Authors: Rezende, M.T., Silva, R., Bernardo, F.d.O. et al.
Publication: Scientific Data – Nature 8, 151, 2021.
Abstract: Amidst the current health crisis and social distancing, telemedicine has become an important part of mainstream of healthcare, and building and deploying computational tools to support screening more efficiently is an increasing medical priority. The early identification of cervical cancer precursor lesions by Pap smear test can identify candidates for subsequent treatment. However, one of the main challenges is the accuracy of the conventional method, often subject to high rates of false negative. While machine learning has been highlighted to reduce the limitations of the test, the absence of high-quality curated datasets has prevented strategies development to improve cervical cancer screening. The Center for Recognition and Inspection of Cells (CRIC) platform enables the creation of CRIC Cervix collection, currently with 400 images (1,376 × 1,020 pixels) curated from conventional Pap smears, with manual classification of 11,534 cells. This collection has the potential to advance current efforts in training and testing machine learning algorithms for the automation of tasks as part of the cytopathological analysis in the routine work of laboratories.
Authors: Diniz, Débora N. ; Rezende, Mariana T. ; Bianchi, Andrea G. C. ; Carneiro, Cláudia M. ; Ushizima, Daniela M. ; de Medeiros, Fátima N. S. ; Souza, Marcone J. F.
Publication: Applied Sciences-Basel, v. 11, p. 4091, 2021.
Abstract: Prevention of cervical cancer could be performed using Pap smear image analysis. This test screens pre-neoplastic changes in the cervical epithelial cells; accurate screening can reduce deaths caused by the disease. Pap smear test analysis is exhaustive and repetitive work performed visually by a cytopathologist. This article proposes a workload-reducing algorithm for cervical cancer detection based on analysis of cell nuclei features within Pap smear images. We investigate eight traditional machine learning methods to perform a hierarchical classification. We propose a hierarchical classification methodology for computer-aided screening of cell lesions, which can recommend fields of view from the microscopy image based on the nuclei detection of cervical cells. We evaluate the performance of several algorithms against the Herlev and CRIC databases, using a varying number of classes during image classification. Results indicate that the hierarchical classification performed best when using Random Forest as the key classifier, particularly when compared with decision trees, k-NN, and the Ridge methods.
Authors: Braga, Alan M.; Marques, Regis C.P. ; Medeiros, Fátima N.S. ; Neto, Jeová F.S. R. ; Bianchi, Andrea G.C. ; Carneiro, Cláudia M. ; Ushizima, Daniela M. .
Publication: Measurement, v. 176, p. 109232, 2021.
Abstract: This paper presents a novel hierarchical nuclei segmentation algorithm for isolated and overlapping cervical cells based on a narrow band level set implementation. Our method applies a new multiscale analysis algorithm to estimate the number of clusters in each image region containing cells, which turns into the input to a narrow band level set algorithm. We assess the nuclei segmentation results on three public cervical cell image databases. Overall, our segmentation method outperformed six state-of-the-art methods concerning the number of correctly segmented nuclei and the Dice coefficient reached values equal to or higher than 0.90. We also carried out classification experiments using features extracted from our segmentation results and the proposed pipeline achieved the highest average accuracy values equal to 0.89 and 0.77 for two-class and three-class problems, respectively. These results demonstrated the suitability of the proposed segmentation algorithm to integrate decision support systems for cervical cell screening.
Authors: Rezende, Mariana T, Bianchi, A. G. C. ; Carneiro, Cláudia M.
Publication: Diagnostic Cytopathology, v. 1, p. dc.24708, 2021.
Abstract: Cervical cancer progresses slowly, increasing the chance of early detection of pre-neoplastic lesions via Pap exam test and subsequently preventing deaths. However, the exam presents both false-negatives and false-positives results. Therefore, automatic methods (AMs) of reading the Pap test have been used to improve the quality control of the exam. We performed a literature review to evaluate the feasibility of implementing AMs in laboratories.
Authors: Flávio H.D. Araújo; Romuere R.V. Silva; Fátima N.S. Medeiros; Jeová Farias Rocha Neto; Paulo Henrique Calaes Oliveira; Andrea G. Campos Bianchi; Daniela M. Ushizima.
Publication: International Journal of Biomedical Engineering and Technology, v. 35, p. 70, 2021.
