Title: Automatic segmentation of nasopharyngeal carcinoma from CT images

Authors: Bilel Daoud; Ali Khalfallah; Leila Farhat; Wafa Mnejja; Ken'ichi Morooka; Med Salim Bouhlel; Jamel Daoud

Addresses: Research Unit: Sciences and Technologies of Image and Telecommunications (SETIT), Higher Institute of Biotechnology of Sfax (ISBS), B.P.W, 216, 3038 Sfax, Tunisia; Faculty of Information Science and Electrical Engineering, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka-shi, Fukuoka 819-0395, Japan ' Research Unit: Sciences and Technologies of Image and Telecommunications (SETIT), Higher Institute of Biotechnology of Sfax (ISBS), B.P.W, 216, 3038 Sfax, Tunisia ' Radiotherapy Department of Habib Bourguiba Hospital of Sfax, Avenue El Ferdaouss, 3029, Sfax, Tunisia ' Radiotherapy Department of Habib Bourguiba Hospital of Sfax, Avenue El Ferdaouss, 3029, Sfax, Tunisia ' Faculty of Information Science and Electrical Engineering, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka-shi, Fukuoka 819-0395, Japan ' Research Unit: Sciences and Technologies of Image and Telecommunications (SETIT), Higher Institute of Biotechnology of Sfax (ISBS), B.P.W, 216, 3038 Sfax, Tunisia ' Radiotherapy Department of Habib Bourguiba Hospital of Sfax, Avenue El Ferdaouss, 3029, Sfax, Tunisia

Abstract: The nasopharyngeal carcinoma (NPC) called also Cavum cancer becomes a public health problem for the Maghreb countries and Southeast Asia. The detection of this cancer could be carried out from computed tomography (CT) scans. In this context, we proposed two approaches based on image clustering to locate affected tissues by the Cavum cancer. These approaches are based respectively on E-M and Otsu segmentation. Compared to the physician manual contouring, our automatic detection proves that the detection of the cancer while using the Otsu clustering in terms of precision, recall and F-measure is more efficient than E-M. Then, we merged the results of these two methods by using the AND and the OR logical operators. The AND fusion yields to an increase of the precision while the OR fusion raises the recall. However, the detection of the NPC using Otsu remain the best solution in terms of F-Measure. Compared to previous studies that provide a surface analysis of the NPC, our approach provides a 3D estimation of this tumour ensuring a better analysis of the patient folder.

Keywords: Cavum cancer; DICOM images; image segmentation; E-M; Otsu; recall; precision; F-measure.

DOI: 10.1504/IJBET.2020.107760

International Journal of Biomedical Engineering and Technology, 2020 Vol.33 No.3, pp.240 - 257

Received: 14 Jan 2017
Accepted: 07 Sep 2017
Published online: 17 Jun 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article