Resilient back-propagation machine learning-based classification on fundus images for retinal microaneurysm detection

BACKGROUND

The timely diagnosis of medical conditions, particularly diabetic retinopathy, relies on the identification of retinal microaneurysms. However, the commonly used retinography method poses a challenge due to the diminutive dimensions and limited differentiation of microaneurysms in images.

PROBLEM STATEMENT

Automated identification of microaneurysms becomes crucial, necessitating the use of comprehensive ad-hoc processing techniques. Although fluorescein angiography enhances detectability, its invasiveness limits its suitability for routine preventative screening.

OBJECTIVE

This study proposes a novel approach for detecting retinal microaneurysms using a fundus scan, leveraging circular reference-based shape features (CR-SF) and radial gradient-based texture features (RG-TF).

METHODOLOGY

The proposed technique involves extracting CR-SF and RG-TF for each candidate microaneurysm, employing a robust back-propagation machine learning method for training. During testing, extracted features from test images are compared with training features to categorize microaneurysm presence.

RESULTS

The experimental assessment utilized four datasets (MESSIDOR, Diaretdb1, e-ophtha-MA, and ROC), employing various measures. The proposed approach demonstrated high accuracy (98.01%), sensitivity (98.74%), specificity (97.12%), and area under the curve (91.72%).

CONCLUSION

The presented approach showcases a successful method for detecting retinal microaneurysms using a fundus scan, providing promising accuracy and sensitivity. This non-invasive technique holds potential for effective screening in diabetic retinopathy and other related medical conditions.

Optimized detection and segmentation of nuclei in gastric cancer images using stain normalization and blurred artifact removal

Histological analysis with microscopy is the gold standard to diagnose and stage cancer, where slides or whole slide images are analyzed for cell morphological and spatial features by pathologists. The nuclei of cancerous cells are characterized by nonuniform chromatin distribution, irregular shapes, and varying size. As nucleus area and shape alone carry prognostic value, detection and segmentation of nuclei are among the most important steps in disease grading. However, evaluation of nuclei is a laborious, time-consuming, and subjective process with large variation among pathologists. Recent advances in digital pathology have allowed significant applications in nuclei detection, segmentation, and classification, but automated image analysis is greatly affected by staining factors, scanner variability, and imaging artifacts, requiring robust image preprocessing, normalization, and segmentation methods for clinically satisfactory results. In this paper, we aimed to evaluate and compare the digital image analysis techniques used in clinical pathology and research in the setting of gastric cancer. A literature review was conducted to evaluate potential methods of improving nuclei detection. Digitized images of 35 patients from a retrospective cohort of gastric adenocarcinoma at Oulu University Hospital in 1987-2016 were annotated for nuclei (n = 9085) by expert pathologists and 14 images of different cancer types from public TCGA dataset with annotated nuclei (n = 7000) were used as a comparison to evaluate applicability in other cancer types. The detection and segmentation accuracy with the selected color normalization and stain separation techniques were compared between the methods. The extracted information can be supplemented by patient's medical data and fed to the existing statistical clinical tools or subjected to subsequent AI-assisted classification and prediction models. The performance of each method is evaluated by several metrics against the annotations done by expert pathologists. The F1-measure of 0.854 ± 0.068 is achieved with color normalization for the gastric cancer dataset, and 0.907 ± 0.044 with color deconvolution for the public dataset, showing comparable results to the earlier state-of-the-art works. The developed techniques serve as a basis for further research on application and interpretability of AI-assisted tools for gastric cancer diagnosis.

Electrocardiography signal compression using non-decimated stationary wavelet transform-based technique

