Recently, deep learning methods have had a tremendous impact on computer vision applications, from image classification and semantic segmentation to object detection and face recognition. Nevertheless, the training of state-of-the-art neural network models is usually based on the availability of large sets of supervised data. Indeed, deep neural networks have a huge number of parameters which, to be properly trained, require a fairly large dataset of supervised examples. This problem is particularly relevant in the medical field due to privacy issues and the high cost of image tagging by medical experts. In this chapter, we present a new approach that allows to reduce this limitation by generating synthetic images with their corresponding supervision. In particular, this approach can be applied in semantic segmentation, where the generated images (and label-maps) can be used to augment real datasets during network training. The main characteristic of our method, differently from other existing techniques, lies in the generation procedure carried out in multiple steps, based on the intuition that, by splitting the procedure in multiple phases, the overall generation task is simplified. The effectiveness of the proposed multi-stage approach has been evaluated on two different domains, retinal fundus and chest X-ray images. In both domains, the multi-stage approach has been compared with the single-stage generation procedure. The results suggest that generating images in multiple steps is more effective and computationally cheaper, yet allowing high resolution, realistic images to be used for training deep networks.

Andreini, P., Bonechi, S., Ciano, G., Graziani, C., Lachi, V., Nikoloulopoulou, N., et al. (2023). Multi-stage Synthetic Image Generation for the Semantic Segmentation of Medical Images. In Artificial Intelligence and Machine Learning for Healthcare (pp. 79-104). Cham : Springer [10.1007/978-3-031-11154-9_5].

Multi-stage Synthetic Image Generation for the Semantic Segmentation of Medical Images

Andreini, Paolo
;
Bonechi, Simone;Graziani, Caterina;Lachi, Veronica;Bianchini, Monica;Scarselli, Franco
2023-01-01

Abstract

Recently, deep learning methods have had a tremendous impact on computer vision applications, from image classification and semantic segmentation to object detection and face recognition. Nevertheless, the training of state-of-the-art neural network models is usually based on the availability of large sets of supervised data. Indeed, deep neural networks have a huge number of parameters which, to be properly trained, require a fairly large dataset of supervised examples. This problem is particularly relevant in the medical field due to privacy issues and the high cost of image tagging by medical experts. In this chapter, we present a new approach that allows to reduce this limitation by generating synthetic images with their corresponding supervision. In particular, this approach can be applied in semantic segmentation, where the generated images (and label-maps) can be used to augment real datasets during network training. The main characteristic of our method, differently from other existing techniques, lies in the generation procedure carried out in multiple steps, based on the intuition that, by splitting the procedure in multiple phases, the overall generation task is simplified. The effectiveness of the proposed multi-stage approach has been evaluated on two different domains, retinal fundus and chest X-ray images. In both domains, the multi-stage approach has been compared with the single-stage generation procedure. The results suggest that generating images in multiple steps is more effective and computationally cheaper, yet allowing high resolution, realistic images to be used for training deep networks.
978-3-031-11153-2
978-3-031-11154-9
Andreini, P., Bonechi, S., Ciano, G., Graziani, C., Lachi, V., Nikoloulopoulou, N., et al. (2023). Multi-stage Synthetic Image Generation for the Semantic Segmentation of Medical Images. In Artificial Intelligence and Machine Learning for Healthcare (pp. 79-104). Cham : Springer [10.1007/978-3-031-11154-9_5].
File in questo prodotto:
File Dimensione Formato  
Chapter_Multi__stage_synthetic_image_generation_for_the_semantic_segmentation_of_medical_images_compressed.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 283.03 kB
Formato Adobe PDF
283.03 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/1216714