1
|
Wu PH, Bedoya M, White J, Brace CL. Feature-based automated segmentation of ablation zones by fuzzy c-mean clustering during low-dose computed tomography. Med Phys 2021; 48:703-714. [PMID: 33237594 PMCID: PMC8594246 DOI: 10.1002/mp.14623] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2020] [Revised: 07/21/2020] [Accepted: 08/10/2020] [Indexed: 12/24/2022] Open
Abstract
PURPOSE Intra-procedural monitoring and post-procedural follow-up is necessary for a successful ablation treatment. An imaging technique which can assess the ablation geometry accurately is beneficial to monitor and evaluate treatment. In this study, we developed an automated ablation segmentation technique for serial low-dose, noisy ablation computed tomography (CT) or contrast-enhanced CT (CECT). METHODS Low-dose, noisy temporal CT and CECT volumes were acquired during microwave ablation on normal porcine liver (four with non-contrast CT and eight with CECT). Highly constrained backprojection (HYPR) processing was used to recover ablation zone information compromised by low-dose noise. First-order statistic features and normalized fractional Brownian features (NBF) were used to segment ablation zones by fuzzy c-mean clustering. After clustering, the segmented ablation zone was refined by cyclic morphological processing. Automatic and manual segmentations were compared to gross pathology with Dice's coefficient (morphological similarity), while cross-sectional dimensions were compared by percent difference. RESULTS Automatic and manual segmentations of the ablation zone were very similar to gross pathology (Dice Coefficients: Auto.-Path. = 0.84 ± 0.02; Manu.-Path. = 0.76 ± 0.03, P = 0.11). The differences in ablation area, major diameter and minor diameter were 17.9 ± 3.2%, 11.1 ± 3.2% and 16.2 ± 3.4%, respectively, when comparing automatic segmentation to gross pathology, which were lower than the differences of 32.9 ± 16.8%, 13.0 ± 9.8% and 21.8 ± 5.8% when comparing manual segmentation to gross pathology. Manual segmentations tended to overestimate gross pathology when ablation area was less than 15 cm2 , but the automated segmentation tended to underestimate gross pathology when ablation zone is larger than 20 cm2 . CONCLUSION Fuzzy c-means clustering may be used to aid automatic segmentation of ablation zones without prior information or user input, making serial CT/CECT has more potential to assess treatments intra-procedurally.
Collapse
Affiliation(s)
- Po-hung Wu
- Department of Electrical and Computer Engineering, University of Wisconsin - Madison, 1415 Engineering Drive, Madison, WI 53706, USA
| | - Mariajose Bedoya
- Department of Medical Physics, University of Wisconsin - Madison, 1111 Highland Ave, Rm 1005, Madison, WI 53705, USA
| | - Jim White
- Department of Biomedical Engineering, University of Wisconsin - Madison, 1415 Engineering Drive, Madison, WI 53706, USA
| | - Christopher L. Brace
- Department of Biomedical Engineering, University of Wisconsin - Madison, 1415 Engineering Drive, Madison, WI 53706, USA
- Department of Radiology, University of Wisconsin - Madison, 1111 Highland Ave, Madison, WI 53705, USA
| |
Collapse
|
2
|
Faridi P, Keselman P, Fallahi H, Prakash P. Experimental assessment of microwave ablation computational modeling with MR thermometry. Med Phys 2020; 47:3777-3788. [PMID: 32506550 DOI: 10.1002/mp.14318] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2020] [Revised: 05/22/2020] [Accepted: 05/24/2020] [Indexed: 12/23/2022] Open
Abstract
PURPOSE Computational models are widely used during the design and characterization of microwave ablation (MWA) devices, and have been proposed for pretreatment planning. Our objective was to assess three-dimensional (3D) transient temperature and ablation profiles predicted by MWA computational models with temperature profiles measured experimentally using magnetic resonance (MR) thermometry in ex vivo bovine liver. MATERIALS AND METHODS We performed MWA in ex vivo tissue under MR guidance using a custom, 2.45 GHz water-cooled applicator. MR thermometry data were acquired for 2 min prior to heating, during 5-10 min microwave exposures, and for 3 min following heating. Fiber-optic temperature sensors were used to validate the accuracy of MR temperature measurements. A total of 13 ablation experiments were conducted using 30-50 W applied power at the applicator input. MWA computational models were implemented using the finite element method, and incorporated temperature-dependent changes in tissue physical properties. Model-predicted ablation zone extents were compared against MRI-derived Arrhenius thermal damage maps using the Dice similarity coefficient (DSC). RESULTS Prior to heating, the observed standard deviation of MR temperature data was in the range of 0.3-0.7°C. Mean absolute error between MR temperature measurements and fiber-optic temperature probes during heating was in the range of 0.5-2.8°C. The mean DSC between model-predicted ablation zones and MRI-derived Arrhenius thermal damage maps for 13 experimental set-ups was 0.95. When comparing simulated and experimentally (i.e. using MRI) measured temperatures, the mean absolute error (MAE %) relative to maximum temperature change was in the range 5%-8.5%. CONCLUSION We developed a system for characterizing 3D transient temperature and ablation profiles with MR thermometry during MWA in ex vivo liver tissue, and applied the system for experimental validation of MWA computational models.
