Erosion and dilation of binary images by arbitrary structuring elements using interval coding

A multiangle polarised imaging-based method for thin section segmentation

The most crucial task of petroleum geology is to explore oil and gas reservoirs in the deep underground. As one of the analysis techniques in petroleum geological research, rock thin section identification method includes particle segmentation, which is one of the key steps. A conventional sandstone thin section image typically contains hundreds of mineral particles with blurred boundaries and complex microstructures inside the particles. Moreover, the complex lithology and low porosity of tight sandstone make traditional image segmentation methods unsuitable for solving the complex thin section segmentation problems. This paper combines petrology and image processing technologies. First, polarised sequence images are aligned, and then the images are transformed to the HSV colour space to extract pores. Second, particles are extracted according to their extinction characteristics. Last, a concavity and corner detection matching method is used to process the extracted particles, thereby completing the segmentation of sandstone thin section images. The experimental results show that our proposed method can more accurately fit the boundaries of mineral particles in sandstone images than existing image segmentation methods. Additionally, when applied in actual production scenarios, our method exhibits excellent performance, greatly improving thin section identification efficiency and significantly assisting experts in identification.

Machine vision-assisted identification of the lung adenocarcinoma category and high-risk tumor area based on CT images

Computed tomography (CT) is a widely used medical imaging technique. It is important to determine the relationship between CT images and pathological examination results of lung adenocarcinoma to better support its diagnosis. In this study, a bilateral-branch network with a knowledge distillation procedure (KDBBN) was developed for the auxiliary diagnosis of lung adenocarcinoma. KDBBN can automatically identify adenocarcinoma categories and detect the lesion area that most likely contributes to the identification of specific types of adenocarcinoma based on lung CT images. In addition, a knowledge distillation process was established for the proposed framework to ensure that the developed models can be applied to different datasets. The results of our comprehensive computational study confirmed that our method provides a reliable basis for adenocarcinoma diagnosis supplementary to the pathological examination. Meanwhile, the high-risk area labeled by KDBBN highly coincides with the related lesion area labeled by doctors in clinical diagnosis.

•

We study machine vision-assisted lung adenocarcinoma classification using CT images

•

We design a holistic machine vision framework, improving classification performance

•

Our method outperforms famous deep CNNs and medical imaging classification methods

•

Our method better explains relations between CT patterns and pathological diagnoses

Lung adenocarcinoma is the most common type of lung cancer; therefore, its early diagnosis is crucial. In this study, we develop a holistic machine vision framework to automatically analyze CT images and identify the lung adenocarcinoma category with impressive performance. Our developed method can provide a reliable supplementary basis for adenocarcinoma diagnosis in clinical settings and can be used to label high-risk areas in CT images so that the relationship between CT characteristics and pathological diagnosis can be determined. Our method can potentially be used as an artificial intelligence (AI) system for adenocarcinoma identification using CT images, which will upgrade adenocarcinoma identification from the traditional expert-based evidence investigation to an automated AI-assisted paradigm.

CSGBBNet: An Explainable Deep Learning Framework for COVID-19 Detection

The COVID-19 virus has swept the world and brought great impact to various fields, gaining wide attention from all walks of life since the end of 2019. At present, although the global epidemic situation is leveling off and vaccine doses have been administered in a large amount, confirmed cases are still emerging around the world. To make up for the missed diagnosis caused by the uncertainty of nucleic acid polymerase chain reaction (PCR) test, utilizing lung CT examination as a combined detection method to improve the diagnostic rate becomes a necessity. Our research considered the time-consuming and labor-intensive characteristics of the traditional CT analyzing process, and developed an efficient deep learning framework named CSGBBNet to solve the binary classification task of COVID-19 images based on a COVID-Seg model for image preprocessing and a GBBNet for classification. The five runs with random seed on the test set showed our novel framework can rapidly analyze CT scan images and give out effective results for assisting COVID-19 detection, with the mean accuracy of 98.49 ± 1.23%, the sensitivity of 99.00 ± 2.00%, the specificity of 97.95 ± 2.51%, the precision of 98.10 ± 2.61%, and the F1 score of 98.51 ± 1.22%. Moreover, our model CSGBBNet performs better when compared with seven previous state-of-the-art methods. In this research, the aim is to link together biomedical research and artificial intelligence and provide some insights into the field of COVID-19 detection.

