Search

Liquid-based cytology (LBC) is a reliable automated technique for the screening of Papanicolaou (Pap) smear data. It is an effective technique for collecting a majority of the cervical cells and aiding cytopathologists in locating abnormal cells. Most methods published in the research literature rely on accurate cell segmentation as a prior, which remains challenging due to a variety of factors, e.g., stain consistency, presence of clustered cells, etc. We propose a method for automatic classification of cervical slide images through generation of labeled cervical patch data and extracting deep hierarchical features by fine-tuning convolution neural networks, as well as a novel graph-based cell detection approach for cellular level evaluation. The results show that the proposed pipeline can classify images of both single cell and overlapping cells. The VGG-19 model is found to be the best at classifying the cervical cytology patch data with 95 % accuracy under precision-recall curve., (©2019 AMIA - All rights reserved.)

Image augmentation is a commonly performed technique to prevent class imbalance in datasets to compensate for insufficient training samples, or to prevent model overfitting. Traditional augmentation (TA) techniques include various image transformations, such as rotation, translation, channel splitting, etc. Alternatively, Generative Adversarial Network (GAN), due to its proven ability to synthesize convincingly-realistic images, has been used to perform image augmentation as well. However, it is unclear whether GAN augmentation (GA) strategy provides an advantage over TA for medical image classification tasks. In this paper, we study the usefulness of TA and GA for classifying abnormal chest X-ray (CXR) images. We first trained a progressive-growing GAN (PG-GAN) to synthesize high-resolution CXRs for performing GA. Then, we trained an abnormality classifier using three training sets individually - training set with TA, with GA and with no augmentation (NA). Finally, we analyzed the abnormality classifier's performance for the three training cases, which led to the following conclusions: (1) GAN strategy is not always superior to TA for improving the classifier's performance; (2) in comparison to NA, however, both TA and GA leads to a significant performance improvement; and, (3) increasing the quantity of images in TA and GA strategies also improves the classifier's performance.

Visual examination forms an integral part of cervical cancer screening. With the recent rise in smartphone-based health technologies, capturing cervical images using a smartphone camera for telemedicine and automated screening is gaining popularity. However, such images are highly prone to image corruption, typically out-of-focus target or camera shake blur. In this paper, we applied a generative adversarial network (GAN) to deblur mobile-phone cervical (MC) images, and we evaluate the deblur quality using various measures. Our evaluation process is three-fold: first, we calculate the peak signal to noise ratio (PSNR) and the structural similarity (SSIM) of a test dataset with ground truth availability. Next, we calculate the perception based image quality evaluator (PIQE) score of a test dataset without ground truth availability. Finally, we classify a dataset of blurred and the corresponding deblurred images into normal/abnormal MC images. The resulting change in classification accuracy was our final assessment. Our evaluation experiments show that deblurring of MC images can potentially improve the accuracy of both manual and automated cancerous lesion screening.

In this paper, we aim to extract the aortic knuckle (AK) contour in chest radiographs, an anatomical structure rarely being addressed in the literature. Since the AK structure is small and thin, simply adopting the deep network methods that are successful for large organ segmentation is inadequate for achieving good pixel-level accuracy and resolving local ambiguities. To address this challenge, we propose a new coarse-to-fine segmentation approach which focuses on global and local information contexts, respectively. Two convolutional networks are used. For the coarse segmentation, we use FasterRCNN; for the fine segmentation, we use U-Net. Our evaluation uses the publicly available JSRT dataset; the results are promising. Besides presenting these results, we analyze issues such as the imprecision of manual contour marking, and automatic generation of the coarse segmentation ground-truth mask used for deep network training. Our approach is general and can be applied to extract other curve-like objects-of-interest.