Customized m-RCNN and hybrid deep classifier for liver cancer segmentation and classification.

Diagnosing liver disease presents a significant medical challenge in impoverished countries, with over 30 billion individuals succumbing to it each year. Existing models for detecting liver abnormalities suffer from lower accuracy and higher constraint metrics. As a result, there is a pressing need for improved, efficient, and effective liver disease detection methods. To address the limitations of current models, this method introduces a deep liver segmentation and classification system based on a Customized Mask-Region Convolutional Neural Network (cm-RCNN). The process begins with preprocessing the input liver image, which includes Adaptive Histogram Equalization (AHE). AHE helps dehaze the input image, remove color distortion, and apply linear transformations to obtain the preprocessed image. Next, a precise region of interest is segmented from the preprocessed image using a novel deep strategy called cm-RCNN. To enhance segmentation accuracy, the architecture incorporates the ReLU activation function and the modified sigmoid activation function. Subsequently, a variety of features are extracted from the segmented image, including ResNet features, shape features (area, perimeter, approximation, and convex hull), and enhanced median binary pattern. These extracted features are then used to train a hybrid classification model, which incorporates classifiers like SqueezeNet and DeepMaxout models. The final classification outcome is determined by averaging the scores obtained from both classifiers.

Adaptive Feature Medical Segmentation Network: an adaptable deep learning paradigm for high-performance 3D brain lesion segmentation in medical imaging.

Introduction: In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic. Methods: We introduce a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability. Results: AFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision. Discussion: The proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing.

Transformative Deep Neural Network Approaches in Kidney Ultrasound Segmentation: Empirical Validation with an Annotated Dataset.

Kidney ultrasound (US) images are primarily employed for diagnosing different renal diseases. Among them, one is renal localization and detection, which can be carried out by segmenting the kidney US images. However, kidney segmentation from US images is challenging due to low contrast, speckle noise, fluid, variations in kidney shape, and modality artifacts. Moreover, well-annotated US datasets for renal segmentation and detection are scarce. This study aims to build a novel, well-annotated dataset containing 44,880 US images. In addition, we propose a novel training scheme that utilizes the encoder and decoder parts of a state-of-the-art segmentation algorithm. In the pre-processing step, pixel intensity normalization improves contrast and facilitates model convergence. The modified encoder-decoder architecture improves pyramid-shaped hole pooling, cascaded multiple-hole convolutions, and batch normalization. The pre-processing step gradually reconstructs spatial information, including the capture of complete object boundaries, and the post-processing module with a concave curvature reduces the false positive rate of the results. We present benchmark findings to validate the quality of the proposed training scheme and dataset. We applied six evaluation metrics and several baseline segmentation approaches to our novel kidney US dataset. Among the evaluated models, DeepLabv3+ performed well and achieved the highest dice, Hausdorff distance 95, accuracy, specificity, average symmetric surface distance, and recall scores of 89.76%, 9.91, 98.14%, 98.83%, 3.03, and 90.68%, respectively. The proposed training strategy aids state-of-the-art segmentation models, resulting in better-segmented predictions. Furthermore, the large, well-annotated kidney US public dataset will serve as a valuable baseline source for future medical image analysis research.

COPD stage detection: leveraging the auto-metric graph neural network with inspiratory and expiratory chest CT images.

Chronic obstructive pulmonary disease (COPD) is a common lung disease that can lead to restricted airflow and respiratory problems, causing a significant health, economic, and social burden. Detecting the COPD stage can provide a timely warning for prompt intervention in COPD patients. However, existing methods based on inspiratory (IN) and expiratory (EX) chest CT images are not sufficiently accurate and efficient in COPD stage detection. The lung region images are autonomously segmented from IN and EX chest CT images to extract the 1 , 781 × 2 lung radiomics and 13 , 824 × 2 3D CNN features. Furthermore, a strategy for concatenating and selecting features was employed in COPD stage detection based on radiomics and 3D CNN features. Finally, we combine all the radiomics, 3D CNN features, and factor risks (age, gender, and smoking history) to detect the COPD stage based on the Auto-Metric Graph Neural Network (AMGNN). The AMGNN with radiomics and 3D CNN features achieves the best performance at 89.7 % of accuracy, 90.9 % of precision, 89.5 % of F1-score, and 95.8 % of AUC compared to six classic machine learning (ML) classifiers. Our proposed approach demonstrates high accuracy in detecting the stage of COPD using both IN and EX chest CT images. This method can potentially establish an efficient diagnostic tool for patients with COPD. Additionally, we have identified radiomics and 3D CNN as more appropriate biomarkers than Parametric Response Mapping (PRM). Moreover, our findings indicate that expiration yields better results than inspiration in detecting the stage of COPD.