Abstract: The nuclei and cytoplasm segmentation of cervical cells is a well studied problem. However, the current segmentation algorithms are not robust to clinical practice due to the high computational cost or because they cannot accurately segment cells with high overlapping. In this paper, we propose a method that is capable of segmenting both cytoplasm and nucleus of each individual cell in a clump of overlapping cells. The proposed method consists of three steps: 1) cellular mass segmentation; 2) nucleus segmentation; 3) cytoplasm identification based on an active contour method. We carried out experiments on both synthetic and real cell images. The performance evaluation of the proposed method showed that it was less sensitive to the increase in the number of cells per image and the overlapping ratio against two other existing algorithms. It has also achieved a promising low processing time and, hence, it has the potential to support expert systems for cervical cell recognition.
Authors:Douglas Isidoro; Cláudia Carneiro ; Mariana Rezende; Fátima S. N. de Medeiros; Daniela M. Ushizima and Andrea G. C. Bianchi
Publication: In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications – Volume 5: VISAPP, 845-852, 2020, Valletta, Malta.
Abstract: This work presents a proposal for the efficient classification of cervical cells based on non-geometric characteristics extracted from nuclear regions of interest. This approach is based on the hypothesis that the nuclei store much of the information about the lesions in addition to their areas being more visible even with a high level of cellular overlap, a common fact in the Pap smears images. Classification systems were used in two and three classes for a set of real images of the cervix from a supervised learning method. The results demonstrate high classification performance and high efficiency for applicability in realistic environments, both computational and biological.
Authors: Diniz, Débora N. ; Souza, Marcone J. F. ; Carneiro, Cláudia M. ; Ushizima, Daniela M. ; de Medeiros, Fátima N. S. ; Oliveira, Paulo H. C. ; Bianchi, Andrea G. C.
Publication: Enterprise Information Systems. ICEIS 2019. (Org.). Lecture Notes in Business Information Processing. 1ed.Switzerland: Springer International Publishing, 2020, v., p. 78-96.
Abstract: The focus of this work is on the detection of nuclei in synthetic images of cervical cells. Finding nuclei is an important step in building a computational method to help cytopathologists identify cell changes from Pap smears. The method developed in this work combines both the Multi-Start and the Iterated Local Search metaheuristics and uses the features of a region to identify a nucleus. It aims to improve the assertiveness of the screening and reduce the professional workload. The irace package was used to automatically calibrate all parameter values of the method. The proposed approach was compared with other methods in the literature according to recall, precision, and F1 metrics using the ISBI Overlapping Cytology Image Segmentation Challenge database (2014). The results show that the proposed method has the second-best values of F1 and recall, while the accuracy is still high.
Authors: Flávio H. D. AraújoRomuere R. V. SilvaDaniela M. Ushizima, Mariana T. RezendeCláudia M. Carneiro, Andrea G. C. Bianchi, Fátima N. S. Medeiros
Publication: Computerized Medical Imaging and Graphics, pages 13-21, vol. 72
Abstract: Ninety years after its invention, the Pap test continues to be the most used method for the early identification of cervical precancerous lesions. In this test, the cytopathologists look for microscopic abnormalities in and around the cells, which is a time-consuming and prone to human error task. This paper introduces computational tools for cytological analysis that incorporate cell segmentation deep learning techniques. These techniques are capable of processing both free-lying and clumps of abnormal cells with a high overlapping rate from digitized images of conventional Pap smears. Our methodology employs a preprocessing step that discards images with a low probability of containing abnormal cells without prior segmentation and, therefore, performs faster when compared with the existing methods. Also, it ranks outputs based on the likelihood of the images to contain abnormal cells. We evaluate our methodology on an image database of conventional Pap smears from real scenarios, with 108 fields-of-view containing at least one abnormal cell and 86 containing only normal cells, corresponding to millions of cells. Our results show that the proposed approach achieves accurate results (MAP = 0.936), runs faster than existing methods, and it is robust to the presence of white blood cells, and other contaminants.
