RESUMO
BACKGROUND: Interval breast cancers are often diagnosed at a more advanced stage than screen-detected cancers. Our aim was to identify features in screening mammograms of the normal breast that would differentiate between future interval cancers and screen-detected cancers, and to understand how each feature affects tumor detectability. METHODS: From a population-based cohort of invasive breast cancer cases in Stockholm-Gotland, Sweden, diagnosed from 2001 to 2008, we analyzed the contralateral mammogram at the preceding negative screening of 394 interval cancer cases and 1009 screen-detected cancers. We examined 32 different image features in digitized film mammograms, based on three alternative dense area identification methods, by a set of logistic regression models adjusted for percent density with interval cancer versus screen-detected cancer as the outcome. Features were forward-selected into a multiple logistic regression model adjusted for mammographic percent density, age, BMI and use of hormone replacement therapy. The associations of the identified features were assessed also in a sample from an independent cohort. RESULTS: Two image features, 'skewness of the intensity gradient' and 'eccentricity', were associated with the risk of interval compared with screen-detected cancer. For the first feature, the per-standard deviation odds ratios were 1.32 (95 % CI: 1.12 to 1.56) and 1.21 (95 % CI: 1.04 to 1.41) in the primary and validation cohort respectively. For the second feature, they were 1.20 (95 % CI: 1.04 to 1.39) and 1.17 (95%CI: 0.98 to 1.39) respectively. The first feature was associated with the tumor size at screen detection, while the second feature was associated with the tumor size at interval detection. CONCLUSIONS: We identified two novel mammographic features in screening mammograms of the normal breast that differentiated between future interval cancers and screen-detected cancers. We present a starting point for further research into features beyond percent density that might be relevant for interval cancer, and suggest ways to use this information to improve screening.
Assuntos
Neoplasias da Mama/diagnóstico por imagem , Neoplasias da Mama/patologia , Mamografia , Idoso , Densidade da Mama , Neoplasias da Mama/epidemiologia , Detecção Precoce de Câncer/métodos , Feminino , Humanos , Processamento de Imagem Assistida por Computador , Mamografia/métodos , Programas de Rastreamento/métodos , Pessoa de Meia-Idade , Gradação de Tumores , Metástase Neoplásica , Estadiamento de Neoplasias , Vigilância da População , Suécia , Carga TumoralRESUMO
BACKGROUND: Chronic obstructive pulmonary disease (COPD) is a severe condition affecting millions worldwide, leading to numerous annual deaths. The absence of significant symptoms in its early stages promotes high underdiagnosis rates for the affected people. Besides pulmonary function failure, another harmful problem of COPD is the systemic effects, e.g., heart failure or voice distortion. However, the systemic effects of COPD might provide valuable information for early detection. In other words, symptoms caused by systemic effects could be helpful to detect the condition in its early stages. OBJECTIVE: The proposed study aims to explore whether the voice features extracted from the vowel "a" utterance carry any information that can be predictive of COPD by employing Machine Learning (ML) on a newly collected voice dataset. METHODS: Forty-eight participants were recruited from the pool of research clinic visitors at Blekinge Institute of Technology (BTH) in Sweden between January 2022 and May 2023. A dataset consisting of 1246 recordings from 48 participants was gathered. The collection of voice recordings containing the vowel "a" utterance commenced following an information and consent meeting with each participant using the VoiceDiagnostic application. The collected voice data was subjected to silence segment removal, feature extraction of baseline acoustic features, and Mel Frequency Cepstrum Coefficients (MFCC). Sociodemographic data was also collected from the participants. Three ML models were investigated for the binary classification of COPD and healthy controls: Random Forest (RF), Support Vector Machine (SVM), and CatBoost (CB). A nested k-fold cross-validation approach was employed. Additionally, the hyperparameters were optimized using grid-search on each ML model. For best performance assessment, accuracy, F1-score, precision, and recall metrics were computed. Afterward, we further examined the best classifier by utilizing the Area Under the Curve (AUC), Average Precision (AP), and SHapley Additive exPlanations (SHAP) feature-importance measures. RESULTS: The classifiers RF, SVM, and CB achieved a maximum accuracy of 77 %, 69 %, and 78 % on the test set and 93 %, 78 % and 97 % on the validation set, respectively. The CB classifier outperformed RF and SVM. After further investigation of the best-performing classifier, CB demonstrated the highest performance, producing an AUC of 82 % and AP of 76 %. In addition to age and gender, the mean values of baseline acoustic and MFCC features demonstrate high importance and deterministic characteristics for classification performance in both test and validation sets, though in varied order. CONCLUSION: This study concludes that the utterance of vowel "a" recordings contain information that can be captured by the CatBoost classifier with high accuracy for the classification of COPD. Additionally, baseline acoustic and MFCC features, in conjunction with age and gender information, can be employed for classification purposes and benefit healthcare for decision support in COPD diagnosis. CLINICAL TRIAL REGISTRATION NUMBER: NCT05897944.