Tubular Structure Segmentation via Multi-Scale Reverse Attention Sparse Convolution.

Cerebrovascular and airway structures are tubular structures used for transporting blood and gases, respectively, providing essential support for the normal activities of the human body. Accurately segmenting these tubular structures is the basis of morphology research and pathological detection. Nevertheless, accurately segmenting these structures from images presents great challenges due to their complex morphological and topological characteristics. To address this challenge, this paper proposes a framework UARAI based on the U-Net multi-scale reverse attention network and sparse convolution network. The framework utilizes a multi-scale structure to effectively extract the global and deep detail features of vessels and airways. Further, it enhances the extraction ability of fine-edged features by a joint reverse attention module. In addition, the sparse convolution structure is introduced to improve the features' expression ability without increasing the model's complexity. Finally, the proposed training sample cropping strategy reduces the influence of block boundaries on the accuracy of tubular structure segmentation. The experimental findings demonstrate that the UARAI-based metrics, namely Dice and IoU, achieve impressive scores of 90.31% and 82.33% for cerebrovascular segmentation and 93.34% and 87.51% for airway segmentation, respectively. Compared to commonly employed segmentation techniques, the proposed method exhibits remarkable accuracy and robustness in delineating tubular structures such as cerebrovascular and airway structures. These results hold significant promise in facilitating medical image analysis and clinical diagnosis, offering invaluable support to healthcare professionals.

A Robust Brain Tumor Detector Using BiLSTM and Mayfly Optimization and Multi-Level Thresholding.

A brain tumor refers to an abnormal growth of cells in the brain that can be either benign or malignant. Oncologists typically use various methods such as blood or visual tests to detect brain tumors, but these approaches can be time-consuming, require additional human effort, and may not be effective in detecting small tumors. This work proposes an effective approach to brain tumor detection that combines segmentation and feature fusion. Segmentation is performed using the mayfly optimization algorithm with multilevel Kapur's threshold technique to locate brain tumors in MRI scans. Key features are achieved from tumors employing Histogram of Oriented Gradients (HOG) and ResNet-V2, and a bidirectional long short-term memory (BiLSTM) network is used to classify tumors into three categories: pituitary, glioma, and meningioma. The suggested methodology is trained and tested on two datasets, Figshare and Harvard, achieving high accuracy, precision, recall, F1 score, and area under the curve (AUC). The results of a comparative analysis with existing DL and ML methods demonstrate that the proposed approach offers superior outcomes. This approach has the potential to improve brain tumor detection, particularly for small tumors, but further validation and testing are needed before clinical use.

The supercapattery designed with a binary composite of niobium silver sulfide (NbAg2S) and activated carbon for enhanced electrochemical performance.

A supercapattery is a hybrid device that is a combination of a battery and a capacitor. Niobium sulfide (NbS), silver sulfide (Ag2S), and niobium silver sulfide (NbAg2S) were synthesized by a simple hydrothermal method. NbAg2S (50/50 wt% ratio) had a specific capacity of 654 C g-1, which was higher than the combined specific capacities of NbS (440 C g-1) and Ag2S (232 C g-1), as determined by the electrochemical investigation of a three-cell assembly. Activated carbon and NbAg2S were combined to develop the asymmetric device (NbAg2S//AC). A maximum specific capacity of 142 C g-1 was delivered by the supercapattery (NbAg2S//AC). The supercapattery (NbAg2S/AC) provided 43.06 W h kg-1 energy density while retaining 750 W kg-1 power density. The stability of the NbAg2S//AC device was evaluated by subjecting it to 5000 cycles. After 5000 cycles, the (NbAg2S/AC) device still had 93% of its initial capacity. This research indicates that merging NbS and Ag2S (50/50 wt% ratio) may be the best choice for future energy storage technologies.

