Image Database Research Articles

Advancing clinical MRI exams with artificial intelligence: Japan's contributions and future prospects.

In this narrative review, we review the applications of artificial intelligence (AI) into clinical magnetic resonance imaging (MRI) exams, with a particular focus on Japan's contributions to this field. In the first part of the review, we introduce the various applications of AI in optimizing different aspects of the MRI process, including scan protocols, patient preparation, image acquisition, image reconstruction, and postprocessing techniques. Additionally, we examine AI's growing influence in clinical decision-making, particularly in areas such as segmentation, radiation therapy planning, and reporting assistance. By emphasizing studies conducted in Japan, we highlight the nation's contributions to the advancement of AI in MRI. In the latter part of the review, we highlight the characteristics that make Japan a unique environment for the development and implementation of AI in MRI examinations. Japan's healthcare landscape is distinguished by several key factors that collectively create a fertile ground for AI research and development. Notably, Japan boasts one of the highest densities of MRI scanners per capita globally, ensuring widespread access to the exam. Japan's national health insurance system plays a pivotal role by providing MRI scans to all citizens irrespective of socioeconomic status, which facilitates the collection of inclusive and unbiased imaging data across a diverse population. Japan's extensive health screening programs, coupled with collaborative research initiatives like the Japan Medical Imaging Database (J-MID), enable the aggregation and sharing of large, high-quality datasets. With its technological expertise and healthcare infrastructure, Japan is well-positioned to make meaningful contributions to the MRI-AI domain. The collaborative efforts of researchers, clinicians, and technology experts, including those in Japan, will continue to advance the future of AI in clinical MRI, potentially leading to improvements in patient care and healthcare efficiency.

Case Ascertainment in Pediatric Heart Failure Using International Classification of Disease Clinical Modification (ICD-CM) Codes.

Most epidemiological studies in pediatric heart failure (HF) use administrative database sources, defining patient cohorts by presence of a single HF ICD code. However, the ability of ICD codes to identify true HF patients is unknown in pediatrics.Here we describe the accuracy of HF ICD-10-CM code search algorithms, in identifying pediatric patients with HF from electronic data sources. Based on the adult HF literature, search algorithms were designed to incorporate HF ICD codes, imaging, and medications. Sensitivity, specificity, positive and negative predictive value and accuracy of the algorithms were tested among children in an advanced HF clinic ("Clinic cohort"). Top-performing algorithms were then tested in a large-scale regional electronic data warehouse (EDW), 01/2017 to 01/2020, generating the "EDW Cohort". False positive cases were identified and characterized by chart review. Within the Clinic Cohort, 78/378 patients (21%) had gold standard HF diagnoses. A search algorithm with one HF ICD coded visit was more sensitive but less specific than > 1 HF ICD coded visit, (sensitivity 94% and specificity 89% versus 69% and 97%, respectively). Correspondingly, > 1 ICD coded visit had a higher PPV than one ICD coded visit; 84% vs. 69%. Accuracy was similar (90% vs 91%). Presence of 1 HF ICD code combined with HF medication had high sensitivity, specificity, PPV, NPV and accuracy, all higher than the single ICD code algorithm. The "1 HF coded visit + any medication" algorithm resulted in highest accuracy (93%). Top-performing algorithms were tested in the EDW: the algorithm with > 1 HF ICD coded visit, and the algorithm with one HF ICD coded visit combined with HF medication. In the EDW Cohort, 133/248 (53.6%) patients had gold standard HF diagnoses though 115/248 (46.3%) were false positive cases; 41% of those had pulmonary over-circulation from congenital heart disease. Excluding children < 30days old and those with a history of an isolated VSD repair, complete AVSD repair, or PDA closure further reduced the proportion of false positives to 50/248 (20%). A search algorithm using a single HF ICD code can have acceptable sensitivity, specificity, PPV, NPV and accuracy in identifying children with HF from within electronic medical records. Similar to adult HF literature, specificity improves by including HF medication. When applied to large data sources, however, the search algorithms result in a high proportion of patients with pulmonary overcirculation related to congenital heart disease. To narrow the population to those with myocardial dysfunction, case identification may require use of ICD codes with linked of administrative, surgical, and/or imaging databases.

