International Journal of Imaging Systems and Technology最新文献

Despite advances in medical sciences, breast cancer remains a deadly disease globally, primarily affecting women. Fortunately, studies claim that breast cancer is treatable if diagnosed early. Late diagnoses have poor prognoses and can affect the patient's quality of life. Therefore, a significant research body is dedicated to establishing and identifying the disease at an initial stage. Deep learning (DL) techniques are garnering attention for aiding medical professionals in detecting this disease using histopathology (HP) image modality. The heterogeneous nature of this disease subtypes results in the imbalances of benign and malignant subtypes. From a DL point of view, this becomes an imbalanced problem deserving special care. Unfortunately, current DL-based techniques do not fully address this issue and suffer from poor metrics and robustness. In this work, we present a DL-based breast cancer automatic detection system (BCADS) using a novel architecture stochastic class-attention net (SCAN). This technique performed better when combined with label smoothing and test time augmentation. This work outperforms the previously reported results for binary and multiclass on the BreaKHis dataset. Also, we validated our method on separate BACH and BCNB datasets to prove its effectiveness and clinical relevancy. We hope that the designed BCADS will help the treating doctor and pathologist in a meaningful way and thus help to reduce the impact of this deadly disease.

Nonalcoholic fatty liver disease (NAFLD) is a prevalent liver disorder affecting approximately 25.2% of the global population, posing risks of liver fibrosis, cancer, and metabolic disturbances. Despite its increasing prevalence, many facets of NAFLD's pathogenesis remain elusive, and there are currently no approved therapeutic drugs, underscoring the critical need for a comprehensive understanding of its pathophysiology to enable early diagnosis and intervention. Experimental animal studies play a pivotal role in elucidating the mechanisms underlying NAFLD and in the exploration of novel pharmacotherapies. Despite the widespread integration of deep learning techniques in human histopathology, their application to scrutinize histological features in animal models warrants exploration. This study presents a pioneering NAFLD assessment system leveraging IFNet and ResNet34 architectures. This automated system adeptly identifies inflammatory cell foci and hepatic steatosis in histopathology sections of rat livers. Remarkably, our approach achieved an impressive 95.6% accuracy in the assessment of hepatic steatosis and 77.7% in the evaluation of inflammation cell foci. By introducing a novel histopathology scoring system, our methodology mitigated subjective variations inherent in traditional pathologist evaluations, concurrently streamlining time and labor costs. This system ensured a standardized and precise assessment of rat liver histology in NAFLD and represented a significant stride toward enhancing the efficiency and objectivity of experimental outcomes.

Papilledema is a prevalent neuro-ophthalmic condition characterized by optic disk swelling. It is known to pose a significant risk of vision loss in its advanced stages. To address the pressing need for accurate detection and grading of papilledema, this study introduces a novel approach utilizing optical coherence tomography (OCT) scans. A cascaded model that combines four transfer learning models—SqueezeNet, AlexNet, GoogleNet, and ResNet-50—for both the detection and grading phases was proposed. Additionally, a specialized convolutional neural network (CNN) model is meticulously designed to cater specifically to the complexities of papilledema analysis. Unlike the fundus camera-based models, this study integrates deep learning models for the diagnosis of papilledema from OCT scans. A new dataset of OCT scans was collected to ensure a comprehensive evaluation of the models. It encompasses a wide range of papilledema, pseudopapilledema, and normal cases. This dataset serves as a valuable resource for training and testing of the proposed models. In addition, two validation strategies have been adopted to ensure the model's generalizability and robustness. Furthermore, it enhances the model's accuracy and reliability. The results are highly promising; remarkable accuracy rates have been achieved. Specifically, the SqueezeNet, AlexNet, GoogleNet, ResNet-50, and customized CNN models achieved accuracy levels of 98.44%, 98.50%, 98.28%, 98.30%, and 96.26%, respectively, for the handout validation strategy. These findings not only demonstrate the efficacy of using deep learning in papilledema detection and grading but also establish the superiority of the proposed models when compared with other relevant studies. By addressing the challenges associated with papilledema, the study significantly contributes to the advancement of neuro-ophthalmic diagnostics. The accurate and efficient detection of papilledema from OCT scans holds immense potential for guiding timely interventions and preserving patients' visual health.

