Computer-aided Lesion Detection Research Articles

Active Case-Finding: An Effective Solution for Tuberculosis Detection in Vulnerable Groups - The Romanian Experience.

Tuberculosis (TB) remains a global health challenge, requiring enhanced active case finding (ACF) through screening strategies. This study assesses the effectiveness of such an approach in locating TB cases among vulnerable groups, such as homeless persons, injecting drug users, those detained in prison, and people living in rural areas. The study focuses on socio-economic characteristics and TB detection rates across Romanian counties using modern techniques including computer-aided detection of lesions on chest X-ray and GeneXpert tests. The results highlight the disproportionate burden of TB in vulnerable groups, by revealing significant differences in TB detection rates between regions. Notably, the TB detection rates among these vulnerable groups (250.85 per 100,000 population) are five times higher than the national incidence rate (46.1). These findings underscore the imperative integration of ACF into National TB Program to provide customized and efficient solutions for diverse vulnerable groups, thereby informing crucial public health initiatives and interventions.

Computer-aided Detection of Lesions from Coronary Angiograms Based on Contrast Learning Technique.

Coronary artery disease is one of the prevalent cardiovascular diseases in the world. Clinically, coronary artery angiography (CAG) is the most efficient diagnostic tool for detecting the stenosis caused by the presence of coronary lesions. Here, we proposed a simple but efficient methodology for predicting the coronary arterial block. The technique of classifying the angiograms collected from 369 patients is implemented using the contrast learning approach. ResNet 152 V2 is used as the deep network. Region of interest (ROI) is found for the diseased arteries for deciding the type of treatment procedure. Four different losses were implemented in this two-level classification technique. This framework achieved an accuracy of 0.81 recall of 0.76, precision of 0.86, specificity of 0.87, and F-score of 0.80. A comparative study with the state-of-the-art is carried out to establish the advantage of the proposed method. This computer-aided approach could be implemented by clinicians quite easily. Clinical relevance-An easy, simple, and fast technique of detecting and deciding treatment of coronary artery stenosis was studied using contrast learning and ROI. A computerised model was designed which can draw conclusion from CAGs even in the absence of clinical annotations.

Abnormality detection in retinal image by individualized background learning

Computer-aided lesion detection (CAD) techniques, which provide potential for automatic early screening of retinal pathologies, are widely studied in retinal image analysis. While many CAD approaches based on lesion samples or lesion features can well detect pre-defined lesion types, it remains challenging to detect various abnormal regions (namely abnormalities) from retinal images. In this paper, we try to identify diverse abnormalities from a retinal test image by finely learning its individualized retinal background (IRB) on which retinal lesions superimpose.3150 normal retinal images are collected as the priors for IRB learning. A preprocessing step is applied to all retinal images for spatial, scale and color normalization. Retinal blood vessels, which have individual variations in different images, are particularly suppressed from all images. A multi-scale sparse coding based learning (MSSCL) algorithm and a repeated learning strategy are proposed for finely learning the IRB. By the MSSCL algorithm, a background space is constructed by sparsely encoding the test image in a multi-scale manner using the dictionary learned from normal retinal images, which will contain more complete IRB information than any single-scale coding result. From the background space, the IRB can be well learned by low-rank approximation and thus different salient lesions can be separated and detected. The MSSCL algorithm will be iteratively repeated on the modified test image in which the detected salient lesions are suppressed, so as to further improve the accuracy of the IRB and suppress lesions in the IRB. Consequently, a high-accuracy IRB can be learned and thus both salient lesions and weak lesions that have low contrasts with the background can be clearly separated. The effectiveness and contributions of the proposed method are validated by experiments over different clinical data-sets and comparisons with the state-of-the-art CAD methods.

Performance evaluation of breast lesion detection systems with expert delineations: a comparative investigation on mammographic images

Performance of computerized diagnostic systems yearning to be approved by medical regulatory bodies must meet the expectations of human experts. Highly accurate lesion segmentation techniques have thus turned out to be an essential part for clinical acceptability of mammography based computer-aided diagnosis systems. The objective of this study is to evaluate the performance of six popular breast tumor detection techniques with manual delineations provided by two experienced radiologists on the mammographic images. In our study, 20 mammographic images from the mini-MIAS database are utilized. For the analysis, input mammographic images are first manually cropped to generate the region of interest (ROI). The ROI images are then pre-processed and segmentation is performed using different techniques, namely: expected maximization, K-means, Fuzzy c-Means (FCM), multilevel thresholding, region growing, and particle swarm optimization. The results were compared against the manual tracings. Among the other five segmentation techniques, FCM achieves the highest Jaccard Index (0.73 ± 0.06) and Dice Similarity Coefficient (0.82 ± 0.08) values. Statistical analysis (t-test, Mann Whitney U test, Wilcoxon test, Chi-Square test, and Kolmogorov–Smirnov test) and graphical analysis (Bland Altman and Regression plots) further prove the stability and reliability of the segmentation methods. Segmentation using FCM demonstrates the most accurate results and can be employed for the detection of breast cancer in the mammographic images. Further, it is concluded that computer-aided lesion detection systems can be used to assist Radiologists in routine clinical practice for the detection of breast tumors in mammographic images.

