Computer-aided diagnosis for breast cancer classification using deep neural networks and transfer learning

BACKGROUND AND OBJECTIVE

 Many developed and non-developed countries worldwide suffer from cancer-related fatal diseases. In particular, the rate of breast cancer in females increases daily, partially due to unawareness and undiagnosed at the early stages. A proper first breast cancer treatment can only be provided by adequately detecting and classifying cancer during the very early stages of its development. The use of medical image analysis techniques and computer-aided diagnosis may help the acceleration and the automation of both cancer detection and classification by also training and aiding less experienced physicians. For large datasets of medical images, convolutional neural networks play a significant role in detecting and classifying cancer effectively.

METHODS

 This article presents a novel computer-aided diagnosis method for breast cancer classification (both binary and multi-class), using a combination of deep neural networks (ResNet 18, ShuffleNet, and Inception-V3Net) and transfer learning on the BreakHis publicly available dataset.

RESULTS AND CONCLUSIONS

 Our proposed method provides the best average accuracy for binary classification of benign or malignant cancer cases of 99.7%, 97.66%, and 96.94% for ResNet, InceptionV3Net, and ShuffleNet, respectively. Average accuracies for multi-class classification were 97.81%, 96.07%, and 95.79% for ResNet, Inception-V3Net, and ShuffleNet, respectively.

Perioperative intravenous contrast administration and the incidence of acute kidney injury after major gastrointestinal surgery: prospective, multicentre cohort study

BACKGROUND

This study aimed to determine the impact of preoperative exposure to intravenous contrast for CT and the risk of developing postoperative acute kidney injury (AKI) in patients undergoing major gastrointestinal surgery.

METHODS

This prospective, multicentre cohort study included adults undergoing gastrointestinal resection, stoma reversal or liver resection. Both elective and emergency procedures were included. Preoperative exposure to intravenous contrast was defined as exposure to contrast administered for the purposes of CT up to 7 days before surgery. The primary endpoint was the rate of AKI within 7 days. Propensity score-matched models were adjusted for patient, disease and operative variables. In a sensitivity analysis, a propensity score-matched model explored the association between preoperative exposure to contrast and AKI in the first 48 h after surgery.

RESULTS

A total of 5378 patients were included across 173 centres. Overall, 1249 patients (23·2 per cent) received intravenous contrast. The overall rate of AKI within 7 days of surgery was 13·4 per cent (718 of 5378). In the propensity score-matched model, preoperative exposure to contrast was not associated with AKI within 7 days (odds ratio (OR) 0·95, 95 per cent c.i. 0·73 to 1·21; P = 0·669). The sensitivity analysis showed no association between preoperative contrast administration and AKI within 48 h after operation (OR 1·09, 0·84 to 1·41; P = 0·498).

CONCLUSION

There was no association between preoperative intravenous contrast administered for CT up to 7 days before surgery and postoperative AKI. Risk of contrast-induced nephropathy should not be used as a reason to avoid contrast-enhanced CT.

Detection of Heart Arrhythmia on Electrocardiogram using Artificial Neural Networks

The electrocardiogram, also known as an electrocardiogram (ECG), is considered to be one of the most significant sources of data regarding the structure and function of the heart. In order to obtain an electrocardiogram, the contractions and relaxations of the heart are first captured in the proper recording medium. Due to the fact that irregularities in the functioning of the heart are reflected in the ECG indications, it is possible to use these indications to diagnose cardiac issues. Arrhythmia is the medical term for the abnormalities that might occur in the regular functioning of the heart (rhythm disorder). Environmental and genetic variables can both play a role in the development of arrhythmias. Arrhythmias are reflected on the ECG sign, which depicts the same region regardless of where in the heart they occur; thus, they may be seen in ECG signals. This is how arrhythmias can be detected. Due to the time limits of this study, the ECG signals of individuals who were healthy, as well as those who suffered from arrhythmias were divided into 10-minute segments. The arithmetic mean approach is one of the fundamental statistical factors. It is used to construct the feature vectors of each received wave and interval, and these vectors offer information regarding arrhythmias in accordance with the agreed-upon temporal restrictions. In order to identify the heart arrhythmias, the obtained feature vectors are fed into a classifier that is based on a multilayer perceptron neural network. In conclusion, ROC analysis and contrast matrix are utilised in order to evaluate the overall correct classification result produced by the ECG-based classifier. Because of this, it has been demonstrated that the method that was recommended has high classification accuracy when attempting to diagnose arrhythmia based on ECG indications. This research makes use of a variety of diagnostic terminologies, including ECG signal, multilayer perceptron neural network, signal processing, disease diagnosis, and arrhythmia diagnosis.

