The CIA lab has recently had 4 articles published in PLOS One and the Journal of Urology.

Automated Staging Of T1 Bladder Cancer Using Digital Pathologic H&E Images: A Deep Learning approach (Journal of Urology). The paper discusses the need for accurately gauging tumor cell intrusion into Lamina Propria in an effort to substage bladder cancer. It explains how transfer learning in conjunction with Convolutional Neural Networks can be used to accurately identify different bladder layers and then compute the distance between tumor nuclei and Lamina Propria. The article is available here:

Identifying tumor in pancreatic neuroendocrine neoplasms from Ki67 images using transfer learning (PLOS One). This paper examines a proposed methodology to automatically differentiate between NET and non-tumor regions based on images of Ki67 stained biopsies. It also uses transfer learning to exploit a rich set of features developed to solve a 1000-class non-pathology problem. When applied to 30 high power fields (HPF) and assessed against a gold standard (evaluation by two expert pathologists), the method resulted in a high sensitivity of 97.8% and specificity of 88.8%. The article is available here:

Nuclear IHC enumeration: A digital phantom to evaluate the performance of automated algorithms in digital pathology (PLOS One). Verifying the accuracy of nuclei detection algorithms can be difficult due to the requirement of acquiring manually annotated ground truth from pathologists and their inherent variability. This paper proposes a method for creating digital immunohistochemistry (IHC) phantoms that can be used to evaluate computer algorithms for enumeration of IHC positive cells. The article is available here:

Optimized generation of high-resolution phantom images using cGAN: Application to quantification of Ki67 breast cancer images (PLOS One). Typically, immunohistochemical staining interpretation is rendered by a trained pathologist using a manual method, which consists of counting each positively- and negatively-stained cell under a microscope. The manual interpretation results in poor reproducibility. To address this issue, we proposed a novel method to create artificial datasets with the known ground truth allowing us to analyze recall, precision, accuracy, and intra- and inter-observer variability in a systematic manner, and enabling us to compare different computer analysis approaches. The article is available here:

Lab members have also presented 4 articles at conferences this year:

Automated T1 bladder risk stratification based on depth of lamina propria invasion from H and E tissue biopsies: a deep learning approach (SPIE Medical Imaging, 2018). The article is available here:

An application of transfer learning to neutrophil cluster detection for tuberculosis: efficient implementation with nonmetric multidimensional scaling and sampling (SPIE Medical Imaging, 2018). The article is available here:

A Deep Learning Approach to Accurately Identify Different Layers of Bladder Wall Using Digital H&E Slides (2018 Annual Meeting of The United States and Canadian Academy of Pathology (USCAP)). The abstract is available here: (Page 595)

A Novel Image Analysis Algorithm To Classify Bladder Wall Layers: A Step Towards Automated Sub-Staging Of T1 Bladder Cancer (2018 Annual Meeting of The United States and Canadian Academy of Pathology (USCAP)). The abstract is available here:

Leave a comment

Your email address will not be published. Required fields are marked *