This paper presents a fully automated pipeline using a sparse convolutional autoencoder for quality control (QC) of affine registrations in large-scale T1-weighted (T1w) and T2-weighted (T2w) magnetic resonance imaging (MRI) studies. Here, a customized 3D convolutional encoder-decoder (autoencoder) framework is proposed and the network is trained in a fully unsupervised manner. For cross-validating the proposed model, we used 1000 correctly aligned MRI images of the human connectome project young adult (HCP-YA) dataset. We proposed that the quality of the registration is proportional to the reconstruction error of the autoencoder. Further, to make this method applicable to unseen datasets, we have proposed dataset-specific optimal threshold calculation (using the reconstruction error) from ROC analysis that requires a subset of the correctly aligned and artificially generated misalignments specific to that dataset. The calculated optimum threshold is used for testing the quality of remaining affine registrations from the corresponding datasets. The proposed framework was tested on four unseen datasets from autism brain imaging data exchange (ABIDE I, 215 subjects), information eXtraction from images (IXI, 577 subjects), Open Access Series of Imaging Studies (OASIS4, 646 subjects), and “Food and Brain” study (77 subjects). The framework has achieved excellent performance for T1w and T2w affine registrations with an accuracy of 100% for HCP-YA. Further, we evaluated the generality of the model on four unseen datasets and obtained accuracies of 81.81% for ABIDE I (only T1w), 93.45% (T1w) and 81.75% (T2w) for OASIS4, and 92.59% for “Food and Brain” study (only T1w) and in the range 88–97% for IXI (for both T1w and T2w and stratified concerning scanner vendor and magnetic field strengths). Moreover, the real failures from “Food and Brain” and OASIS4 datasets were detected with sensitivities of 100% and 80% for T1w and T2w, respectively. In addition, AUCs of > 0.88 in all scenarios were obtained during threshold calculation on the four test sets.

Among the most rapidly developing areas in computer vision is object detection. Mask detection is the main objective of the effort. With the use of deep learning and computer vision techniques, this project offers a reliable method for mask identification that is implemented using RESNET architecture. Identifying faces and differentiating between people wearing masks and those without is the main goal. The model is refined via transfer learning on a customized dataset that includes annotated photos of faces that have been masked, masked incorrectly and unmasked faces. © 2024 Taylor & Francis Group, London.

Quick and accurate structural damage detection is essential for maintaining the safety and integrity of infrastructure, especially following natural disasters. Traditional methods of damage assessment, which rely on manual inspections, can be labor-intensive and subject to human error. This paper introduces a hybrid deep learning model that combines the capabilities of ResNet50 and GoogLeNet, further enhanced by a convolutional block attention module (CBAM), proposed to improve both the accuracy and performance in detecting structural damage. For training purposes, a diverse dataset of images depicting both structural damage cases and undamaged cases was used. To further enhance the robustness, data augmentation techniques were also employed. In this research, precision, recall, F1-score, and accuracy were employed to evaluate the effectiveness of the introduced hybrid deep learning model. Our findings indicate that the hybrid deep neural network introduced in this study significantly outperformed standalone architectures such as ResNet50 and GoogLeNet, making it a highly effective solution for applications in disaster response and infrastructure maintenance.

Automated classification of blood cells from microscopic images is an interesting research area owing to advancements of efficient neural network models. The existing deep learning methods rely on large data for network training and generating such large data could be time-consuming. Further, explainability is required via class activation mapping for better understanding of the model predictions. Therefore, we developed a Siamese twin network (STN) model based on contrastive learning that trains on relatively few images for the classification of healthy peripheral blood cells using EfficientNet-B3 as the base model. Hence, in this study, a total of 17,092 publicly accessible cell histology images were analyzed from which 6% were used for STN training, 6% for few-shot validation, and the rest 88% for few-shot testing. The proposed architecture demonstrates percent accuracies of 97.00, 98.78, 94.59, 95.70, 98.86, 97.09, 99.71, and 96.30 during 8-way 5-shot testing for the classification of basophils, eosinophils, immature granulocytes, erythroblasts, lymphocytes, monocytes, platelets, and neutrophils, respectively. Further, we propose a novel class activation mapping scheme that highlights the important regions in the test image for the STN model interpretability. Overall, the proposed framework could be used for a fully automated self-exploratory classification of healthy peripheral blood cells. Graphical abstract: The whole proposed framework demonstrates the Siamese twin network training and 8-way k-shot testing. The values indicate the amount of dissimilarity. [Figure : see fulltext.]