Study on intelligent recognition of urban road subgrade defect based on deep learning.

China's operational highway subgrades exhibit a trend of diversifying types and an increasing number of defects, leading to more frequent urban road safety incidents. This paper starts from the non-destructive testing of urban road subgrade defects using geological radar, aiming to achieve intelligent identification of subgrade pathologies with geological radar. The GprMax forward simulation software is used to establish multi-layer composite structural models of the subgrade, studying the characteristics of geological radar images for different types of subgrade diseases. Based on the forward simulation images of geological radar for subgrade defects and field measurement data, a geological radar subgrade defect image database is established. The Faster R-CNN deep learning algorithm is applied to achieve target detection, recognition, and classification of subgrade defect images. By comparing the loss value, total number of identified regions, and recognition accuracy as metrics, the study compares four improved versions of the Faster R-CNN algorithm. The results indicate that the faster_rcnn_inception_v2 version is more suitable for the intelligent identification of non-destructive testing of urban road subgrade defects.

NCOG-23. CLINICIAN AND PATIENT REPORTED OUTCOMES IN YOUNG ADULTS WITH GLIOBLASTOMA: RESULTS FROM A MULTIMODAL PROSPECTIVE STUDY

Abstract The median age for glioblastoma (GBM) is 65 years old, however, younger patients have a similarly dismal prognosis. The adolescent and young adult (AYA) population (15-39 years) is a unique and understudied population. Our study aimed to identify survivorship needs in adult patients in AYA population (&amp;lt;40 yrs) with GBM through analysis of patient and clinician-reported outcomes (PROs and CROs). The Molecular, Imaging and Neurological assessment Database (MIND-CNS) captures Neurological Assessment in Neuro-Oncology (NANO) scores, MDASI-BT and FACIT-SP12 responses at first clinic visit and follow-ups for patients with GBM. We tested associations of the two age groups (18-39 vs. 40 years and older) with each domain of NANO, MDASI-BT and FACIT-SP12 at baseline and at follow-up visits using multivariate logistic regression models, adjusting for MGMT promoter methylation and extent of resection. There were 104 patients with GBM enrolled, including 11 young adults, (median =30 years) and 93 older adults (median =65 years). Young and older adults scored similarly in the domains of NANO, MDASI-BT, and FACIT-SP12 at baseline. MDASI domains at follow-up showed statistically significant lower scores on weakness, fatigue, distress, irritability, drowsiness, and disturbed sleep in younger vs. older adults (adjusted p&amp;lt;0.05). Younger adults had less difficulty with memory and concentration, and their symptoms interfered less with work, walking, and overall enjoyment of life. They also reported feeling more peaceful, finding greater comfort and strength in their faith and beliefs. A comparison of NANO score at baseline and progression will be performed at data maturation. While PROs were similar at baseline, young adults reported lower severity in their physical symptoms and higher spiritual well-being compared to older adults at follow-up visits, highlighting different survivorship experiences. Data maturation will allow for deeper analysis to better inform supportive strategies.

Diagnostic Accuracy of Spectral Doppler Indices and Sonoelastography in Predicting Malignancy in Breast Imaging Reporting and Database System 3 Breast Lesions With Histopathology as the Reference Standard

Diagnostic Accuracy of Spectral Doppler Indices and Sonoelastography in Predicting Malignancy in Breast Imaging Reporting and Database System 3 Breast Lesions With Histopathology as the Reference Standard

Enhancing wildfire detection: a novel algorithm for controllable generation of wildfire smoke images

Background The lack of wildfire smoke image data is one of the most important factors hindering the development of image-based wildfire detection. Smoke image generation based on image inpainting techniques is a solution worthy of study. However, it is difficult to generate smoke texture with context consistency in complex backgrounds with current image inpainting methods. Aims This work aims to provide a wildfire smoke image database for specific scenarios. Methods We designed an algorithm based on generative adversarial networks (GANs) to generate smoke images. The algorithm includes a multi-scale fusion module to ensure consistency between the generated smoke and backgrounds. Additionally, a local feature-matching mechanism in the discriminator guides the generator to capture real smoke’s feature distribution. Key results We generated 13,400 wildfire smoke images based on forest background images and early fire simulation from the Fire Dynamics Simulator (FDS). Conclusions A variety of advanced object detection algorithms were trained based on the generated data. The experimental results confirmed that the addition of the generated data to the real datasets can effectively improve model performance. Implications This study paves a way for generating object datasets to enhance the reliability of watchtower or satellite wildfire monitoring.

