Pathological Microscopic Images Research Articles

Blind Image Quality Assessment for Pathological Microscopic Image under Screen and Immersion Scenarios.

The high-quality pathological microscopic images are essential for physicians or pathologists to make a correct diagnosis. Image quality assessment (IQA) can quantify the visual distortion degree of images and guide the imaging system to improve image quality, thus raising the quality of pathological microscopic images. Current IQA methods are not ideal for pathological microscopy images due to their specificity. In this paper, we present deep learning-based blind image quality assessment model with saliency block and patch block for pathological microscopic images. The saliency block and patch block can handle the local and global distortions, respectively. To better capture the area of interest of pathologists when viewing pathological images, the saliency block is fine-tuned by eye movement data of pathologists. The patch block can capture lots of global information strongly related to image quality via the interaction between different image patches from different positions. The performance of the developed model is validated by the home-made Pathological Microscopic Image Quality Database under Screen and Immersion Scenarios (PMIQD-SIS) and cross-validated by the five public datasets. The results of ablation experiments demonstrate the contribution of the added blocks. The dataset and the corresponding code are publicly available at: https://github.com/mikugyf/PMIQD-SIS.

Artificial intelligence in ex vivo confocal laser scanning microscopy

Visual data, such as clinical photographs or pictures from imaging examination methods, such as ex vivo confocal laser scanning microscopy (CLSM), are particularly suitable for machine learning techniques. The aim was to find out whether data have already been published on this innovative application in ex vivo CLSM and what potential challenges and limitations could arise. Review of the literature and summary of current knowledge and personal experience on the use of artificial intelligence (AI) in ex vivo CLSM. Successful integration of digital hematoxylin-eosin-like staining has made ex vivo CLSM significantly more accessible for digital assessments. Several machine learning techniques have been developed to date in such away that they have been able to identify malignant skin lesions on clinical photographs and pathological microscopic images with similar accuracy compared to experts, or even find visual patterns that have been overlooked by experts and that correlate with certain dermatological diseases. One study on the use of AI in ex vivo CLSM for automated tumor detection has been published to date. Several challenges and limitations can arise when using AI in ex vivo CLSM. The already digitized ex vivo CLSM, which was established for rapid section examination purposes, is apredestined method for the development and use of new applications with machine learning in the healthcare sector. The results of further studies on this topic are anticipated with great hope.

Construction of Multi-Scale Model of Pancreatic Cancer Tumor from MRI Image and Pathological Microscopic Images

Construction of Multi-Scale Model of Pancreatic Cancer Tumor from MRI Image and Pathological Microscopic Images

A novel enhancement technique for pathological microscopic image using neutrosophic similarity score scaling

In 2011, Food and Drug Administration (FDA or USFDA) certified the automated cell morphology (ACM) systems for medical use in USA. The brightness, contrast and color appearance are all factors that play a major role in the diagnosis of many blood diseases. Accordingly, enhancement of pathological microscopic image (PMI) is a crucial step to increase the efficiency of computer assisted software. Some of the previous PMI enhancement methods neglected the illumination information and others used a reference image for template matching. These methods worked under strictly controlled conditions. In this paper, a robust technique is proposed for pathological images enhancement based on neutrosophic similarity score scaling. The color image is separated into three channels, and then each channel is represented in the neutrosophic domain into three subsets T, I and F. Neutrosophic similarity score (NSS) under multi-criteria are computed and used to scale the input image. The main contribution of this paper is that red, green and blue coefficients derived from the neutrosophic calculations lead directly to an adaptive pathology image enhancement and take into consideration many color image quality (IQ) parameters like illumination, contrast and color balance where it does not focus on a single IQ parameter like previous methods. In the experiments, several microscopic image quality measurements are utilized to evaluate the proposed method’s performance versus the previous enhancement techniques. The experimental results demonstrate that our proposed system is promising with low complexity, adaptive with different resolution and lighting conditions. This provides the basis for automatic medical diagnosis and further processing of medical images.

Liver Image Mosaicing System Based on Scale Invariant Feature Transform and Point Set Matching Method

Image mosaic is an important research content in digital image processing, and could be used to solve the prob- lem of observing large objects with narrow view, such as 360 degree panorama stitching. Microscopic observation of liver biopsy is a commonly used method in diagnosing liver diseases, which are always rely on the whole liver slice. Therefore, the liver pathological microscopic image mosaic is the best way to formulate it. This paper proposes a liver image mosaic- ing system based on scale invariant feature transform and point set matching method, which includes the feature point se- lection and location process to find the extremum point, screen them, and precisely position them. This system takes the affine transformation as the motion model, and adopts a new matching algorithm for the rigid transformation to accelerate solving the motion parameter. The design and implementation of the liver image mosaicing system have completed more than 100 cases successfully, which shows the effectiveness and robustness of our algorithms.

The Using of Combination Algorithm to the Gastric Carcinoma Nucleus Segmentation

The nucleus segmentation of gastric carcinoma pathological section microscopic image is a challenge. Watershed and GVF model can be applied to ordinary nucleus segmentation, but each has its advantages and disadvantages. Combine two algorithms and pathology expertise. The initial contours of nucleus are achieved by watershed transformation first, and then the final contours are approaching by GVF model. Experiments show that the combined algorithm is valid.

Signal analysis and compression performance evaluation of pathological microscopic images.

Digitizing high-quality microscopic images and developing input/output technology for displaying those results is critical to telepathology in which pathological microscopic images are transferred to remote locations where they are diagnosed by specialists. This paper will discuss the results achieved by directly digitizing (nonfilm process) pathological microscopic images at a 2k x 2k resolution, and then using a super-high-definition imaging system to analyze their signals and evaluate compression performance. We will start off by digitizing samples that a pathologist will actually use in making a diagnosis, and then analyze their color distribution and spatial frequencies characteristics by comparing them to general images. This will make it apparent that such pathological images characteristically contain high spatial frequency in their chrominance components. We will also discuss the evaluation results of color differences for L*a*b* space and compression ratios achieved when using JPEG to encode pathological images. We will also present a subjective evaluation of the influence subsampling of chrominance components has on image quality.