RESUMO
Brain tumor detection depicts a tough job because of its shape, size and appearance variations. In this manuscript, a deep learning model is deployed to predict input slices as a tumor (unhealthy)/non-tumor (healthy). This manuscript employs a high pass filter image to prominent the inhomogeneities field effect of the MR slices and fused with the input slices. Moreover, the median filter is applied to the fused slices. The resultant slices quality is improved with smoothen and highlighted edges of the input slices. After that, based on these slices' intensity, a 4-connected seed growing algorithm is applied, where optimal threshold clusters the similar pixels from the input slices. The segmented slices are then supplied to the fine-tuned two layers proposed stacked sparse autoencoder (SSAE) model. The hyperparameters of the model are selected after extensive experiments. At the first layer, 200 hidden units and at the second layer 400 hidden units are utilized. The testing is performed on the softmax layer for the prediction of the images having tumors and no tumors. The suggested model is trained and checked on BRATS datasets i.e., 2012(challenge and synthetic), 2013, and 2013 Leaderboard, 2014, and 2015 datasets. The presented model is evaluated with a number of performance metrics which demonstrates the improved performance.
Assuntos
Algoritmos , Neoplasias Encefálicas/diagnóstico por imagem , Neoplasias Encefálicas/patologia , Aprendizado Profundo , Diagnóstico por Computador/métodos , Humanos , Processamento de Imagem Assistida por Computador/métodosRESUMO
Space-occupying lesions (SOL) brain detected on brain MRI are benign and malignant tumors. Several brain tumor segmentation algorithms have been developed but there is a need for a clinically acquired dataset that is used for real-time images. This research is done to facilitate reporting of MRI done for brain tumor detection by incorporating computer-aided detection. Another objective was to make reporting unbiased by decreasing inter-observer errors and expediting daily reporting sessions to decrease radiologists' workload. This is an experimental study. The proposed dataset contains clinically acquired multiplanar, multi-sequential MRI slices (MPMSI) which are used as input to the segmentation model without any preprocessing. The proposed AJBDS-2023 consists of 10667 images of real patients imaging data with a size of 320*320*3. Acquired images have T1W, TW2, Flair, T1W contrast, ADC, and DWI sequences. Pixel-based ground-truth annotated images of the tumor core and edema of 6334 slices are made manually under the supervision of a radiologist. Quantitative assessment of AJBDS-2023 images is done by a novel U-network on 4333 MRI slices. The diagnostic accuracy of our algorithm U-Net trained on AJBDS-2023 was 77.4 precision, 82.3 DSC, 87.4 specificity, 93.8 sensitivity, and 90.4 confidence interval. An experimental analysis of AJBDS-2023 done by the U-Net segmentation model proves that the proposed AJBDS-2023 dataset has images without preprocessing, which is more challenging and provides a more realistic platform for evaluation and analysis of newly developed algorithms in this domain and helps radiologists in MRI brain reporting more realistically.
RESUMO
Complications in diabetes lead to diabetic retinopathy (DR) hence affecting the vision. Computerized methods performed a significant role in DR detection at the initial phase to cure vision loss. Therefore, a method is proposed in this study that consists of three models for localization, segmentation, and classification. A novel technique is designed with the combination of pre-trained ResNet-18 and YOLOv8 models based on the selection of optimum layers for the localization of DR lesions. The localized images are passed to the designed semantic segmentation model on selected layers and trained on optimized learning hyperparameters. The segmentation model performance is evaluated on the Grand-challenge IDRID segmentation dataset. The achieved results are computed in terms of mean IoU 0.95,0.94, 0.96, 0.94, and 0.95 on OD, SoftExs, HardExs, HAE, and MAs respectively. Another classification model is developed in which deep features are derived from the pre-trained Efficientnet-b0 model and optimized using a Genetic algorithm (GA) based on the selected parameters for grading of NPDR lesions. The proposed model achieved greater than 98 % accuracy which is superior to previous methods.