Similarity ratings for basic-level categories from the Nosofsky et al. (2018) database of rock images

Similarity ratings for basic-level categories from the Nosofsky et al. (2018) database of rock images

Enhancing the Robustness of the E_BLIND/D_LC Digital Watermarking Algorithm Against DCT-Filtering Removal Attacks

The paper focuses on evaluating and improving the robustness of watermarking algorithms against DCT-filtering, a common image processing technique that can be used to remove embedded watermarks from cover images. The study examines the EBLIND/DLC watermarking algorithm, which operates in the spatial domain and is designed to embed a 1-bit message into an image. To evaluate robustness against DCT-filtering, the research utilizes software implementations of the watermarking algorithms, the dctdnoiz filter from FFmpeg, and the Flickr8k image database, which contains 8091 images. An extension to the E_BLIND/D_LC algorithm is proposed to enhance its robustness against DCT-filtering. The paper presents an experiment comparing the robustness of the extended algorithm with the original E_BLIND/D_LC. The results demonstrate that the extended algorithm improves robustness against DCT-filtering and also maintains better image quality, as measured by the PSNR metric, at equal levels of robustness in terms of the number of successful watermark detections after filtering. This suggests that the proposed extension effectively balances enhanced robustness against DCT-filtering with the preservation of image quality. The experiment confirms that the extended version outperforms the original algorithm in both detection reliability and image quality under DCT-filtering conditions. The paper includes links to the algorithm implementations on C++ programming language and the Python testing scripts, which can be useful for further research and practical applications in software development.

Development of an automated artificial intelligence-based system for urogenital schistosomiasis diagnosis using digital image analysis techniques and a robotized microscope.

Urogenital schistosomiasis is considered a Neglected Tropical Disease (NTD) by the World Health Organization (WHO). It is estimated to affect 150 million people worldwide, with a high relevance in resource-poor settings of the African continent. The gold-standard diagnosis is still direct observation of Schistosoma haematobium eggs in urine samples by optical microscopy. Novel diagnostic techniques based on digital image analysis by Artificial Intelligence (AI) tools are a suitable alternative for schistosomiasis diagnosis. Digital images of 24 urine sediment samples were acquired in non-endemic settings. S. haematobium eggs were manually labeled in digital images by laboratory professionals and used for training YOLOv5 and YOLOv8 models, which would achieve automatic detection and localization of the eggs. Urine sediment images were also employed to perform binary classification of images to detect erythrocytes/leukocytes with the MobileNetv3Large, EfficientNetv2, and NasNetLarge models. A robotized microscope system was employed to automatically move the slide through the X-Y axis and to auto-focus the sample. A total number of 1189 labels were annotated in 1017 digital images from urine sediment samples. YOLOv5x training demonstrated a 99.3% precision, 99.4% recall, 99.3% F-score, and 99.4% mAP0.5 for S. haematobium detection. NasNetLarge has an 85.6% accuracy for erythrocyte/leukocyte detection with the test dataset. Convolutional neural network training and comparison demonstrated that YOLOv5x for the detection of eggs and NasNetLarge for the binary image classification to detect erythrocytes/leukocytes were the best options for our digital image database. The development of low-cost novel diagnostic techniques based on the detection and identification of S. haematobium eggs in urine by AI tools would be a suitable alternative to conventional microscopy in non-endemic settings. This technical proof-of-principle study allows laying the basis for improving the system, and optimizing its implementation in the laboratories.

