Limits...
Characterizing Heterogeneity within Head and Neck Lesions Using Cluster Analysis of Multi-Parametric MRI Data.

Borri M, Schmidt MA, Powell C, Koh DM, Riddell AM, Partridge M, Bhide SA, Nutting CM, Harrington KJ, Newbold KL, Leach MO - PLoS ONE (2015)

Bottom Line: Cumulative distributions of voxels, containing pre and post-treatment data and including both primary tumours and lymph nodes, were partitioned into k clusters (k = 2, 3 or 4).Principal component analysis and cluster validation were employed to investigate data composition and to independently determine the optimal number of clusters.Partitioning with the optimal number of clusters (k = 4), determined with cluster validation, produced the best separation between reducing and non-reducing clusters.

View Article: PubMed Central - PubMed

Affiliation: CR-UK Cancer Imaging Centre, The Royal Marsden NHS Foundation Trust and The Institute of Cancer Research, London, United Kingdom.

ABSTRACT

Purpose: To describe a methodology, based on cluster analysis, to partition multi-parametric functional imaging data into groups (or clusters) of similar functional characteristics, with the aim of characterizing functional heterogeneity within head and neck tumour volumes. To evaluate the performance of the proposed approach on a set of longitudinal MRI data, analysing the evolution of the obtained sub-sets with treatment.

Material and methods: The cluster analysis workflow was applied to a combination of dynamic contrast-enhanced and diffusion-weighted imaging MRI data from a cohort of squamous cell carcinoma of the head and neck patients. Cumulative distributions of voxels, containing pre and post-treatment data and including both primary tumours and lymph nodes, were partitioned into k clusters (k = 2, 3 or 4). Principal component analysis and cluster validation were employed to investigate data composition and to independently determine the optimal number of clusters. The evolution of the resulting sub-regions with induction chemotherapy treatment was assessed relative to the number of clusters.

Results: The clustering algorithm was able to separate clusters which significantly reduced in voxel number following induction chemotherapy from clusters with a non-significant reduction. Partitioning with the optimal number of clusters (k = 4), determined with cluster validation, produced the best separation between reducing and non-reducing clusters.

Conclusion: The proposed methodology was able to identify tumour sub-regions with distinct functional properties, independently separating clusters which were affected differently by treatment. This work demonstrates that unsupervised cluster analysis, with no prior knowledge of the data, can be employed to provide a multi-parametric characterization of functional heterogeneity within tumour volumes.

No MeSH data available.


Related in: MedlinePlus

Cluster analysis.(a) Cumulative distribution of voxels (primary tumours + lymph nodes), partitioned with k = 4, in the bi-dimensional space formed by the two parameters IAUGC60 and ADC. IAUGC60 is expressed in units of mmol·s, ADC in units of ×10−3 mm2/s. (b,c) Corresponding cluster analysis maps of a responding (b) and a non-responding (c) lymph node, at baseline and post-induction chemotherapy (IC). Different colours indicate a difference in functionality at baseline.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4580650&req=5

pone.0138545.g004: Cluster analysis.(a) Cumulative distribution of voxels (primary tumours + lymph nodes), partitioned with k = 4, in the bi-dimensional space formed by the two parameters IAUGC60 and ADC. IAUGC60 is expressed in units of mmol·s, ADC in units of ×10−3 mm2/s. (b,c) Corresponding cluster analysis maps of a responding (b) and a non-responding (c) lymph node, at baseline and post-induction chemotherapy (IC). Different colours indicate a difference in functionality at baseline.

Mentions: Referring to the data analysed with k = 4, Fig 4 provides an example of the obtained colour maps, contrasting two LNs found to have different clinical outcomes assessed during long-term follow-up. The LN in Fig 4b, containing predominantly voxels belonging to Clusters 1 and 2 at baseline, responded to treatment, while the LN in Fig 4c, containing predominantly voxels belonging to Clusters 3 and 4, did not respond.


