|
Zhen Xu, Sergio Escalera, Adrien Pavao, Magali Richard, Wei-Wei Tu, Quanming Yao, et al. (2022). Codabench: Flexible, easy-to-use, and reproducible meta-benchmark platform. PATTERNS - Patterns, 3(7), 100543.
Abstract: Obtaining a standardized benchmark of computational methods is a major issue in data-science communities. Dedicated frameworks enabling fair benchmarking in a unified environment are yet to be developed. Here, we introduce Codabench, a meta-benchmark platform that is open sourced and community driven for benchmarking algorithms or software agents versus datasets or tasks. A public instance of Codabench is open to everyone free of charge and allows benchmark organizers to fairly compare submissions under the same setting (software, hardware, data, algorithms), with custom protocols and data formats. Codabench has unique features facilitating easy organization of flexible and reproducible benchmarks, such as the possibility of reusing templates of benchmarks and supplying compute resources on demand. Codabench has been used internally and externally on various applications, receiving more than 130 users and 2,500 submissions. As illustrative use cases, we introduce four diverse benchmarks covering graph machine learning, cancer heterogeneity, clinical diagnosis, and reinforcement learning.
Keywords: Machine learning; data science; benchmark platform; reproducibility; competitions
|
|
|
Eloi Puertas, Sergio Escalera, & Oriol Pujol. (2015). Generalized Multi-scale Stacked Sequential Learning for Multi-class Classification. PAA - Pattern Analysis and Applications, 18(2), 247–261.
Abstract: In many classification problems, neighbor data labels have inherent sequential relationships. Sequential learning algorithms take benefit of these relationships in order to improve generalization. In this paper, we revise the multi-scale sequential learning approach (MSSL) for applying it in the multi-class case (MMSSL). We introduce the error-correcting output codesframework in the MSSL classifiers and propose a formulation for calculating confidence maps from the margins of the base classifiers. In addition, we propose a MMSSL compression approach which reduces the number of features in the extended data set without a loss in performance. The proposed methods are tested on several databases, showing significant performance improvement compared to classical approaches.
Keywords: Stacked sequential learning; Multi-scale; Error-correct output codes (ECOC); Contextual classification
|
|
|
Mohammad Ali Bagheri, Qigang Gao, & Sergio Escalera. (2015). Combining Local and Global Learners in the Pairwise Multiclass Classification. PAA - Pattern Analysis and Applications, 18(4), 845–860.
Abstract: Pairwise classification is a well-known class binarization technique that converts a multiclass problem into a number of two-class problems, one problem for each pair of classes. However, in the pairwise technique, nuisance votes of many irrelevant classifiers may result in a wrong class prediction. To overcome this problem, a simple, but efficient method is proposed and evaluated in this paper. The proposed method is based on excluding some classes and focusing on the most probable classes in the neighborhood space, named Local Crossing Off (LCO). This procedure is performed by employing a modified version of standard K-nearest neighbor and large margin nearest neighbor algorithms. The LCO method takes advantage of nearest neighbor classification algorithm because of its local learning behavior as well as the global behavior of powerful binary classifiers to discriminate between two classes. Combining these two properties in the proposed LCO technique will avoid the weaknesses of each method and will increase the efficiency of the whole classification system. On several benchmark datasets of varying size and difficulty, we found that the LCO approach leads to significant improvements using different base learners. The experimental results show that the proposed technique not only achieves better classification accuracy in comparison to other standard approaches, but also is computationally more efficient for tackling classification problems which have a relatively large number of target classes.
Keywords: Multiclass classification; Pairwise approach; One-versus-one
|
|
|
Frederic Sampedro, Anna Domenech, & Sergio Escalera. (2014). Obtaining quantitative global tumoral state indicators based on whole-body PET/CT scans: A breast cancer case study. NMC - Nuclear Medicine Communications, 35(4), 362–371.
Abstract: Objectives: In this work we address the need for the computation of quantitative global tumoral state indicators from oncological whole-body PET/computed tomography scans. The combination of such indicators with other oncological information such as tumor markers or biopsy results would prove useful in oncological decision-making scenarios.
Materials and methods: From an ordering of 100 breast cancer patients on the basis of oncological state through visual analysis by a consensus of nuclear medicine specialists, a set of numerical indicators computed from image analysis of the PET/computed tomography scan is presented, which attempts to summarize a patient’s oncological state in a quantitative manner taking into consideration the total tumor volume, aggressiveness, and spread.
Results: Results obtained by comparative analysis of the proposed indicators with respect to the experts’ evaluation show up to 87% Pearson’s correlation coefficient when providing expert-guided PET metabolic tumor volume segmentation and 64% correlation when using completely automatic image analysis techniques.
Conclusion: Global quantitative tumor information obtained by whole-body PET/CT image analysis can prove useful in clinical nuclear medicine settings and oncological decision-making scenarios. The completely automatic computation of such indicators would improve its impact as time efficiency and specialist independence would be achieved.
|
|
|
Frederic Sampedro, Anna Domenech, Sergio Escalera, & Ignasi Carrio. (2015). Deriving global quantitative tumor response parameters from 18F-FDG PET-CT scans in patients with non-Hodgkins lymphoma. NMC - Nuclear Medicine Communications, 36(4), 328–333.
Abstract: OBJECTIVES:
The aim of the study was to address the need for quantifying the global cancer time evolution magnitude from a pair of time-consecutive positron emission tomography-computed tomography (PET-CT) scans. In particular, we focus on the computation of indicators using image-processing techniques that seek to model non-Hodgkin's lymphoma (NHL) progression or response severity.
MATERIALS AND METHODS:
A total of 89 pairs of time-consecutive PET-CT scans from NHL patients were stored in a nuclear medicine station for subsequent analysis. These were classified by a consensus of nuclear medicine physicians into progressions, partial responses, mixed responses, complete responses, and relapses. The cases of each group were ordered by magnitude following visual analysis. Thereafter, a set of quantitative indicators designed to model the cancer evolution magnitude within each group were computed using semiautomatic and automatic image-processing techniques. Performance evaluation of the proposed indicators was measured by a correlation analysis with the expert-based visual analysis.
RESULTS:
The set of proposed indicators achieved Pearson's correlation results in each group with respect to the expert-based visual analysis: 80.2% in progressions, 77.1% in partial response, 68.3% in mixed response, 88.5% in complete response, and 100% in relapse. In the progression and mixed response groups, the proposed indicators outperformed the common indicators used in clinical practice [changes in metabolic tumor volume, mean, maximum, peak standardized uptake value (SUV mean, SUV max, SUV peak), and total lesion glycolysis] by more than 40%.
CONCLUSION:
Computing global indicators of NHL response using PET-CT imaging techniques offers a strong correlation with the associated expert-based visual analysis, motivating the future incorporation of such quantitative and highly observer-independent indicators in oncological decision making or treatment response evaluation scenarios.
|
|