RESUMO
We demonstrate a technique to improve structural data obtained from Optical Projection Tomography (OPT) using Image Fusion (IF) and contrast normalization. This enables the visualization of molecular expression patterns in biological specimens with highly variable contrast values. In the approach, termed IF-OPT, different exposures are fused by assigning weighted contrasts to each. When applied to projection images from mouse organs and digital phantoms our results demonstrate the capability of IF-OPT to reveal high and low signal intensity details in challenging specimens. We further provide measurements to highlight the benefits of the new algorithm in comparison to other similar methods.
Assuntos
Algoritmos , Aumento da Imagem/métodos , Interpretação de Imagem Assistida por Computador/métodos , Imagem Molecular/métodos , Reconhecimento Automatizado de Padrão/métodos , Técnica de Subtração , Tomografia Óptica/métodos , Animais , CamundongosRESUMO
Due to the exponential growth of medical information in the form of, e.g., text, images, Electrocardiograms (ECGs), X-rays, and multimedia, the management of a patient's data has become a huge challenge. In particular, the extraction of features from various different formats and their representation in a homogeneous way are areas of interest in medical applications. Multimedia Information Retrieval (MMIR) frameworks, like the Generic Multimedia Analysis Framework (GMAF), can contribute to solving this problem, when adapted to special requirements and modalities of medical applications. In this paper, we demonstrate how typical multimedia processing techniques can be extended and adapted to medical applications and how these applications benefit from employing a Multimedia Feature Graph (MMFG) and specialized, efficient indexing structures in the form of Graph Codes. These Graph Codes are transformed to feature relevant Graph Codes by employing a modified Term Frequency Inverse Document Frequency (TFIDF) algorithm, which further supports value ranges and Boolean operations required in the medical context. On this basis, various metrics for the calculation of similarity, recommendations, and automated inferencing and reasoning can be applied supporting the field of diagnostics. Finally, the presentation of these new facilities in the form of explainability is introduced and demonstrated. Thus, in this paper, we show how Graph Codes contribute new querying options for diagnosis and how Explainable Graph Codes can help to readily understand medical multimedia formats.
RESUMO
Mouse models for streptozotocin (STZ) induced diabetes probably represent the most widely used systems for preclinical diabetes research, owing to the compound's toxic effect on pancreatic ß-cells. However, a comprehensive view of pancreatic ß-cell mass distribution subject to STZ administration is lacking. Previous assessments have largely relied on the extrapolation of stereological sections, which provide limited 3D-spatial and quantitative information. This data descriptor presents multiple ex vivo tomographic optical image datasets of the full ß-cell mass distribution in mice subject to single high and multiple low doses of STZ administration, and in glycaemia recovered mice. The data further include information about structural features, such as individual islet ß-cell volumes, spatial coordinates, and shape as well as signal intensities for both insulin and GLUT2. Together, they provide the most comprehensive anatomical record of the effects of STZ administration on the islet of Langerhans in mice. As such, this data descriptor may serve as reference material to facilitate the planning, use and (re)interpretation of this widely used disease model.
