Background: Cytology is one of the important diagnostic tests done on effusion fluid. It can detect malignant cells in up to 60% of malignant cases. The most important benign cell present in these effusions is the mesothelial cell. Mesothelial atypia can be striking andmay simulate metastatic carcinoma. Many clinical conditions may produce such a reactive atypical cells as in anemia,SLE, liver cirrhosis and many other conditions. Recently many studies showed the value of computerized image analysis in differentiating atypical cells from malignant adenocarcinoma cells in effusion smears. Other studies support the reliability of the quantitative analysisand morphometric features and proved that they are objective prognostic indices. Methods: Sixty three cases of pleural and peritoneal smears, previously reported as benign (19) cases, malignant (21) cases or atypical (23) cases, were retrieved from the files. In each of these smears; nuclear area, perimeter, and roundness coefficient of 80-100 cell were determined at x400 magnification by the use of image analysis system. Statistical analysis was performed using analysis of variance and Tukey's HSD test. Results: The mean values of nuclear roundness, nuclear perimeter and nuclear area vary between the three groups (benign, atypical and malignant cells) by using analysis of variance (p > 0.01). The value of nuclear roundness, perimeter and area did not differ significantly between benign and atypical cells (Tukey’s test: p<0.01). On the other hand, the value of nuclear roundness, perimeter and area showed a significant difference between malignant and atypical cells(Tukey's test: p> 0.01). Conclusion: In conclusion, our data suggest that cytomorphometry performed on effusion smear cells may provide important information for the differentiation of atypical cells from malignant cells, in which the values of atypical cells are closer to those of benign cells during the examination of pleural and peritoneal smears by the use of image analysis system
<p>In this paper, a simple color image compression system has been proposed using image signal decomposition. Where, the RGB image color band is converted to the less correlated YUV color model and the pixel value (magnitude) in each band is decomposed into 2-values; most and least significant. According to the importance of the most significant value (MSV) that influenced by any simply modification happened, an adaptive lossless image compression system is proposed using bit plane (BP) slicing, delta pulse code modulation (Delta PCM), adaptive quadtree (QT) partitioning followed by an adaptive shift encoder. On the other hand, a lossy compression system is introduced to handle the least significant value (LSV), it is based on
... Show More
(7)
(1)
(40)
(38)
Artificial intelligence (AI) is entering many fields of life nowadays. One of these fields is biometric authentication. Palm print recognition is considered a fundamental aspect of biometric identification systems due to the inherent stability, reliability, and uniqueness of palm print features, coupled with their non-invasive nature. In this paper, we develop an approach to identify individuals from palm print image recognition using Orange software in which a hybrid of AI methods: Deep Learning (DL) and traditional Machine Learning (ML) methods are used to enhance the overall performance metrics. The system comprises of three stages: pre-processing, feature extraction, and feature classification or matching. The SqueezeNet deep le
... Show More
(6)
(3)
Artificial intelligence (AI) is entering many fields of life nowadays. One of these fields is biometric authentication. Palm print recognition is considered a fundamental aspect of biometric identification systems due to the inherent stability, reliability, and uniqueness of palm print features, coupled with their non-invasive nature. In this paper, we develop an approach to identify individuals from palm print image recognition using Orange software in which a hybrid of AI methods: Deep Learning (DL) and traditional Machine Learning (ML) methods are used to enhance the overall performance metrics. The system comprises of three stages: pre-processing, feature extraction, and feature classification or matching. The SqueezeNet deep le
... Show More
(6)
(3)
(1)
(1)
This paper proposes a new method Object Detection in Skin Cancer Image, the minimum
spanning tree Detection descriptor (MST). This ObjectDetection descriptor builds on the
structure of the minimum spanning tree constructed on the targettraining set of Skin Cancer
Images only. The Skin Cancer Image Detection of test objects relies on their distances to the
closest edge of thattree. Our experimentsshow that the Minimum Spanning Tree (MST) performs
especially well in case of Fogginessimage problems and in highNoisespaces for Skin Cancer
Image.
The proposed method of Object Detection Skin Cancer Image wasimplemented and tested on
different Skin Cancer Images. We obtained very good results . The experiment showed that
The confirming of security and confidentiality of multimedia data is a serious challenge through the growing dependence on digital communication. This paper offers a new image cryptography based on the Chebyshev chaos polynomials map, via employing the randomness characteristic of chaos concept to improve security. The suggested method includes block shuffling, dynamic offset chaos key production, inter-layer XOR, and block 90 degree rotations to disorder the correlations intrinsic in image. The method is aimed for efficiency and scalability, accomplishing complexity order for n-pixels over specific cipher rounds. The experiment outcomes depict great resistant to cryptanalysis attacks, containing statistical, differential and brut
... Show More
(8)
(2)
In this paper, an efficient image segmentation scheme is proposed of boundary based & geometric region features as an alternative way of utilizing statistical base only. The test results vary according to partitioning control parameters values and image details or characteristics, with preserving the segmented image edges.
General Background: Deep image matting is a fundamental task in computer vision, enabling precise foreground extraction from complex backgrounds, with applications in augmented reality, computer graphics, and video processing. Specific Background: Despite advancements in deep learning-based methods, preserving fine details such as hair and transparency remains a challenge. Knowledge Gap: Existing approaches struggle with accuracy and efficiency, necessitating novel techniques to enhance matting precision. Aims: This study integrates deep learning with fusion techniques to improve alpha matte estimation, proposing a lightweight U-Net model incorporating color-space fusion and preprocessing. Results: Experiments using the AdobeComposition-1k
... Show More