Characterizing Heterogeneity within Head and Neck Lesions Using Cluster Analysis of Multi-Parametric MRI Data.

Borri M, Schmidt MA, Powell C, Koh DM, Riddell AM, Partridge M, Bhide SA, Nutting CM, Harrington KJ, Newbold KL, Leach MO - PLoS ONE (2015)

Cluster analysis.(a) Cumulative distribution of voxels (primary tumours + lymph nodes), partitioned with k = 4, in the bi-dimensional space formed by the two parameters IAUGC60 and ADC. IAUGC60 is expressed in units of mmol·s, ADC in units of ×10−3 mm2/s. (b,c) Corresponding cluster analysis maps of a responding (b) and a non-responding (c) lymph node, at baseline and post-induction chemotherapy (IC). Different colours indicate a difference in functionality at baseline.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4580650&req=5

pone.0138545.g004: Cluster analysis.(a) Cumulative distribution of voxels (primary tumours + lymph nodes), partitioned with k = 4, in the bi-dimensional space formed by the two parameters IAUGC60 and ADC. IAUGC60 is expressed in units of mmol·s, ADC in units of ×10−3 mm2/s. (b,c) Corresponding cluster analysis maps of a responding (b) and a non-responding (c) lymph node, at baseline and post-induction chemotherapy (IC). Different colours indicate a difference in functionality at baseline.
Mentions: Referring to the data analysed with k = 4, Fig 4 provides an example of the obtained colour maps, contrasting two LNs found to have different clinical outcomes assessed during long-term follow-up. The LN in Fig 4b, containing predominantly voxels belonging to Clusters 1 and 2 at baseline, responded to treatment, while the LN in Fig 4c, containing predominantly voxels belonging to Clusters 3 and 4, did not respond.

Bottom Line: Cumulative distributions of voxels, containing pre and post-treatment data and including both primary tumours and lymph nodes, were partitioned into k clusters (k = 2, 3 or 4).Principal component analysis and cluster validation were employed to investigate data composition and to independently determine the optimal number of clusters.Partitioning with the optimal number of clusters (k = 4), determined with cluster validation, produced the best separation between reducing and non-reducing clusters.

View Article: PubMed Central - PubMed

Affiliation: CR-UK Cancer Imaging Centre, The Royal Marsden NHS Foundation Trust and The Institute of Cancer Research, London, United Kingdom.

ABSTRACT

Purpose: To describe a methodology, based on cluster analysis, to partition multi-parametric functional imaging data into groups (or clusters) of similar functional characteristics, with the aim of characterizing functional heterogeneity within head and neck tumour volumes. To evaluate the performance of the proposed approach on a set of longitudinal MRI data, analysing the evolution of the obtained sub-sets with treatment.

Material and methods: The cluster analysis workflow was applied to a combination of dynamic contrast-enhanced and diffusion-weighted imaging MRI data from a cohort of squamous cell carcinoma of the head and neck patients. Cumulative distributions of voxels, containing pre and post-treatment data and including both primary tumours and lymph nodes, were partitioned into k clusters (k = 2, 3 or 4). Principal component analysis and cluster validation were employed to investigate data composition and to independently determine the optimal number of clusters. The evolution of the resulting sub-regions with induction chemotherapy treatment was assessed relative to the number of clusters.

Results: The clustering algorithm was able to separate clusters which significantly reduced in voxel number following induction chemotherapy from clusters with a non-significant reduction. Partitioning with the optimal number of clusters (k = 4), determined with cluster validation, produced the best separation between reducing and non-reducing clusters.

Conclusion: The proposed methodology was able to identify tumour sub-regions with distinct functional properties, independently separating clusters which were affected differently by treatment. This work demonstrates that unsupervised cluster analysis, with no prior knowledge of the data, can be employed to provide a multi-parametric characterization of functional heterogeneity within tumour volumes.

No MeSH data available.


Related in: MedlinePlus