Deep neural networks can differentiate thyroid pathologies on infrared hyperspectral images.

BACKGROUND AND OBJECTIVE: The thyroid is a gland responsible for producing important body hormones. Several pathologies can affect this gland, such as thyroiditis, hypothyroidism, and thyroid cancer. The visual histological analysis of thyroid specimens is a valuable process that enables pathologists to detect diseases with high efficiency, providing the patient with a better prognosis. Existing computer vision systems developed to aid in the analysis of histological samples have limitations in distinguishing pathologies with similar characteristics or samples containing multiple diseases. To overcome this challenge, hyperspectral images are being studied to represent biological samples based on their molecular interaction with light. METHODS: In this study, we address the acquisition of infrared absorbance spectra from each voxel of histological specimens. This data is then used for the development of a multiclass fully-connected neural network model that discriminates spectral patterns, enabling the classification of voxels as healthy, cancerous, or goiter. RESULTS: Through experiments using the k-fold cross-validation protocol, we obtained an average accuracy of 93.66 %, a sensitivity of 93.47 %, and a specificity of 96.93 %. Our results demonstrate the feasibility of using infrared hyperspectral imaging to characterize healthy tissue and thyroid pathologies using absorbance measurements. The proposed deep learning model has the potential to improve diagnostic efficiency and enhance patient outcomes.

Histopathological diagnosis of colon cancer using micro-FTIR hyperspectral imaging and deep learning.

BACKGROUND AND OBJECTIVE: Current studies based on digital biopsy images have achieved satisfactory results in detecting colon cancer despite their limited visual spectral range. Such methods may be less accurate when applied to samples taken from the tumor margin region or to samples containing multiple diagnoses. In contrast with the traditional computer vision approach, micro-FTIR hyperspectral images quantify the tissue-light interaction on a histochemical level and characterize different tissue pathologies, as they present a unique spectral signature. Therefore, this paper investigates the possibility of using hyperspectral images acquired over micro-FTIR absorbance spectroscopy to characterize healthy, inflammatory, and tumor colon tissues. METHODS: The proposed method consists of modeling hyperspectral data into a voxel format to detect the patterns of each voxel using fully connected deep neural network. A web-based computer-aided diagnosis tool for inference is also provided. RESULTS: Our experiments were performed using the K-fold cross-validation protocol in an intrapatient approach and achieved an overall accuracy of 99% using a deep neural network and 96% using a linear support vector machine. Through the experiments, we noticed the high performance of the method in characterizing such tissues using deep learning and hyperspectral images, indicating that the infrared spectrum contains relevant information and can be used to assist pathologists during the diagnostic process.

Verruciform xanthoma associated with lichen planus.

Verruciform xanthoma (VX) is a rare benign lesion of unknown etiology, with a rough or papillary aspect, painless, sessile, well-defined, most lesions do not exceed 2 cm in their largest diameter, the degree of keratinization of the surface influences color, varying white to red, affecting mainly the gingiva and alveolar mucosa, and can also be seen in skin and genital. Herein, we present a report a clinical case of oral verruciform xanthoma in the buccal mucosa associated with the lichen planus lesion, as well as the morphological and immunohistochemical characteristics of the lesion. The clinical diagnostic hypothesis of oral lichen planus of the white reticular lesions on the buccal mucosa and on the tongue was confirmed by histopathology before a subepithelial connective tissue exhibiting intense inflammatory infiltrate in a predominantly lymphocytic band. In contrast, the hypothesis of the verrucous lesion in the left buccal mucosa was leukoplakia, with histopathological evidence showing exophytic and digitiform proliferations with parakeratin plugs between the papillary projections. Subepithelial connective tissue was characterized by macrophages with foamy cytoplasm (xanthoma cells). An immunohistochemical examination was performed, showing positivity for CD68, a macrophage marker, in addition to testing by Schiff's periodic acid (PAS) with diastasis, which was detected the presence of lipids inside these macrophages. The patient is free of recurrences of verruciform xanthoma and is being monitored due to the presence of lesions of oral lichen planus.

Prediction of Radiation-Related Dental Caries Through PyRadiomics Features and Artificial Neural Network on Panoramic Radiography.