Heuristic approach for computer-aided lesion detection in mammograms

Digital mammography is a common screening method for early detection of breast cancer. Its efficiency varies from 60 to 90 %, depending on various factors such as breast density, quality of the mammogram as well as experience and knowledge of the radiologist (Andolina and Lille in Mammographic imaging: a practical guide, Lippincott Williams & Wilkins, Philadelphia, 2010). One of the most effective ways to increase the cancer detection rate is double reading (Fernandez-Lozano in Soft Comput 19(9):2469---2480, 2015). Regarding the fact that only the early-stage patients have high chances of survival, a computer-aided detection (CAD) system for mammography that provides a second, independent diagnosis should be considered a valuable and lifesaving tool. In this paper we present a new heuristic approach focused on analyzing characteristics of the mammogram that may indicate the presence of breast cancer. Described soft computing detection algorithm based on local features allows us to extract microcalcifications and possible tumor areas from the image. Because calcifications are associated with certain types of lesions, we believe that this idea would result in improving existing medical information systems. Future inclusion of fuzzy classifiers in the algorithm may also provide additional diagnostic value. Conducted research confirms that proposed procedure correctly identifies the regions of interest and could be used as a base of a CAD system in a double-reading procedures.

Progress in Fully Automated Abdominal CT Interpretation.

Automated analysis of abdominal CT has advanced markedly over just the last few years. Fully automated assessment of organs, lymph nodes, adipose tissue, muscle, bowel, spine, and tumors are some examples where tremendous progress has been made. Computer-aided detection of lesions has also improved dramatically. This article reviews the progress and provides insights into what is in store in the near future for automated analysis for abdominal CT, ultimately leading to fully automated interpretation.

Detection of Brain Tumor for MRI using Hybrid Method Wavelet and Clustering Algorithm

Automatic segmentation of brain tumor using computer analysis aided diagnosis in clinical practice but it is still a challenging task, especially when there are lesions needing to be outlined. In the applications of image-based diagnosis and computer-aided lesion detection, image segmentation is an important procedure .Features extracted from image analysis in companion with image segmentation algorithms are used to provide region-based information for clinical evaluation procedures. Brain tumor diagnosis is easy by using these medical equipments. The physician needs the correct measurement of the tumor area for the further treatment, this need to extract the abnormal part from the 2D MRI scan accurately and measure the region of interest. The HumanComputer interaction is helpful for this procedure. In this search the wavelet transformation is used as well as the Kmean algorithm is used. the wavelet transformation is not sufficient to produce a good result for the brain tumor detection. so the K-mean clustering method with different classes gives best result.

Segmentation of brain tumour using Enhanced Thresholding Algorithm and Calculatethe area of the tumour

Automatic segmentation of brain tumor using computer analysis aided diagnosis in clinical practice but it is still a challenging task, especially when there are lesions needing to be outlined. In the applications of image-based diagnosis and computer-aided lesion detection, image segmentation is an important procedure. Features extracted from image analysis in companion with image segmentation algorithms are used to provide region-based information for clinical evaluation procedures. Brain tumor diagnosis is easy by using these medical equipments. The physician needs the correct measurement of the tumor area for the further treatment, this need to extract the abnormal part from the 2D MRI scan accurately and measure the region of interest. The Human-Computer interaction is helpful for this procedure. In this search the Enhanced Thresholding Algorithm is used to Area calculation of tumor.

Automated chest wall line detection for whole‐breast segmentation in sagittal breast MR images

