MLIR Lattner, Chris; Amini, Mehdi; Bondhugula, Uday ...
2021 IEEE/ACM International Symposium on Code Generation and Optimization (CGO),
02/2021
Conference Proceeding
This work presents MLIR, a novel approach to building reusable and extensible compiler infrastructure. MLIR addresses software fragmentation, compilation for heterogeneous hardware, significantly ...reducing the cost of building domain specific compilers, and connecting existing compilers together.
MLIR facilitates the design and implementation of code generators, translators and optimizers at different levels of abstraction and across application domains, hardware targets and execution environments. The contribution of this work includes (1) discussion of MLIR as a research artifact, built for extension and evolution, while identifying the challenges and opportunities posed by this novel design, semantics, optimization specification, system, and engineering. (2) evaluation of MLIR as a generalized infrastructure that reduces the cost of building compilers---describing diverse use-cases to show research and educational opportunities for future programming languages, compilers, execution environments, and computer architecture. The paper also presents the rationale for MLIR, its original design principles, structures and semantics.
In blocky and layered rock slopes, toppling failure is a conventional type of instability which may occur in mining and civil engineering. If this kind of slope failure happens as a consequence of ...another type of failure, it is mentioned to as secondary toppling failure. “slide-toe-toppling” is a kind of secondary toppling failures, where the toe part of the slope is toppled as a consequence of a semi or non-circular sliding failure at the upper of the slope. This failure has been studied using physical modelling and analytical method. In the present study, firstly a brief review of the toppling failure in rock slopes is summarized, and the mechanism of slide-toe-toppling failure is described. Then, this failure is examined through a series of numerical modelling. Distinct element method (UDEC software) and finite element method (Phase2 software) were used in this research. Three types of slide-toe-toppling failures, including flexural, blocky, and block-flexural, are simulated. Comparison between two numerical modellings (distinct element and finite element methods) with the result of pre-existing physical models and analytical solution, illustrates that UDEC software has a better agreement than Phase2 software. This accordance indicates that this numerical code is well capable to analyze the behavior of slide-toe-toppling failure.
We focus on reviewing state-of-the-art developments of dedicated PET scanners with irregular geometries and the potential of different aspects of multifunctional PET imaging. First, we discuss ...advances in non-conventional PET detector geometries. Then, we present innovative designs of organ-specific dedicated PET scanners for breast, brain, prostate, and cardiac imaging. We will also review challenges and possible artifacts by image reconstruction algorithms for PET scanners with irregular geometries, such as non-cylindrical and partial angular coverage geometries and how they can be addressed. Then, we attempt to address some open issues about cost/benefits analysis of dedicated PET scanners, how far are the theoretical conceptual designs from the market/clinic, and strategies to reduce fabrication cost without compromising performance.
To investigate the impact of harmonization on the performance of CT, PET, and fused PET/CT radiomic features toward the prediction of mutations status, for epidermal growth factor receptor (EGFR) and ...Kirsten rat sarcoma viral oncogene (KRAS) genes in non-small cell lung cancer (NSCLC) patients.
Radiomic features were extracted from tumors delineated on CT, PET, and wavelet fused PET/CT images obtained from 136 histologically proven NSCLC patients. Univariate and multivariate predictive models were developed using radiomic features before and after ComBat harmonization to predict EGFR and KRAS mutation statuses. Multivariate models were built using minimum redundancy maximum relevance feature selection and random forest classifier. We utilized 70/30% splitting patient datasets for training/testing, respectively, and repeated the procedure 10 times. The area under the receiver operator characteristic curve (AUC), accuracy, sensitivity, and specificity were used to assess model performance. The performance of the models (univariate and multivariate), before and after ComBat harmonization was compared using statistical analyses.
While the performance of most features in univariate modeling was significantly improved for EGFR prediction, most features did not show any significant difference in performance after harmonization in KRAS prediction. Average AUCs of all multivariate predictive models for both EGFR and KRAS were significantly improved (q-value < 0.05) following ComBat harmonization. The mean ranges of AUCs increased following harmonization from 0.87–0.90 to 0.92–0.94 for EGFR, and from 0.85–0.90 to 0.91–0.94 for KRAS. The highest performance was achieved by harmonized F_R0.66_W0.75 model with AUC of 0.94, and 0.93 for EGFR and KRAS, respectively.
Our results demonstrated that regarding univariate modelling, while ComBat harmonization had generally a better impact on features for EGFR compared to KRAS status prediction, its effect is feature-dependent. Hence, no systematic effect was observed. Regarding the multivariate models, ComBat harmonization significantly improved the performance of all radiomics models toward more successful prediction of EGFR and KRAS mutation statuses in lung cancer patients. Thus, by eliminating the batch effect in multi-centric radiomic feature sets, harmonization is a promising tool for developing robust and reproducible radiomics using vast and variant datasets.