BACKGROUND


In telecardiology, the bio-signal acquisition processing and communication for clinical purposes occupies larger storage and significant bandwidth over a communication channel. Electrocardiograph (ECG) compression with effective reproductivity is highly desired. In the present work, a compression technique for ECG signals with less distortion by using a non-decimated stationary wavelet with a run-length encoding scheme has been proposed.
Method:
In the present work non-decimated stationary wavelet transform (NSWT) method has been developed to compress the ECG signals. The signal is subdivided into N levels with different thresholding values. The wavelet coefficients having values larger than the threshold are evaluated and the remaining are suppressed. In the presented technique, the biorthogonal wavelet is employed as it improves the compression ratio as well percentage root means square ratio when compared to the existing method and exhibits better results. Then the coefficients are pre-processed by using the Savitzky-Golay filter which discards the corrupted signals. The wavelet coefficients are quantized using dead-zone quantization which removes the value close to zeros. To encode these values run length encoding scheme is applied and compressed ECG signals are obtained.
Results:
The presented methodology has been evaluated on the MIT-BIH arrhythmias database which contains 4800 ECG fragments from forty-eight clinical records. An average compression ratio = 33.12, PRD =1.99, NPRD =2.53, and QS = 16.57 is obtained in the proposed technique.
Conclusion:
The proposed technique exhibits a high compression ratio and reduces distortion compared to the existing method.&#xD.

Automatic detection of intracranial aneurysms in 3D-DSA based on a Bayesian optimized filter

Background

Intracranial aneurysm is a common type of cerebrovascular disease with a risk of devastating subarachnoid hemorrhage if it is ruptured. Accurate computer-aided detection of aneurysms can help doctors improve the diagnostic accuracy, and it is very helpful in reducing the risk of subarachnoid hemorrhage. Aneurysms are detected in 2D or 3D images from different modalities. 3D images can provide more vascular information than 2D images, and it is more difficult to detect. The detection performance of 2D images is related to the angle of view; it may take several angles to determine the aneurysm. As the gold standard for the diagnosis of vascular diseases, the detection on digital subtraction angiography (DSA) has more clinical value than other modalities. In this study, we proposed an adaptive multiscale filter to detect intracranial aneurysms on 3D-DSA.

Methods

Adaptive aneurysm detection consists of three parts. The first part is a filter based on Hessian matrix eigenvalues, whose parameters are automatically obtained by Bayesian optimization. The second part is aneurysm extraction based on region growth and adaptive thresholding. The third part is the iterative detection strategy for multiple aneurysms.

Results

The proposed method was quantitatively evaluated on data sets of 145 patients. The results showed a detection precision of 94.6%, and a sensitivity of 96.4% with a false-positive rate of 6.2%. Among aneurysms smaller than 5 mm, 93.9% were found. Compared with aneurysm detection on 2D-DSA, automatic detection on 3D-DSA can effectively reduce the misdiagnosis rate and obtain more accurate detection results. Compared with other modalities detection, we also get similar or better detection performance.

Conclusions

The experimental results show that the proposed method is stable and reliable for aneurysm detection, which provides an option for doctors to accurately diagnose aneurysms.

Meta-analysis of peptides to detect protein significance

Shotgun assays are widely used in biotechnologies to characterize large molecules, which are hard to be measured as a whole directly. For instance, in Liquid Chromatography - Mass Spectrometry (LC-MS) shotgun experiments, proteins in biological samples are digested into peptides, and then peptides are separated and measured. However, in proteomics study, investigators are usually interested in the performance of the whole proteins instead of those peptide fragments. In light of meta-analysis, we propose an adaptive thresholding method to select informative peptides, and combine peptide-level models to protein-level analysis. The meta-analysis procedure and modeling rationale can be adapted to data analysis of other types of shotgun assays.

A novel framework for MR image segmentation and quantification by using MedGA

BACKGROUND AND OBJECTIVES

Image segmentation represents one of the most challenging issues in medical image analysis to distinguish among different adjacent tissues in a body part. In this context, appropriate image pre-processing tools can improve the result accuracy achieved by computer-assisted segmentation methods. Taking into consideration images with a bimodal intensity distribution, image binarization can be used to classify the input pictorial data into two classes, given a threshold intensity value. Unfortunately, adaptive thresholding techniques for two-class segmentation work properly only for images characterized by bimodal histograms. We aim at overcoming these limitations and automatically determining a suitable optimal threshold for bimodal Magnetic Resonance (MR) images, by designing an intelligent image analysis framework tailored to effectively assist the physicians during their decision-making tasks.