RESUMO
The development of genotypes that can tolerate high levels of salt is crucial for the efficient use of salt-affected land and for enhancing crop productivity worldwide. Therefore, incorporating salinity tolerance is a critical trait that crops must possess. Salt resistance is a complex character, controlled by multiple genes both physiologically and genetically. To examine the genetic foundation of salt tolerance, we assessed 16 F1 hybrids and their eight parental lines under normal and salt stress (15 dS/m) conditions. Under salt stress conditions significant reduction was observed for plant height (PH), bolls/plant (NBP), boll weight (BW), seed cotton yield (SCY), lint% (LP), fiber length (FL), fiber strength (FS), potassium to sodium ratio (K+/Na+), potassium contents (K+), total soluble proteins (TSP), carotenoids (Car) and chlorophyll contents. Furthermore, the mean values for hydrogen peroxide (H2O2), sodium contents (Na+), catalase (CAT), superoxide dismutase (SOD), peroxidase (POD), and fiber fineness (FF) were increased under salt stress. Moderate to high heritability and genetic advancement was observed for NBP, BW, LP, SCY, K+/Na+, SOD, CAT, POD, Car, TSP, FL, and FS. Mean performance and multivariate analysis of 24 cotton genotypes based on various agro-physiological and biochemical parameters suggested that the genotypes FBS-Falcon, Barani-333, JSQ-White Hold, Ghauri, along with crosses FBS-FALCON × JSQ-White Hold, FBG-222 × FBG-333, FBG-222 × Barani-222, and Barani-333 × FBG-333 achieved the maximum values for K+/Na+, K+, TSP, POD, Chlb, CAT, Car, LP, FS, FL, PH, NBP, BW, and SCY under salt stress and declared as salt resistant genotypes. The above-mentioned genotypes also showed relatively higher expression levels of Ghi-ERF-2D.6 and Ghi-ERF-7A.6 at 15 dS/m and proved the role of these ERF genes in salt tolerance in cotton. These findings suggest that these genotypes have the potential for the development of salt-tolerant cotton varieties with desirable fiber quality traits.
Assuntos
Gossypium , Tolerância ao Sal , Gossypium/genética , Gossypium/metabolismo , Gossypium/fisiologia , Tolerância ao Sal/genética , Regulação da Expressão Gênica de Plantas , Proteínas de Plantas/genética , Proteínas de Plantas/metabolismo , Genótipo , Potássio/metabolismo , Estresse Salino/genética , FenótipoRESUMO
KRAS is the signature gene responsible for the occurrence of pancreatic cancer, which is a complex, multifactorial and intractable lethal malignancy. Prevention and treatment of the ailment have always been a key motivation behind the search for new therapeutic drug molecules. G-quadruplexes are non-canonical guanine-rich secondary structures, commonly formed at eukaryotic telomeric ends, oncogenic promotors and G-rich regions of the DNA. These G-quadruplexes play a crucial role in the regulation of gene expression and maintenance of genome integrity, therefore, they are considered as emerging potential therapeutic drug targets. The present study is concerned with the discovery of a potential stabilizer for KRAS22RT G-quadruplex DNA, located in the NHE region of the promotor, while inhibiting the upregulation of KRAS proto-oncogene, as an alternative approach for the treatment of pancreatic cancer. Various chemical libraries have been virtually screened against the targeted G4 structure and 143 compounds showed promising results. However, molecular dynamic studies, ADME and toxicity analyses predicted that three compounds belonging to the class of tetra-substituted phenanthrolines (i.e., 7i, 7j and 7k) can not only effectively stabilize KRAS22RT G4 structure but also have least toxic effects in the in vivo system. Therefore, it is highly recommended to further investigate their effectiveness and efficacy through experimental analysis in laboratory.Communicated by Ramaswamy H. Sarma.
Assuntos
Quadruplex G , Neoplasias Pancreáticas , Humanos , Proteínas Proto-Oncogênicas p21(ras)/genética , DNA/química , Neoplasias Pancreáticas/tratamento farmacológico , Neoplasias Pancreáticas/genética , Neoplasias PancreáticasRESUMO
Background: COVID-19 is a novel virus that affects the upper respiratory tract, as well as the lungs. The scale of the global COVID-19 pandemic, its spreading rate, and deaths are increasing regularly. Computed tomography (CT) scans can be used carefully to detect and analyze COVID-19 cases. In CT images/scans, ground-glass opacity (GGO) is found in the early stages of infection. While in later stages, there is a superimposed pulmonary consolidation. Methods: This research investigates the quantum machine learning (QML) and classical machine learning (CML) approaches for the analysis of COVID-19 images. The recent developments in quantum computing have led researchers to explore new ideas and approaches using QML. The proposed approach consists of two phases: in phase I, synthetic CT images are generated through the conditional adversarial network (CGAN) to increase the size of the dataset for accurate training and testing. In phase II, the classification of COVID-19/healthy images is performed, in which two models are proposed: CML and QML. Result: The proposed model achieved 0.94 precision (Pn), 0.94 accuracy (Ac), 0.94 recall (Rl), and 0.94 F1-score (Fe) on POF Hospital dataset while 0.96 Pn, 0.96 Ac, 0.95 Rl, and 0.96 Fe on UCSD-AI4H dataset. Conclusion: The proposed method achieved better results when compared to the latest published work in this domain.
