Systematic evaluation of three different commercial software solutions for automatic segmentation for adaptive therapy in head-and-neck, prostate and pleural cancer

Our plain-English summary of Systematic evaluation of three different commercial software solutions for automatic segmentation for adaptive therapy in head-and-neck, prostate and pleural cancer, by M. La Macchia, F. Fellin, M. Amichetti, et al (Radiation Oncology, 2012).

The study

• Authors: M. La Macchia, F. Fellin, M. Amichetti, M. Cianchetti, S. Gianolini, V. Paola, A.J. Lomax, L. Widesott
• Journal: Radiation Oncology
• Published: 2012;7:160
• Cited by: 138 articles, as counted by NIH iCite
• Read it: PubMed · Publisher · Free full text

Abstract

Purpose: To validate, in the context of adaptive radiotherapy, three commercial software solutions for atlas-based segmentation.

Methods And Materials: Fifteen patients, five for each group, with cancer of the Head&Neck, pleura, and prostate were enrolled in the study. In addition to the treatment planning CT (pCT) images, one replanning CT (rCT) image set was acquired for each patient during the RT course. Three experienced physicians outlined on the pCT and rCT all the volumes of interest (VOIs). We used three software solutions (VelocityAI 2.6.2 (V), MIM 5.1.1 (M) by MIMVista and ABAS 2.0 (A) by CMS-Elekta) to generate the automatic contouring on the repeated CT. All the VOIs obtained with automatic contouring (AC) were successively corrected manually. We recorded the time needed for: 1) ex novo ROIs definition on rCT; 2) generation of AC by the three software solutions; 3) manual correction of AC.To compare the quality of the volumes obtained automatically by the software and manually corrected with those drawn from scratch on rCT, we used the following indexes: overlap coefficient (DICE), sensitivity, inclusiveness index, difference in volume, and displacement differences on three axes (x, y, z) from the isocenter.

Results: The time saved by the three software solutions for all the sites, compared to the manual contouring from scratch, is statistically significant and similar for all the three software solutions. The time saved for each site are as follows: about an hour for Head&Neck, about 40 minutes for prostate, and about 20 minutes for mesothelioma. The best DICE similarity coefficient index was obtained with the manual correction for: A (contours for prostate), A and M (contours for H&N), and M (contours for mesothelioma).

Conclusions: From a clinical point of view, the automated contouring workflow was shown to be significantly shorter than the manual contouring process, even though manual correction of the VOIs is always needed.

In plain English

This study compared three commercial radiotherapy software programs (ABAS 2.0, MIM 5.1.1 and VelocityAI 2.6.2). Each program automatically redraws the outlines of tumor target areas and nearby organs on a repeat CT scan taken during radiation treatment. The study included 15 patients: five with locally-advanced head and neck tumors, five with high-risk prostate cancer, and five with malignant pleural mesothelioma who had had surgery and were receiving follow-up chest radiation. Physicians' outlines drawn from scratch served as the reference. The automatic outlines always needed manual correction, but automatic drawing plus correction took less time than drawing from scratch. For the mesothelioma patients, the average time saved was 22 minutes with ABAS and MIM and 15 minutes with VelocityAI. The overlap score (DICE index) for their target outline rose from an average of 0.85 before manual correction to 0.9 after. The authors noted that because there were few patients, none of the differences between the programs would have been statistically significant after a correction for multiple comparisons. They did not assess effects on radiation dose. The study does not concern asbestos exposure.

We wrote this plain-English summary from the full article with the help of AI, and a second AI model checked each sentence against the article. It is not the authors' wording; the abstract and the article are their own account.

What the study did and found

• Design: Comparative evaluation of three commercial automatic contouring (segmentation) software programs on clinical CT scans
• Who was studied: 15 radiotherapy patients: 5 with locally-advanced head and neck tumors, 5 with malignant pleural mesothelioma (previously treated with what the article calls extraperitoneal pleuro-pneumonectomy, and receiving adjuvant thoracic irradiation), and 5 with high-risk prostate cancer. Each patient had a planning CT and a repeat CT taken during the radiotherapy course. The authors are based in Trento, Italy, and Switzerland. Dates are not given.
• Exposure: No asbestos exposure was studied. The comparison was of software (ABAS 2.0, MIM 5.1.1, VelocityAI 2.6.2) used to deform outlines from the planning CT onto a replanning CT taken during treatment.
• Main results:
  • Mesothelioma patients: average time saved compared with contouring from scratch was 22 min with ABAS and MIM, and 15 min with VelocityAI
  • Prostate patients: average time saved was 55 min with MIM, 31 min with ABAS and 41 min with VelocityAI
  • Head and neck patients: average time saved was 1 hour 23 min with ABAS, 1 hour 4 min with MIM and 45 min with VelocityAI
  • Mesothelioma patients: the DICE overlap index for the target volume improved, for all three programs, from an average of 0.85 before manual correction to 0.9 after
  • Mesothelioma patients: for the inclusiveness index, MIM usually performed best, both before and after manual correction
  • With the Holm-Bonferroni correction, none of the differences between the software programs would have been statistically significant
• The authors' conclusion: The authors concluded that the automatic contouring workflow was significantly shorter than manual contouring from scratch, although manual correction of the outlines is always needed.
• Limitations the authors state:
  • Small number of patients
  • Effects of the contour differences on radiation dose were not evaluated
  • Head and neck replanning CT scans were done without contrast media, which would have helped
  • The head and neck contouring physician had been using one of the programs in clinical practice before the analysis
  • Other differences between the programs were not evaluated

Topics

The National Library of Medicine indexes this study under subjects our site covers: Lung cancer.

Medical terms in this study, explained in our Lexicon: Pleura, Mesothelioma.

Related studies

• Is there a single spot size and grid for intensity modulated proton therapy? Simulation of head and neck, prostate and mesothelioma cases — L. Widesott, A.J. Lomax, et al. (2012)
• Occupational exposure to rock wool and glass wool and risk of cancers of the lung and the head and neck: a systematic review and meta-analysis — L. Lipworth, C. La Vecchia, et al. (2009)
• Systematic screening for occupations and occupational exposures in head and neck squamous cell carcinoma patients — S. Deneuve, B. Charbotel, et al. (2019)
• Assessing Tumor-Infiltrating Lymphocytes in Solid Tumors: A Practical Review for Pathologists and Proposal for a Standardized Method from the International Immuno-Oncology Biomarkers Working Group: Part 2: TILs in Melanoma, Gastrointestinal Tract Carcinomas, Non-Small Cell Lung Carcinoma and Mesothelioma, Endometrial and Ovarian Carcinomas, Squamous Cell Carcinoma of the Head and Neck, Genitourinary Carcinomas, and Primary Brain Tumors — S. Hendry, R. Salgado, et al. (2017)
• Plasma osteopontin levels in patients with head and neck cancer and cervix cancer are critically dependent on the choice of ELISA system — D. Vordermark, H.M. Said, et al. (2006)
• Occupational exposure to chlorinated solvents and risk of head and neck cancer in men: a population-based case-control study in France — C. Barul, A. Fayossé, et al. (2017)

Browse more research in Radiation Oncology, or return to medical research.