Witness identification in multiple instance learning using random subspaces

Carbonneau, Marc‐André; Granger, Éric; Gagnon, Ghyslain

doi:10.1109/icpr.2016.7900199

Cited by 10 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RSIS [30]: This method probabilistically identifies the witnesses in positive bags using a procedure based on random subspacing and clustering introduced in [48]. Training subsets are sampled using the probabilistic labels of the instance to train an ensemble of SVM.…”

Section: Reference Methodsmentioning

confidence: 99%

“…• The performance of MIL algorithms depends on several properties of the data set [15,18,20,21,23,48]. • When it is necessary to model combinations of instances to infer bag labels, bag-level and embedding methods perform better [15,21,49].…”

Section: Studies On Milmentioning

confidence: 99%

“…They found that algorithms yielding best bag classification performance were not the algorithms providing the most consistent instance labels. Carbonneau et al [48] studied the ability to identify witnesses (positive instances) of several MIL methods. They found that depending on the nature of the data, some algorithms perform well while others would have difficulty learning.…”

Section: Studies On Milmentioning

confidence: 99%

See 2 more Smart Citations

Multiple instance learning: A survey of problem characteristics and applications

Carbonneau¹,

Cheplygina²,

Granger³

et al. 2018

Pattern Recognition

Self Cite

542

313

View full text Add to dashboard Cite

Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits various problems and allows to leverage weakly labeled data. Consequently, it has been used in diverse application fields such as computer vision and document classification. However, learning from bags raises important challenges that are unique to MIL. This paper provides a comprehensive survey of the characteristics which define and differentiate the types of MIL problems. Until now, these problem characteristics have not been formally identified and described. As a result, the variations in performance of MIL algorithms from one data set to another are difficult to explain. In this paper, MIL problem characteristics are grouped into four broad categories: the composition of the bags, the types of data distribution, the ambiguity of instance labels, and the task to be performed. Methods specialized to address each category are reviewed. Then, the extent to which these characteristics manifest themselves in key MIL application areas are described. Finally, experiments are conducted to compare the performance of 16 state-of-the-art MIL methods on selected problem characteristics. This paper provides insight on how the problem characteristics affect MIL algorithms, recommendations for future benchmarking and promising avenues for research.

show abstract

Section: Reference Methodsmentioning

confidence: 99%

Section: Studies On Milmentioning

confidence: 99%

Section: Studies On Milmentioning

confidence: 99%

See 1 more Smart Citation

Multiple instance learning: A survey of problem characteristics and applications

Carbonneau¹,

Cheplygina²,

Granger³

et al. 2018

Pattern Recognition

Self Cite

542

313

View full text Add to dashboard Cite

show abstract

“…In addition, including numerous patches not associated with AD can lead to a low proportion of instances containing AD pathological changes in bags labeled as the AD class. This method can cause serious class imbalance problems and degrade performance for many real-world problems 38,39 . Therefore, localizing the brain regions and extracting patches from these regions are important and challenging problems.…”

Section: Introductionmentioning

confidence: 99%

Deep Joint Learning of Pathological Region Localization and Alzheimer's Disease Diagnosis

Park¹,

Suk²

2022

Preprint

View full text Add to dashboard Cite

The identification of Alzheimer's disease (AD) using structural magnetic resonance imaging (sMRI) has been studied based on the subtle morphological changes in the brain. One of the typical approaches is a deep learning-based patch-level feature representation. For this approach, however, the predetermined patches before learning the diagnostic model can limit classification performance. To mitigate this problem, we propose the BrainBagNet with a position-based gate (PG), which applies position information of brain images represented through the 3D coordinates. Our proposed method represents the patch-level class evidence based on both MR scan and position information for image-level prediction. To validate our proposed method, we conducted experiments comparing our methods with state-of-the-art methods and evaluating the robust performances of two publicly available datasets: 1) ADNI and 2) AIBL. Furthermore, our proposed method outperformed classification performance in both AD diagnosis and mild cognitive impairment conversion prediction tasks over the comparative methods and analyzed our results from diverse perspectives. Based on our experimental results, we believe that the proposed method has the potential to provide new insights and perspectives in deep-learning based patch-level feature representation studies. Code is available at: github.com/ku-milab/PG-BrainBagNet.

show abstract

“…In addition, including numerous patches not associated with AD can lead to a low proportion of instances containing AD pathological changes in bags labeled as the AD class. This method can cause serious class imbalance problems and degrade performance for many real-world problems (Carbonneau et al, 2016(Carbonneau et al, , 2018. Therefore, localizing the pathological brain regions and extracting patches from these regions are an important and challenging problems.…”

Section: Introductionmentioning

confidence: 99%

Deep Joint Learning of Pathological Region Localization and Alzheimer's Disease Diagnosis

Park¹,

Suk²

2021

Preprint

View full text Add to dashboard Cite

The identification of Alzheimer's disease (AD) and its early stages using structural magnetic resonance imaging (MRI) has been attracting the attention of researchers. Various data-driven approaches have been introduced to capture subtle and local morphological changes of the brain accompanied by the disease progression.One of the typical approaches for capturing subtle changes is patch-level feature representation. However, the predetermined regions to extract patches can limit classification performance by interrupting the exploration of potential biomarkers. In addition, the existing patch-level analyses have difficulty explaining their decisionmaking because the final decision is made using nonlinear interactions of patch-level feature representations.To address these problems, we propose the BrainBagNet with a position-based gate (PG-BrainBagNet), a framework for jointly learning pathological region localization and AD diagnosis in an end-to-end manner.In advance, as all scans are aligned to a template in image processing, the position of brain images can be represented through the 3D Cartesian space shared by the overall MRI scans. Therefore, we represent coordinates in the 3D Cartesian space containing the volumetric position information of MRI scans by combining positions from the coronal, sagittal, and axial planes. Then, the proposed method represents the patch-level response from whole-brain MRI scans and discriminative brain-region from position information. Based on the outcomes, the patch-level class evidence is calculated, and then the image-level prediction is inferred by a transparent aggregation. The proposed models were evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) datasets (i.e., ADNI-1 and ADNI-2). In five-fold cross-validation, the classification performance of the proposed method outperformed that of the state-of-the-art methods in both AD diagnosis (AD vs. normal control) and mild cognitive impairment (MCI) conversion prediction (progressive MCI vs. stable MCI) tasks. In addition, changes in the identified discriminant regions and patch-level class evidence according to the patch size used for model training are presented and analyzed. Code is available at: github.com/ku-milab/PG-BrainBagNet.

show abstract

Witness identification in multiple instance learning using random subspaces

Cited by 10 publications

References 22 publications

Multiple instance learning: A survey of problem characteristics and applications

Multiple instance learning: A survey of problem characteristics and applications

Deep Joint Learning of Pathological Region Localization and Alzheimer's Disease Diagnosis

Deep Joint Learning of Pathological Region Localization and Alzheimer's Disease Diagnosis

Contact Info

Product

Resources

About