Brain tumor classification from MRI scans: a framework of hybrid deep learning model with Bayesian optimization and quantum theory-based marine predator algorithm

Brain tumor classification is one of the most difficult tasks for clinical diagnosis and treatment in medical image analysis. Any errors that occur throughout the brain tumor diagnosis process may result in a shorter human life span. Nevertheless, most currently used techniques ignore certain features that have particular significance and relevance to the classification problem in favor of extracting and choosing deep significance features. One important area of research is the deep learning-based categorization of brain tumors using brain magnetic resonance imaging (MRI). This paper proposes an automated deep learning model and an optimal information fusion framework for classifying brain tumor from MRI images. The dataset used in this work was imbalanced, a key challenge for training selected networks. This imbalance in the training dataset impacts the performance of deep learning models because it causes the classifier performance to become biased in favor of the majority class. We designed a sparse autoencoder network to generate new images that resolve the problem of imbalance. After that, two pretrained neural networks were modified and the hyperparameters were initialized using Bayesian optimization, which was later utilized for the training process. After that, deep features were extracted from the global average pooling layer. The extracted features contain few irrelevant information; therefore, we proposed an improved Quantum Theory-based Marine Predator Optimization algorithm (QTbMPA). The proposed QTbMPA selects both networks' best features and finally fuses using a serial-based approach. The fused feature set is passed to neural network classifiers for the final classification. The proposed framework tested on an augmented Figshare dataset and an improved accuracy of 99.80%, a sensitivity rate of 99.83%, a false negative rate of 17%, and a precision rate of 99.83% is obtained. Comparison and ablation study show the improvement in the accuracy of this work.

Combining CNN Features with Voting Classifiers for Optimizing Performance of Brain Tumor Classification

Brain tumors and other nervous system cancers are among the top ten leading fatal diseases. The effective treatment of brain tumors depends on their early detection. This research work makes use of 13 features with a voting classifier that combines logistic regression with stochastic gradient descent using features extracted by deep convolutional layers for the efficient classification of tumorous victims from the normal. From the first and second-order brain tumor features, deep convolutional features are extracted for model training. Using deep convolutional features helps to increase the precision of tumor and non-tumor patient classification. The proposed voting classifier along with convoluted features produces results that show the highest accuracy of 99.9%. Compared to cutting-edge methods, the proposed approach has demonstrated improved accuracy.

Breast Cancer Classification Using Synthesized Deep Learning Model with Metaheuristic Optimization Algorithm