Deep Segmentation Networks for Segmenting Kidneys and Detecting Kidney Stones in Unenhanced Abdominal CT Images.

Recent breakthroughs of deep learning algorithms in medical imaging, automated detection, and segmentation techniques for renal (kidney) in abdominal computed tomography (CT) images have been limited. Radiomics and machine learning analyses of renal diseases rely on the automatic segmentation of kidneys in CT images. Inspired by this, our primary aim is to utilize deep semantic segmentation learning models with a proposed training scheme to achieve precise and accurate segmentation outcomes. Moreover, this work aims to provide the community with an open-source, unenhanced abdominal CT dataset for training and testing the deep learning segmentation networks to segment kidneys and detect kidney stones. Five variations of deep segmentation networks are trained and tested both dependently (based on the proposed training scheme) and independently. Upon comparison, the models trained with the proposed training scheme enable the highly accurate 2D and 3D segmentation of kidneys and kidney stones. We believe this work is a fundamental step toward AI-driven diagnostic strategies, which can be an essential component of personalized patient care and improved decision-making in treating kidney diseases.

Supervised and weakly supervised deep learning models for COVID-19 CT diagnosis: A systematic review.

Artificial intelligence (AI) and computer vision (CV) methods become reliable to extract features from radiological images, aiding COVID-19 diagnosis ahead of the pathogenic tests and saving critical time for disease management and control. Thus, this review article focuses on cascading numerous deep learning-based COVID-19 computerized tomography (CT) imaging diagnosis research, providing a baseline for future research. Compared to previous review articles on the topic, this study pigeon-holes the collected literature very differently (i.e., its multi-level arrangement). For this purpose, 71 relevant studies were found using a variety of trustworthy databases and search engines, including Google Scholar, IEEE Xplore, Web of Science, PubMed, Science Direct, and Scopus. We classify the selected literature in multi-level machine learning groups, such as supervised and weakly supervised learning. Our review article reveals that weak supervision has been adopted extensively for COVID-19 CT diagnosis compared to supervised learning. Weakly supervised (conventional transfer learning) techniques can be utilized effectively for real-time clinical practices by reusing the sophisticated features rather than over-parameterizing the standard models. Few-shot and self-supervised learning are the recent trends to address data scarcity and model efficacy. The deep learning (artificial intelligence) based models are mainly utilized for disease management and control. Therefore, it is more appropriate for readers to comprehend the related perceptive of deep learning approaches for the in-progress COVID-19 CT diagnosis research.

Deep Learning Applications in Computed Tomography Images for Pulmonary Nodule Detection and Diagnosis: A Review.

Lung cancer has one of the highest mortality rates of all cancers and poses a severe threat to people's health. Therefore, diagnosing lung nodules at an early stage is crucial to improving patient survival rates. Numerous computer-aided diagnosis (CAD) systems have been developed to detect and classify such nodules in their early stages. Currently, CAD systems for pulmonary nodules comprise data acquisition, pre-processing, lung segmentation, nodule detection, false-positive reduction, segmentation, and classification. A number of review articles have considered various components of such systems, but this review focuses on segmentation and classification parts. Specifically, categorizing segmentation parts based on lung nodule type and network architectures, i.e., general neural network and multiview convolution neural network (CNN) architecture. Moreover, this work organizes related literature for classification of parts based on nodule or non-nodule and benign or malignant. The essential CT lung datasets and evaluation metrics used in the detection and diagnosis of lung nodules have been systematically summarized as well. Thus, this review provides a baseline understanding of the topic for interested readers.

Review and classification of AI-enabled COVID-19 CT imaging models based on computer vision tasks.