Publication: Journal of Visual Communication and Image Representation, pages 105-116, vol 62
Abstract: This paper introduces computational tools for cell classification into normal and abnormal, as well as content-based-image-retrieval (CBIR) for cell recommendation. It also proposes the radial feature descriptors (RFD), which define evenly interspaced segments around the nucleus, and proportional to the convexity of the nuclear boundary. Experiments consider Herlev and CRIC image databases as input to classification via Random Forest and bootstrap; we compare 14 different feature sets by means of False Negative Rate (FNR) and Kappa (k), obtaining FNR = 0.2 and k = 0.89 for Herlev, and FNR = 0.14 and k = 0.78 for CRIC. Next, we sort and rank cell images using convolutional neural networks and evaluate performance with the Mean Average Precision (MAP), achieving MAP = 0.84 and MAP = 0.82 for Herlev and CRIC, respectively. Cell classification show encouraging results regarding RFD, including its sensitivity to intensity variation around the nuclear membrane as it bypasses cytoplasm segmentation.
Authors: Daniel S. Ferreira, Geraldo L. B. RamalhoDébora TorresAlessandra H. G. Tobias, Mariana T. RezendeFátima N. S. MedeirosAndrea G. C. Bianchi, Cláudia M. Carneiro, Daniela M. Ushizima
Publication: Computer Methods and Programs in Biomedicine
Abstract: Background and objectives: Saliency refers to the visual perception quality that makes objects in a scene to stand out from others and attract attention. While computational saliency models can simulate the expert’s visual attention, there is little evidence about how these models perform when used to predict the cytopathologist’s eye fixations. Saliency models may be the key to instrumenting fast object detection on large Pap smear slides under real noisy conditions, artifacts, and cell occlusions. This paper describes how our computational schemes retrieve regions of interest (ROI) of clinical relevance using visual attention models. We also compare the performance of different computed saliency models as part of cell screening tasks, aiming to design a computer-aided diagnosis systems that supports cytopathologists. Method: We record eye fixation maps from cytopathologists at work, and compare with 13 different saliency prediction algorithms, including deep learning. We develop cell-specific convolutional neural networks (CNN) to investigate the impact of bottom-up and top-down factors on saliency prediction from real routine exams. By combining the eye tracking data from pathologists with computed saliency models, we assess algorithms reliability in identifying clinically relevant cells. Results: The proposed cell-specific CNN model outperforms all other saliency prediction methods, particularly regarding the number of false positives. Our algorithm also detects the most clinically relevant cells, which are among the three top salient regions, with accuracy above 98% for all diseases, except carcinoma (87%). Bottom-up methods performed satisfactorily, with saliency maps that enabled ROI detection above 75% for carcinoma and 86% for other pathologies. Conclusions: ROIs extraction using our saliency prediction methods enabled ranking the most relevant clinical areas within the image, a viable data reduction strategy to guide automatic analyses of Pap smear slides. Top-down factors for saliency prediction on cell images increases the accuracy of the estimated maps while bottom-up algorithms proved to be useful for predicting the cytopathologist’s eye fixations depending on parameters, such as the number of false positive and negative. Our contributions are: comparison among 13 state-of-the-art saliency models to cytopathologists’ visual attention and deliver a method that the associate the most conspicuous regions to clinically relevant cells.
Authors: Débora N. Diniz, Marcone J. F. Souza, Claudia M. Carneiro, Daniela M. Ushizima, Fatima N. S. de Medeiros Sombra, Paulo H. C. Oliveira and Andrea G. C. Bianchi
Publication: 21st International Conference on Enterprise Information Systems
Abstract: In this work, we propose an Iterated Local Search (ILS) approach to detect cervical cell nuclei from digitized Pap smear slides. The problem consists in finding the best values for the parameters to identify where the cell nuclei are located in the image. This is an important step in building a computational tool to help pathologists to identify cell alterations from Pap tests. Our approach is evaluated by using the ISBI Overlapping Cervical Cytology Image Segmentation Challenge (2014) database, which has 945 synthetic images and their respective ground truth. The precision achieved by the proposed heuristic approach is among the best ones in the literature; however, the recall still needs improvement.
