and the noise removed. In the second step, the abnormalities are segmented using the proposed HRAK algorithm. In the third step, the false positives are reduced using texture and shape features and the bagged trees classifier. Finally, the support vector machine (SVM) is used to classify the abnormalities as malignant or benign. The proposed CAD system is verified with both the MIAS and CBIS-DDSM databases. The experimental results proved to be successful. The accuracy detection rate achieves 93,15% for sensitivity and 0,467 FPPI for MIAS and 90,85% for sensitivity and 0,65 FPPI for CBIS-DDSM. The accuracy classification rate achieves 94,2% and the AUC 0,95 for MIAS and 90,44% and 0,9 for CBIS-DDSM.

FAB classification of acute leukemia using an ensemble of neural networks

Acute leukemia is the most frequently occurring malignancy present in human blood and a kind of liquid cancer. This hematological disorder can impinge on bone marrow and lymphatic system. Accordingly, a computer-aided classification system is proposed for French–American–British classification of Acute Leukemia using an ensemble of neural networks which is validated on 180 microscopic blood images taken from online benchmark dataset. As per the requirement of pathologists in real-life examination scenario various objectives are formulated as (i) correct nucleus segmentation in blood cell image, (ii) correct classification of FAB classes of acute leukemia (L1, L2, L3, M2, M3, and M5). To accomplish these research objectives the proposed method consist of segmentation section, feature extraction section, feature pruning section and classification section. The classification of the proposed method consists of two subsections as subsection1 is comprised of single six class PCA based neural network as PCA-NN0 (L1/L2/L3/M2/M3/M5) and subsection 2 contains an ensemble of 15 binary PCA based neural network classifiers as PCA-NN1 (L1/L2), PCA-NN2(L1/L3), PCA-NN3(L1/M2), PCA-NN4(L1/M3), PCA-NN5(L1/M5), PCA-NN6(L2/L3), PCA-NN7(L2/M2), PCA-NN8(L2/M3), PCA-NN9(L2/M5), PCA-NN10(L3/M2), PCA-NN11(L3/M3), PCA-NN12(L3/M5), PCA-NN13(M2/M3), PCA-NN14(M2/M5), PCA-NN15(M3/M5). The achieved accuracy for experiment 1 is 86.4% using PCA-NN0. The output of two most plausible classes predicted by PCA-NN0 is passed to other binary PCA based neural network i.e. PCA-NN1 to PCA-NN15. After passing all the test images to subsection 2, the achieved accuracy is 94.2% from the exhaustive experiment 2. The outcome of the work verifies the capabilities of computer-aided classification system to substitute the conventional diagnostic systems.

Sanders classification of calcaneal fractures in CT images with deep learning and differential data augmentation techniques

BackgroundClassification of the type of calcaneal fracture on CT images is essential in driving treatment. However, human-based classification can be challenging due to anatomical complexities and CT image constraints. The use of computer-aided classification system in standard practice is additionally hindered by the availability of training images. The aims of this study is to 1) propose a deep learning network combined with data augmentation technique to classify calcaneal fractures on CT images into the Sanders system, and 2) assess the efficiency of such approach with differential training methods. MethodsIn this study, the Principle component analysis (PCA) network was selected for the deep learning neural network architecture for its superior performance. CT calcaneal images were processed through PCA filters, binary hashing, and a block-wise histogram. The Augmentor pipeline including rotation, distortion, and flips was applied to generate artificial calcaneus fractured images. Two types of training approaches and five data sample sizes were investigated to evaluate the performance of the proposed system with and without data augmentation. ResultsCompared to the original performance, use of augmented images during training improved network performance accuracy by almost twofold in classifying Sanders fracture types for all dataset sizes. A fivefold increase in the number of augmented training images improved network classification accuracy by 35%. The proposed deep CNN model achieved 72% accuracy in classifying CT calcaneal images into the four Sanders categories when trained with sufficient augmented artificial images. ConclusionThe proposed deep-learning algorithm coupled with data augmentation provides a feasible and efficient approach to the use of computer-aided system in assisting physicians in evaluating calcaneal fracture types.

Computer-aided classification of suspicious pigmented lesions using wide-field images

Background and objectiveEarly identification of melanoma is conducted through whole-body visual examinations to detect suspicious pigmented lesions, a situation that fluctuates in accuracy depending on the experience and time of the examiner. Computer-aided diagnosis tools for skin lesions are typically trained using pre-selected single-lesion images, taken under controlled conditions, which limits their use in wide-field scenes. Here, we propose a computer-aided classifier system with such input conditions to aid in the rapid identification of suspicious pigmented lesions at the primary care level. Methods133 patients with a multitude of skin lesions were recruited for this study. All lesions were examined by a board-certified dermatologist and classified into “suspicious” and “non-suspicious”. A new clinical database was acquired and created by taking Wide-Field images of all major body parts with a consumer-grade camera under natural illumination condition and with a consistent source of image variability. 3–8 images were acquired per patient on different sites of the body, and a total of 1759 pigmented lesions were extracted. A machine learning classifier was optimized and build into a computer aided classification system to binary classify each lesion using a suspiciousness score. ResultsIn a testing set, our computer-aided classification system achieved a sensitivity of 100% for suspicious pigmented lesions that were later confirmed by dermoscopy examination (“SPL_A”) and 83.2% for suspicious pigmented lesions that were not confirmed after examination (“SPL_B”). Sensitivity for non-suspicious lesions was 72.1%, and accuracy was 75.9%. With these results we defined a suspiciousness score that is aligned with common macro-screening (naked eye) practices. ConclusionsThis work demonstrates that wide-field photography combined with computer-aided classification systems can distinguish suspicious from non-suspicious pigmented lesions, and might be effective to assess the severity of a suspicious pigmented lesions. We believe this approach could be useful to support skin screenings at a population-level.