METHODS

In this work, we present a novel evolutionary framework for image enhancement, automatic global thresholding, and segmentation, which is here applied to different clinical scenarios involving bimodal MR image analysis: (i) uterine fibroid segmentation in MR guided Focused Ultrasound Surgery, and (ii) brain metastatic cancer segmentation in neuro-radiosurgery therapy. Our framework exploits MedGA as a pre-processing stage. MedGA is an image enhancement method based on Genetic Algorithms that improves the threshold selection, obtained by the efficient Iterative Optimal Threshold Selection algorithm, between the underlying sub-distributions in a nearly bimodal histogram.

RESULTS

The results achieved by the proposed evolutionary framework were quantitatively evaluated, showing that the use of MedGA as a pre-processing stage outperforms the conventional image enhancement methods (i.e., histogram equalization, bi-histogram equalization, Gamma transformation, and sigmoid transformation), in terms of both MR image enhancement and segmentation evaluation metrics.

CONCLUSIONS

Thanks to this framework, MR image segmentation accuracy is considerably increased, allowing for measurement repeatability in clinical workflows. The proposed computational solution could be well-suited for other clinical contexts requiring MR image analysis and segmentation, aiming at providing useful insights for differential diagnosis and prognosis.

Multi-tissue and multi-scale approach for nuclei segmentation in H&E stained images

Background

Accurate nuclei detection and segmentation in histological images is essential for many clinical purposes. While manual annotations are time-consuming and operator-dependent, full automated segmentation remains a challenging task due to the high variability of cells intensity, size and morphology. Most of the proposed algorithms for the automated segmentation of nuclei were designed for specific organ or tissues.

Results

The aim of this study was to develop and validate a fully multiscale method, named MANA (Multiscale Adaptive Nuclei Analysis), for nuclei segmentation in different tissues and magnifications. MANA was tested on a dataset of H&E stained tissue images with more than 59,000 annotated nuclei, taken from six organs (colon, liver, bone, prostate, adrenal gland and thyroid) and three magnifications (10×, 20×, 40×). Automatic results were compared with manual segmentations and three open-source software designed for nuclei detection. For each organ, MANA obtained always an F1-score higher than 0.91, with an average F1 of 0.9305 ± 0.0161. The average computational time was about 20 s independently of the number of nuclei to be detected (anyway, higher than 1000), indicating the efficiency of the proposed technique.

Conclusion

To the best of our knowledge, MANA is the first fully automated multi-scale and multi-tissue algorithm for nuclei detection. Overall, the robustness and versatility of MANA allowed to achieve, on different organs and magnifications, performances in line or better than those of state-of-art algorithms optimized for single tissues.

Semi-automatic 3D morphological reconstruction of neurons with densely branching morphology: Application to retinal AII amacrine cells imaged with multi-photon excitation microscopy

BACKGROUND

Accurate reconstruction of the morphology of single neurons is important for morphometric studies and for developing compartmental models. However, manual morphological reconstruction can be extremely time-consuming and error-prone and algorithms for automatic reconstruction can be challenged when applied to neurons with a high density of extensively branching processes.

NEW METHOD

We present a procedure for semi-automatic reconstruction specifically adapted for densely branching neurons such as the AII amacrine cell found in mammalian retinas. We used whole-cell recording to fill AII amacrine cells in rat retinal slices with fluorescent dyes and acquired digital image stacks with multi-photon excitation microscopy. Our reconstruction algorithm combines elements of existing procedures, with segmentation based on adaptive thresholding and reconstruction based on a minimal spanning tree. We improved this workflow with an algorithm that reconnects neuron segments that are disconnected after adaptive thresholding, using paths extracted from the image stacks with the Fast Marching method.

RESULTS

By reducing the likelihood that disconnected segments were incorrectly connected to neighboring segments, our procedure generated excellent morphological reconstructions of AII amacrine cells.

COMPARISON WITH EXISTING METHODS

Reconstructing an AII amacrine cell required about 2h computing time, compared to 2-4days for manual reconstruction. To evaluate the performance of our method relative to manual reconstruction, we performed detailed analysis using a measure of tree structure similarity (DIADEM score), the degree of projection area overlap (Dice coefficient), and branch statistics.

CONCLUSIONS

We expect our procedure to be generally useful for morphological reconstruction of neurons filled with fluorescent dyes.

