Publicaciones

RL1, Publisher: CEUR Workshop Proceedings, Link>

AUTHORS

Vicente Castro, Hans Löbel, Pablo Pino, Denis Parra, Gregory Schuit

ABSTRACT

This article describes PUC Chile team’s participation in the Concept Detection task of ImageCLEFmedical challenge 2021, which resulted in the team earning the fourth place. We made two submissions, the first one based on a naive approach which resulted in a F-1 score of 0.141, and an improved version which leveraged the Perceptual Similarity among images and obtained a final F-1 score of 0.360. We describe in detail our data analysis, our different approaches, and conclude by discussing some ideas for future work

RL1, Publisher: CLEF2021 Working Notes, CEUR Workshop Proceedings, Link>

AUTHORS

Hans Löbel, Pablo Pino, Vicente Castro, Denis Parra

ABSTRACT

This article describes PUC Chile team’s participation in the Caption Prediction task of ImageCLEFmedical challenge 2021, which resulted in the team winning this task. We first show how a very simple approach based on statistical analysis of captions, without relying on images, results in a competitive baseline score. Then, we describe how to improve the performance of this preliminary submission by encoding the medical images with a ResNet CNN, pre-trained on ImageNet and later fine-tuned with the challenge dataset. Afterwards, we use this visual encoding as the input for a multi-label classification approach for caption prediction. W

2022, Publisher: CLEF2021 Working Notes, CEUR Workshop Proceedings, Link>

AUTHORS

Pablo Pino, H Lobel, José Miguel Quintana, Pablo Messina, Ria Deane, Daniel Florea, Denis Parra

ABSTRACT

This article describes the participation and results of the PUC Chile team in the Turberculosis task in the context of ImageCLEFmedical challenge 2021. We were ranked 7th based on the kappa metric and 4th in terms of accuracy. We describe three approaches we tried in order to address the task. Our best approach used 2D images visually encoded with a DenseNet neural network, which representations were concatenated to finally output the classification with a softmax layer. We describe in detail this and other two approaches, and we conclude by discussing some ideas for future work.

RL1, Publisher: Link>

AUTHORS

Pablo Pino, Denis Parra, Cecilia Besa, Claudio Lagos

ABSTRACT

We address the task of automatically generating a medical report from chest X-rays. Many authors have proposed deep learning models to solve this task, but they focus mainly on improving NLP metrics, such as BLEU and CIDEr, which are not suitable to measure clinical correctness in clinical reports. In this work, we propose CNN-TRG, a Template-based Report Generation model that detects a set of abnormalities and verbalizes them via fixed sentences, which is much simpler than other state-of-the-art NLG methods and achieves better results in medical correctness metrics. We benchmark our model in the IU X-ray and MIMIC-CXR datasets against naive baselines as well as deep learning-based models, by employing the Chexpert labeler and MIRQI as clinical correctness evaluations, and NLP metrics as secondary evaluation. We also provide further evidence indicating that traditional NLP metrics are not suitable for this task by presenting their lack of robustness in multiple cases. We show that slightly altering a template-based model can increase NLP metrics considerably while maintaining high clinical performance. Our work contributes by a simple but effective approach for chest X-ray report generation, as well as by supporting a model evaluation focused primarily on clinical correctness metrics and secondarily on NLP metrics.

2022, Publisher: ACM Computing Surveys, Link>

AUTHORS

Marcelo Andia, Pablo Messina, Pablo Pino, Sergio Uribe, Cecilia Besa, Álvaro Soto, Claudia Prieto, Cristian Tejos, Daniel Capurro, Denis Parra

ABSTRACT

Every year physicians face an increasing demand of image-based diagnosis from patients, a problem that can be addressed with recent artificial intelligence methods. In this context, we survey works in the area of automatic report generation from medical images, with emphasis on methods using deep neural networks, with respect to: (1) Datasets, (2) Architecture Design, (3) Explainability and (4) Evaluation Metrics. Our survey identifies interesting developments, but also remaining challenges. Among them, the current evaluation of generated reports is especially weak, since it mostly relies on traditional Natural Language Processing (NLP) metrics, which do not accurately capture medical correctness.