Optimized Fusion of CNNs to Diagnose Pulmonary Diseases on Chest X-Rays

Guarrasi, Valerio; Soda, Paolo

doi:10.1007/978-3-031-06427-2_17

Cited by 2 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first step is to detect which is the subset of models to be combined to get the best multimodal architecture providing the best multimodal data representation. This subset is determined by solving a multi-objective maximization problem that leverages on two scores computed on a validation set for each

[39] , [40] , [41] . The first score is any measure derived from the confusion matrix, shortly referred as

, whilst the second is a measure of the diversity between the unimodal learning models, denoted as

.…”

Section: Methodsmentioning

confidence: 99%

Multi-objective optimization determines when, which and how to fuse deep networks: An application to predict COVID-19 outcomes

Guarrasi

Soda

2023

Computers in Biology and Medicine

View full text Add to dashboard Cite

[39] , [40] , [41] . The first score is any measure derived from the confusion matrix, shortly referred as

, whilst the second is a measure of the diversity between the unimodal learning models, denoted as

.…”

Section: Methodsmentioning

confidence: 99%

Multi-objective optimization determines when, which and how to fuse deep networks: An application to predict COVID-19 outcomes

Guarrasi

Soda

2023

Computers in Biology and Medicine

View full text Add to dashboard Cite

A Multimodal Ensemble Driven by Multiobjective Optimisation to Predict Overall Survival in Non-Small-Cell Lung Cancer

et al. 2022

View full text Add to dashboard Cite

Lung cancer accounts for more deaths worldwide than any other cancer disease. In order to provide patients with the most effective treatment for these aggressive tumours, multimodal learning is emerging as a new and promising field of research that aims to extract complementary information from the data of different modalities for prognostic and predictive purposes. This knowledge could be used to optimise current treatments and maximise their effectiveness. To predict overall survival, in this work, we investigate the use of multimodal learning on the CLARO dataset, which includes CT images and clinical data collected from a cohort of non-small-cell lung cancer patients. Our method allows the identification of the optimal set of classifiers to be included in the ensemble in a late fusion approach. Specifically, after training unimodal models on each modality, it selects the best ensemble by solving a multiobjective optimisation problem that maximises both the recognition performance and the diversity of the predictions. In the ensemble, the labels of each sample are assigned using the majority voting rule. As further validation, we show that the proposed ensemble outperforms the models learning a single modality, obtaining state-of-the-art results on the task at hand.

show abstract

Optimized Fusion of CNNs to Diagnose Pulmonary Diseases on Chest X-Rays

Cited by 2 publications

References 27 publications

Multi-objective optimization determines when, which and how to fuse deep networks: An application to predict COVID-19 outcomes

Multi-objective optimization determines when, which and how to fuse deep networks: An application to predict COVID-19 outcomes

A Multimodal Ensemble Driven by Multiobjective Optimisation to Predict Overall Survival in Non-Small-Cell Lung Cancer

Contact Info

Product

Resources

About