RESUMO
The visual inspection of histopathological samples is the benchmark for detecting breast cancer, but a strenuous and complicated process takes a long time of the pathologist practice. Deep learning models have shown excellent outcomes in clinical diagnosis and image processing and advances in various fields, including drug development, frequency simulation, and optimization techniques. However, the resemblance of histopathologic images of breast cancer and the inclusion of stable and infected tissues in different areas make detecting and classifying tumors on entire slide images more difficult. In breast cancer, a correct diagnosis is needed for complete care in a limited amount of time. An effective detection can relieve the pathologist's workload and mitigate diagnostic subjectivity. Therefore, this research work investigates improved the pre-trained xception and deeplabv3+ design semantic model. The model has been trained on input images with ground masks on the tuned parameters that significantly improve the segmentation of ultrasound breast images into respective classes, that is, benign/malignant. The segmentation model delivered an accuracy of greater than 99% to prove the model's effectiveness. The segmented images and histopathological breast images are transferred to the 4-qubit-quantum circuit with six-layered architecture to detect breast malignancy. The proposed framework achieved remarkable performance as contrasted to currently published methodologies. HIGHLIGHTS: This research proposed hybrid semantic model using pre-trained xception and deeplabv3 for breast microscopic cancer classification in to benign and malignant classes at accuracy of 95% accuracy, 99% accuracy for detection of breast malignancy.
Assuntos
Neoplasias da Mama , Mama , Neoplasias da Mama/diagnóstico por imagem , Feminino , Humanos , Processamento de Imagem Assistida por Computador/métodosRESUMO
Worldwide, more than 1.5 million deaths are occur due to liver cancer every year. The use of computed tomography (CT) for early detection of liver cancer could save millions of lives per year. There is also an urgent need for a computerized method to interpret, detect and analyze CT scans reliably, easily, and correctly. However, precise segmentation of minute tumors is a difficult task because of variation in the shape, intensity, size, low contrast of the tumor, and the adjacent tissues of the liver. To address these concerns, a model comprised of three parts: synthetic image generation, localization, and segmentation, is proposed. An optimized generative adversarial network (GAN) is utilized for generation of synthetic images. The generated images are localized by using the improved localization model, in which deep features are extracted from pre-trained Resnet-50 models and fed into a YOLOv3 detector as an input. The proposed modified model localizes and classifies the minute liver tumor with 0.99 mean average precision (mAp). The third part is segmentation, in which pre-trained Inceptionresnetv2 employed as a base-Network of Deeplabv3 and subsequently is trained on fine-tuned parameters with annotated ground masks. The experiments reflect that the proposed approach has achieved greater than 95% accuracy in the testing phase and it is proven that, in comparison to the recently published work in this domain, this research has localized and segmented the liver and minute liver tumor with more accuracy.
RESUMO
Blood is made up of leukocytes (WBCs), erythrocytes (RBCs), and thrombocytes. The ratio of blood cancer diseases is increasing rapidly, among which leukemia is one of the famous cancer which may lead to death. Leukemia cancer is initiated by the unnecessary growth of immature WBCs present in the sponge tissues of bone marrow. It is generally analyzed by etiologists by perceiving slides of blood smear images under a microscope. The morphological features and blood cells count facilitated the etiologists to detect leukemia. Due to the late detection and expensive instruments used for leukemia analysis, the death rate has risen significantly. The fluorescence-based cell sorting technique and manual recounts using a hemocytometer are error-prone and imprecise. Leukemia detection methods consist of pre-processing, segmentation, features extraction, and classification. In this article, recent deep learning methodologies and challenges for leukemia detection are discussed. These methods are helpful to examine the microscopic blood smears images and for the detection of leukemia more accurately.