This article presents a systematic overview of artificial intelligence (AI) and computer vision strategies for diagnosing the coronavirus disease of 2019 (COVID-19) using computerized tomography (CT) medical images. We analyzed the previous review works and found that all of them ignored classifying and categorizing COVID-19 literature based on computer vision tasks, such as classification, segmentation, and detection. Most of the COVID-19 CT diagnosis methods comprehensively use segmentation and classification tasks. Moreover, most of the review articles are diverse and cover CT as well as X-ray images. Therefore, we focused on the COVID-19 diagnostic methods based on CT images. Well-known search engines and databases such as Google, Google Scholar, Kaggle, Baidu, IEEE Xplore, Web of Science, PubMed, ScienceDirect, and Scopus were utilized to collect relevant studies. After deep analysis, we collected 114 studies and reported highly enriched information for each selected research. According to our analysis, AI and computer vision have substantial potential for rapid COVID-19 diagnosis as they could significantly assist in automating the diagnosis process. Accurate and efficient models will have real-time clinical implications, though further research is still required. Categorization of literature based on computer vision tasks could be helpful for future research; therefore, this review article will provide a good foundation for conducting such research.

Predictors of outcome in super refractory status epilepticus.

PURPOSE: We conducted this study to determine the clinical, electrophysiological and radiological predictors of outcome in Super Refractory Status Epilepticus (SRSE). METHODS: Data of patients treated for SRSE between January 2000 and November 2019, archived prospectively in our SE registry were analyzed. Functional outcome was measured by Glasgow outcome score (GOS) at the time of hospital discharge and was divided into: good i.e. GOS ≥ 3 and bad outcome i.e. GOS < 3. The predictors of outcome were determined using appropriate statistical tests by univariate and multivariate analysis, p < 0.05 was considered as statistically significant. RESULTS: Of the 384 patients with status epilepticus (SE) identified during the study, 28 (8%) were diagnosed as SRSE and were included in the final analysis. Acute symptomatic SE comprising 15 (53.6%) patients was the most common etiology of SRSE. Thirteen patients (three patients with viral encephalitis and 10 patients with clinically possible autoimmune encephalitis) had New Onset Refractory Status Epilepticus (NORSE) like clinical presentation.12 patients (42.9%) had good outcome and 16 patients (57.1%) had bad outcome. Multivariate logistic regression analysis showed that independent predictors of poor outcome were: duration of ICU stay (p < 0.001); EEG findings such as non-convulsive SE in coma (0.032), spontaneous burst suppression (0.001) and postictal diffuse attenuation (<0.001); delay in starting anesthesia (0.002); and delay in starting immunotherapy in NORSE due to autoimmune encephalitis (0.002). CONCLUSION: We could determine independent therapeutic and electrophysiological prognostic factors for SRSE. Early initiation of treatment and stringent management of these factors especially in an younger age-group, aided by continuous EEG monitoring and a thorough etiological work-up can result in good outcomes in more than one-third of cases.

Successful Endovascular Treatment of Cerebral Venous Thrombosis with a Novel, Larger Aspiration Catheter (REACT): A Case Report.

Cerebral venous thrombosis (CVT) is a rare clinical entity, with clinical presentations extending from headache and seizures to coma and death. For adults developing progressive neurological worsening despite adequate medical management, endovascular thrombolysis and/or mechanical thrombectomy may be considered as treatment options. We present one such patient with CVT who developed seizures and slipped into a coma, despite best medical management. A large-bore aspiration catheter was used as a standalone system for the endovascular procedure. The venous sinuses were successfully re-canalized. The patient was discharged a week later with a modified Rankin scale of 2. Studies show that endovascular thrombolysis used alone or in conjunction with thrombectomy for CVT has a higher risk of hemorrhagic complications. If we were to use mechanical thrombectomy devices (that are specifically designed for intracranial clot retrieval) as a stand-alone system, we would probably have better clinical outcomes with a lower risk of hemorrhagic complications.

An audit of the predictors of outcome in status epilepticus from a resource-poor country: a comparison with developed countries.