Breast cancer is the second leading cause of mortality among women. Early and accurate detection plays a crucial role in lowering its mortality rate. Timely detection and classification of breast cancer enable the most effective treatment. Convolutional neural networks (CNNs) have significantly improved the accuracy of tumor detection and classification in medical imaging compared to traditional methods. This study proposes a comprehensive classification technique for identifying breast cancer, utilizing a synthesized CNN, an enhanced optimization algorithm, and transfer learning. The primary goal is to assist radiologists in rapidly identifying anomalies. To overcome inherent limitations, we modified the Ant Colony Optimization (ACO) technique with opposition-based learning (OBL). The Enhanced Ant Colony Optimization (EACO) methodology was then employed to determine the optimal hyperparameter values for the CNN architecture. Our proposed framework combines the Residual Network-101 (ResNet101) CNN architecture with the EACO algorithm, resulting in a new model dubbed EACO-ResNet101. Experimental analysis was conducted on the MIAS and DDSM (CBIS-DDSM) mammographic datasets. Compared to conventional methods, our proposed model achieved an impressive accuracy of 98.63%, sensitivity of 98.76%, and specificity of 98.89% on the CBIS-DDSM dataset. On the MIAS dataset, the proposed model achieved a classification accuracy of 99.15%, a sensitivity of 97.86%, and a specificity of 98.88%. These results demonstrate the superiority of the proposed EACO-ResNet101 over current methodologies.

D2LFS2Net: Multi‐class skin lesion diagnosis using deep learning and variance‐controlled Marine Predator optimisation: An application for precision medicine

In computer vision applications like surveillance and remote sensing, to mention a few, deep learning has had considerable success. Medical imaging still faces a number of difficulties, including intra‐class similarity, a scarcity of training data, and poor contrast skin lesions, notably in the case of skin cancer. An optimisation‐aided deep learning‐based system is proposed for accurate multi‐class skin lesion identification. The sequential procedures of the proposed system start with preprocessing and end with categorisation. The preprocessing step is where a hybrid contrast enhancement technique is initially proposed for lesion identification with healthy regions. Instead of flipping and rotating data, the outputs from the middle phases of the hybrid enhanced technique are employed for data augmentation in the next step. Next, two pre‐trained deep learning models, MobileNetV2 and NasNet Mobile, are trained using deep transfer learning on the upgraded enriched dataset. Later, a dual‐threshold serial approach is employed to obtain and combine the features of both models. The next step was the variance‐controlled Marine Predator methodology, which the authors proposed as a superior optimisation method. The top features from the fused feature vector are classified using machine learning classifiers. The experimental strategy provided enhanced accuracy of 94.4% using the publicly available dataset HAM10000. Additionally, the proposed framework is evaluated compared to current approaches, with remarkable results.

Effectively Predicting the Presence of Coronary Heart Disease Using Machine Learning Classifiers

Coronary heart disease is one of the major causes of deaths around the globe. Predicating a heart disease is one of the most challenging tasks in the field of clinical data analysis. Machine learning (ML) is useful in diagnostic assistance in terms of decision making and prediction on the basis of the data produced by healthcare sector globally. We have also perceived ML techniques employed in the medical field of disease prediction. In this regard, numerous research studies have been shown on heart disease prediction using an ML classifier. In this paper, we used eleven ML classifiers to identify key features, which improved the predictability of heart disease. To introduce the prediction model, various feature combinations and well-known classification algorithms were used. We achieved 95% accuracy with gradient boosted trees and multilayer perceptron in the heart disease prediction model. The Random Forest gives a better performance level in heart disease prediction, with an accuracy level of 96%.

Enhancing Prediction of Brain Tumor Classification Using Images and Numerical Data Features

Brain tumors, along with other diseases that harm the neurological system, are a significant contributor to global mortality. Early diagnosis plays a crucial role in effectively treating brain tumors. To distinguish individuals with tumors from those without, this study employs a combination of images and data-based features. In the initial phase, the image dataset is enhanced, followed by the application of a UNet transfer-learning-based model to accurately classify patients as either having tumors or being normal. In the second phase, this research utilizes 13 features in conjunction with a voting classifier. The voting classifier incorporates features extracted from deep convolutional layers and combines stochastic gradient descent with logistic regression to achieve better classification results. The reported accuracy score of 0.99 achieved by both proposed models shows its superior performance. Also, comparing results with other supervised learning algorithms and state-of-the-art models validates its performance.

