Deep Active Learning for Automatic Mitotic Cell Detection on HEp-2 Specimen Medical Images

Abstract

Identifying Human Epithelial Type 2 (HEp-2) mitotic cells is a crucial procedure in anti-nuclear antibodies (ANAs) testing, which is the standard protocol for detecting connective tissue diseases (CTD). Due to the low throughput and labor-subjectivity of the ANAs’ manual screening test, there is a need to develop a reliable HEp-2 computer-aided diagnosis (CAD) system. The automatic detection of mitotic cells from the microscopic HEp-2 specimen images is an essential step to support the diagnosis process and enhance the throughput of this test. This work proposes a deep active learning (DAL) approach to overcoming the cell labeling challenge. Moreover, deep learning detectors are tailored to automatically identify the mitotic cells directly in the entire microscopic HEp-2 specimen images, avoiding the segmentation step. The proposed framework is validated using the I3A Task-2 dataset over 5-fold cross-validation trials. Using the YOLO predictor, promising mitotic cell prediction results are achieved with an average of 90.011% recall, 88.307% precision, and 81.531% mAP. Whereas, average scores of 86.986% recall, 85.282% precision, and 78.506% mAP are obtained using the Faster R-CNN predictor. Employing the DAL method over four labeling rounds effectively enhances the accuracy of the data annotation, and hence, improves the prediction performance. The proposed framework could be practically applicable to support medical personnel in making rapid and accurate decisions about the mitotic cells’ existence.

A Comprehensive Review and Analysis of Deep Learning-Based Medical Image Adversarial Attack and Defense

“…Deep neural networks (DNNs) have achieved remarkable success in natural imageprocessing tasks. The field of medical image analysis is not left out [1][2][3], including skin lesion diagnosis [4], diabetic retinopathy detection, and tumor segmentation [5,6]. Notably, an AI-based diabetic retinopathy detection system [7,8] has been approved by the Food and Drug Administration (FDA) of the United States [9].…”

Automatic Classification of Antinuclear Antibody Patterns With Machine Learning

“…However, recently in all image-related tasks, deep learning-based methods replaced traditional computer vision algorithms due to their efficiency and high accuracy. Concurrent with our work, there have been other studies that use deep learning on HEp-2 specimen medical images.Anaam et al show that mitotic cells can be detected in those images with high precision[15]. Their method requires bounding box annotations on the images which is expensive to obtain.…”