Assuntos
Diabetes Mellitus Experimental , Ilhotas Pancreáticas , Animais , Glicemia/análise , Insulina/análise , Camundongos , Estreptozocina/análiseRESUMO
The management of prostate cancer (PCa) is dependent on biomarkers of biological aggression. This includes an invasive biopsy to facilitate a histopathological assessment of the tumor's grade. This review explores the technical processes of applying magnetic resonance imaging based radiomic models to the evaluation of PCa. By exploring how a deep radiomics approach further optimizes the prediction of a PCa's grade group, it will be clear how this integration of artificial intelligence mitigates existing major technological challenges faced by a traditional radiomic model: image acquisition, small data sets, image processing, labeling/segmentation, informative features, predicting molecular features and incorporating predictive models. Other potential impacts of artificial intelligence on the personalized treatment of PCa will also be discussed. The role of deep radiomics analysis-a deep texture analysis, which extracts features from convolutional neural networks layers, will be highlighted. Existing clinical work and upcoming clinical trials will be reviewed, directing investigators to pertinent future directions in the field. For future progress to result in clinical translation, the field will likely require multi-institutional collaboration in producing prospectively populated and expertly labeled imaging libraries.
RESUMO
OBJECTIVE: We provide an e-Science perspective on the workflow from risk factor discovery and classification of disease to evaluation of personalized intervention programs. As case studies, we use personalized prostate and breast cancer screenings. MATERIALS AND METHODS: We describe an e-Science initiative in Sweden, e-Science for Cancer Prevention and Control (eCPC), which supports biomarker discovery and offers decision support for personalized intervention strategies. The generic eCPC contribution is a workflow with 4 nodes applied iteratively, and the concept of e-Science signifies systematic use of tools from the mathematical, statistical, data, and computer sciences. RESULTS: The eCPC workflow is illustrated through 2 case studies. For prostate cancer, an in-house personalized screening tool, the Stockholm-3 model (S3M), is presented as an alternative to prostate-specific antigen testing alone. S3M is evaluated in a trial setting and plans for rollout in the population are discussed. For breast cancer, new biomarkers based on breast density and molecular profiles are developed and the US multicenter Women Informed to Screen Depending on Measures (WISDOM) trial is referred to for evaluation. While current eCPC data management uses a traditional data warehouse model, we discuss eCPC-developed features of a coherent data integration platform. DISCUSSION AND CONCLUSION: E-Science tools are a key part of an evidence-based process for personalized medicine. This paper provides a structured workflow from data and models to evaluation of new personalized intervention strategies. The importance of multidisciplinary collaboration is emphasized. Importantly, the generic concepts of the suggested eCPC workflow are transferrable to other disease domains, although each disease will require tailored solutions.
Assuntos
Neoplasias da Mama/diagnóstico , Biologia Computacional , Detecção Precoce de Câncer , Medicina de Precisão , Neoplasias da Próstata/diagnóstico , Fluxo de Trabalho , Idoso , Algoritmos , Biomarcadores Tumorais/análise , Mineração de Dados , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Modelos Biológicos , Medição de Risco , SuéciaRESUMO
BACKGROUND: Mammographic percent density is an established marker of breast cancer risk. In a study of screen film mammograms, we recently reported a novel feature from the pectoral muscle region to be associated with breast cancer risk independently of area percent density (APD). We now investigate whether our novel feature is associated with risk in a study based on full-field digital mammography (FFDM). METHODS: We carried out a breast cancer risk analysis using a data set of 3,552 healthy controls and 278 cases. We included three image-based measures in our analyses: volumetric percent density (VPD), APD, and the mean intensity of the pectoral muscle (MIP). The datasets comprised different machine vendors and models. In addition, the controls dataset was used to test for the association of our measures against rs10995190, in the ZNF365 gene, a genetic variant known to be associated with mammography density and breast cancer risk. RESULTS: MIP was associated with breast cancer risk [per SD OR, 0.811; 95% confidence interval (CI), 0.707-0.930; P = 0.0028] after adjusting for conventional covariates and VPD. It was also associated with the genetic variant rs10995190 after adjusting for VPD and other covariates (per allele effect = 0.111; 95% CI, 0.053-0.170; P = 1.8 × 10(-4)). Results were similar when adjusting for APD instead of VPD. CONCLUSION: MIP is a novel mammographic marker, which is associated with breast cancer risk and the genetic variant rs10995190 independently of PD measures. IMPACT: Inclusion of MIP in risk models should be considered for studies using PD from FFDM.