Breast magnetic resonance imaging (MRI) plays an important role in the clinical management of breast cancer. Computerized analysis is increasingly used to quantify breast MRI features in applications such as computer-aided lesion detection and fibroglandular tissue estimation for breast cancer risk assessment. Automated segmentation of the whole-breast as an organ from the other parts imaged is an important step in aiding lesion localization and fibroglandular tissue quantification. For this task, identifying the chest wall line (CWL) is most challenging due to image contrast variations, intensity discontinuity, and bias field. In this work, the authors develop and validate a fully automated image processing algorithm for accurate delineation of the CWL in sagittal breast MRI. The CWL detection is based on an integrated scheme of edge extraction and CWL candidate evaluation. The edge extraction consists of applying edge-enhancing filters and an edge linking algorithm. Increased accuracy is achieved by the synergistic use of multiple image inputs for edge extraction, where multiple CWL candidates are evaluated by the dynamic time warping algorithm coupled with the construction of a CWL reference. Their method is quantitatively validated by a dataset of 60 3D bilateral sagittal breast MRI scans (in total 3360 2D MR slices) that span the full American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) breast density range. Agreement with manual segmentation obtained by an experienced breast imaging radiologist is assessed by both volumetric and boundary-based metrics, including four quantitative measures. In terms of breast volume agreement with manual segmentation, the overlay percentage expressed by the Dice's similarity coefficient is 95.0% and the difference percentage is 10.1%. More specifically, for the segmentation accuracy of the CWL boundary, the CWL overlay percentage is 92.7% and averaged deviation distance is 2.3 mm. Their method requires ≈ 4.5 min for segmenting each 3D breast MRI scan (56 slices) in comparison to ≈ 35 min required for manual segmentation. Further analysis indicates that the segmentation performance of their method is relatively stable across the different BI-RADS density categories and breast volume, and also robust with respect to a varying range of the major parameters of the algorithm. Their fully automated method achieves high segmentation accuracy in a time-efficient manner. It could support large scale quantitative breast MRI analysis and holds the potential to become integrated into the clinical workflow for breast cancer clinical applications in the future.

Evaluation of computer-aided detection of lesions in mammograms obtained with a digital phase-contrast mammography system

A computer-aided detection (CAD) system was evaluated for its ability to detect microcalcifications and masses on images obtained with a digital phase-contrast mammography (PCM) system, a system characterised by the sharp images provided by phase contrast and by the high resolution of 25-μm-pixel mammograms. Fifty abnormal and 50 normal mammograms were collected from about 3,500 mammograms and printed on film for reading on a light box. Seven qualified radiologists participated in an observer study based on receiver operating characteristic (ROC) analysis. The average of the areas under ROC curve (AUC) values for the ROC analysis with and without CAD were 0.927 and 0.897 respectively (P = 0.015). The AUC values improved from 0.840 to 0.888 for microcalcifications (P = 0.034) and from 0.947 to 0.962 for masses (P = 0.025) respectively. The application of CAD to the PCM system is a promising approach for the detection of breast cancer in its early stages.

Computer-aided lesion detection for brain pet images

We proposed a new method for the automatic detection of lesions in brain PET images based on the asymmetry across segments of the segmented PET data. Per-pixel asymmetry feature detection is experimentally compared with our per-segment approach. The proposed per-segment method is shown to produce fewer false positives in the brain PET data examples presented. Also, the algorithm is shown to provide accurate demarcation of the tumour in each plane of PET data. Therefore. this method offers potential advantages in region-of-interest (ROI) extraction for kinetic modelling and quantitative analysis.

Current status and future direction of computer-aided diagnosis in chest CT

The vast amount of image data acquired during a thoracic computed tomography (CT) scan makes lung nodule detection a burdensome task. Moreover, the expanding role of CT as a diagnostic imaging modality and the growing acceptance of low-dose CT protocols for lung cancer screening promise to further impact radiologists' workloads. This increase in the number of CT studies being performed combined with multi-slice scanners that yield a greater number of images per study makes computerized analysis of CT images a practical necessity. Computer-aided detection of lesions is already a clinical reality in mammographic breast cancer screening, and such methods are expected to achieve similar success in CT lung cancer screening programs due to the potential for oversight errors on the part of human observers. This paper presents the rationale for computerized analysis of thoracic CT images, reviews the current state of automated lung nodule detection methods for CT, identifies issues that investigators must address, and speculates on future advances.

Computer-aided lesion detection with statistical model-based features in PET images

Positron emission tomography (PET) with the glucose analog [/sup 18/F] fluorodeoxyglucose is proving to be useful in cancer diagnosis and treatment. However, as in all nuclear medicine imaging technologies, lesion detection with PET is often hindered by limited spatial resolution and low signal-to-noise ratios. Under such conditions, conventional diagnosis by visual inspection usually becomes difficult and potentially inaccurate. In this paper, we propose use of computer-aided lesion detection methods for PET imaging by applying a maximum likelihood ratio test and a composite hypothesis test, assuming that the mean positron emission rate is deterministic or random, respectively. In our approach, different statistical models characterizing the mean positron emission rate, the raw sinogram data and the filtered backprojection (FBP) reconstructed image are used to derive the test criteria. Three methods to estimate the unknown parameters of the test functions from observations are presented. The performance of one of the proposed methods is evaluated and compared with both simulated and experimental phantom data. In the preliminary trials, the methods detect correctly (with a high probability >0.9) lesions of diameter/spl ges/15 mm with lesion-to-background contrast 1.1:1. Under the same conditions, the test lesion could not be detected by visual inspection alone in the images reconstructed by either the FBP or the maximum likelihood iterative algorithms. The methods may also be used for the objective assessment of the quality of images reconstructed from different algorithms.