BoxShrink: From Bounding Boxes to Segmentation Masks

TL;DR

BoxShrink offers a fast, model-free method to convert bounding boxes into segmentation masks, improving weakly-supervised medical image segmentation accuracy without additional training.

Contribution

It introduces a novel, training-free framework with two variants for transforming bounding boxes into segmentation masks, enhancing weakly-supervised segmentation performance.

Findings

Average 4% IoU improvement across models

Applicable to medical image segmentation tasks

Open-sourced implementation available

Abstract

One of the core challenges facing the medical image computing community is fast and efficient data sample labeling. Obtaining fine-grained labels for segmentation is particularly demanding since it is expensive, time-consuming, and requires sophisticated tools. On the contrary, applying bounding boxes is fast and takes significantly less time than fine-grained labeling, but does not produce detailed results. In response, we propose a novel framework for weakly-supervised tasks with the rapid and robust transformation of bounding boxes into segmentation masks without training any machine learning model, coined BoxShrink. The proposed framework comes in two variants - rapid-BoxShrink for fast label transformations, and robust-BoxShrink for more precise label transformations. An average of four percent improvement in IoU is found across several models when being trained using BoxShrink in a weakly-supervised setting, compared to using only bounding box annotations as inputs on a colonoscopy image data set. We open-sourced the code for the proposed framework and published it online.