Search

Background Earlier we have shown that high frequency of acinar cells in the pancreatic transsection line predicts postoperative pancreatic fistula after pancreaticoduodenectomy (PD). Acinar cell count method (ACM) is fast to perform during operation. In this study our aim was to validate the accuracy of ACM to compare it with other published risk prediction methods. Methods 87 patients who underwent PD without any trial including perioperative medications were collected from a single hospital. Data on demographics, surgical details, postoperative complications clinically relevant pancreatic fistulae (CR-POPF) and clinically relevant Clavien-Dindo complications (CR-CDC) were registered. Thirteen previously published risk prediction methods were included in the comparison, such as pancreatic duct diameter, palpable texture of pancreas, Braga score (BC), Fistula Risk Score, Modified Fistula Risk Score, Alternative Fistula Risk Score and multiple radiological parameters. ROC-curves were calculated to compare sensitivity and specificity for identifying high risk patients for CR-POPF and CR-CDC. Results The three most accurate risk prediction methods for CR-POPF were ACM (sensitivity 88.9%, specificity 52.6%; p = 0.043), BC (87.5%, 56.6%; p = 0.039) and visceral fat area to subcutaneous fat area ratio (75.5%, 80.0%; p = 0.032). In predicting CR-CDC the three most accurate methods were ACM (73.9%, 56.2%; p = 0.033), BC (68.4%, 59.5%; p = 0.036) and TPAI (78.3%, 41.7%; p = 0.012). Conclusion ACM was shown to be as good as the more complicated risk scoring methods in the prediction of CR-POPF. It was good also in predicting all clinically relevant complications. ACM is easy to use during operation and can be recommended as a routine risk prediction method.

Computerized parenchymal analysis has shown potential to be utilized as an imaging biomarker to estimate the risk of breast cancer. Parenchymal analysis of digital mammograms is based on the extraction of computerized measures to build machine learning-based models for the prediction of breast cancer risk. However, the choice of the region of interest (ROI) for feature extraction within the breast remains an open problem. In this work we perform a comparison between five different methods suggested in the literature for automated ROI selection, including the whole breast (WB), the maximum squared (MS), the retro-areolar region (RA), the lattice-based (LB), and the polar-based (PB) selection methods. For the experiments, we built a retrospective dataset of 896 screening mammograms from 224 women (112 cases and 112 healthy controls). The performance of each ROI selection method was measured in terms of the area under the curve (AUC) values. The AUC values varied between 0.55 and 0.79 depending on the method and experimental settings. The best performance on an independent test set was achieved by the MS method (AUC of 0.59, 95% CI: 0.55-0.64). This method is fully-automated and does not require adjusting hyper-parameters. Based on our results, we prompt the use of the MS method for ROI selection in the computerized parenchymal analysis for breast cancer risk assessment.

Purpose To assess the association between breast cancer risk and mammographic parenchymal measures obtained using a fully-automated, publicly available software, OpenBreast. Methods This retrospective case-control study involved screening mammograms of asymptomatic women diagnosed with breast cancer between 2016 and 2017. The 114 cases were matched with corresponding healthy controls by birth and screening years and the mammographic system used. Parenchymal analysis was performed using OpenBreast, a software implementing a computerized parenchymal analysis algorithm. Breast percent density was measured with an interactive thresholding method. The parenchymal measures were Box-Cox transformed and adjusted for age and percent density. Changes in the odds ratio per standard deviation (OPERA) with 95% confidence intervals (CIs) and the area under the ROC curve (AUC) for parenchymal measures and percent densities were used to evaluate the discrimination between cases and controls. Differences in AUCs were assessed using DeLong’s test. Results The adjusted OPERA value of parenchymal measures was 2.49 (95% CI: 1.79–3.47). Parenchymal measures using OpenBreast were more accurate (AUC = 0.779) than percent density (AUC = 0.609) in discriminating between cases and controls (p Conclusions Parenchymal measures obtained with the evaluated software were positively associated with breast cancer risk and were more accurate than percent density in the prediction of risk.

Breast density has been identified as one of the strongest risk factors for breast cancer. However, the development of reliable and reproducible methods for the automatic dense tissue segmentation has been an important challenge. Due to the complexity of the acquisition process of mammography images, current approaches need to be calibrated for specific mammographic systems or require access to raw mammograms. In this work, we introduce the Morphological Area Gradient (MAG) as a generic measure for mammography images. MAG is generic in the sense that it does not need calibration or access to raw mammograms. At the core of MAG is the derivative of the area of segmented tissue with respect to the pixel intensity. We have found that the high-density regions can be automatically segmented by minimizing the MAG of a mammogram. To verify the performance of MAG, we collected 566 full-field digital mammograms using two different medical devices and a human expert manually annotated the high-density regions in each image. The proposed MAG method yields a median absolute error of 7.6% and a Dices similarity coefficient of 0.83, which are superior to other clinically validated state-of-the-art algorithms.

Mammography is one of the main diagnostic tools for the breast and is increasingly utilized for breast cancer risk assessment. Recently, parenchymal analysis has emerged as a computational tool that works by extracting imaging features from mammograms in order to infer the level of risk of a patient. In standard screening mammography, two views for each breast are obtained: the cranio-caudal (CC) and the medio-lateral oblique (MLO) views. However, to the best of our knowledge, the question of whether the choice of a given view can influence the performance of parenchymal analysis has not been researched in the literature. The aim of this work is to evaluate the utilization of different views for risk estimation based on the computerized analysis of parenchymal patterns in mammography images. We implemented a parenchymal analysis method and tested it on a sample of 228 women in a retrospective case/control study. Based on the obtained results we support the use of the CC view for parenchymal analysis since this reduces computational cost without affecting performance.

Background Few of the structural changes caused by Parkinson’s disease (PD) are visible in magnetic resonance imaging (MRI) with visual inspection but there is a need for a method capable of observing the changes beyond the human eye. Texture analysis offers a technique that enables the quantification of the image gray-level patterns. Purpose To investigate the value of quantitative image texture analysis method in diagnosis and follow-up of PD patients. Material and Methods Twenty-six PD patients underwent MRI at baseline and after 2 years of follow-up. Four co-occurrence matrix-based texture parameters, describing the image homogeneity and complexity, were calculated within clinically interesting areas of the brain. In addition, correlations with clinical characteristics (Unified Parkinson’s Disease Ranking Scales I–III and Mini-Mental State Examination score) along with a comparison to healthy controls were evaluated. Results Patients at baseline and healthy volunteers differed in their brain MR image textures mostly in the areas of substantia nigra pars compacta, dentate nucleus, and basilar pons. During the 2-year follow-up of the patients, textural differences appeared mainly in thalamus and corona radiata. Texture parameters in all the above mentioned areas were also found to be significantly related to clinical scores describing the severity of PD. Conclusion Texture analysis offers a quantitative method for detecting structural changes in brain MR images. However, the protocol and repeatability of the method must be enhanced before possible clinical use.