Assuntos
Algoritmos , Leucemia , Humanos , Leucócitos , Leucemia/diagnóstico , Eritrócitos , Processamento de Imagem Assistida por Computador/métodosRESUMO
Coronavirus19 is caused due to infection in the respiratory system. It is the type of RNA virus that might infect animal and human species. In the severe stage, it causes pneumonia in human beings. In this research, hand-crafted and deep microscopic features are used to classify lung infection. The proposed work consists of two phases; in phase I, infected lung region is segmented using proposed U-Net deep learning model. The hand-crafted features are extracted such as histogram orientation gradient (HOG), noise to the harmonic ratio (NHr), and segmentation based fractal texture analysis (SFTA) from the segmented image, and optimum features are selected from each feature vector using entropy. In phase II, local binary patterns (LBPs), speeded up robust feature (Surf), and deep learning features are extracted using a pretrained network such as inceptionv3, ResNet101 from the input CT images, and select optimum features based on entropy. Finally, the optimum selected features using entropy are fused in two ways, (i) The hand-crafted features (HOG, NHr, SFTA, LBP, SURF) are horizontally concatenated/fused (ii) The hand-crafted features (HOG, NHr, SFTA, LBP, SURF) are combined/fused with deep features. The fused optimum features vector is passed to the ensemble models (Boosted tree, bagged tree, and RUSBoosted tree) in two ways for the COVID19 classification, (i) classification using fused hand-crafted features (ii) classification using fusion of hand-crafted features and deep features. The proposed methodology is tested /evaluated on three benchmark datasets. Two datasets employed for experiments and results show that hand-crafted & deep microscopic feature's fusion provide better results compared to only hand-crafted fused features.
Assuntos
COVID-19 , Humanos , Inteligência , Redes Neurais de Computação , SARS-CoV-2RESUMO
BACKGROUND AND OBJECTIVE: Brain tumor occurs because of anomalous development of cells. It is one of the major reasons of death in adults around the globe. Millions of deaths can be prevented through early detection of brain tumor. Earlier brain tumor detection using Magnetic Resonance Imaging (MRI) may increase patient's survival rate. In MRI, tumor is shown more clearly that helps in the process of further treatment. This work aims to detect tumor at an early phase. METHODS: In this manuscript, Weiner filter with different wavelet bands is used to de-noise and enhance the input slices. Subsets of tumor pixels are found with Potential Field (PF) clustering. Furthermore, global threshold and different mathematical morphology operations are used to isolate the tumor region in Fluid Attenuated Inversion Recovery (Flair) and T2 MRI. For accurate classification, Local Binary Pattern (LBP) and Gabor Wavelet Transform (GWT) features are fused. RESULTS: The proposed approach is evaluated in terms of peak signal to noise ratio (PSNR), mean squared error (MSE) and structured similarity index (SSIM) yielding results as 76.38, 0.037 and 0.98 on T2 and 76.2, 0.039 and 0.98 on Flair respectively. The segmentation results have been evaluated based on pixels, individual features and fused features. At pixels level, the comparison of proposed approach is done with ground truth slices and also validated in terms of foreground (FG) pixels, background (BG) pixels, error region (ER) and pixel quality (Q). The approach achieved 0.93 FG and 0.98 BG precision and 0.010 ER on a local dataset. On multimodal brain tumor segmentation challenge dataset BRATS 2013, 0.93 FG and 0.99 BG precision and 0.005 ER are acquired. Similarly on BRATS 2015, 0.97 FG and 0.98 BG precision and 0.015 ER are obtained. In terms of quality, the average Q value and deviation are 0.88 and 0.017. At the fused feature based level, specificity, sensitivity, accuracy, area under the curve (AUC) and dice similarity coefficient (DSC) are 1.00, 0.92, 0.93, 0.96 and 0.96 on BRATS 2013, 0.90, 1.00, 0.97, 0.98 and 0.98 on BRATS 2015 and 0.90, 0.91, 0.90, 0.77 and 0.95 on local dataset respectively. CONCLUSION: The presented approach outperformed as compared to existing approaches.