Diabetic retinopathy (DR) is one of the major complications caused by diabetes and is usually identified from retinal fundus images. Screening of DR from digital fundus images could be time-consuming and error-prone for ophthalmologists. For efficient DR screening, good quality of the fundus image is essential and thereby reduces diagnostic errors. Hence, in this work, an automated method for quality estimation (QE) of digital fundus images using an ensemble of recent state-of-the-art EfficientNetV2 deep neural network models is proposed. The ensemble method was cross-validated and tested on one of the largest openly available datasets, the Deep Diabetic Retinopathy Image Dataset (DeepDRiD). We obtained a test accuracy of 75% for the QE, outperforming the existing methods on the DeepDRiD. Hence, the proposed ensemble method may be a potential tool for automated QE of fundus images and could be handy to ophthalmologists.

The offloading of computationally intensive tasks to edge servers is indispensable in the mobile edge computing (MEC) environment. Once the tasks are offloaded, the subsequent challenges lie in buffering them and assigning them to edge virtual machine (VM) resources to meet the multicriteria requirement. Furthermore, the edge resources’ availability is dynamic in nature and needs a joint prediction and optimal allocation for the efficient usage of resources and fulfillment of the tasks’ requirements. To this end, this work has three contributions. First, a delay sensitivity-based priority scheduling (DSPS) policy is presented to schedule the tasks as per their deadline. Secondly, based on exploratory data analysis and inferred seasonal patterns in the usage of edge CPU resources from the GWA-T-12 Bitbrains VM utilization dataset, the availability of VM resources is predicted by using a Holt–Winters-based univariate algorithm (HWVMR) and a vector autoregression-based multivariate algorithm (VARVMR). Finally, for optimal and fast task assignment, a parallel differential evolution-based task allocation (pDETA) strategy is proposed. The proposed algorithms are evaluated extensively with standard performance metrics, and the results show nearly 22%, 35%, and 69% improvements in cost and 41%, 52%, and 78% improvements in energy when compared with MTSS, DE, and min–min strategies, respectively.

Lung and colon cancers are among the leading causes of human mortality and morbidity. Early diagnostic work up of these diseases include radiography, ultrasound, magnetic resonance imaging, and computed tomography. Certain blood tumor markers for carcinoma lung and colon also aid in the diagnosis. Despite the lab and diagnostic imaging, histopathology remains the gold standard, which provides cell-level images of tissue under examination. To read these images, a histopathologist spends a large amount of time. Furthermore, using conventional diagnostic methods involve high-end equipment as well. This leads to limited number of patients getting final diagnosis and early treatment. In addition, there are chances of inter-observer errors. In recent years, deep learning has shown promising results in the medical field. This has helped in early diagnosis and treatment according to severity of disease. With the help of EffcientNetV2 models that have been cross-validated and tested fivefold, we propose an automated method for detecting lung (lung adenocarcinoma, lung benign, and lung squamous cell carcinoma) and colon (colon adenocarcinoma and colon benign) cancer subtypes from LC25000 histopathology images. A state-of-the-art deep learning architecture based on the principles of compound scaling and progressive learning, EffcientNetV2 large, medium, and small models. An accuracy of 99.97%, AUC of 99.99%, F1-score of 99.97%, balanced accuracy of 99.97%, and Matthew’s correlation coefficient of 99.96% were obtained on the test set using the EffcientNetV2-L model for the 5-class classification of lung and colon cancers, outperforming the existing methods. Using gradCAM, we created visual saliency maps to precisely locate the vital regions in the histopathology images from the test set where the models put more attention during cancer subtype predictions. This visual saliency maps may potentially assist pathologists to design better treatment strategies. Therefore, it is possible to use the proposed pipeline in clinical settings for fully automated lung and colon cancer detection from histopathology images with explainability.

The automated classification of brain tumors plays an important role in supporting radiologists in decision making. Recently, vision transformer (ViT)-based deep neural network architectures have gained attention in the computer vision research domain owing to the tremendous success of transformer models in natural language processing. Hence, in this study, the ability of an ensemble of standard ViT models for the diagnosis of brain tumors from T1-weighted (T1w) magnetic resonance imaging (MRI) is investigated. Pretrained and finetuned ViT models (B/16, B/32, L/16, and L/32) on ImageNet were adopted for the classification task. A brain tumor dataset from figshare, consisting of 3064 T1w contrast-enhanced (CE) MRI slices with meningiomas, gliomas, and pituitary tumors, was used for the cross-validation and testing of the ensemble ViT model’s ability to perform a three-class classification task. The best individual model was L/32, with an overall test accuracy of 98.2% at 384 × 384 resolution. The ensemble of all four ViT models demonstrated an overall testing accuracy of 98.7% at the same resolution, outperforming individual model’s ability at both resolutions and their ensembling at 224 × 224 resolution. In conclusion, an ensemble of ViT models could be deployed for the computer-aided diagnosis of brain tumors based on T1w CE MRI, leading to radiologist relief.