The prediction and detection of radiation-related caries (RRC) are crucial to manage the side effects of the head and the neck cancer (HNC) radiotherapy (RT). Despite the demands for the prediction of RRC, no study proposes and evaluates a prediction method. This study introduces a method based on artificial intelligence neural network to predict and detect either regular caries or RRC in HNC patients under RT using features extracted from panoramic radiograph. We selected fifteen HNC patients (13 men and 2 women) to analyze, retrospectively, their panoramic dental images, including 420 teeth. Two dentists manually labeled the teeth to separate healthy and teeth with either type caries. They also labeled the teeth by resistant and vulnerable, as predictive labels telling about RT aftermath caries. We extracted 105 statistical/morphological image features of the teeth using PyRadiomics. Then, we used an artificial neural network classifier (ANN), firstly, to select the best features (using maximum weights) and then label the teeth: in caries and non-caries while detecting RRC, and resistant and vulnerable while predicting RRC. To evaluate the method, we calculated the confusion matrix, receiver operating characteristic (ROC), and area under curve (AUC), as well as a comparison with recent methods. The proposed method showed a sensibility to detect RRC of 98.8% (AUC = 0.9869) and to predict RRC achieved 99.2% (AUC = 0.9886). The proposed method to predict and detect RRC using neural network and PyRadiomics features showed a reliable accuracy able to perform before starting RT to decrease the side effects on susceptible teeth.

BioBankWarden: A web-based system to support translational cancer research by managing clinical and biomaterial data.

BACKGROUND: Researchers of translational medicine face numerous challenges in attempting to bring research results to the bedside. This field of research covers a wide range of resources, including blood and tissue samples, which are processed for isolation of RNA and DNA to study cancer omics data (genomics, proteomics and metabolomics). Clinical information about patients׳ habits, family history, physical examinations, remissions, etc., is also important to underpin studies aimed at identifying patterns that lead to the development of cancer and to its successful treatment. PURPOSE: Development of a web-based computer system-BioBankWarden-to manage, consolidate and integrate these diversified data, enabling cancer research groups to retrieve and analyze clinical and biomolecular data within an integrative environment. The system has a three-tier architecture comprising database, logic and user-interface layers. RESULTS: The system׳s integrated database and user-friendly interface allow for the control of patient records, biomaterial storage, research groups, research projects, users and biomaterial exchange. CONCLUSIONS: BioBankWarden can be used to store and retrieve specific information from different clinical fields linked to biomaterials collected from patients, providing the functionalities required to support translational research in the field of cancer.

Morphometric information to reduce the semantic gap in the characterization of microscopic images of thyroid nodules.

BACKGROUND: The analyses of several systems for medical-imaging processing typically support the extraction of image attributes, but do not comprise some information that characterizes images. For example, morphometry can be applied to find new information about the visual content of an image. The extension of information may result in knowledge. Subsequently, results of mappings can be applied to recognize exam patterns, thus improving the accuracy of image retrieval and allowing a better interpretation of exam results. Although successfully applied in breast lesion images, the morphometric approach is still poorly explored in thyroid lesions due to the high subjectivity thyroid examinations. OBJECTIVE: This paper presents a theoretical-practical study, considering Computer Aided Diagnosis (CAD) and Morphometry, to reduce the semantic discontinuity between medical image features and human interpretation of image content. METHOD: The proposed method aggregates the content of microscopic images characterized by morphometric information and other image attributes extracted by traditional object extraction algorithms. This method carries out segmentation, feature extraction, image labeling and classification. Morphometric analysis was included as an object extraction method in order to verify the improvement of its accuracy for automatic classification of microscopic images. RESULTS: To validate this proposal and verify the utility of morphometric information to characterize thyroid images, a CAD system was created to classify real thyroid image-exams into Papillary Cancer, Goiter and Non-Cancer. Results showed that morphometric information can improve the accuracy and precision of image retrieval and the interpretation of results in computer-aided diagnosis. For example, in the scenario where all the extractors are combined with the morphometric information, the CAD system had its best performance (70% of precision in Papillary cases). CONCLUSION: Results signalized a positive use of morphometric information from images to reduce semantic discontinuity between human interpretation and image characterization.

A New Method for Automated Identification and Morphometry of Myelinated Fibers Through Light Microscopy Image Analysis.

Nerve morphometry is known to produce relevant information for the evaluation of several phenomena, such as nerve repair, regeneration, implant, transplant, aging, and different human neuropathies. Manual morphometry is laborious, tedious, time consuming, and subject to many sources of error. Therefore, in this paper, we propose a new method for the automated morphometry of myelinated fibers in cross-section light microscopy images. Images from the recurrent laryngeal nerve of adult rats and the vestibulocochlear nerve of adult guinea pigs were used herein. The proposed pipeline for fiber segmentation is based on the techniques of competitive clustering and concavity analysis. The evaluation of the proposed method for segmentation of images was done by comparing the automatic segmentation with the manual segmentation. To further evaluate the proposed method considering morphometric features extracted from the segmented images, the distributions of these features were tested for statistical significant difference. The method achieved a high overall sensitivity and very low false-positive rates per image. We detect no statistical difference between the distribution of the features extracted from the manual and the pipeline segmentations. The method presented a good overall performance, showing widespread potential in experimental and clinical settings allowing large-scale image analysis and, thus, leading to more reliable results.

