CNN-O-ELMNet: Optimized Lightweight and Generalized Model for Lung Disease Classification and Severity Assessment.

The high burden of lung diseases on healthcare necessitates effective detection methods. Current Computer-aided design (CAD) systems are limited by their focus on specific diseases and computationally demanding deep learning models. To overcome these challenges, we introduce CNN-O-ELMNet, a lightweight classification model designed to efficiently detect various lung diseases, surpassing the limitations of disease-specific CAD systems and the complexity of deep learning models. This model combines a convolutional neural network for deep feature extraction with an optimized extreme learning machine, utilizing the imperialistic competitive algorithm for enhanced predictions. We then evaluated the effectiveness of CNN-O-ELMNet using benchmark datasets for lung diseases: distinguishing pneumothorax vs. non-pneumothorax, tuberculosis vs. normal, and lung cancer vs. healthy cases. Our findings demonstrate that CNN-O-ELMNet significantly outperformed (p < 0.05) state-of-the-art methods in binary classifications for tuberculosis and cancer, achieving accuracies of 97.85% and 97.70%, respectively, while maintaining low computational complexity with only 2481 trainable parameters. We also extended the model to categorize lung disease severity based on Brixia scores. Achieving a 96.20% accuracy in multi-class assessment for mild, moderate, and severe cases, makes it suitable for deployment in lightweight healthcare devices.

Physiological and antioxidant responses associated with Sub1 gene introgressed rice (Oryza sativa L.) lines under complete submergence.

Rice is the only crop which is well adapted to aquatic environment but, it is unable to survive if completely submerged for several weeks. Breeding rice varieties with submergence tolerance is one of the best approaches to alleviate the adverse effect of submergence which requires the introgression of Sub1 gene into elite rice varieties. Hence, the study was undertaken to introgress submergence tolerant gene into the rice variety Jaya through Marker-Assisted Backcross Breeding. Also the physiological and biochemical responses like survival percentage, underwater shoot elongation, total carbohydrate content and superoxide dismutase activity were also studied in Sub1 introgressed lines. We could develop twenty Sub1 introgressed lines with Sub1 region of 3.1-5.1mb and with 80.0- 95.3% recurrent parent genome recovery. Sub1 introgressed Jaya lines and the tolerant checks FR13A and Swarna Sub1 had lower shoot elongation under water, higher superoxide dismutase activity (about 5 times) upto 4 h after de-submergence which resulted in higher survival percentage. The reduced shoot elongation of tolerant varieties reduced the utilization of stored carbohydrate. Through our research we introgressed Sub1 gene into rice variety Jaya through Marker-Assisted Backcross Breeding and could study the physiological responses under submergence by which we confirmed the presence of Sub1 gene in these lines. These lines could be field evaluated and could be released as a new variety thus helping the farmers of flood prone areas of Kerala.

Deep Bidirectional Classification Model for COVID-19 Disease Infected Patients.

In December of 2019, a novel coronavirus (COVID-19) appeared in Wuhan city, China and has been reported in many countries with millions of people infected within only four months. Chest computed Tomography (CT) has proven to be a useful supplement to reverse transcription polymerase chain reaction (RT-PCR) and has been shown to have high sensitivity to diagnose this condition. Therefore, radiological examinations are becoming crucial in early examination of COVID-19 infection. Currently, CT findings have already been suggested as an important evidence for scientific examination of COVID-19 in Hubei, China. However, classification of patient from chest CT images is not an easy task. Therefore, in this paper, a deep bidirectional long short-term memory network with mixture density network (DBM) model is proposed. To tune the hyperparameters of the DBM model, a Memetic Adaptive Differential Evolution (MADE) algorithm is used. Extensive experiments are drawn by considering the benchmark chest-Computed Tomography (chest-CT) images datasets. Comparative analysis reveals that the proposed MADE-DBM model outperforms the competitive COVID-19 classification approaches in terms of various performance metrics. Therefore, the proposed MADE-DBM model can be used in real-time COVID-19 classification systems.

Enhanced Binary Hexagonal Extrema Pattern (EBHXEP) Descriptor for Iris Liveness Detection.

Biometric traits are frequently used by security agencies for automatic recognition of a person. There are numerous biometric traits used for person identification. In recent years, iris biometric trait becomes very popular and efficient in many security applications. However, biometric systems are prone to presentation attack. This attack is carried out by using spoofing of any biometric modality and present as a genuine trait. The effect of an artificial artifact of a humanoid iris could be in the form of contact lens attack and print attack make difficult the expected policy of a biometric liveness system. In this paper, the different and enhanced feature descriptor has been proposed i.e. Enhanced Binary Hexagonal Extrema Pattern (EBHXEP) for forged iris detection. The relationship between the center pixel and its hexa neighbor has been explored by the suggested descriptor. The Proposed approach is tested on ATVS-FIr DB and IIIT-D CLI database for iris liveness detection and the results show better results for liveness detection in term of accuracy and average error rate.

Feature selection and classification of leukocytes using random forest.

In automatic segmentation of leukocytes from the complex morphological background of tissue section images, a vast number of artifacts/noise are also extracted causing large amount of multivariate data generation. This multivariate data degrades the performance of a classifier to discriminate between leukocytes and artifacts/noise. However, the selection of prominent features plays an important role in reducing the computational complexity and increasing the performance of the classifier as compared to a high-dimensional features space. Therefore, this paper introduces a novel Gini importance-based binary random forest feature selection method. Moreover, the random forest classifier is used to classify the extracted objects into artifacts, mononuclear cells, and polymorphonuclear cells. The experimental results establish that the proposed method effectively eliminates the irrelevant features, maintaining the high classification accuracy as compared to other feature reduction methods.

Automated microscopic image analysis for leukocytes identification: a survey.

Automatic quantification and classification of leukocytes in microscopic images are of paramount importance in the perspective of disease identification, its progress and drugs development. Extracting numerical values of leukocytes from microscopic images of blood or tissue sections represents a tricky challenge. Research efforts in quantification of these cells include normalization of images, segmentation of its nuclei and cytoplasm followed by their classification. However, there are several related problems viz., coarse background, overlapped nuclei, conversion of 3-D nuclei into 2-D nuclei etc. In this review, we have categorized, evaluated, and discussed recently developed methods for leukocyte identification. After reviewing these methods and finding their constraints, a future research perspective has been presented. Further, the challenges faced by the pathologists with respect to these problems are also discussed.