Atlas-based automatic segmentation of head and neck organs at risk and nodal target volumes: a clinical validation

Abstract

BackgroundIntensity modulated radiotherapy for head and neck cancer necessitates accurate definition of organs at risk (OAR) and clinical target volumes (CTV). This crucial step is time consuming and prone to inter- and intra-observer variations. Automatic segmentation by atlas deformable registration may help to reduce time and variations. We aim to test a new commercial atlas algorithm for automatic segmentation of OAR and CTV in both ideal and clinical conditions.MethodsThe updated Brainlab automatic head and neck atlas segmentation was tested on 20 patients: 10 cN0-stages (ideal population) and 10 unselected N-stages (clinical population). Following manual delineation of OAR and CTV, automatic segmentation of the same set of structures was performed and afterwards manually corrected. Dice Similarity Coefficient (DSC), Average Surface Distance (ASD) and Maximal Surface Distance (MSD) were calculated for “manual to automatic” and “manual to corrected” volumes comparisons.ResultsIn both groups, automatic segmentation saved about 40% of the corresponding manual segmentation time. This effect was more pronounced for OAR than for CTV. The edition of the automatically obtained contours significantly improved DSC, ASD and MSD. Large distortions of normal anatomy or lack of iodine contrast were the limiting factors.ConclusionsThe updated Brainlab atlas-based automatic segmentation tool for head and neck Cancer patients is timesaving but still necessitates review and corrections by an expert.

The feasibility of atlas‐based automatic segmentation of MRI for H&N radiotherapy planning

“…The use of multiple atlas images aims to overcome anatomical variations between different patients, using a voting methodology by which individual voxels are placed within or outside the segmented structure 13 , 24 . Atlas‐based segmentation using a CT atlas has now entered routine clinical practice for segmentation of OAR and lymph node target volumes on planning CT scans 6 , 8 , 13 . For head and neck radiotherapy delineation, these techniques have demonstrated time sparing benefits 6 , 8 and a reduction in interobserver variability (25) .…”

“…Atlas‐based segmentation using a CT atlas has now entered routine clinical practice for segmentation of OAR and lymph node target volumes on planning CT scans 6 , 8 , 13 . For head and neck radiotherapy delineation, these techniques have demonstrated time sparing benefits 6 , 8 and a reduction in interobserver variability (25) . It remains clear from these studies that automatic segmentation is not sufficiently accurate to remove the need for a manual editing process 6 , 8 , 26 …”

“…A prospective study of atlas‐based automatic segmentation showed an average time saving of 30% for atlas‐based segmentation of OAR followed by a manual edit compared with manual delineation (6) . Similarly, another study showed an approximate time saving of 40% by using automatic segmentation for OAR and lymph node levels (8) . Studies have already demonstrated the role of automatic segmentation for OAR and target volume delineation in adaptive head and neck radiotherapy planning (11) …”

“…This manual process is recognized as being subject to interobserver variability. Although manual delineation is considered the gold standard, there is considerable interest in the use of methods of automatic segmentation to decrease the overall physician‐delineation time and to potentially reduce inherent interobserver and intraobserver variability 6 , 7 , 8 . A role for automatic segmentation is likely to become increasingly important with current interest in adaptive approaches to radiotherapy (9) .…”

“…A role for automatic segmentation is likely to become increasingly important with current interest in adaptive approaches to radiotherapy (9) . Accurate automatic segmentation has been found to be feasible and accurate on CT for OAR with reproducible anatomy/contrast with surrounding tissues 6 , 8 , 10 . A prospective study of atlas‐based automatic segmentation showed an average time saving of 30% for atlas‐based segmentation of OAR followed by a manual edit compared with manual delineation (6) .…”