Collapse
Affiliation(s)
- Pegah Faridi
- Mike Wiegers Department of Electrical and Computer Engineering, Kansas State University, Manhattan, KS, 66506, USA
| | - Paul Keselman
- Hoglund Brain Imaging Center, University of Kansas Medical Center, Kansas City, KS, 66160, USA
| | - Hojjatollah Fallahi
- Mike Wiegers Department of Electrical and Computer Engineering, Kansas State University, Manhattan, KS, 66506, USA
| | - Punit Prakash
- Mike Wiegers Department of Electrical and Computer Engineering, Kansas State University, Manhattan, KS, 66506, USA
| |
Collapse
|
3
|
Hann A, Bettac L, Haenle MM, Graeter T, Berger AW, Dreyhaupt J, Schmalstieg D, Zoller WG, Egger J. Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound. Sci Rep 2017; 7:12779. [PMID: 28986569 PMCID: PMC5630585 DOI: 10.1038/s41598-017-12925-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2017] [Accepted: 09/20/2017] [Indexed: 12/19/2022] Open
Abstract
Manual segmentation of hepatic metastases in ultrasound images acquired from patients suffering from pancreatic cancer is common practice. Semiautomatic measurements promising assistance in this process are often assessed using a small number of lesions performed by examiners who already know the algorithm. In this work, we present the application of an algorithm for the segmentation of liver metastases due to pancreatic cancer using a set of 105 different images of metastases. The algorithm and the two examiners had never assessed the images before. The examiners first performed a manual segmentation and, after five weeks, a semiautomatic segmentation using the algorithm. They were satisfied in up to 90% of the cases with the semiautomatic segmentation results. Using the algorithm was significantly faster and resulted in a median Dice similarity score of over 80%. Estimation of the inter-operator variability by using the intra class correlation coefficient was good with 0.8. In conclusion, the algorithm facilitates fast and accurate segmentation of liver metastases, comparable to the current gold standard of manual segmentation.
Collapse
Affiliation(s)
- Alexander Hann
- Department of Internal Medicine I, Ulm University, Ulm, Germany. .,Department of Internal Medicine and Gastroenterology, Katharinenhospital, Kriegsbergstraße 60, 70174, Stuttgart, Germany.