Display omitted
•We examine the impact of harmonization on multimodality PET/CT radiomics for EGFR and KRAS mutation prediction in NSCLC.•Harmonization had overall a better impact on features for EGFR prediction compared to KRAS, in univariate analysis.•Harmonization effect is feature dependent without a systematic effect on performance, in univariate analysis.•Harmonization significantly improved the performance of multivariate models for EGFR and KRAS mutation prediction.•Harmonization is promising for batch-effect elimination, for robust and reproducible biological status capturing.
The aim of this work is to investigate the applicability of radiomic features alone and in combination with clinical information for the prediction of renal cell carcinoma (RCC) patients’ overall ...survival after partial or radical nephrectomy. Clinical studies of 210 RCC patients from The Cancer Imaging Archive (TCIA) who underwent either partial or radical nephrectomy were included in this study. Regions of interest (ROIs) were manually defined on CT images. A total of 225 radiomic features were extracted and analyzed along with the 59 clinical features. An elastic net penalized Cox regression was used for feature selection. Accelerated failure time (AFT) with the shared frailty model was used to determine the effects of the selected features on the overall survival time. Eleven radiomic and twelve clinical features were selected based on their non-zero coefficients. Tumor grade, tumor malignancy, and pathology t-stage were the most significant predictors of overall survival (OS) among the clinical features (
p
< 0.002, < 0.02, and < 0.018, respectively). The most significant predictors of OS among the selected radiomic features were flatness, area density, and median (
p
< 0.02, < 0.02, and < 0.05, respectively). Along with important clinical features, such as tumor heterogeneity and tumor grade, imaging biomarkers such as tumor flatness, area density, and median are significantly correlated with OS of RCC patients.
This study aimed to investigate the value of clinical, radiomic features extracted from gross tumor volumes (GTVs) delineated on CT images, dose distributions (Dosiomics), and fusion of CT and dose ...distributions to predict outcomes in head and neck cancer (HNC) patients.
A cohort of 240 HNC patients from five different centers was obtained from The Cancer Imaging Archive. Seven strategies, including four non-fusion (Clinical, CT, Dose, DualCT-Dose), and three fusion algorithms (latent low-rank representation referred (LLRR),Wavelet, weighted least square (WLS)) were applied. The fusion algorithms were used to fuse the pre-treatment CT images and 3-dimensional dose maps. Overall, 215 radiomics and Dosiomics features were extracted from the GTVs, alongside with seven clinical features incorporated. Five feature selection (FS) methods in combination with six machine learning (ML) models were implemented. The performance of the models was quantified using the concordance index (CI) in one-center-leave-out 5-fold cross-validation for overall survival (OS) prediction considering the time-to-event.
The mean CI and Kaplan-Meier curves were used for further comparisons. The CoxBoost ML model using the Minimal Depth (MD) FS method and the glmnet model using the Variable hunting (VH) FS method showed the best performance with CI = 0.73 ± 0.15 for features extracted from LLRR fused images. In addition, both glmnet-Cindex and Coxph-Cindex classifiers achieved a CI of 0.72 ± 0.14 by employing the dose images (+ incorporated clinical features) only.
Our results demonstrated that clinical features, Dosiomics and fusion of dose and CT images by specific ML-FS models could predict the overall survival of HNC patients with acceptable accuracy. Besides, the performance of ML methods among the three different strategies was almost comparable.
Evaluation of blocky or layered rock slopes against toppling failures has remained of great concern for engineers in various rock mechanics projects. Several step-by-step analytical solutions have ...been developed for analyzing these types of slope failures. However, manual application of these analytical solutions for real case studies can be time-consuming, complicated, and in certain cases even impossible. This study will first examine existing methods for toppling failure analyses that are reviewed, modified and generalized to consider the effects of a wide range of external and dead loads on slope stability. Next, based on the generalized presented formulae, a Windows form computer code is programmed using Visual C# for analysis of common types of toppling failures. Input parameters, including slope geometry, joint sets parameters, rock and soil properties, ground water level, dynamic loads, support anchor loads as well as magnitudes and forms of external forces, are first loaded into the code. The input data are then saved and used to graphically draw the slope model. This is followed by automatic identification of the toppling failure mode and a deterministic analysis of the slope stability against this failure mode. The results are presented using a graphical approach. The developed code allows probabilistic introduction of the input parameters via probability distribution functions (PDFs) and thus a probabilistic analysis of the toppling failure modes using Monte-Carlo simulation technique. This allows calculation of the probability of slope failure. Finally, several published case studies and typical examples are analyzed with the developed code. The outcomes are compared with those of the main references to assess the performance and robustness of the developed computer code. The comparisons demonstrate good agreement between the results.
