Detecting nodular basal cell carcinoma in pathology imaging using deep learning image segmentation

Jeannie Ren, Rivka Lax, James G. Krueger, James Browning, John Carucci, Kevin White, Samantha Lish, Daniel S. Gareau

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

With over 4.3 million new cases in the U.S. every year, basal cell carcinoma (BCC), is the most common form of skin cancer. Pathologists must examine pathology images to diagnose BCC, potentially resulting in delay, error, and inconsistency. To address the need for standardized, expedited diagnosis, we created an automated diagnostic machine to identify BCC given pathology images. In MATLAB, we adapted a deep neural network image segmentation model, UNet, to train on BCC images and their corresponding masks, which can learn to highlight these nodules in pathology images by outputting a computer-generated mask. We trained the U-Net on one image from the dataset and compared the computer-generated mask output from testing on three types of images: an image from a different region of the same image taken with the same microscope, an image from a different tissue sample with a different microscope, and an image taken with a confocal microscope. We observed good, medium and poor results, respectively, illustrating that performance depends on the similarity between test and training data. In subsequent tests using data augmentation, we achieved sensitivity of 0.82±0.07 and specificity of 0.87±0.16 on N = 6 sample sections from 3 different BCCs imaged with the same microscope system. These data show that the U-Net performed well with a relatively few number of training images. Examining the errors raised interesting questions regarding what the errors mean and how they possibly arose. By creating a surgeon interface for rapid pathological assessment and machine learning diagnostics for pathological features, the BCC diagnosis process will be expedited and standardized.

Original languageEnglish (US)
Title of host publicationPhotonics in Dermatology and Plastic Surgery 2020
EditorsBernard Choi, Haishan Zeng
PublisherSPIE
ISBN (Electronic)9781510631854
DOIs
StatePublished - 2020
Externally publishedYes
EventPhotonics in Dermatology and Plastic Surgery 2020 - San Francisco, United States
Duration: Feb 1 2020Feb 2 2020

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume11211
ISSN (Print)1605-7422

Conference

ConferencePhotonics in Dermatology and Plastic Surgery 2020
Country/TerritoryUnited States
CitySan Francisco
Period2/1/202/2/20

Keywords

  • Automated diagnosis
  • Basal Cell Carcinoma
  • Deep learning
  • Image segmentation
  • Machine learning
  • Skin cancer

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Detecting nodular basal cell carcinoma in pathology imaging using deep learning image segmentation'. Together they form a unique fingerprint.

Cite this