Mining Negative Temporal Contexts For False Positive Suppression In Real-Time Ultrasound Lesion Detection

TL;DR

This paper introduces UltraDet, a real-time ultrasound lesion detection model that leverages negative temporal contexts from previous frames to effectively suppress false positives, improving accuracy and speed.

Contribution

The paper proposes a novel method to extract and utilize negative temporal contexts with inverse optical flow for false positive suppression in ultrasound lesion detection.

Findings

UltraDet outperforms previous state-of-the-art methods.

Achieves real-time inference speed.

Demonstrates significant false positive reduction.

Abstract

During ultrasonic scanning processes, real-time lesion detection can assist radiologists in accurate cancer diagnosis. However, this essential task remains challenging and underexplored. General-purpose real-time object detection models can mistakenly report obvious false positives (FPs) when applied to ultrasound videos, potentially misleading junior radiologists. One key issue is their failure to utilize negative symptoms in previous frames, denoted as negative temporal contexts (NTC). To address this issue, we propose to extract contexts from previous frames, including NTC, with the guidance of inverse optical flow. By aggregating extracted contexts, we endow the model with the ability to suppress FPs by leveraging NTC. We call the resulting model UltraDet. The proposed UltraDet demonstrates significant improvement over previous state-of-the-arts and achieves real-time inference speed. We release the code, checkpoints, and high-quality labels of the CVA-BUS dataset in https://github.com/HaojunYu1998/UltraDet.