Abstract
This study aimed to investigate the diagnostic performance of machine learning-based radiomics analysis to diagnose coronary artery disease status and risk from rest/stress Myocardial ...Perfusion Imaging (MPI) single-photon emission computed tomography (SPECT). A total of 395 patients suspicious of coronary artery disease who underwent 2-day stress-rest protocol MPI SPECT were enrolled in this study. The left ventricle myocardium, excluding the cardiac cavity, was manually delineated on rest and stress images to define a volume of interest. Added to clinical features (age, sex, family history, diabetes status, smoking, and ejection fraction), a total of 118 radiomics features, were extracted from rest and stress MPI SPECT images to establish different feature sets, including Rest-, Stress-, Delta-, and Combined-radiomics (all together) feature sets. The data were randomly divided into 80% and 20% subsets for training and testing, respectively. The performance of classifiers built from combinations of three feature selections, and nine machine learning algorithms was evaluated for two different diagnostic tasks, including 1) normal/abnormal (no CAD vs. CAD) classification, and 2) low-risk/high-risk CAD classification. Different metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE), were reported for models’ evaluation. Overall, models built on the Stress feature set (compared to other feature sets), and models to diagnose the second task (compared to task 1 models) revealed better performance. The Stress-mRMR-KNN (feature set-feature selection-classifier) reached the highest performance for task 1 with AUC, ACC, SEN, and SPE equal to 0.61, 0.63, 0.64, and 0.6, respectively. The Stress-Boruta-GB model achieved the highest performance for task 2 with AUC, ACC, SEN, and SPE of 0.79, 0.76, 0.75, and 0.76, respectively. Diabetes status from the clinical feature family, and dependence count non-uniformity normalized, from the NGLDM family, which is representative of non-uniformity in the region of interest were the most frequently selected features from stress feature set for CAD risk classification. This study revealed promising results for CAD risk classification using machine learning models built on MPI SPECT radiomics. The proposed models are helpful to alleviate the labor-intensive MPI SPECT interpretation process regarding CAD status and can potentially expedite the diagnostic process.
The potential release of pollutants from a low-grade ore dump in the Miduk mine was evaluated based on geochemical and mineralogical characteristics. The main environmental risks associated with the ...dump were the potential for acid mine drainage (AMD) generation and the transport of acidic leachate with high contents of toxic elements (As, Pb, Cu and Zn) into the depths of Earth. Geochemical characteristics of rocks such as the content of sulphur species (S
total
, S
pyrite
and S
sulphate
) were assessed. In addition, the elemental composition of the rock and leaching solution samples were determined. Based on both static and NAG tests, materials with a paste pH < 4 had the high potential of AMD generation. Principal component analysis (PCA) was employed to integrate the results of AMD prediction tests with mineralogical and geochemical compositions of the rocks. Based on PCA, eight principal components (PC1–PC8) were accounted for 93% of the total variance of data. Two components of PC2 and PC3 were determined as primary factors of AMD generation. The extracted principal components were interpolated within the dump by ordinary kriging method. Based on the environmental risk map of the PC3, the main source of AMD generation is the north-eastern part of the dump, which spatially varied from the dump surface up to a depth of 3 m. Heterogeneous distribution of preferential paths by providing different oxygen and moisture contents is responsible for non-uniform pyrite oxidation at different parts of the dump. The results of the present study will provide useful information for further rock dump management approaches.
Electrokinetic remediation is a cost-effective and efficient method that utilizes electrical current to transport ions within the subsurface. This process aims to remediate soil contamination caused ...by industrial activities, which poses threats to wildlife, water quality, and air quality. To assess the impact of the electrokinetic process on tank leaching efficiency, two electrode configurations were tested: vertical and horizontal arrays. These tests considered variable electrode spacing and different voltages in the soil residue. Additionally, the movement of copper cations from the anode to the cathode under this process was investigated. Results show that the horizontal electrode array is more effective in transporting soil moisture because of its broader contact with the soil. After 20 days of using the electrokinetic method with vertical electrodes, the soil moisture content decreased by 12.28%; with horizontal electrodes, it dropped by 38.4%. Also, the concentration of copper in the soil near the cathode electrode increased from 0.54 to 0.77% after 20 days. The estimated copper ion content in the cathode area after 20 days was between 150 and 350 mol/m3, aligning closely with the measured value of 192.5 mol/m3. These results indicate that the electrokinetic process can significantly enhance copper recovery efficiency in tank leaching processes and curtail environmental side effects. Overall, this study provides valuable insights into the benefits of using the electrokinetic process to remediate leaching residue and improve the efficiency of industrial processes.