Parkinson's disease (PD), a severe and progressive neurological illness, affects millions of individuals worldwide. For effective treatment and management of PD, an accurate and early diagnosis is crucial. This study presents a deep learning-based model for the diagnosis of PD using a resting state electroencephalogram (EEG) signal. The objective of the study is to develop an automated model that can extract complex hidden nonlinear features from EEG and demonstrate its generalizability on unseen data. The model is designed using a hybrid model, consisting of a convolutional neural network (CNN), bidirectional gated recurrent unit (Bi-GRU), and attention mechanism. The proposed method is evaluated on three public datasets (UC San Diego, PRED-CT, and University of Iowa [UI] dataset), with one dataset used for training and the other two for evaluation. The proposed model demonstrated remarkable performance, attaining high accuracy scores of 99.4%, 84%, and 73.2% using UC San Diego, PRED-CT, and UI datasets, respectively. These results justify the effectiveness and robustness of the proposed model across diverse datasets, highlighting its potential for versatile applications in data analysis and prediction tasks. Our proposed hybrid spatiotemporal attention-based model has been developed with 10-fold cross-validation (CV) for UC San Diego dataset and 10-fold CV and leave-one-out cross-validation (LOOCV) strategies for PRED-CT and UI datasets. Our results indicate that the proposed PD detection system is accurate and robust. The developed prototype can be used for other neurodegenerative diseases such as Alzheimer's disease, Huntington's disease, and so forth.

Cardiac cine magnetic resonance imaging (MRI) is one of the important means to assess cardiac functions and vascular abnormalities. Mitigating artifacts arising during image reconstruction and accelerating cardiac cine MRI acquisition to obtain high-quality images is important. A novel end-to-end deep learning network is developed to improve cardiac cine MRI reconstruction. First, a U-Net is adopted to obtain the initial reconstructed images in k-space. Further to remove the motion artifacts, the motion-guided deformable alignment (MGDA) module with second-order bidirectional propagation is introduced to align the adjacent cine MRI frames by maximizing spatial–temporal information to alleviate motion artifacts. Finally, the multi-resolution fusion (MRF) module is designed to correct the blur and artifacts generated from alignment operation and obtain the last high-quality reconstructed cardiac images. At an 8× acceleration rate, the numerical measurements on the ACDC dataset are structural similarity index (SSIM) of 78.40% ± 4.57%, peak signal-to-noise ratio (PSNR) of 30.46 ± 1.22 dB, and normalized mean squared error (NMSE) of 0.0468 ± 0.0075. On the ACMRI dataset, the results are SSIM of 87.65% ± 4.20%, PSNR of 30.04 ± 1.18 dB, and NMSE of 0.0473 ± 0.0072. The proposed method exhibits high-quality results with richer details and fewer artifacts for cardiac cine MRI reconstruction on different accelerations.

In the field of medical image analysis, object detection plays a crucial role by providing interpretable diagnostic information to healthcare professionals. Although current object detection models have achieved remarkable success in conventional images, their performance in detecting abnormalities in medical images has not been as satisfactory. This is primarily due to the complexity of anatomical structures in medical images, and the fact that some lesions may have subtle features, particularly in the case of early-stage, small-scale abnormalities. To address this challenge, we introduce SOCR-YOLO, a novel lesion detection model with online convolutional reparameterization based on channel shuffling. First, it employs the SOCR (Shuffled Channel with Online Convolutional Re-parameterization) module to establish a connection between feature concatenation and computational efficiency, aiming to extract more comprehensive information while reducing time consumption. Second, it incorporates the Bi-FPN structure to achieve multiscale feature fusion. Lastly, the loss function has been optimized to improve the model training process. We evaluated two datasets, chest x-ray (Vindr-CXR) and brain tumor (Br35H), provided by the Kaggle competition. Experimental results show that the proposed method has outperformed several state-of-the-art models, including YOLOv8, YOLO-NAS, and RT-DETR, in both speed and accuracy. Notably, in the context of chest x-ray anomaly detection, SOCR-YOLO exhibits a 1.8% enhancement in accuracy over YOLOv8 while simultaneously reducing floating-point operations by 26.3%. Additionally, a similar 1.8% improvement in accuracy is observed in the detection of brain tumors. The results indicate the superior ability of our model to detect multiscale variations and small lesions.

Skin diseases are among the leading causes of disability worldwide and are a significant cause of morbidity in sub-Saharan Africa. It can be cured if identified early. Only an expert dermatologist can classify skin disease by examining clinical signs. Sometimes, it can happen that dermatologists do not correctly classify the Skin disease, and therefore prescribe inappropriate drugs to the patient. Various research has been done to automate skin disease classification. Almost all the studies were concentrated on classifying three to four types of skin diseases. Developing a model that can be used in real-world practical AI applications is important. In this study, we present an ensemble model based on the hard-voting scheme of three deep CNN architectures: SKDCNET, FVGG16, and InceptionV3 for automatic classification of the top eight skin diseases. The proposed model utilizes three architectural diversities: training from scratch, fine-tuning, and transfer learning. We used median filter noise removal and data augmentation technique to increase the number of training datasets. The proposed ensemble model produces 98% of accuracy. As an outcome of this study, the proposed model has the potential to be used as a decision support method for dermatologists. It can also contribute to the early identification (treatment) of skin diseases to reduce their further spread.