Development of an Automated Visibility Analysis Framework for Pavement Markings Based on the Deep Learning Approach

Pavement markings play a critical role in reducing crashes and improving safety on public roads. As road pavements age, maintenance work for safety purposes becomes critical. However, inspecting all pavement markings at the right time is very challenging due to the lack of available human resources. This study was conducted to develop an automated condition analysis framework for pavement markings using machine learning technology. The proposed framework consists of three modules: a data processing module, a pavement marking detection module, and a visibility analysis module. The framework was validated through a case study of pavement markings training data sets in the U.S. It was found that the detection model of the framework was very precise, which means most of the identified pavement markings were correctly classified. In addition, in the proposed framework, visibility was confirmed as an important factor of driver safety and maintenance, and visibility standards for pavement markings were defined.

An Empirical Radiometric Intercomparison Methodology Based on Global Simultaneous Nadir Overpasses Applied to Landsat 8 and Sentinel-2

The Simultaneous Nadir Overpass (SNO) method was developed by the NOAA/NESDIS to improve the consistency and quality of climate data acquired by different meteorological satellites. Taking advantage of the reduced impact induced by the Bidirectional Reflectance Distribution Function (BRDF), atmospheric effects, illumination and viewing geometries during an SNO, we created a sensor comparison methodology for all spectral targets. The method is illustrated by applying it to the assessment of data acquired by the Landsat 8 (L8), Sentinel-2A (S2A), and Sentinel-2B (S2B) optical sensors. Multiple SNOs were identified and selected without the need for orbit propagators. Then, by locating spatially homogeneous areas, it was possible to assess, for a wide range of Top-of-Atmosphere reflectance values, the relationship between the L8 bands and the corresponding ones of S2A and S2B. The results yield high coefficients of determination for S2 A/B with respect to L8. All are higher than 0.980 for S2A and 0.984 for S2B. If the S2 band 8 (wide near-infrared, NIR) is excluded then the lowest coefficients of determination become 0.997 and 0.999 from S2A and S2B, respectively. This methodology can be complementary to those based on Pseudo-Invariant Calibration Sites (PICS) due to its simplicity, highly correlated results and the wide range of compared reflectances and spectral targets.

Fast and simple tool for the quantification of biofilm-embedded cells sub-populations from fluorescent microscopic images

Fluorescent staining is a common tool for both quantitative and qualitative assessment of pro- and eukaryotic cells sub-population fractions by using microscopy and flow cytometry. However, direct cell counting by flow cytometry is often limited, for example when working with cells rigidly adhered either to each other or to external surfaces like bacterial biofilms or adherent cell lines and tissue samples. An alternative approach is provided by using fluorescent microscopy and confocal laser scanning microscopy (CLSM), which enables the evaluation of fractions of cells subpopulations in a given sample. For the quantitative assessment of cell fractions in microphotographs, we suggest a simple two-step algorithm that combines single cells selection and the statistical analysis. To facilitate the first step, we suggest a simple procedure that supports finding the balance between the detection threshold and the typical size of single cells based on objective cell size distribution analysis. Based on a series of experimental measurements performed on bacterial and eukaryotic cells under various conditions, we show explicitly that the suggested approach effectively accounts for the fractions of different cell sub-populations (like the live/dead staining in our samples) in all studied cases that are in good agreement with manual cell counting on microphotographs and flow cytometry data. This algorithm is implemented as a simple software tool that includes an intuitive and user-friendly graphical interface for the initial adjustment of algorithm parameters to the microphotographs analysis as well as for the sequential analysis of homogeneous series of similar microscopic images without further user intervention. The software tool entitled BioFilmAnalyzer is freely available online at https://bitbucket.org/rogex/biofilmanalyzer/downloads/.