Authors: Flavio H.D.Araujo, Romuere R. V. Silva, Fatima N. S. Medeiros, Dilworth D. Parkinson, Alexander Hexemer, Claudia M. Carneiro, Daniela M. Ushizima
Publication: Expert Systems and Applications, pages 35-48, vol 109
Abstract: The explosion in the rate, quality and diversity of image acquisition instruments has propelled the development of expert systems to organize and query image collections more efficiently. Recommendation systems that handle scientific images are rare, particularly if records lack metadata. This paper introduces new strategies to enable fast searches and image ranking from large pictorial datasets with or without labels. The main contribution is the development of pyCBIR, a deep neural network software to search scientific images by content. This tool exploits convolutional layers with locality sensitivity hashing for querying images across domains through a user-friendly interface. Our results report image searches over databases ranging from thousands to millions of samples. We test pyCBIR search capabilities using three convNets against four scientific datasets, including samples from cell microscopy, microtomography, atomic diffraction patterns, and materials photographs to demonstrate 95% accurate recommendations in most cases. Furthermore, all scientific data collections are released.
Authors: Romuere Silva, Flavio Araujo, Mariana Rezende, Paulo Oliveira, Fatima Medeiros, Rodrigo Veras, Daniela Ushizima
Publication: International Journal of Biomedical Engineering and Technology
Abstract: Despite research on cervical cells since 1925, systems to automatically screen images from conventional Pap smear tests continue unavailable. One of the main challenges in deploying precise software tools is to validate cell signatures. In this paper, we introduce an analysis framework, CRIC-feat, that expedites the investigation of different image databases and respective descriptors, particularly applicable to Pap images. This paper provides a three-fold contribution: (a) we first review and discuss the main feature extraction protocols for cell description and implementations suitable for cervical cells, (b) we present a new application of Gray Level Run Length (GLRLM) features to Pap images and (c) we evaluate 93 cell classification approaches, and provide a guideline for obtaining the most accurate description, based on two current public databases with digital images of real cells. Finally, we show that the nucleus information is preponderant in cell classification, particularly when considering the GLRLM feature set.
Authors: Alessandra H. G. Tobias, Aline C. Vitalino, Mariana T. Rezende, Renata R. R. Oliveira, Wendel Coura-Vidal, Rita G. Amaral, Claudia M. Carneiro
Publication: Cytopathology: official journal of the British Society for Clinical Cytology, pages 428-435, vol 29
Abstract: Background: An objective of quality control for cervical cytopathology is reducing high rates of false-negative results of laboratory tests. Therefore, methods to review smears such as rapid prescreening and 100% rapid review, which have shown better performance detecting false-negative results, have been widely used. The performance of rapid prescreening and the performance of 100% rapid review as internal quality control methods for cervical cytology examinations were evaluated. Methods: For 24 months, 9318 conventional cervical cytology smears underwent rapid prescreening and routine screening. The 100% rapid review method was performed for 8244 smears classified as negative during routine screening. Any discordant results underwent detailed review to define the final diagnosis. This was considered the gold standard for evaluating the performance of rapid prescreening and 100% rapid review. Results: Routine screening showed increases of 13.3% and 11.5% in the detection of abnormal smears with rapid prescreening and 100% rapid review, respectively. The relative percentage variation showed a 38.1% increase in the diagnosis of atypical squamous cells of undetermined significance with routine screening and rapid prescreening and a 12.5% increase in the diagnosis of atypical squamous cells, cannot exclude high-grade squamous intraepithelial lesion with both rapid prescreening and 100% rapid review. Sensitivity rates of rapid prescreening and routine screening were 48.2% and 83.2%, respectively. Sensitivity rates of rapid prescreening and 100% rapid review were 65.7% and 57.8%, respectively, for detecting false-negative results. Conclusions: Inclusion of rapid prescreening and/or 100% rapid review improved the diagnostic sensitivity of the cervical cytology examination and reduced false-negative results of routine screening and can provide good quality control.
Publication: 2017 IEEE Congress on Evolutionary Computation (CEC)
Abstract: The automation process of Pap smear analysis holds the potential to address women’s health care in the face of an increasing population and respective collected data. A fundamental step for automating analysis is cell detection from light microscopy images. Such information serves as input to cell classification algorithms and diagnostic recommendation tools. This paper describes an approach to nuclei cell segmentation, which critically impacts the following steps for cell analyses. We developed an algorithm combining clustering and genetic algorithms to detect image regions with high diagnostic value. A major problem when performing the segmentation of images is the cellular overlay. We introduce a new nuclear targeting approach using heuristics associated with a multi-objective genetic algorithm. Our experiments show results using a public 45-image dataset, including comparison to other cell detection approaches. The findings suggest an improvement in the nuclei segmentation and promise to support more sophisticated schemes for data quality control.