Status epilepticus is a neurological emergency with significant morbidity and mortality. This study describes the clinical profile, treatment, and predictors of outcome of status epilepticus in a tertiary referral centre in a developing country and aims to highlight the similarities and differences from data available from the western world. A retrospective analysis of data of patients treated for status epilepticus was conducted from prospectively maintained records, between January 2000 and September 2010. The demographic data, clinical profile and investigations (including neuroimaging and EEG), aetiology, treatment, and outcomes were studied and compared with data available from the western world. The analysis included 108 events in 84 patients. A single episode of status epilepticus was treated in 72 patients (86%) and multiple status epilepticus events, ranging from two to six per patient, were managed in 12 patients (14%). Mean age was 24.1±20.3 years and 63% were males. The types of status epilepticus included convulsive status in 98 (90.7%), non-convulsive status in seven (6.5%), and myoclonic status in three (2.8%). The majority of events (60%) were remote symptomatic, 16% were acute symptomatic, 16% were of unexplained aetiology, and 8% were progressive symptomatic. In 85 events (79%), status epilepticus could be aborted with first and second-line drugs. The remaining 23 events (21%) progressed to refractory status epilepticus, among which, 13 (56%) were controlled with continuous intravenous midazolam infusion. Case fatality rate was 11%, neurological sequelae were reported in 22%, and 67% returned to baseline. Acute symptomatic status, older age, altered sensorium at the time of admission, and delayed hospitalisation were predictors of poor outcome. Aetiology was the most important determinant of outcome of status epilepticus, as in reports from the western world, with remote symptomatic aetiology secondary to gliosis being the most common. Treatment delay was frequent and adversely affected the outcome.

Insights from a rare clinical presentation of herpes simplex encephalitis: adding to the catatonic dilemma?

BACKGROUND: Catatonia is associated with a variety of psychiatric and medical illnesses. Very little research is available on the syndrome and the exact neurobiological correlates are not known. Though various cortical and subcortical circuits are implicated in the pathogenesis, the role of cerebellum is unknown. We report an unusual presentation of herpes simplex encephalitis, clinically as catatonic stupor and radiologically as isolated symmetrical cerebellar involvement affecting the posterior cerebellum. We discuss the possible role of the cerebellum in producing a catatonic state. CASE REPORT: We describe the clinical presentation of catatonia in a 19-year-old woman with herpes simplex encephalitis. Her magnetic reasonance imaging showed features of viral cerebellitis involving the posterior cerebellum with hemorrhagic transformation. She lacked the classical frontotemporal involvement of herpes and recovered completely without physical or neuropsychological sequelae. She did not show signs associated with cerebellar disease at any point during the illness. CONCLUSIONS: This case provides compelling evidence for the possible role of the posterior cerebellum in the clinical presentation of catatonia. This is probably related to its role in controlling the nonmotor cerebral functions through corticocerebellar connections. Further studies of catatonic syndromes are needed to establish this association.

Extraoccipital photoparoxysmal response in a case of focal encephalitis.

Photoparoxysmal response (PPR) is commonly associated with idiopathic generalised epilepsies. Most of the focal events induced by intermittent photic stimulation (IPS) are reported to be of occipital origin. Only six temporal lobe epilepsy patients have been reported in the literature with focal PPR at extraoccipital sites. We report a four-year-old girl with possible encephalitis who presented initially with epilepsia partialis continua of limbs on the right side. Interictally, she had left centro-parietal periodic lateralized epileptiform discharges (PLEDs). She responded to medical treatment and was free of seizures and motor and cognitive deficits at six months follow-up. Repeat EEG at follow-up showed left centro-parietal spikes accentuated by IPS. This is the first report of an extraoccipital, extratemporal focus showing PPR. The possible mechanism of PPR from this fronto-parietal epileptogenic focus is discussed.

Structural correlates of fixation-off sensitivity: Evidences from a case of symptomatic occipital epilepsy with bilateral occipital gliosis.

The fixation-off sensitivity (FOS), an epileptic phenomenon induced by elimination of central vision and fixation, is rarely seen in symptomatic occipital lobe epilepsy. The cerebral mechanisms and the structural correlate underlying FOS remain unclear. We describe a 19-year-old male with persistent left sided FOS following perinatal insult. MRI revealed asymmetric changes with more gliosis and ulegyria over the left posterior occipital cortex corresponding to the topographic representation of the macula. We suggest that the extensive denervation of the area representing macula along with the presence of hyperexitable ulegyric cortex is responsible for the phenomenon of FOS.