Comparative performance of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN models for detection of multiple weed species

Weeds pose a serious production challenge in various agronomic crops by reducing their grain yields. Increasing cases of herbicide-resistant (HR) weed populations further exacerbate the problem. Future weed control tactics require the integration of non-chemical and reduced chemical-based strategies that can target site- and specie-specific weed management (SSSWM). Advanced machine learning technology has the potential to localize and detect weed seedlings to implement SSSWM. However, due to large biological variability among various weed species and environmental conditions where they grow, accurate and precise weed detection remains challenging. The main objectives of this research were to (1) develop an annotated image database of cocklebur (Xanthium strumarium L.), dandelion (Taraxacum officinale), common waterhemp (Amaranthus tuberculatus), Palmer amaranth (Amaranthus palmeri) and common lambsquarters (Chenopodium album L.), and (2) investigate the comparative performance (speed and accuracy) of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN algorithms in detecting those weed species. A weed dataset with bounding box annotations for each weed species was created, consisting of images collected under variable field conditions which were preprocessed and augmented to create a dataset of 2348 color images. The YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN were trained using the annotated weed image database to detect each weed species. Results indicated that YOLOv11 was the fastest model with inference time of 13.5 milliseconds (ms) followed by YOLOv8 and YOLOv10 with inference time 23 and 19.3 milliseconds (ms), respectively. The YOLOv9 had the highest accuracy in detecting different weed species with an overall mean average precision (mAP@0.5) of 0.935. In contrast, the Detectron2 with Fast R-CNN configuration provided mAP@0.5 of 0.821 with an inference time of 63.8 ms. These results suggest that the YOLO series algorithms have the potential for real-time deployment for weed species detection more accurately and faster than Faster R-CNN in agricultural fields.

ValveVision AI - a multimodal language model for qualitative reporting of the aortic valve in echocardiography

Abstract Background The precise assessment of the aortic valve via echocardiography is critical for early detection and management of aortic valve diseases. Until recently, previous studies have examined machine learning models to estimate individual measurements and severity of aortic stenosis (AS) from echocardiographic images. These image processing algorithms, while precise in their narrow focus, fall short in mirroring the holistic and interconnected clinical judgment typical of human echocardiographers in producing a qualitative report. Large language models (LLMs), particularly image-to-text multi-modal LLMs, are a fundamental advance in the field of deep learning with implications for a host of applications in medical imaging. They promise to encapsulate not just discrete data points typical in traditional machine learning, but also the complex contextual interrelations in clinical diagnosis. Methods In this study, a large-scale heterogeneous database of echocardiographic images containing over 90,681 studies with textual descriptors of the aortic valve was used to train a single, image-to-text multimodal LLM called ValveVision AI. The ground truth textual summaries were drafted by level III echocardiographers in a clinical setting between 2015-2020. BLEU and ROUGE score was calculated. The models were retrospectively assessed on a holdout dataset. Reviewing physicians compared the generated summary to the ground truth and binarily agreed or rejected it. Receiver Operating Characteristics (ROC) for distinct pathologies were also assessed (Figure I). Results ValveVision AI performed with a BLEU score of 0.45 and a ROUGE score of 0.49. The performance of the model in reporting on classification of moderate/severe vs none/mild AS in concordance with the validation protocol described above achieved a specificity of 91.98% and a sensitivity of 83.89%, along with more precise qualitative description. Qualitatively, the model exhibited the capability of zero-shot learning in certain instances, however, this result remains an area of exploration. Conclusion This study represents to our knowledge, the first attempt at an image-representation to text-tokenizer deep learning model architecture to mimic the thought and subtlety of echocardiographic qualitative analysis of the aortic valve. The results suggest that this multimodal LLM has sufficient accuracy to create a preliminary textual summary of the aortic valve that, if paired with a point of care ultrasound (POCUS) device in a primary care setting, may facilitate case triage, increase efficiency, and determine a more precise care pathway for patients.

