Automatic pharynx and larynx cancer segmentation framework (PLCSF) on contrast enhanced MR images

Abstract

A novel and effective pharynx and larynx cancer segmentation framework (PLCSF) is presented for automatic base of tongue and larynx cancer segmentation from gadolinium-enhanced T1-weighted magnetic resonance images (MRI). The aim of the proposed PLCSF is to assist clinicians in radiotherapy treatment planning. The initial processing of MRI data in PLCSF includes cropping of region of interest; reduction of artefacts and detection of the throat region for the location prior. Further, modified fuzzy c-means clustering is developed to robustly separate candidate cancer pixels from other tissue types. In addition, region-based level set method is evolved to ensure spatial smoothness for the final segmentation boundary after noise removal using non-linear and morphological filtering. Validation study of PLCSF on 102 axial MRI slices demonstrate mean dice similarity coefficient of 0.79 and mean modified Hausdorff distance of 2.2 mm when compared with manual segmentations. Comparison of PLCSF with other algorithms validates the robustness of the PLCSF. Inter- and intra-variability calculations from manual segmentations suggest that PLCSF can help to reduce the human subjectivity

Automatic 3D Detection and Segmentation of Head and Neck Cancer from MRI Data

“…The data contains T1-weighted Gadoliniumenhanced MR images. This part will demonstrate some results of proposed algorithm on real data, and also some quantitative study compared with 2D plus interpolation algorithm [8], and other 3D algorithm [18].…”

“…Steps of tumour detection on central slice are also shown in Fig.2. The throat is detected by two fuzzy rules [8]. Then modified fuzzy c-mean (MFCM) [14] utilises intensity and spatial information of pixels to organise them into five clusters.…”

“…The work in [6] applies 3D level set segmentation to bone segmentation from CT data which have a significant contrast difference. Our previous work [8] presented an automatic 2D tumour segmentation method, which was tested on real MRI slices. In [9], 3D throat detection was obtained as interpolation of segmented 2D MRI slices.…”

Automatic 3D segmentation of MRI data for detection of head and neck cancerous lymph nodes

“…Cancerous lymph nodes detection is performed slice by slice. For each MRI slice, the throat is detected by two fuzzy rules [2]. Then a modified fuzzy c-mean (MFCM) algorithm [12] utilises intensity and spatial information of pixels to organise them into five clusters.…”

“…Definition of this region is fundamental for accurate and effective radiation treatment planning. Development of automated delineation methods can help reduce inter and intra variabilities of manual tumour delineation, providing objective and reliable assistance to clinical oncologists to reduce work load and improve radiation treatment [2]. Fig.…”