Assuntos
Neoplasias da Mama/diagnóstico , Mama/patologia , Glândulas Mamárias Humanas/anormalidades , Mamografia/métodos , Músculos Peitorais/diagnóstico por imagem , Músculos Peitorais/patologia , Densidade da Mama , Neoplasias da Mama/etiologia , Estudos de Casos e Controles , Feminino , Seguimentos , Humanos , Pessoa de Meia-Idade , Estadiamento de Neoplasias , Prognóstico , Estudos Prospectivos , Intensificação de Imagem Radiográfica/métodos , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Medição de Risco , Fatores de RiscoRESUMO
PURPOSE: To compare tumor characteristics and risk factors of interval breast cancers and screen-detected breast cancers, taking mammographic density into account. PATIENTS AND METHODS: Women diagnosed with invasive breast cancer from 2001 to 2008 in Stockholm, Sweden, with data on tumor characteristics (n = 4,091), risk factors, and mammographic density (n = 1,957) were included. Logistic regression was used to compare interval breast cancers with screen-detected breast cancers, overall and by highest and lowest quartiles of percent mammographic density. RESULTS: Compared with screen-detected breast cancers, interval breast cancers in nondense breasts (≤ 20% mammographic density) were significantly more likely to exhibit lymph node involvement (odds ratio [OR], 3.55; 95% CI, 1.74 to 7.13) and to be estrogen receptor negative (OR, 4.05; 95% CI, 2.24 to 7.25), human epidermal growth factor receptor 2 positive (OR, 5.17; 95% CI, 1.64 to 17.01), progesterone receptor negative (OR, 2.63; 95% CI, 1.58 to 4.38), and triple negative (OR, 5.33; 95% CI, 1.21 to 22.46). In contrast, interval breast cancers in dense breasts (> 40.9% mammographic density) were less aggressive than interval breast cancers in nondense breasts (overall difference, P = .008) and were phenotypically more similar to screen-detected breast cancers. Risk factors differentially associated with interval breast cancer relative to screen-detected breast cancer after adjusting for age and mammographic density were family history of breast cancer (OR, 1.32; 95% CI, 1.02 to 1.70), current use of hormone replacement therapy (HRT; OR, 1.84; 95% CI, 1.38 to 2.44), and body mass index more than 25 kg/m(2) (OR, 0.49; 95% CI, 0.29 to 0.82). CONCLUSION: Interval breast cancers in women with low mammographic density have the most aggressive phenotype. The effect of HRT on interval breast cancer risk is not fully explained by mammographic density. Family history is associated with interval breast cancers, possibly indicating disparate genetic background of screen-detected breast cancers and interval breast cancers.