A similarity-based data warehousing environment for medical images.

A core issue of the decision-making process in the medical field is to support the execution of analytical (OLAP) similarity queries over images in data warehousing environments. In this paper, we focus on this issue. We propose imageDWE, a non-conventional data warehousing environment that enables the storage of intrinsic features taken from medical images in a data warehouse and supports OLAP similarity queries over them. To comply with this goal, we introduce the concept of perceptual layer, which is an abstraction used to represent an image dataset according to a given feature descriptor in order to enable similarity search. Based on this concept, we propose the imageDW, an extended data warehouse with dimension tables specifically designed to support one or more perceptual layers. We also detail how to build an imageDW and how to load image data into it. Furthermore, we show how to process OLAP similarity queries composed of a conventional predicate and a similarity search predicate that encompasses the specification of one or more perceptual layers. Moreover, we introduce an index technique to improve the OLAP query processing over images. We carried out performance tests over a data warehouse environment that consolidated medical images from exams of several modalities. The results demonstrated the feasibility and efficiency of our proposed imageDWE to manage images and to process OLAP similarity queries. The results also demonstrated that the use of the proposed index technique guaranteed a great improvement in query processing.

Computer-aided diagnosis system based on fuzzy logic for breast cancer categorization.

BACKGROUND: Fuzzy logic can help reduce the difficulties faced by computational systems to represent and simulate the reasoning and the style adopted by radiologists in the process of medical image analysis. The study described in this paper consists of a new method that applies fuzzy logic concepts to improve the representation of features related to image description in order to make it semantically more consistent. Specifically, we have developed a computer-aided diagnosis tool for automatic BI-RADS categorization of breast lesions. The user provides parameters such as contour, shape and density and the system gives a suggestion about the BI-RADS classification. METHODS: Initially, values of malignancy were defined for each image descriptor, according to the BI-RADS standard. When analyzing contour, for example, our method considers the matching of features and linguistic variables. Next, we created the fuzzy inference system. The generation of membership functions was carried out by the Fuzzy Omega algorithm, which is based on the statistical analysis of the dataset. This algorithm maps the distribution of different classes in a set. RESULTS: Images were analyzed by a group of physicians and the resulting evaluations were submitted to the Fuzzy Omega algorithm. The results were compared, achieving an accuracy of 76.67% for nodules and 83.34% for calcifications. CONCLUSIONS: The fit of definitions and linguistic rules to numerical models provided by our method can lead to a tighter connection between the specialist and the computer system, yielding more effective and reliable results.

Two-dimensional sample entropy analysis of rat sural nerve aging.

Entropy analysis of images are usually performed using Shannon entropy, which calculates the probability of occurrency of each gray level on the image. However, not only the pixel gray level but also the spatial distribution of pixels might be important for image analysis. On the other hand, sample entropy (SampEn) is an important tool for estimation of irregularity in time series, which calculates the probability of pattern occurrence within the series. Therefore, we propose here an extension of SampEn to a two-dimensional case, namely SampEn2D, as an entropy method for extracting features from images that accounts for the spatial distribution of pixels. SampEn2D was applied to histological segments of sural nerve obtained from young (30 days) and elderly (720 days) rats. Morphometric indexes, such as the total number of myelinated fibers and the average myelinated fibers area and perimeter were also calculated. Results show that SampEn2D can extract useful information from histological nerve images, classifying elderly rat image as more regular than young rat. As SampEn2D is related to irregularity/unpredictability, we can conclude that the proposed method is complementary to morphometric indexes. Further studies are being built to validate SampEn2D.

Computational framework to support integration of biomolecular and clinical data within a translational approach.