Left ventricular apical aneurysms and outcomes in hypertrophic cardiomyopathy

Abstract Background/Introduction The presence of left ventricular apical aneurysm (LVAA) has been shown to be associated with increased risk of adverse events in patients with hypertrophic cardiomyopathy (HCM). However, the between LVAA size and outcomes is uncertain. Purpose To explore associations between baseline LVAA diameter and progressive changes in LVAA size over time and poor outcomes in HCM patients. Methods Our HCM multimodality imaging database (transthoracic echocardiography (TTE) or cardiac magnetic resonance (CMR)) was retrospectively assessed for studies reporting LVAA, defined as one or more akinetic or dyskinetic apical segments. LVAA size (widest systolic diameter in millimetres in the transverse plane) was recorded at two time points: earliest identification and most recent imaging, with LVAA size progression (mm/year) calculated. Patients’ electronic records were reviewed for composite outcome including stroke, apical thrombus, death, and appropriate therapy from implantable cardioverter defibrillator (ICD). Continuous variables are presented as mean ± standard deviation (SD), categorical data numerically or as percentages. Comparisons between groups were made using Wilcoxon ranks sum and Fischer exact test for continuous and binary variables, respectively. Cox regression was used to assess independent associations with composite outcomes. A p value of &amp;lt;0.05 was considered statistically significant. Results A total of 106 patients were identified with LVAA and clinical follow-up (mean age 64.7±11.4 years, 70% male). Mean follow-up duration was 6.5±3.0 years. Baseline LVAA was confirmed by CMR and TTE in 70 and 30% of cases respectively. Mean LVAA size at baseline was 16.2±7.6 mm (range 6-56 mm). During multivariate Cox analysis, baseline LVAA size in mm was independently associated with the composite outcome (HR 1.04, 95% CIs 1.0 to 1.08, p=0.04). Mean duration between baseline and maximal LVAA size scan was 5.4±3.0 years. Median progression in LVAA size was 1.0 (IQR 0.6 to 1.8) mm per annum (range 0.0 to 8.1 mm). During multivariate analysis, LVAA progression rate in mm per year was independently associated with the composite outcome (HR 1.4 95% CIs 1.11 to 1.7, p=0.002). Conclusion(s) These data support the association between LVAA size and poor outcomes in HCM patients. We also demonstrate the progressive nature of LVAAs and indicate those more rapidly increasing in size are at highest risk of adverse events, with potential implications for management strategies.

Improving Automatic Coronary Stenosis Classification Using a Hybrid Metaheuristic with Diversity Control.

This study proposes a novel Hybrid Metaheuristic with explicit diversity control, aimed at finding an optimal feature subset by thoroughly exploring the search space to prevent premature convergence. Background/Objectives: Unlike traditional evolutionary computing techniques, which only consider the best individuals in a population, the proposed strategy also considers the worst individuals under certain conditions. In consequence, feature selection frequencies tend to be more uniform, decreasing the probability of premature convergent results and local-optima solutions. Methods: An image database containing 608 images, evenly balanced between positive and negative coronary stenosis cases, was used for experiments. A total of 473 features, including intensity, texture, and morphological types, were extracted from the image bank. A Support Vector Machine was employed to classify positive and negative stenosis cases, with Accuracy and the Jaccard Coefficient used as performance metrics. Results: The proposed strategy achieved a classification rate of 0.92 for Accuracy and 0.85 for the Jaccard Coefficient, obtaining a subset of 16 features, which represents a discrimination rate of 0.97 from the 473 initial features. Conclusions: The Hybrid Metaheuristic with explicit diversity control improved the classification performance of coronary stenosis cases compared to previous literature. Based on the achieved results, the identified feature subset demonstrates potential for use in clinical practice, particularly in decision-support information systems.

Deep Learning-Based Flap Detection System Using Thermographic Images in Plastic Surgery

In reconstructive surgery, flaps are the cornerstone for repairing tissue defects, but postoperative monitoring of their viability remains a challenge. Among the imagistic techniques for monitoring flaps, the thermal camera has demonstrated its value as an efficient indirect method that is easy to use and easy to integrate into clinical practice. This provides a narrow color spectrum image that is amenable to the development of an artificial neural network in the context of current technological progress. In the present study, we introduce a novel attention-enhanced recurrent residual U-Net (AER2U-Net) model that is able to accurately segment flaps on thermographic images. This model was trained on a uniquely generated database of thermographic images obtained by monitoring 40 patients who required flap surgery. We compared the proposed AER2U-Net with several state-of-the-art neural networks used for multi-modal segmentation of medical images, all of which are based on the U-Net architecture (U-Net, R2U-Net, AttU-Net). Experimental results demonstrate that our model (AER2U-Net) achieves significantly better performance on our unique dataset compared to these existing U-Net variants, showing an accuracy of 0.87. This deep learning-based algorithm offers a non-invasive and precise method to monitor flap vitality and detect postoperative complications early, with further refinement needed to enhance its clinical applicability and effectiveness.