Publication: IEEE Journal of Biomedical and Health Informatics, pages 441-450, vol 21
Abstract: In this paper, we introduce and evaluate the systems submitted to the first Overlapping Cervical Cytology Image Segmentation Challenge, held in conjunction with the IEEE International Symposium on Biomedical Imaging 2014. This challenge was organized to encourage the development and benchmarking of techniques capable of segmenting individual cells from overlapping cellular clumps in cervical cytology images, which is a prerequisite for the development of the next generation of computer-aided diagnosis systems for cervical cancer. In particular, these automated systems must detect and accurately segment both the nucleus and cytoplasm of each cell, even when they are clumped together and, hence, partially occluded. However, this is an unsolved problem due to the poor contrast of cytoplasm boundaries, the large variation in size and shape of cells, and the presence of debris and the large degree of cellular overlap. The challenge initially utilized a database of 16 high-resolution (×40 magnification) images of complex cellular fields of view, in which the isolated real cells were used to construct a database of 945 cervical cytology images synthesized with a varying number of cells and degree of overlap, in order to provide full access of the segmentation ground truth. These synthetic images were used to provide a reliable and comprehensive framework for quantitative evaluation on this segmentation problem. Results from the submitted methods demonstrate that all the methods are effective in the segmentation of clumps containing at most three cells, with overlap coefficients up to 0.3. This highlights the intrinsic difficulty of this challenge and provides motivation for significant future improvement.
Publication: Revista Brasileira de Ginecologia e Obstetrícia, pages 65-70, vol. 38
Abstract: Objective: The objective of this study is to assess the performance of cytopathology laboratories providing services to the Brazilian Unified Health System (Sistema Único de Saúde – SUS) in the State of Minas Gerais, Brazil. Methods: This descriptive study uses data obtained from the Cervical Cancer Information System from January to December 2012. Three quality indicators were analyzed to assess the quality of cervical cytopathology tests: positivity index, percentage of atypical squamous cells (ASCs) in abnormal tests, and percentage of tests compatiblewith high-grade squamous intraepithelial lesions (HSILs). Laboratories were classified according to their production scale in tests per year≤5,000; from 5,001 to 10,000; from 10,001 to 15,000; and 15,001. Based on the collection of variables and the classification of laboratories according to production scale, we created and analyzed a database using Microsoft Office Excel 97-2003. Results: In the Brazilian state of Minas Gerais, 146 laboratories provided services to the SUS in 2012 by performing a total of 1,277,018 cervical cytopathology tests. Half of these laboratories had production scales≤5,000 tests/year and accounted for 13.1% of all tests performed in the entire state; in turn, 13.7% of these laboratories presented production scales of > 15,001 tests/year and accounted for 49.2% of the total of tests performed in the entire state. The positivity indexes of most laboratories providing services to the SUS in 2012, regardless of production scale, were below or well below recommended limits. Of the 20 laboratories that performed more than 15,001 tests per year, only three presented percentages of tests compatible with HSILs above the lower limit recommended by the Brazilian Ministry of Health. Conclusion: The majority of laboratories providing services to the SUS in Minas Gerais presented quality indicators outside the range recommended by the Brazilian Ministry of Health.
Authors: Alan M. Braga, Regis C. P. Marques, Fátima N. S. Medeiros, Daniela M. Ushizima
Publication: XXVIII Conference on Graphics, Patterns and Images
Abstract: This paper introduces a hierarchical approach basedon a binary level set algorithm for cervical cell segmentation.The proposed program recursively segments a region into twonew regions, starting from the whole image. In each step of thehierarchical process, we use a multiscale strategy to estimatethe number of clusters of the current region. A new division isperformed if two or more clusters are detected. The segmentationprocess automatically terminates when all regions cannot bedivided further, according to the criteria imposed by the proposedmethod. Experiments performed on the Herlev dataset showedthe effectiveness of the proposed hierarchical algorithm.
