Deep learning models for automatic tumor segmentation and total tumor volume assessment in patients with colorectal liver metastases

Nina J. Wesdorp, J. Michiel Zeeuw, Sam C.J. Postma, Joran Roor, Jan Hein T.M. van Waesberghe, Janneke E. van den Bergh, Irene M. Nota, Shira Moos, Ruby Kemna, Fijoy Vadakkumpadan, Courtney Ambrozic, Susan van Dieren, Martinus J. van Amerongen, Thiery Chapelle, Marc R.W. Engelbrecht, Michael F. Gerhards, Dirk Grunhagen, Thomas M. van Gulik, John J. Hermans, Koert P. de JongJoost M. Klaase, Mike S.L. Liem, Krijn P. van Lienden, I. Quintus Molenaar, Gijs A. Patijn, Arjen M. Rijken, Theo M. Ruers, Cornelis Verhoef, Johannes H.W. de Wilt, Henk A. Marquering, Jaap Stoker, Rutger Jan Swijnenburg, Cornelis J.A. Punt, Joost Huiskens, Geert Kazemier

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)

Abstract

Background: We developed models for tumor segmentation to automate the assessment of total tumor volume (TTV) in patients with colorectal liver metastases (CRLM). Methods: In this prospective cohort study, pre- and post-systemic treatment computed tomography (CT) scans of 259 patients with initially unresectable CRLM of the CAIRO5 trial (NCT02162563) were included. In total, 595 CT scans comprising 8,959 CRLM were divided into training (73%), validation (6.5%), and test sets (21%). Deep learning models were trained with ground truth segmentations of the liver and CRLM. TTV was calculated based on the CRLM segmentations. An external validation cohort was included, comprising 72 preoperative CT scans of patients with 112 resectable CRLM. Image segmentation evaluation metrics and intraclass correlation coefficient (ICC) were calculated. Results: In the test set (122 CT scans), the autosegmentation models showed a global Dice similarity coefficient (DSC) of 0.96 (liver) and 0.86 (CRLM). The corresponding median per-case DSC was 0.96 (interquartile range [IQR] 0.95–0.96) and 0.80 (IQR 0.67–0.87). For tumor segmentation, the intersection-over-union, precision, and recall were 0.75, 0.89, and 0.84, respectively. An excellent agreement was observed between the reference and automatically computed TTV for the test set (ICC 0.98) and external validation cohort (ICC 0.98). In the external validation, the global DSC was 0.82 and the median per-case DSC was 0.60 (IQR 0.29–0.76) for tumor segmentation. Conclusions: Deep learning autosegmentation models were able to segment the liver and CRLM automatically and accurately in patients with initially unresectable CRLM, enabling automatic TTV assessment in such patients. Relevance statement: Automatic segmentation enables the assessment of total tumor volume in patients with colorectal liver metastases, with a high potential of decreasing radiologist’s workload and increasing accuracy and consistency. Key points: • Tumor response evaluation is time-consuming, manually performed, and ignores total tumor volume. • Automatic models can accurately segment tumors in patients with colorectal liver metastases. • Total tumor volume can be accurately calculated based on automatic segmentations. Graphical Abstract: [Figure not available: see fulltext.].

Original languageEnglish
Article number75
JournalEuropean Radiology Experimental
Volume7
Issue number1
DOIs
Publication statusPublished - Dec 2023

Keywords

  • Artificial intelligence
  • Colorectal cancer
  • Deep learning
  • Liver neoplasms
  • Tomography (x-ray computed)

Cite this