A dual stage adaptive thresholding (DuSAT) for automatic mass detection in mammograms

BACKGROUND AND OBJECTIVE

Early detection and diagnosis of breast cancer through mammography screening reduces breast cancer mortality by around 20%. However it is often a complex process to differentiate abnormalities due to the ill-defined margins and subtle appearances.

METHOD

This paper investigates a new computer aided approach to detect the abnormalities in the digital mammograms using a Dual Stage Adaptive Thresholding (DuSAT). The suspicious mass region is identified using global histogram and local window thresholding method. The global thresholding is done based on the Histogram Peak Analysis (HPA) of the entire image and the threshold is obtained by maximizing the proposed threshold selection criteria. The local thresholding is carried out for each pixel in a defined neighborhood window that provides precise segmentation results.

RESULTS

The algorithm is verified with 300 images in the DDSM database and 170 images in the mini-MIAS database. Experimental results show that the proposed algorithm achieves an average sensitivity of 92.5% with 1.06 FP/image for DDSM database and an average sensitivity of 93.5% with 0.62 FP/image for mini-MIAS database.

CONCLUSION

The achieved results depict that the proposed approach provides better results compared to other state-of-art methods for mass detection that helps the radiologists in diagnosis of breast cancer at early stage.

QRS detection using adaptive filters: A comparative study

Electrocardiogram (ECG) is one of the most important physiological signals of human body, which contains important clinical information about the heart. Monitoring of ECG signal is done through QRS detection. In this paper, an improved QRS detection algorithm, based on adaptive filtering principle, has been designed. Enumeration of the effectiveness of various LMS variants used in adaptive filtering based QRS detection algorithm has been done through fidelity parameters like sensitivity and positive predictivity. Whole family of LMS algorithm has been implemented for comparison. Sign-sign LMS, sign error LMS, basic LMS and normalized LMS are re-implemented, while variable leaky LMS, variable step-size LMS, leaky LMS, recursive least squares (RLS), and fractional LMS are novel combination presented in this paper. After analysis of the obtained results, performance of leaky-LMS algorithm is found to be the best with sensitivity, positive predictivity, and processing time of 99.68%, 99.84%, and 0.45s respectively. Reported results are tested and evaluated over MIT/BIH arrhythmia database. Presented study also concludes that the performance of most of the variants gets affected due to low SNR but the Leaky LMS performs better even under heavy noise conditions.

Minimax Rate-optimal Estimation of High-dimensional Covariance Matrices with Incomplete Data

Missing data occur frequently in a wide range of applications. In this paper, we consider estimation of high-dimensional covariance matrices in the presence of missing observations under a general missing completely at random model in the sense that the missingness is not dependent on the values of the data. Based on incomplete data, estimators for bandable and sparse covariance matrices are proposed and their theoretical and numerical properties are investigated. Minimax rates of convergence are established under the spectral norm loss and the proposed estimators are shown to be rate-optimal under mild regularity conditions. Simulation studies demonstrate that the estimators perform well numerically. The methods are also illustrated through an application to data from four ovarian cancer studies. The key technical tools developed in this paper are of independent interest and potentially useful for a range of related problems in high-dimensional statistical inference with missing data.

Mass Detection in Mammographic Images Using Wavelet Processing and Adaptive Threshold Technique

Detection of mass in mammogram for early diagnosis of breast cancer is a significant assignment in the reduction of the mortality rate. However, in some cases, screening of mass is difficult task for radiologist, due to variation in contrast, fuzzy edges and noisy mammograms. Masses and micro-calcifications are the distinctive signs for diagnosis of breast cancer. This paper presents, a method for mass enhancement using piecewise linear operator in combination with wavelet processing from mammographic images. The method includes, artifact suppression and pectoral muscle removal based on morphological operations. Finally, mass segmentation for detection using adaptive threshold technique is carried out to separate the mass from background. The proposed method has been tested on 130 (45 + 85) images with 90.9 and 91 % True Positive Fraction (TPF) at 2.35 and 2.1 average False Positive Per Image(FP/I) from two different databases, namely Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM). The obtained results show that, the proposed technique gives improved diagnosis in the early breast cancer detection.