Breast cancer (BC) is one of the deadly forms of cancer, causing mortality worldwide in the female population. The standard imaging procedures for screening BC involve mammography and ultrasonography. However, these imaging procedures cannot differentiate subtypes of benign and malignant cancers. Here, histopathology images could provide better sensitivity toward benign and malignant cancer subtypes. Recently, vision transformers have been gaining attention in medical imaging due to their success in various computer vision tasks. Swin transformer (SwinT) is a variant of vision transformer that works on the concept of non-overlapping shifted windows and is a proven method for various vision detection tasks. Thus, in this study, we investigated the ability of an ensemble of SwinTs in the two-class classification of benign vs. malignant and eight-class classification of four benign and four malignant subtypes, using an openly available BreaKHis dataset containing 7909 histopathology images acquired at different zoom factors of 40×, 100×, 200×, and 400×. The ensemble of SwinTs (including tiny, small, base, and large) demonstrated an average test accuracy of 96.0% for the eight-class and 99.6% for the two-class classification, outperforming all the previous works. Thus, an ensemble of SwinTs could identify BC subtypes using histopathological images and may lead to pathologist relief.

Magnetic resonance imaging (MRI)-based morphometry and relaxometry are proven methods for the structural assessment of the human brain in several neurological disorders. These procedures are generally based on T1-weighted (T1w) and/or T2-weighted (T2w) MRI scans, and rigid and affine registrations to a standard template(s) are essential steps in such studies. Therefore, a fully automatic quality control (QC) of these registrations is necessary in big data scenarios to ensure that they are suitable for subsequent processing. A supervised machine learning (ML) framework is proposed by computing similarity metrics such as normalized cross-correlation, normalized mutual information, and correlation ratio locally. We have used these as candidate features for cross-validation and testing of different ML classifiers. For 5-fold repeated stratified grid search cross-validation, 400 correctly aligned, 2000 randomly generated misaligned images were used from the human connectome project young adult (HCP-YA) dataset. To test the cross-validated models, the datasets from autism brain imaging data exchange (ABIDE I) and information eXtraction from images (IXI) were used. The ensemble classifiers, random forest, and AdaBoost yielded best performance with F1-scores, balanced accuracies, and Matthews correlation coefficients in the range of 0.95–1.00 during cross-validation. The predictive accuracies reached 0.99 on the Test set #1 (ABIDE I), 0.99 without and 0.96 with noise on Test set #2 (IXI, stratified w.r.t scanner vendor and field strength). The cross-validated and tested ML models could be used for QC of both T1w and T2w rigid and affine registrations in large-scale MRI studies.

Registration to a reference image is an important step during preprocessing of structural brain magnetic resonance imaging (MRI) in group studies for disease diagnosis and prognosis. The manual quality control (QC) of these many images is time-consuming, tedious, and requires prior expertise. Owing to the availability of free MRI datasets and the recent advances in computational infrastructure and deep learning frameworks, it is now feasible to train a deep learning model on larger datasets. To facilitate fully automatic QC in large-scale MRI studies, we proposed 3D deep convolutional neural network models for checking rigid and affine registrations of T1-weighted and T2-weighted MRI data. Because it is a supervised learning approach, five artificially misaligned images are generated for each image type and registration type. The proposed models were cross-validated and tested on the dataset from IXI consisting of 580 T1w and 576 T2w images, where 80 percent of them are used for cross-validation and remaining for testing. Performance metrics such as accuracy, F1-score, recall, precision, and specificity demonstrated a value greater than or equal to 0.99. Therefore, the models could be deployed during fully automatic QC of rigid and affine registrations in the bigdata structural MRI processing pipeline.

Autism Spectrum Disorder (ASD) is accompanied by brain tissue changes in areas that control behavior, cognition, and motor functions, deficient in the disorder. The objective of this research was to evaluate brain structural changes in ASD patients compared to control subjects using voxel-by-voxel image entropy from T1-weighted imaging data of 115 ASD and 105 control subjects from autism brain imaging data exchange. For all subjects, entropy maps were calculated, normalized to a common space and smoothed. Then, the entropy maps were compared at each voxel between groups using analysis of covariance (covariates; age, gender). Increased entropy in ASD patients, indicating chronic injury, emerged in several vital regions including frontal temporal and parietal lobe regions, corpus callosum, cingulate cortices, and hippocampi. Entropy procedure showed significant effect size and demonstrated wide-spread changes in sites that control social behavior, cognitive, and motor activities, suggesting severe damage in those areas. The neuropathological mechanisms contributing to tissue injury remain unclear and possibly due to factors including genetic, atypical early brain growth during childhood.