Lite ENSAM: a lightweight cancer segmentation model for 3D Computed Tomography

Agnar Martin Bjørnstad, Elias Stenhede, Arian Ranjbar

Keywords: Computed Tomography, Multimodal, Tumor Segmentation

TL;DR: We present Lite ENSAM, a lightweight volumetric tumor segmentation model adapted from ENSAM, achieving competitive accuracy (DSC 76.06%, NSD 78.99%) and fast inference (14.4 s) on CPU in the MICCAI FLARE 2025 Task 1 Subtask 2.

Abstract: Accurate tumor size measurement is a cornerstone of evaluating cancer treatment response. The most widely adopted standard for this purpose is the Response Evaluation Criteria in Solid Tumors (RECIST) v1.1, which relies on measuring the longest tumor diameter in a single plane. However, volumetric measurements have been shown to provide a more reliable assessment of treatment effect. Their clinical adoption has been limited, though, due to the labor-intensive nature of manual volumetric annotation. In this paper, we present Lite ENSAM, a lightweight adaptation of the ENSAM architecture designed for efficient volumetric tumor segmentation from CT scans annotated with RECIST annotations. Lite ENSAM was submitted to the MICCAI FLARE 2025 Task 1: Pan-cancer Segmentation in CT Scans, Subtask 2, where it achieved a Dice Similarity Coefficient (DSC) of 76.06\% and a Normalized Surface Dice (NSD) of 78.99\%, with an average total RAM time of 50,556 MB s and an average inference time of 14.39 seconds on CPU on the public validation dataset.

Submission Number: 7