Microaneurysm Detection Using Principal Component Analysis and Machine Learning Methods.

Diabetic retinopathy (DR) is an eye abnormality caused by long-term diabetes and it is the most common cause of blindness before the age of 50. Microaneurysms (MAs), resulting from leakage from retinal blood vessels, are early indicators of DR. In this paper, we analyzed MA detectability using small 25 by 25 pixel patches extracted from fundus images in the DIAbetic RETinopathy DataBase - Calibration Level 1 (DIARETDB1). Raw pixel intensities of extracted patches served directly as inputs into the following classifiers: random forest (RF), neural network, and support vector machine. We also explored the use of two techniques (principal component analysis and RF feature importance) for reducing input dimensionality. With traditional machine learning methods and leave-10-patients-out cross validation, our method outperformed a deep learning-based MA detection method, with AUC performance improved from 0.962 to 0.985 and F-measure improved from 0.913 to 0.926, using the same DIARETDB1 database. Furthermore, we validated our method on a different dataset-retinopathy online challenge (ROC) data set. The performance of the three classifiers and the pattern with different percentage of principal components are consistent on the two data sets. Especially, we trained the RF on DIARETDB1 and applied it to ROC; the performance is very similar to that of the RF trained and tested using cross validation on ROC data set. This result indicates that our method has the potential to generalize to different datasets.

Radiogenomics of lower-grade glioma: algorithmically-assessed tumor shape is associated with tumor genomic subtypes and patient outcomes in a multi-institutional study with The Cancer Genome Atlas data.

Recent studies identified distinct genomic subtypes of lower-grade gliomas that could potentially be used to guide patient treatment. This study aims to determine whether there is an association between genomics of lower-grade glioma tumors and patient outcomes using algorithmic measurements of tumor shape in magnetic resonance imaging (MRI). We analyzed preoperative imaging and genomic subtype data from 110 patients with lower-grade gliomas (WHO grade II and III) from The Cancer Genome Atlas. Computer algorithms were applied to analyze the imaging data and provided five quantitative measurements of tumor shape in two and three dimensions. Genomic data for the analyzed cohort of patients consisted of previously identified genomic clusters based on IDH mutation and 1p/19q co-deletion, DNA methylation, gene expression, DNA copy number, and microRNA expression. Patient outcomes were quantified by overall survival. We found that there is a strong association between angular standard deviation (ASD), which measures irregularity of the tumor boundary, and the IDH-1p/19q subtype (p < 0.0017), RNASeq cluster (p < 0.0002), DNA copy number cluster (p < 0.001), and the cluster of clusters (p < 0.0002). The RNASeq cluster was also associated with bounding ellipsoid volume ratio (p < 0.0005). Tumors in the IDH wild type cluster and R2 RNASeq cluster which are associated with much poorer outcomes generally had higher ASD reflecting more irregular shape. ASD also showed association with patient overall survival (p = 0.006). Shape features in MRI were strongly associated with genomic subtypes and patient outcomes in lower-grade glioma.

Algorithmic three-dimensional analysis of tumor shape in MRI improves prognosis of survival in glioblastoma: a multi-institutional study.

In this retrospective, IRB-exempt study, we analyzed data from 68 patients diagnosed with glioblastoma (GBM) in two institutions and investigated the relationship between tumor shape, quantified using algorithmic analysis of magnetic resonance images, and survival. Each patient's Fluid Attenuated Inversion Recovery (FLAIR) abnormality and enhancing tumor were manually delineated, and tumor shape was analyzed by automatic computer algorithms. Five features were automatically extracted from the images to quantify the extent of irregularity in tumor shape in two and three dimensions. Univariate Cox proportional hazard regression analysis was performed to determine how prognostic each feature was of survival. Kaplan Meier analysis was performed to illustrate the prognostic value of each feature. To determine whether the proposed quantitative shape features have additional prognostic value compared with standard clinical features, we controlled for tumor volume, patient age, and Karnofsky Performance Score (KPS). The FLAIR-based bounding ellipsoid volume ratio (BEVR), a 3D complexity measure, was strongly prognostic of survival, with a hazard ratio of 0.36 (95% CI 0.20-0.65), and remained significant in regression analysis after controlling for other clinical factors (P = 0.0061). Three enhancing-tumor based shape features were prognostic of survival independently of clinical factors: BEVR (P = 0.0008), margin fluctuation (P = 0.0013), and angular standard deviation (P = 0.0078). Algorithmically assessed tumor shape is statistically significantly prognostic of survival for patients with GBM independently of patient age, KPS, and tumor volume. This shows promise for extending the utility of MR imaging in treatment of GBM patients.

The impact of time on seizure prediction performance in the FSPEEG database.

We demonstrate evidence that high discriminability between preictal and interictal intracranial electroencephalogram (iEEG) recordings [1,2] of the Freiburg database (FSPEEG) may be due to the amount of time that occurred between recordings, as opposed to the underlying seizure state, i.e., preictal or interictal. After replicating published classification methods and results, we performed two experiments. In the first experiment, almost perfect discriminability between discontinuous interictal recordings and almost perfect discriminability between discontinuous preictal recordings were observed as the amount of time between recordings increased. Further, a second experiment demonstrated that the classification performance for patients with large time gaps between preictal and interictal recordings was noticeably higher than the classification performance for patients with contiguous preictal and interictal files. These results provide evidence that time likely plays a major role in the discriminability of the iEEG features considered in this study, regardless of the underlying seizure state. Feature nonstationarity is present and may, under certain conditions, lead to overestimation or underestimation of the probability of seizure occurrence.

An analysis of resting-state functional transcranial Doppler recordings from middle cerebral arteries.

Functional transcrannial Doppler (fTCD) is used for monitoring the hemodynamics characteristics of major cerebral arteries. Its resting-state characteristics are known only when considering the maximal velocity corresponding to the highest Doppler shift (so called the envelope signals). Significantly more information about the resting-state fTCD can be gained when considering the raw cerebral blood flow velocity (CBFV) recordings. In this paper, we considered simultaneously acquired envelope and raw CBFV signals. Specifically, we collected bilateral CBFV recordings from left and right middle cerebral arteries using 20 healthy subjects (10 females). The data collection lasted for 15 minutes. The subjects were asked to remain awake, stay silent, and try to remain thought-free during the data collection. Time, frequency and time-frequency features were extracted from both the raw and the envelope CBFV signals. The effects of age, sex and body-mass index were examined on the extracted features. The results showed that the raw CBFV signals had a higher frequency content, and its temporal structures were almost uncorrelated. The information-theoretic features showed that the raw recordings from left and right middle cerebral arteries had higher content of mutual information than the envelope signals. Age and body-mass index did not have statistically significant effects on the extracted features. Sex-based differences were observed in all three domains and for both, the envelope signals and the raw CBFV signals. These findings indicate that the raw CBFV signals provide valuable information about the cerebral blood flow which can be utilized in further validation of fTCD as a clinical tool.