Assuntos
Neoplasias da Mama/diagnóstico por imagem , Neoplasias da Mama/diagnóstico , Glândulas Mamárias Humanas/anormalidades , Mamografia/métodos , Adulto , Idoso , Mama/patologia , Densidade da Mama , Neoplasias da Mama/epidemiologia , Detecção Precoce de Câncer/métodos , Reações Falso-Negativas , Feminino , Terapia de Reposição Hormonal , Humanos , Modelos Logísticos , Pessoa de Meia-Idade , Razão de Chances , Fenótipo , Prognóstico , Receptores de Estrogênio/metabolismo , Sistema de Registros , Fatores de Risco , SuéciaRESUMO
BACKGROUND: Mammographic density is a strong risk factor for breast cancer. METHODS: We present a novel approach to enhance area density measures that takes advantage of the relative density of the pectoral muscle that appears in lateral mammographic views. We hypothesized that the grey scale of film mammograms is normalized to volume breast density but not pectoral density and thus pectoral density becomes an independent marker of volumetric density. RESULTS: From analysis of data from a Swedish case-control study (1,286 breast cancer cases and 1,391 control subjects, ages 50-75 years), we found that the mean intensity of the pectoral muscle (MIP) was highly associated with breast cancer risk [per SD: OR = 0.82; 95% confidence interval (CI), 0.75-0.88; P = 6 × 10(-7)] after adjusting for a validated computer-assisted measure of percent density (PD), Cumulus. The area under curve (AUC) changed from 0.600 to 0.618 due to using PD with the pectoral muscle as reference instead of a standard area-based PD measure. We showed that MIP is associated with a genetic variant known to be associated with mammographic density and breast cancer risk, rs10995190, in a subset of women with genetic data. We further replicated the association between MIP and rs10995190 in an additional cohort of 2,655 breast cancer cases (combined P = 0.0002). CONCLUSIONS: MIP is a marker of volumetric density that can be used to complement area PD in mammographic density studies and breast cancer risk assessment. IMPACT: Inclusion of MIP in risk models should be considered for studies using area PD from analog films.
Assuntos
Neoplasias da Mama/diagnóstico , Glândulas Mamárias Humanas/anormalidades , Mamografia/métodos , Músculos Peitorais/diagnóstico por imagem , Intensificação de Imagem Radiográfica/métodos , Idoso , Área Sob a Curva , Densidade da Mama , Neoplasias da Mama/genética , Proteínas de Ligação a DNA/genética , Feminino , Genótipo , Humanos , Pessoa de Meia-Idade , Polimorfismo de Nucleotídeo Único , Curva ROC , Interpretação de Imagem Radiográfica Assistida por Computador , Fatores de Risco , Fatores de Transcrição/genéticaRESUMO
INTRODUCTION: Mammographic density, the white radiolucent part of a mammogram, is a marker of breast cancer risk and mammographic sensitivity. There are several means of measuring mammographic density, among which are area-based and volumetric-based approaches. Current volumetric methods use only unprocessed, raw mammograms, which is a problematic restriction since such raw mammograms are normally not stored. We describe fully automated methods for measuring both area and volumetric mammographic density from processed images. METHODS: The data set used in this study comprises raw and processed images of the same view from 1462 women. We developed two algorithms for processed images, an automated area-based approach (CASAM-Area) and a volumetric-based approach (CASAM-Vol). The latter method was based on training a random forest prediction model with image statistical features as predictors, against a volumetric measure, Volpara, for corresponding raw images. We contrast the three methods, CASAM-Area, CASAM-Vol and Volpara directly and in terms of association with breast cancer risk and a known genetic variant for mammographic density and breast cancer, rs10995190 in the gene ZNF365. Associations with breast cancer risk were evaluated using images from 47 breast cancer cases and 1011 control subjects. The genetic association analysis was based on 1011 control subjects. RESULTS: All three measures of mammographic density were associated with breast cancer risk and rs10995190 (p<0.025 for breast cancer risk and p<1 × 10(-6) for rs10995190). After adjusting for one of the measures there remained little or no evidence of residual association with the remaining density measures (p>0.10 for risk, p>0.03 for rs10995190). CONCLUSIONS: Our results show that it is possible to obtain reliable automated measures of volumetric and area mammographic density from processed digital images. Area and volumetric measures of density on processed digital images performed similar in terms of risk and genetic association.
