ACTIVE: A Deep Model for Sperm and Impurity Detection in Microscopic Videos
This work addresses the problem of automating sperm and impurity detection for medical or biological analysis, reducing manual intervention and bias, but it is incremental as it applies deep learning to a new domain rather than creating a novel paradigm.
The paper tackled the challenging task of detecting sperms and impurities in microscopic videos, which suffer from small size, low contrast, and morphological variability, by introducing a deep learning model based on DBFEN and CCFPN, achieving state-of-the-art AP50 scores of 91.13% for sperm and 59.64% for impurity detection.
The accurate detection of sperms and impurities is a very challenging task, facing problems such as the small size of targets, indefinite target morphologies, low contrast and resolution of the video, and similarity of sperms and impurities. So far, the detection of sperms and impurities still largely relies on the traditional image processing and detection techniques which only yield limited performance and often require manual intervention in the detection process, therefore unfavorably escalating the time cost and injecting the subjective bias into the analysis. Encouraged by the successes of deep learning methods in numerous object detection tasks, here we report a deep learning model based on Double Branch Feature Extraction Network (DBFEN) and Cross-conjugate Feature Pyramid Networks (CCFPN).DBFEN is designed to extract visual features from tiny objects with a double branch structure, and CCFPN is further introduced to fuse the features extracted by DBFEN to enhance the description of position and high-level semantic information. Our work is the pioneer of introducing deep learning approaches to the detection of sperms and impurities. Experiments show that the highest AP50 of the sperm and impurity detection is 91.13% and 59.64%, which lead its competitors by a substantial margin and establish new state-of-the-art results in this problem.