Counting Cattle in Argentina with AI and Satellite Images

Abstract. From a specific need of the national institution responsible for plant and animal health in Argentina, SENASA, this collaborative work between the public sectors together with academia arises. The objective was the development of a Deep Learning algorithm for the detection of livestock, cows in particular, in very high-resolution satellite images (provided by the Argentine Space Agency (CONAE)) and its subsequent counting. The basic elements involved in the development of artificial intelligence are detailed, such as the selection and acquisition of satellite images, their very thorough preprocessing and labelling, details of the training stage and some forms of error quantification. The image database is made up of about 320 scenes (based on very high resolution (VHR) satellite data from the Pleiades and Pleiades NEO sensors, ©Airbus 2022, distributed by CONAE) of the Pampas and Patagonian regions in Argentina. Around 8,000 labels of different types of animals were generated, the most common were cows and sheep. Also labels that did not represent animals to contribute to training. Finally, some very promising preliminary results are presented, such as the average error in the count that was achieved was ± four cows. The usefulness of these tools is reflected in better management of renewable natural resources linked to animal health issues, fiscal issues and within the framework of the 2030 Agenda and Sustainable Development Goals #12, #15 and #17.

Vision Transformers for identifying asteroids interacting with secular resonances

Currently, more than 1.4 million asteroids are known in the main belt. Future surveys, like those that the Vera C. Rubin Observatory will perform, may increase this number to up to 8 million. While in the past identification of asteroids interacting with secular resonances was performed by a visual analysis of images of resonant arguments, this method is no longer feasible in the age of big data. Deep learning methods based on Convolutional Neural Networks (CNNs) have been used in the recent past to automatically classify databases of several thousands of images of resonant arguments for resonances like the ν6, the g−2g6+g5, and the s−s6−g5+g6. However, it has been shown that computer vision methods based on the Transformer architecture tend to outperform CNN models if the scale of the image database is large enough. Here, for the first time, we developed a Vision Transformer (ViT) model and applied it to publicly available databases for the three secular resonances quoted above. ViT architecture outperforms CNN models in speed and accuracy while avoiding overfitting concerns. If hyper-parameter tuning research is undertaken for each analyzed database, ViT models should be preferred over CNN architectures.

Blind Separation of Skin Chromophores from Multispectral Dermatological Images.

Background/Objectives: Based on Blind Source Separation and the use of multispectral imaging, the new approach we propose in this paper aims to improve the estimation of the concentrations of the main skin chromophores (melanin, oxyhemoglobin and deoxyhemoglobin), while considering shading as a fully-fledged source. Methods: In this paper, we demonstrate that the use of the Infra-Red spectral band, in addition to the traditional RGB spectral bands of dermatological images, allows us to model the image provided by each spectral band as a mixture of the concentrations of the three chromophores in addition to that of the shading, which are estimated through four steps using Blind Source Separation. Results: We studied the performance of our new method on a database of real multispectral dermatological images of melanoma by proposing a new quantitative performances measurement criterion based on mutual information. We then validated these performances on a database of multispectral dermatological images that we simulated using our own new protocol. Conclusions: All the results obtained demonstrated the effectiveness of our new approach for estimating the concentrations of the skin chromophores from a multispectral dermatological image, compared to traditional approaches that consist of using only the RGB image by neglecting shading.

Multi-View Soft Attention-Based Model for the Classification of Lung Cancer-Associated Disabilities.