Long-bone fracture detection in digital X-ray images based on digital-geometric techniques

Automated fracture detection is an essential part of a computer-aided tele-medicine system. In this paper, we have proposed a unified technique for the detection and evaluation of orthopaedic fractures in long-bone digital X-ray image. We have also developed a software tool that can be conveniently used by paramedics or specialist doctors. The proposed tool first segments the bone region of an input digital X-ray image from its surrounding flesh region and then generates the bone-contour using an adaptive thresholding approach. Next, it performs unsupervised correction of bone-contour discontinuities that might have been generated because of segmentation errors, and finally detects the presence of fracture in the bone. Moreover, the method can also localize the line-of-break for easy visualization of the fracture, identify its orientation, and assess the extent of damage in the bone. Several concepts from digital geometry such as relaxed straightness and concavity index are utilized to correct contour imperfections, and to detect fracture locations and type. Experiments on a database of several long-bone digital X-ray images show satisfactory results.

Inference for High-dimensional Differential Correlation Matrices

Motivated by differential co-expression analysis in genomics, we consider in this paper estimation and testing of high-dimensional differential correlation matrices. An adaptive thresholding procedure is introduced and theoretical guarantees are given. Minimax rate of convergence is established and the proposed estimator is shown to be adaptively rate-optimal over collections of paired correlation matrices with approximately sparse differences. Simulation results show that the procedure significantly outperforms two other natural methods that are based on separate estimation of the individual correlation matrices. The procedure is also illustrated through an analysis of a breast cancer dataset, which provides evidence at the gene co-expression level that several genes, of which a subset has been previously verified, are associated with the breast cancer. Hypothesis testing on the differential correlation matrices is also considered. A test, which is particularly well suited for testing against sparse alternatives, is introduced. In addition, other related problems, including estimation of a single sparse correlation matrix, estimation of the differential covariance matrices, and estimation of the differential cross-correlation matrices, are also discussed.

Improvement of retinal blood vessel detection using morphological component analysis

Detection and quantitative measurement of variations in the retinal blood vessels can help diagnose several diseases including diabetic retinopathy. Intrinsic characteristics of abnormal retinal images make blood vessel detection difficult. The major problem with traditional vessel segmentation algorithms is producing false positive vessels in the presence of diabetic retinopathy lesions. To overcome this problem, a novel scheme for extracting retinal blood vessels based on morphological component analysis (MCA) algorithm is presented in this paper. MCA was developed based on sparse representation of signals. This algorithm assumes that each signal is a linear combination of several morphologically distinct components. In the proposed method, the MCA algorithm with appropriate transforms is adopted to separate vessels and lesions from each other. Afterwards, the Morlet Wavelet Transform is applied to enhance the retinal vessels. The final vessel map is obtained by adaptive thresholding. The performance of the proposed method is measured on the publicly available DRIVE and STARE datasets and compared with several state-of-the-art methods. An accuracy of 0.9523 and 0.9590 has been respectively achieved on the DRIVE and STARE datasets, which are not only greater than most methods, but are also superior to the second human observer's performance. The results show that the proposed method can achieve improved detection in abnormal retinal images and decrease false positive vessels in pathological regions compared to other methods. Also, the robustness of the method in the presence of noise is shown via experimental result.

R peak detection in electrocardiogram signal based on an optimal combination of wavelet transform, hilbert transform, and adaptive thresholding

Electrocardiogram (ECG) is one of the most common biological signals which play a significant role in the diagnosis of heart diseases. One of the most important parts of ECG signal processing is interpretation of QRS complex and obtaining its characteristics. R wave is one of the most important sections of this complex, which has an essential role in diagnosis of heart rhythm irregularities and also in determining heart rate variability (HRV). This paper employs Hilbert and wavelet transforms as well as adaptive thresholding method to investigate an optimal combination of these signal processing techniques for the detection of R peak. In the experimental sections of this paper, the proposed algorithms are evaluated using both ECG signals from MIT-BIH database and synthetic data simulated in MATLAB environment with different arrhythmias, artifacts, and noise levels. Finally, by using wavelet and Hilbert transforms as well as by employing adaptive thresholding technique, an optimal combinational method for R peak detection namely WHAT is obtained that outperforms other techniques quantitatively and qualitatively.