Impact of postoperative acute kidney injury in patients undergoing major gastrointestinal surgery on 1-year survival and renal outcomes: a national multicentre cohort study

BACKGROUND

The intermediate-term impact of acute kidney injury (AKI) in patients after major gastrointestinal and liver surgery has not been well characterized. This study aimed to evaluate the 1-year mortality rate and renal outcomes associated with postoperative AKI in a national prospective cohort.

METHODS

This prospective multicentre, observational cohort with 1-year postoperative follow-up included adults undergoing major gastrointestinal and liver surgery across the UK and Ireland between 23 September and 18 November 2015. AKI was defined according to Kidney Disease Improving Global Outcomes (KDIGO) criteria. The primary outcome was death at 1-year after surgery, and the secondary outcome was Major Adverse Kidney Events (MAKE-365). Cox proportionate and multilevel logistic regression were used to account for case mix.

RESULTS

Of 5745 patients across 173 centres, 1-year follow-up data was completed for 3504 patients (62.2 per cent, 126 centres), with attrition largely explained by centre non-participation (63.1 per cent). Some 13.6 per cent (475 of 3504) patients developed AKI by 7 days after surgery (stage 1: 9.2 per cent; stage 2/3: 4.3 per cent). At 1 year, 10.8 per cent (378 patients) experienced a MAKE-365 endpoint (303 patients had died, 61 had renal replacement therapy and 78 had renal dysfunction). Patients who experienced AKI by 7 days after surgery had a higher hazard of death at 1 year for KDIGO stage 1 (hazard ratio 1.50 (95 per cent c.i. 1.08 to 2.08), P = 0.016) and KDIGO stage 2/3 (hazard ratio 2.96 (95 per cent c.i. 2.02 to 4.33), P < 0.001). Both KDIGO stage 1 (odds ratio 2.09 (95 per cent c.i. 1.50 to 2.92), P < 0.001) and stage 2/3 (odds ratio 9.26 (95 per cent c.i. 6.31 to 13.59), P < 0.001) AKI were independently associated with MAKE-365.

CONCLUSION

AKI events within 7 days after gastrointestinal or liver surgery are associated with significantly worse survival and renal outcomes at 1 year.

A Secure Framework toward IoMT-Assisted Data Collection, Modeling, and Classification for Intelligent Dermatology Healthcare Services

The abnormal growth of the skin cells is known as skin cancer. It is one of the main problems in the dermatology area. Skin lesions or malignancies have been a source of worry for many individuals in recent years. Irrespective of the skin tone, there exist three major classes of skin lesions, i.e., basal cell carcinoma, squamous cell carcinoma, and melanoma. The early diagnosis of these lesions is equally important for human life. In the proposed work, a secure IoMT-Assisted framework is introduced that can help the patients to do the initial screening of skin lesions remotely. The initially proposed approach uses an IoMT-based data collection device which is accessible by patients to capture skin lesions images. Next, the captured skin sample is encrypted and sent to the collected image toward cloud storage. Later, the received sample image is classified into appropriate class labels using an ensemble classifier. In the proposed framework, four CNN models were ensemble i.e., VGG-16, DenseNet-201, Inception-V3, and Efficient-B7. The framework has experimented with the "HAM10000" dataset having 7 different kinds of skin lesions data. Although DenseNet-201 performed well, the ensemble model provides the highest accuracy with 87.22 percent as well as its test loss/error is lower than others with 0.4131. Moreover, the ensemble model's classification ability is much higher with an AUC score of 0.9745. Moreover, A recommendation team has been assigned to assess the sample of the patient as well as suggest the patient according to classified results by the CAD.

