Color Standardization and Stain Intensity Calibration for Whole Slide Image-Based Immunohistochemistry Assessment

Automated quantification of human epidermal growth factor receptor 2 (HER2) immunohistochemistry (IHC) using whole slide imaging (WSI) is expected to eliminate subjectivity in visual assessment. However, the color intensity in WSI varies depending on the staining process and scanner device. Such variations affect the image analysis results. This paper presents methods to diminish the influence of color variation produced in the staining process using a calibrator slide consisting of peptide-coated microbeads. The calibrator slide is stained along with tissue sample slides, and the 3,3'-diaminobenzidine (DAB) color intensities of the microbeads are used for calibrating the color variation of the sample slides. An off-the-shelf image analysis tool is employed for the automated assessment, in which cells are classified by the thresholds for the membrane staining. We have adopted two methods for calibrating the color variation based on the DAB color intensities obtained from the calibrator slide: (1) thresholds for classifying the DAB membranous intensity are adjusted, and (2) the color intensity of WSI is corrected. In the experiment, the calibrator slides and tissue of breast cancer slides were stained together on different days and used to test our protocol. With the proposed protocol, the discordance in the HER2 evaluation was reduced to one slide out of 120 slides.

Analysis of Cytology Pap Smear Images Based on Ensemble Deep Learning Approach

The fourth most prevalent cancer in women is cervical cancer, and early detection is crucial for effective treatment and prognostic prediction. Conventional cervical cancer screening and classifying methods are less reliable and accurate as they heavily rely on the expertise of a pathologist. As such, colposcopy is an essential part of preventing cervical cancer. Computer-assisted diagnosis is essential for expanding cervical cancer screening because visual screening results in misdiagnosis and low diagnostic effectiveness due to doctors' increased workloads. Classifying a single cervical cell will overwhelm the physicians, in addition to the existence of overlap between cervical cells, which needs efficient algorithms to separate each cell individually. Focusing on the whole image is the best way and an easy task for the diagnosis. Therefore, looking for new methods to diagnose the whole image is necessary and more accurate. However, existing recognition algorithms do not work well for whole-slide image (WSI) analysis, failing to generalize for different stains and imaging, and displaying subpar clinical-level verification. This paper describes the design of a full ensemble deep learning model for the automatic diagnosis of the WSI. The proposed network discriminates between four classes with high accuracy, reaching up to 99.6%. This work is distinct from existing research in terms of simplicity, accuracy, and speed. It focuses on the whole staining slice image, not on a single cell. The designed deep learning structure considers the slice image with overlapping and non-overlapping cervical cells.

Deep learning-based fully automated differential diagnosis of eyelid basal cell and sebaceous carcinoma using whole slide images

Background

The differential diagnosis of eyelid basal cell carcinoma (BCC) and sebaceous carcinoma (SC) is highly dependent on pathologist’s experience. Herein, we proposed a fully automated differential diagnostic method, which used deep learning (DL) to accurately classify eyelid BCC and SC based on whole slide images (WSIs).

Methods

We used 116 haematoxylin and eosin (H&E)-stained sections from 116 eyelid BCC patients and 180 H&E-stained sections from 129 eyelid SC patients treated at the Shanghai Ninth People’s Hospital from 2017 to 2019. The method comprises two stages: patch prediction by the DenseNet-161 architecture-based DL model and WSI differentiation by an average-probability strategy-based integration module, and its differential performance was assessed by the carcinoma differentiation accuracy and F1 score. We compared the classification performance of the method with that of three pathologists, two junior and one senior. To validate the auxiliary value of the method, we compared the pathologists’ BCC and SC classification with and without the assistance of our proposed method.

Results

Our proposed method achieved an accuracy of 0.983, significantly higher than that of the three pathologists (0.644 and 0.729 for the two junior pathologists and 0.831 for the senior pathologist). With the method’s assistance, the pathologists’ accuracy increased significantly (P<0.05), by 28.8% and 15.2%, respectively, for the two junior pathologists and by 11.8% for the senior pathologist.

Conclusions

Our proposed method accurately classifies eyelid BCC and SC and effectively improves the diagnostic accuracy of pathologists. It may therefore facilitate the development of appropriate and timely therapeutic plans.

Detection of Cervical Cancer Cells in Whole Slide Images Using Deformable and Global Context Aware Faster RCNN-FPN

Cervical cancer is a worldwide public health problem with a high rate of illness and mortality among women. In this study, we proposed a novel framework based on Faster RCNN-FPN architecture for the detection of abnormal cervical cells in cytology images from a cancer screening test. We extended the Faster RCNN-FPN model by infusing deformable convolution layers into the feature pyramid network (FPN) to improve scalability. Furthermore, we introduced a global contextual aware module alongside the Region Proposal Network (RPN) to enhance the spatial correlation between the background and the foreground. Extensive experimentations with the proposed deformable and global context aware (DGCA) RCNN were carried out using the cervical image dataset of "Digital Human Body" Vision Challenge from the Alibaba Cloud TianChi Company. Performance evaluation based on the mean average precision (mAP) and receiver operating characteristic (ROC) curve has demonstrated considerable advantages of the proposed framework. Particularly, when combined with tagging of the negative image samples using traditional computer-vision techniques, 6-9% increase in mAP has been achieved. The proposed DGCA-RCNN model has potential to become a clinically useful AI tool for automated detection of cervical cancer cells in whole slide images of Pap smear.