A Novel Computerized Cell Count Algorithm for Biofilm Analysis

Biofilms are the preferred sessile and matrix-embedded life form of most microorganisms on surfaces. In the medical field, biofilms are a frequent cause of treatment failure because they protect the bacteria from antibiotics and immune cells. Antibiotics are selected according to the minimal inhibitory concentration (MIC) based on the planktonic form of bacteria. Determination of the minimal biofilm eradicating concentration (MBEC), which can be up to 1,000-fold greater than the MIC, is not currently conducted as routine diagnostic testing, primarily because of the methodical hurdles of available biofilm assessing protocols that are time- and cost-consuming. Comparative analysis of biofilms is also limited as most quantitative methods such as crystal violet staining are indirect and highly imprecise. In this paper, we present a novel algorithm for assessing biofilm resistance to antibiotics that overcomes several of the limitations of alternative methods. This algorithm aims for a computer-based analysis of confocal microscope 3D images of biofilms after live/dead stains providing various biofilm parameters such as numbers of viable and dead cells and their vertical distributions within the biofilm, or biofilm thickness. The performance of this algorithm was evaluated using computer-simulated 2D and 3D images of coccal and rodent cells varying different parameters such as cell density, shading or cell size. Finally, genuine biofilms that were untreated or treated with nitroxoline or colistin were analyzed and the results were compared with quantitative microbiological standard methods. This novel algorithm allows a direct, fast and reproducible analysis of biofilms after live/dead staining. It performed well in biofilms of moderate cell densities in a 2D set-up however the 3D analysis remains still imperfect and difficult to evaluate. Nevertheless, this is a first try to develop an easy but conclusive tool that eventually might be implemented into routine diagnostics to determine the MBEC and to improve outcomes of patients with biofilm-associated infections.

Web tools for large-scale 3D biological images and atlases

Background

Large-scale volumetric biomedical image data of three or more dimensions are a significant challenge for distributed browsing and visualisation. Many images now exceed 10GB which for most users is too large to handle in terms of computer RAM and network bandwidth. This is aggravated when users need to access tens or hundreds of such images from an archive. Here we solve the problem for 2D section views through archive data delivering compressed tiled images enabling users to browse through very-large volume data in the context of a standard web-browser. The system provides an interactive visualisation for grey-level and colour 3D images including multiple image layers and spatial-data overlay.

Results

The standard Internet Imaging Protocol (IIP) has been extended to enable arbitrary 2D sectioning of 3D data as well a multi-layered images and indexed overlays. The extended protocol is termed IIP3D and we have implemented a matching server to deliver the protocol and a series of Ajax/Javascript client codes that will run in an Internet browser. We have tested the server software on a low-cost linux-based server for image volumes up to 135GB and 64 simultaneous users. The section views are delivered with response times independent of scale and orientation. The exemplar client provided multi-layer image views with user-controlled colour-filtering and overlays.

Conclusions

Interactive browsing of arbitrary sections through large biomedical-image volumes is made possible by use of an extended internet protocol and efficient server-based image tiling. The tools open the possibility of enabling fast access to large image archives without the requirement of whole image download and client computers with very large memory configurations. The system was demonstrated using a range of medical and biomedical image data extending up to 135GB for a single image volume.