Assuntos
Neoplasias da Mama/diagnóstico por imagem , Processamento de Imagem Assistida por Computador/métodos , Mamografia/métodos , Adulto , Idoso , Neoplasias da Mama/genética , Proteínas de Ligação a DNA/genética , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Fatores de Risco , Fatores de Transcrição/genéticaRESUMO
By adapting OPT to include the capability of imaging in the near infrared (NIR) spectrum, we here illustrate the possibility to image larger bodies of pancreatic tissue, such as the rat pancreas, and to increase the number of channels (cell types) that may be studied in a single specimen. We further describe the implementation of a number of computational tools that provide: 1/ accurate positioning of a specimen's (in our case the pancreas) centre of mass (COM) at the axis of rotation (AR); 2/ improved algorithms for post-alignment tuning which prevents geometric distortions during the tomographic reconstruction and 3/ a protocol for intensity equalization to increase signal to noise ratios in OPT-based BCM determinations. In addition, we describe a sample holder that minimizes the risk for unintentional movements of the specimen during image acquisition. Together, these protocols enable assessments of BCM distribution and other features, to be performed throughout the volume of intact pancreata or other organs (e.g. in studies of islet transplantation), with a resolution down to the level of individual islets of Langerhans.
Assuntos
Diabetes Mellitus Experimental/patologia , Células Secretoras de Insulina/patologia , Espectroscopia de Luz Próxima ao Infravermelho/métodos , Tomografia Óptica/métodos , Animais , Camundongos , RatosRESUMO
Since it was first presented in 2002, optical projection tomography (OPT) has emerged as a powerful tool for the study of biomedical specimen on the mm to cm scale. In this paper, we present computational tools to further improve OPT image acquisition and tomographic reconstruction. More specifically, these methods provide: semi-automatic and precise positioning of a sample at the axis of rotation and a fast and robust algorithm for determination of postalignment values throughout the specimen as compared to existing methods. These tools are easily integrated for use with current commercial OPT scanners and should also be possible to implement in "home made" or experimental setups for OPT imaging. They generally contribute to increase acquisition speed and quality of OPT data and thereby significantly simplify and improve a number of three-dimensional and quantitative OPT based assessments.
Assuntos
Algoritmos , Artefatos , Processamento de Imagem Assistida por Computador/métodos , Tomografia Óptica/métodos , Animais , Feminino , Insulina/química , Ilhotas Pancreáticas/metabolismo , Camundongos , Camundongos Endogâmicos C57BL , Modelos Teóricos , Imagens de FantasmasRESUMO
Optical projection tomography (OPT) imaging is a powerful tool for three-dimensional imaging of gene and protein distribution patterns in biomedical specimens. We have previously demonstrated the possibility, by this technique, to extract information of the spatial and quantitative distribution of the islets of Langerhans in the intact mouse pancreas. In order to further increase the sensitivity of OPT imaging for this type of assessment, we have developed a protocol implementing a computational statistical approach: contrast limited adaptive histogram equalization (CLAHE). We demonstrate that this protocol significantly increases the sensitivity of OPT imaging for islet detection, helps preserve islet morphology and diminish subjectivity in thresholding for tomographic reconstruction. When applied to studies of the pancreas from healthy C57BL/6 mice, our data reveal that, at least in this strain, the pancreas harbors substantially more islets than has previously been reported. Further, we provide evidence that the gastric, duodenal and splenic lobes of the pancreas display dramatic differences in total and relative islet and ß-cell mass distribution. This includes a 75% higher islet density in the gastric lobe as compared to the splenic lobe and a higher relative volume of insulin producing cells in the duodenal lobe as compared to the other lobes. Altogether, our data show that CLAHE substantially improves OPT based assessments of the islets of Langerhans and that lobular origin must be taken into careful consideration in quantitative and spatial assessments of the pancreas.