Background: The detection of lung nodules at their early stages may significantly enhance the survival rate and prevent progression to severe disability caused by advanced lung cancer, but it often requires manual and laborious efforts for radiologists, with limited success. To alleviate it, we propose a Multi-View Soft Attention-Based Convolutional Neural Network (MVSA-CNN) model for multi-class lung nodular classifications in three stages (benign, primary, and metastatic). Methods: Initially, patches from each nodule are extracted into three different views, each fed to our model to classify the malignancy. A dataset, namely the Lung Image Database Consortium Image Database Resource Initiative (LIDC-IDRI), is used for training and testing. The 10-fold cross-validation approach was used on the database to assess the model's performance. Results: The experimental results suggest that MVSA-CNN outperforms other competing methods with 97.10% accuracy, 96.31% sensitivity, and 97.45% specificity. Conclusions: We hope the highly predictive performance of MVSA-CNN in lung nodule classification from lung Computed Tomography (CT) scans may facilitate more reliable diagnosis, thereby improving outcomes for individuals with disabilities who may experience disparities in healthcare access and quality.

Towards transforming malaria vector surveillance using VectorBrain: a novel convolutional neural network for mosquito species, sex, and abdomen status identifications

Malaria is a major public health concern, causing significant morbidity and mortality globally. Monitoring the local population density and diversity of the vectors transmitting malaria is critical to implementing targeted control strategies. However, the current manual identification of mosquitoes is a time-consuming and intensive task, posing challenges in low-resource areas like sub-Saharan Africa; in addition, existing automated identification methods lack scalability, mobile deployability, and field-test validity. To address these bottlenecks, a mosquito image database with fresh wild-caught specimens using basic smartphones is introduced, and we present a novel CNN-based architecture, VectorBrain, designed for identifying the species, sex, and abdomen status of a mosquito concurrently while being efficient and lightweight in computation and size. Overall, our proposed approach achieves 94.44±2% accuracy with a macro-averaged F1 score of 94.10±2% for the species classification, 97.66±1% accuracy with a macro-averaged F1 score of 96.17±1% for the sex classification, and 82.20±3.1% accuracy with a macro-averaged F1 score of 81.17±3% for the abdominal status classification. VectorBrain running on local mobile devices, paired with a low-cost handheld imaging tool, is promising in transforming the mosquito vector surveillance programs by reducing the burden of expertise required and facilitating timely response based on accurate monitoring.

Detection and classification on MRI images of brain tumor using YOLO NAS deep learning model

If a brain tumor is not properly diagnosed, it might result in fatal consequences and major health issues. As a result, a key component of diagnosis is the early identification of brain tumors and the precise categorization of brain tumor types. This research work focusses on detection and classification such as pituitary, meningioma, glioma, and non-tumorous tumors from brain tumor MRI image using YOLO NAS model. Advances in deep learning have led to an increasing awareness of computer-aided diagnosis technology. To improve classification performance, the input data set is acquired from the REMBRANDT repository using the Digital Database of Brain Tumor Magnetic Resonance Images. The primary phases of this task include segmentation, classification, and pre-processing. The researcher preprocessed the RGB image to exclude any undesired spots before locating the ROI. For each brain tumor image, we used the hybrid anisotropic diffusion filtering (HADF) technique to remove noise. The Encoder-Decoder Network (En–DeNet), which uses a deep neural network based on U-Net as the encoder and a pre-trained EfficientNet as the decoder, is then used to segment the MRI images. A proposed model was developed using a deep learning-based YOLO NAS technique to identify brain cancers from MRI images such as meningioma tumors, non-tumor, glioma tumors, and pituitary tumors. The suggested model's classification performance is weighed based on parameters such as precision, F1-score, sensitivity, accuracy, and specificity. The proposed fusion method YOLO NAS has improved classification results of accuracy (AC = 0.997%), specificity (SP = 0.985%), precision (PR = 0.982%), F1-score (F1 = 0.992%), and sensitivity (SE = 0.985%) using 2570 MRI data for training and 630 data for testing and validation of brain tumor cases. The results show that the brain tumor type classification system based on the proposed YOLO NAS technique works better than the DNN, PDCNN, DenseNet-161, and DCNN-SGD model classifiers.