White blood cells classification using multi-fold pre-processing and optimized CNN model

White blood cells (WBCs) play a vital role in immune responses against infections and foreign agents. Different WBC types exist, and anomalies within them can indicate diseases like leukemia. Previous research suffers from limited accuracy and inflated performance due to the usage of less important features. Moreover, these studies often focus on fewer WBC types, exaggerating accuracy. This study addresses the crucial task of classifying WBC types using microscopic images. This study introduces a novel approach using extensive pre-processing with data augmentation techniques to produce a more significant feature set to achieve more promising results. The study conducts experiments employing both conventional deep learning and transfer learning models, comparing performance with state-of-the-art machine and deep learning models. Results reveal that a pre-processed feature set and convolutional neural network classifier achieves a significantly better accuracy of 0.99. The proposed method demonstrates superior accuracy and computational efficiency compared to existing state-of-the-art works.

An Intelligent Framework for Cyber-Physical Satellite System and IoT-Aided Aerial Vehicle Security Threat Detection

The small-drone technology domain is the outcome of a breakthrough in technological advancement for drones. The Internet of Things (IoT) is used by drones to provide inter-location services for navigation. But, due to issues related to their architecture and design, drones are not immune to threats related to security and privacy. Establishing a secure and reliable network is essential to obtaining optimal performance from drones. While small drones offer promising avenues for growth in civil and defense industries, they are prone to attacks on safety, security, and privacy. The current architecture of small drones necessitates modifications to their data transformation and privacy mechanisms to align with domain requirements. This research paper investigates the latest trends in safety, security, and privacy related to drones, and the Internet of Drones (IoD), highlighting the importance of secure drone networks that are impervious to interceptions and intrusions. To mitigate cyber-security threats, the proposed framework incorporates intelligent machine learning models into the design and structure of IoT-aided drones, rendering adaptable and secure technology. Furthermore, in this work, a new dataset is constructed, a merged dataset comprising a drone dataset and two benchmark datasets. The proposed strategy outperforms the previous algorithms and achieves 99.89% accuracy on the drone dataset and 91.64% on the merged dataset. Overall, this intelligent framework gives a potential approach to improving the security and resilience of cyber-physical satellite systems, and IoT-aided aerial vehicle systems, addressing the rising security challenges in an interconnected world.

Serious gaming for graduates employability enhancement

Higher Education Institutions (HEIs) are blamed for being insouciant about the business world and not efficiently steeling students with employment abilities. As a reply to this exigency from business owners, HEIs have started to show commitment to graduate employability through developing and adopting new educational material, such Serious Games (SGs), to help students acquire these soft skills. This paper explores the students’ perceptions of the significance of SGs on soft skills and therefore boosting graduate employability. We carried out a quantitative and qualitative study with 322 students from business colleges in the aim to focus on the impact of user experience in SGs on critical thinking and teamwork. The results highlight the strong influence of SGs to acquire these soft skills.

Leveraging artificial intelligence for diagnosis of children autism through facial expressions

The global population contains a substantial number of individuals who experience autism spectrum disorder, thus requiring immediate identification to enable successful intervention approaches. The authors assess the detection of autism-related learning difficulties in children by evaluating deep learning models that use transfer learning methods along with fine-tuning methods. Using autism spectrum disorder (ASD) diagnosed child RGB images data, researchers evaluated six prevalent deep learning structures: DenseNet201, ResNet152, VGG16, VGG19, MobileNetV2, and EfficientNet-B0. ResNet152 reached the highest accuracy rate of 89% when functioning independently. This paper develops a hybrid deep-learning model by integrating ResNet152 with Vision Transformers (ViT) to achieve better classification performance. The ViT-ResNet152 model's convolutional and transformer processing elements worked together to improve the accuracy of the diagnosis to 91.33% and make it better at finding different cases of autism spectrum disorder (ASD).The research outcomes demonstrate that AI tools show promise for delivering highly precise and standardized methods to detect ASD at an early stage. Future research needs to include multiple data types as well as extend dataset variability while optimizing hybrid architecture systems to elevate diagnostic forecasting. The incorporation of artificial intelligence in ASD evaluation services holds promise to transform early therapy approaches, which leads to better results for autistic children all around the globe.