In recent years, many attempts have been dedicated to the creation of automated devices that could assist both expert and beginner dermatologists towards fast and early diagnosis of skin lesions. Tasks such as skin lesion classification and segmentation have been extensively addressed with deep learning algorithms, which in some cases reach a diagnostic accuracy comparable to that of expert physicians. However, the general lack of interpretability and reliability severely hinders the ability of those approaches to actually support dermatologists in the diagnosis process. In this paper a novel skin image retrieval system is presented, which exploits features extracted by Convolutional Neural Networks to gather similar images from a publicly available dataset, in order to assist the diagnosis process of both expert and novice practitioners. In the proposed framework, ResNet-50 is initially trained for the classification of dermoscopic images; then, the feature extraction part is isolated, and an embedding network is built on top of it. The embedding learns an alternative representation, which allows to check image similarity by means of a distance measure. Experimental results reveal that the proposed method is able to select meaningful images, which can effectively boost the classification accuracy of human dermatologists.

Supporting Skin Lesion Diagnosis with Content-Based Image Retrieval / Allegretti, Stefano; Bolelli, Federico; Pollastri, Federico; Longhitano, Sabrina; Pellacani, Giovanni; Grana, Costantino. - (2021), pp. 8053-8060. ((Intervento presentato al convegno 2020 25th International Conference on Pattern Recognition (ICPR) tenutosi a Milan, Italy nel Jan 10-15 [10.1109/ICPR48806.2021.9412419].

Supporting Skin Lesion Diagnosis with Content-Based Image Retrieval

Stefano Allegretti;Federico Bolelli;Federico Pollastri;Sabrina Longhitano;Giovanni Pellacani;Costantino Grana
2021-01-01

Abstract

In recent years, many attempts have been dedicated to the creation of automated devices that could assist both expert and beginner dermatologists towards fast and early diagnosis of skin lesions. Tasks such as skin lesion classification and segmentation have been extensively addressed with deep learning algorithms, which in some cases reach a diagnostic accuracy comparable to that of expert physicians. However, the general lack of interpretability and reliability severely hinders the ability of those approaches to actually support dermatologists in the diagnosis process. In this paper a novel skin image retrieval system is presented, which exploits features extracted by Convolutional Neural Networks to gather similar images from a publicly available dataset, in order to assist the diagnosis process of both expert and novice practitioners. In the proposed framework, ResNet-50 is initially trained for the classification of dermoscopic images; then, the feature extraction part is isolated, and an embedding network is built on top of it. The embedding learns an alternative representation, which allows to check image similarity by means of a distance measure. Experimental results reveal that the proposed method is able to select meaningful images, which can effectively boost the classification accuracy of human dermatologists.
2020 25th International Conference on Pattern Recognition (ICPR)
Milan, Italy
Jan 10-15
8053
8060
Allegretti, Stefano; Bolelli, Federico; Pollastri, Federico; Longhitano, Sabrina; Pellacani, Giovanni; Grana, Costantino
Supporting Skin Lesion Diagnosis with Content-Based Image Retrieval / Allegretti, Stefano; Bolelli, Federico; Pollastri, Federico; Longhitano, Sabrina; Pellacani, Giovanni; Grana, Costantino. - (2021), pp. 8053-8060. ((Intervento presentato al convegno 2020 25th International Conference on Pattern Recognition (ICPR) tenutosi a Milan, Italy nel Jan 10-15 [10.1109/ICPR48806.2021.9412419].
File in questo prodotto:
File Dimensione Formato  
2020_ICPR_Supporting_Skin_Lesion_Diagnosis_with_Content_Based_Image_Retrieval.pdf

Open access

Tipologia: Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione 1.71 MB
Formato Adobe PDF
1.71 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1212172
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 13
social impact