BACKGROUND: The use of the knowledge produced by sciences to promote human health is the main goal of translational medicine. To make it feasible we need computational methods to handle the large amount of information that arises from bench to bedside and to deal with its heterogeneity. A computational challenge that must be faced is to promote the integration of clinical, socio-demographic and biological data. In this effort, ontologies play an essential role as a powerful artifact for knowledge representation. Chado is a modular ontology-oriented database model that gained popularity due to its robustness and flexibility as a generic platform to store biological data; however it lacks supporting representation of clinical and socio-demographic information. RESULTS: We have implemented an extension of Chado - the Clinical Module - to allow the representation of this kind of information. Our approach consists of a framework for data integration through the use of a common reference ontology. The design of this framework has four levels: data level, to store the data; semantic level, to integrate and standardize the data by the use of ontologies; application level, to manage clinical databases, ontologies and data integration process; and web interface level, to allow interaction between the user and the system. The clinical module was built based on the Entity-Attribute-Value (EAV) model. We also proposed a methodology to migrate data from legacy clinical databases to the integrative framework. A Chado instance was initialized using a relational database management system. The Clinical Module was implemented and the framework was loaded using data from a factual clinical research database. Clinical and demographic data as well as biomaterial data were obtained from patients with tumors of head and neck. We implemented the IPTrans tool that is a complete environment for data migration, which comprises: the construction of a model to describe the legacy clinical data, based on an ontology; the Extraction, Transformation and Load (ETL) process to extract the data from the source clinical database and load it in the Clinical Module of Chado; the development of a web tool and a Bridge Layer to adapt the web tool to Chado, as well as other applications. CONCLUSIONS: Open-source computational solutions currently available for translational science does not have a model to represent biomolecular information and also are not integrated with the existing bioinformatics tools. On the other hand, existing genomic data models do not represent clinical patient data. A framework was developed to support translational research by integrating biomolecular information coming from different "omics" technologies with patient's clinical and socio-demographic data. This framework should present some features: flexibility, compression and robustness. The experiments accomplished from a use case demonstrated that the proposed system meets requirements of flexibility and robustness, leading to the desired integration. The Clinical Module can be accessed in http://dcm.ffclrp.usp.br/caib/pg=iptrans.

A new family of distance functions for perceptual similarity retrieval of medical images.

A long-standing challenge of content-based image retrieval (CBIR) systems is the definition of a suitable distance function to measure the similarity between images in an application context which complies with the human perception of similarity. In this paper, we present a new family of distance functions, called attribute concurrence influence distances (AID), which serve to retrieve images by similarity. These distances address an important aspect of the psychophysical notion of similarity in comparisons of images: the effect of concurrent variations in the values of different image attributes. The AID functions allow for comparisons of feature vectors by choosing one of two parameterized expressions: one targeting weak attribute concurrence influence and the other for strong concurrence influence. This paper presents the mathematical definition and implementation of the AID family for a two-dimensional feature space and its extension to any dimension. The composition of the AID family with L (p) distance family is considered to propose a procedure to determine the best distance for a specific application. Experimental results involving several sets of medical images demonstrate that, taking as reference the perception of the specialist in the field (radiologist), the AID functions perform better than the general distance functions commonly used in CBIR.

Laf 1. 0: implantação de um sistema informatizado para laboratórios de antropologia forense / Laf 1. 0: establishment of a computerized system for laboratories of forensic anthropology

Desenvolvimento de um software para cadastro e recuperação de informações em Antropologia Forense baseado no protocolo desenvolvido durante o projeto “UK –Brazil Scientific Cooperation – Forensic Anthropology and Identification of Human Remains”. Metodologia: Por se tratar de um aplicativo acessado via Browser (software que permite o acesso à Internet, como o Microsoft Internet Explorer®) foi necessária a escolha de uma linguagem de programação que se enquadrasse nesse requisito juntamente com uma aplicação servidora. A linguagem escolhida foi PHP® e a aplicação servidora foi o Apache®. Para o armazenamento dos dados foi escolhido o Sistema Gerenciador de Banco de Dados MySQL®...

A Software development for registration and recovery of information on Objective: A Software development for registration and recovery of information on Forensic Anthropology, based on the protocol developed during the project “UK – Brazil Scientific Cooperation – Forensic Anthropology and Identification of Human Remains”. Methods: Considering it is a Browser accessed application (software that allows Internet access, as Microsoft Internet Explorer®), it was necessary to choose an adequate programming language to this requirement as the server application. The chosen language was PHP® and the server application was Apache®. For data storage it was chosen the Data Bank Managing System MySQL®. Forensic Anthropology, based on the protocol developed during the project “UK – Brazil ScientificCooperation – Forensic Anthropology and Identification of Human Remains”. Methods: Considering it is a Browser accessed application (software that allows Internet access, as Microsoft InternetExplorer®), it was necessary to choose an adequate programming language to this requirement as the server application. The chosen language was PHP® and the server application was Apache®. For data storage it was chosen the Data Bank Managing System MySQL®...

Using relevance feedback to reduce the semantic gap in content-based image retrieval of mammographic masses.

This paper presents the use of relevance feedback (RFb) to reduce the semantic gap in content-based image retrieval (CBIR) of mammographic masses. Tests were conducted where the radiologists' classification of the lesions based on the BI-RADS categories were used with techniques of query-point movement to incorporate RFb. The measures of similarity of images used for CBIR were based upon Zernike moments. The performance of CBIR was measured in terms of precision and recall of retrieval. The results indicate improvement due to RFb of up to 41.6% in precision. In our experiments, the gain in the performance of CBIR with RFb was associated with the BI-RADS category of the query mammographic image, with large improvement in cases of lesions belonging to categories 4 and 5. The proposed method could find applications in computer-aided diagnosis (CAD) of breast cancer.