Efficient 2-D grayscale morphological transformations with arbitrary flat structuring elements

An efficient algorithm is presented for the computation of grayscale morphological operations with arbitrary 2-D flat structuring elements (S.E.). The required computing time is independent of the image content and of the number of gray levels used. It always outperforms the only existing comparable method, which was proposed in the work by Van Droogenbroeck and Talbot, by a factor between 3.5 and 35.1, depending on the image type and shape of S.E. So far, filtering using multiple S.E.s is always done by performing the operator for each size and shape of the S.E. separately. With our method, filtering with multiple S.E.s can be performed by a single operator for a slightly reduced computational cost per size or shape, which makes this method more suitable for use in granulometries, dilation-erosion scale spaces, and template matching using the hit-or-miss transform. The discussion focuses on erosions and dilations, from which other transformations can be derived.

A computer-aided method to expedite the evaluation of prognosis for childhood acute lymphoblastic leukemia

This study presented a fully-automated computer-aided method (scheme) to detect metaphase chromosomes depicted on microscopic digital images, count the total number of chromosomes in each metaphase cell, compute the DNA index, and correlate the results to the prognosis of childhood acute lymphoblastic leukemia (ALL). The computer scheme first uses image filtering, threshold, and labeling algorithms to segment and count the number of the suspicious "chromosome," and then computes a feature vector for each "detected chromosome." Based on these features, a knowledge-based classifier is used to eliminate those "non-chromosome" objects (i.e., inter-phase cells, stain debris, and other kinds of background noises). Due to the possible overlap of the chromosomes, a classification criterion was used to identify the overlapped chromosomes and adjust the initially counted number of the total chromosomes in each image. In this preliminary study with 60 testing images (depicting metaphase chromosome cells) acquired from three pediatric patients, the computer scheme generated results matched with the diagnostic results provided by the clinical cytogeneticists. The results demonstrated the feasibility or potential of using a computerized method to replace the tedious and the reader-dependent diagnostic methods commonly used in genetic laboratories to date.

Application of automation to the detection of radiation damage using FISH technology

A whole chromosome painting approach was employed to highlight the damaging effects of low-to-moderate doses of ionizing radiation. A detailed tally of damage involving the painted chromosomes 1 and 2 was compiled from visual analysis and compared with the results of an automatic image processing approach, where the possible outcomes were 'normal', 'abnormal', or 'rejected'. The performance of the automatic approach was tested using a set of 9000 bicolour metaphase images harvested from whole-blood cell culture following irradiation levels of 0.0, 0.5, 1.0 and 2.0 Gy. Every metaphase image in the set was analysed visually. The automatic analysis model was based on two simple image criteria to distinguish normal from abnormal; either an increase in the number of painted objects or a large asymmetry in the area distribution of the expected number of painted objects. A result was obtained without a full karyotype analysis. In practice, automatic analysis produced a set of images for review that were enriched by a factor of 3-4 in true abnormal images. Fast visual review of these images (approximately 200/h) selected the true abnormals. A comparison of the automatic analysis with the visual analysis showed that automated analysis correctly identified 60% of normal cells, 59% of abnormal cells and 73% of rejected cells.

Fully automatic chromosome segmentation

This paper is concerned with automatic segmentation of high resolution digitized metaphases. This includes automatic detection and rejection of interphase nuclei, stain debris, and other "noise"; automatic detection and segmentation of touching and overlapping chromosome clusters; and automatic rejection of cells which are evaluated as being incomplete, or incorrectly segmented, or where the cell is otherwise unsuitable for further analysis. In this paper, a rule-based approach is described which treats the cell as a whole rather than as a series of individual chromosomes or clusters. The rules adapt classification and segmentation parameters for each cell. Initially, different sets of parameters are chosen according to the staining method of the cells, and the goal of the segmentation. A chromosome number predictor is used to guide the adaptation of the parameters and to estimate the performance. The adaptation is iterative, and the self-adjustment will stop when either a satisfactory result is achieved or if the cell is rejected. The method was implemented on both a Sun workstation and a Cytoscan, a commercial machine for chromosome analysis. Seven hundred and thirteen cells from real data have been tested. A success rate of 90-95% has been achieved. The procedure has been implemented in an automatic aberration scoring system for routine use.