| | - Lucas Bettac
- Department of Internal Medicine I, Ulm University, Ulm, Germany
| | - Mark M Haenle
- Department of Internal Medicine I, Ulm University, Ulm, Germany
| | - Tilmann Graeter
- Department of Diagnostic and Interventional Radiology, Ulm University, Ulm, Germany
| | | | - Jens Dreyhaupt
- Institute of Epidemiology & Medical Biometry, Ulm University, Ulm, Germany
| | - Dieter Schmalstieg
- Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16, 8010, Graz, Austria
| | - Wolfram G Zoller
- Department of Internal Medicine and Gastroenterology, Katharinenhospital, Kriegsbergstraße 60, 70174, Stuttgart, Germany
| | - Jan Egger
- Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16, 8010, Graz, Austria.,BioTechMed, Krenngasse 37/1, 8010, Graz, Austria
| |
Collapse
|
4
|
Interactive Outlining of Pancreatic Cancer Liver Metastases in Ultrasound Images. Sci Rep 2017; 7:892. [PMID: 28420871 PMCID: PMC5429849 DOI: 10.1038/s41598-017-00940-z] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2016] [Accepted: 03/20/2017] [Indexed: 02/01/2023] Open
Abstract
Ultrasound (US) is the most commonly used liver imaging modality worldwide. Due to its low cost, it is increasingly used in the follow-up of cancer patients with metastases localized in the liver. In this contribution, we present the results of an interactive segmentation approach for liver metastases in US acquisitions. A (semi-) automatic segmentation is still very challenging because of the low image quality and the low contrast between the metastasis and the surrounding liver tissue. Thus, the state of the art in clinical practice is still manual measurement and outlining of the metastases in the US images. We tackle the problem by providing an interactive segmentation approach providing real-time feedback of the segmentation results. The approach has been evaluated with typical US acquisitions from the clinical routine, and the datasets consisted of pancreatic cancer metastases. Even for difficult cases, satisfying segmentations results could be achieved because of the interactive real-time behavior of the approach. In total, 40 clinical images have been evaluated with our method by comparing the results against manual ground truth segmentations. This evaluation yielded to an average Dice Score of 85% and an average Hausdorff Distance of 13 pixels.
Collapse
|
5
|
Ahmad I, Gribble A, Murtza I, Ikram M, Pop M, Vitkin A. Polarization image segmentation of radiofrequency ablated porcine myocardial tissue. PLoS One 2017; 12:e0175173. [PMID: 28380013 PMCID: PMC5381909 DOI: 10.1371/journal.pone.0175173] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2016] [Accepted: 03/21/2017] [Indexed: 11/19/2022] Open
Abstract
Optical polarimetry has previously imaged the spatial extent of a typical radiofrequency ablated (RFA) lesion in myocardial tissue, exhibiting significantly lower total depolarization at the necrotic core compared to healthy tissue, and intermediate values at the RFA rim region. Here, total depolarization in ablated myocardium was used to segment the total depolarization image into three (core, rim and healthy) zones. A local fuzzy thresholding algorithm was used for this multi-region segmentation, and then compared with a ground truth segmentation obtained from manual demarcation of RFA core and rim regions on the histopathology image. Quantitative comparison of the algorithm segmentation results was performed with evaluation metrics such as dice similarity coefficient (DSC = 0.78 ± 0.02 and 0.80 ± 0.02), sensitivity (Sn = 0.83 ± 0.10 and 0.91 ± 0.08), specificity (Sp = 0.76 ± 0.17 and 0.72 ± 0.17) and accuracy (Acc = 0.81 ± 0.09 and 0.71 ± 0.10) for RFA core and rim regions, respectively. This automatic segmentation of parametric depolarization images suggests a novel application of optical polarimetry, namely its use in objective RFA image quantification.
Collapse
Affiliation(s)
- Iftikhar Ahmad
- Department of Physics and Applied Mathematics, Pakistan Institute of Engineering and Applied Science (PIEAS), Nilore, Islamabad, Pakistan
- * E-mail:
| | - Adam Gribble
- Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada
- Division of Biophysics and Bioimaging, Princess Margaret Cancer Centre, University Health Network, 610 University Avenue, Toronto, Ontario, Canada
| | - Iqbal Murtza
- Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Science (PIEAS), Nilore, Islamabad, Pakistan
| | - Masroor Ikram
- Department of Physics and Applied Mathematics, Pakistan Institute of Engineering and Applied Science (PIEAS), Nilore, Islamabad, Pakistan
| | - Mihaela Pop
- Sunnybrook Research Institute, Department of Medical Biophysics, University of Toronto, 2075 Bayview Avenue, Toronto, Ontario, Canada
| | - Alex Vitkin
- Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada
- Division of Biophysics and Bioimaging, Princess Margaret Cancer Centre, University Health Network, 610 University Avenue, Toronto, Ontario, Canada
- Department of Radiation Oncology, University of Toronto, 610 University Avenue, Toronto, Ontario Canada
| |
Collapse
|