Authors: Geraldo L. B. Ramalho, D. S. Ferreira, Andrea G. C. Bianchi, Claudia M. Carneiro, Fatima N. S. Medeiros, Daniela Ushizima
Publication: IEEE International Symposium on Biomedical Imaging (ISBI 2015)
Abstract: Cell occlusion, staining variation, particulate forms and diversity of cervical cells are some of the challenges in automating cervical cytology. This paper tackles some of these issues, including the detection of nucleus and cytoplasm from a new standardization for specimen preparation through mono/thin-layer technology. Our approach consists of three main steps: (a) rough segmentation of subcellular compartments using super pixel combined to Voronoi diagrams, (b) structural refinement of the cytoplasm boundary through calculus of variations, and (c) morphological reconstruction combined to optimization methods to determine minimum enclosing ellipse. We test our implementation on real 3D cervical cell images, containing several cells at different occlusion levels and variable contrast. Our results show both qualitative and quantitative assessment of the datasets, using a completely automated computer program. The quantitative performance presents average Dice Coefficient higher than 87%.
Authors: Daniela M. Ushizima, Andrea G. C. Bianchi, Claudia M. Carneiro
Publication: International Symposium on Biomedical Imaging
Abstract: We propose and implement a computer vision algorithm for detecting individual cells, including the ability to distinguish subcellular compartments, such as nucleus and cytoplasm. Our approach consists of three main steps: (a) cellular mass estimation, and (b) nuclei detection through superpixel representation and, (c) cytoplasm detection through nuclear narrow-band seeding, graph-based region growing and Voronoi diagrams. We test our implementation on both real and simulated cervical cell images, containing an assortment of cells and configurations that often present occlusion and/or poor contrast. Our results show both qualitative and quantitative assessment of the datasets, using a completely automated computer program. The quantitative performance presents average Dice Coefficient higher than 86% for both training and testing sets.
Authors: Dandara E. M. Sana, Priscila M. Miranda, Bruna C. V. Pitol, Nayara N. T. S., Ismael D. C. G. Silva, Rita C. Stocco, Willy Beçak, Angélica A. Lima, Cláudia M. Carneiro
Publication: Diagnostic Cytopathology, pages 785-792, vol. 41
Abstract: Herein, we evaluated cervical samples from normal tissue or HPV-infected tissue, to determine if the relative nuclear/cytoplasmic ratio (NA/CA) and the presence of nonclassical cytological criteria are a novel cytological criterion for the diagnosis of HPV. Significantly, larger NA/CA ratios were found for the HPV-ATYPIA+ and HPV+ATYPIA+ groups compared with HPV-ATYPIA- group, regardless of collection method. For the samples collected with a spatula, only three samples from the HPV-ATIPIA- group showed four or more nonclassical parameters (i.e., were positive), while a larger number of the samples in the HPV-ATYPIA+, HPV+ATYPIA-, and HPV+ATYPIA+ groups were positive (13, 4, and 13 samples, respectively). Among those collected with a brush, no sample showed four or more nonclassical criteria in the HPV-ATYPIA- group, while a number of samples were positive in the HPV-ATYPIA+, HPV+ATYPIA-, and HPV+ATYPIA+ groups (4, 3, and 4 samples, respectively). HPV infection was associated with significant morphometrical changes; no increase in the NA/CA ratio was found in the HPV+ATYPIA- samples, compared with the HPV-ATIPIA- samples collected with either a spatula or a brush. In conclusion, by including nonclassical cytological criteria into the patient diagnosis, we were able to reduce the number of false negative and false positive HPV diagnoses made using conventional cytology alone.
Authors: Daniela M. Ushizima, Alessandra H. Gomes, Claudia M. Carneiro, Andrea G. C. Bianchi
Publication: 12th International Conference on Machine Learning and Applications (ICMLA)
Abstract: Cervical cancer screening is one of the most widespread tests in the world, and the acquisition of digital images of Pap smears is about to become part of the laboratories routine. The ability to collect these standard exam data has increased drastically, and available tools for image analysis and quantification are not accurate and/or customized enough to deliver relevant information about the image content. Aiming at enabling pathology laboratories to deal with large amounts of digitized Pap smears slides, we propose to design computer vision algorithms for quantitative analysis and pattern recognition from 2D images. The goal is to bring high technology to laboratories focused on underserved communities of women for the prevention of cervical cancer, in these public health care institutions, there is no perspective of using “omics” data in the medium term, but only clinical annotations and Pap smears slides. Here, we describe our project and propose computational tools adapted to this application, addressing the needs from end-to-end, including enhancement, noise minimization, segmentation of regions of interest, extraction and classification of objects.