pith. sign in

arxiv: 1606.05718 · v1 · pith:DRVWUL3Knew · submitted 2016-06-18 · 🧬 q-bio.QM · cs.CV

Deep Learning for Identifying Metastatic Breast Cancer

classification 🧬 q-bio.QM cs.CV
keywords deeplearningpathologistslidewholebreastcancerchallenge
0
0 comments X
read the original abstract

The International Symposium on Biomedical Imaging (ISBI) held a grand challenge to evaluate computational systems for the automated detection of metastatic breast cancer in whole slide images of sentinel lymph node biopsies. Our team won both competitions in the grand challenge, obtaining an area under the receiver operating curve (AUC) of 0.925 for the task of whole slide image classification and a score of 0.7051 for the tumor localization task. A pathologist independently reviewed the same images, obtaining a whole slide image classification AUC of 0.966 and a tumor localization score of 0.733. Combining our deep learning system's predictions with the human pathologist's diagnoses increased the pathologist's AUC to 0.995, representing an approximately 85 percent reduction in human error rate. These results demonstrate the power of using deep learning to produce significant improvements in the accuracy of pathological diagnoses.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Detecting Breast Carcinoma Metastasis on Whole-Slide Images by Partially Subsampled Multiple Instance Learning

    stat.ME 2026-04 unverdicted novelty 5.0

    A Gaussian mixture MIL framework with partially subsampled instances improves metastasis prediction accuracy on breast cancer whole-slide images over prior methods.

  2. Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis

    eess.IV 2020-06 unverdicted novelty 4.0

    Sequential deep learning model classifies infectious keratitis images at 80% accuracy, outperforming ophthalmologists on a 120-image test set.

  3. Dealing with Topological Information within a Fully Convolutional Neural Network

    cs.CV 2019-06 unverdicted novelty 4.0

    A geodesic operator pre-processing step is introduced to let FCNs exploit topological information for segmenting histological images of pigmented reconstructed epidermis.

  4. Deep Instance-Level Hard Negative Mining Model for Histopathology Images

    cs.CV 2019-06 unverdicted novelty 4.0

    A deep MIL model with attention, adaptive hard-sample weighting, and attention-driven hard-negative bag generation reports state-of-the-art classification on colon and breast cancer histopathology datasets.

  5. An AI-Augmented Lesion Detection Framework For Liver Metastases With Model Interpretability

    eess.IV 2019-07 unverdicted novelty 3.0

    Proposes an AI-augmented interactive system with built-in model interpretability to assist RECIST-based assessment of liver metastases.

  6. Machine learning and behavioral economics for personalized choice architecture

    econ.GN 2019-07 unverdicted novelty 3.0

    Machine learning can support personalized choice architecture in behavioral economics by using individual trait and psychological data to design targeted interventions.

  7. Semi-Supervised Learning for Cancer Detection of Lymph Node Metastases

    cs.CV 2019-06 unverdicted novelty 3.0

    A CNN model trained with pseudo-label semi-supervised learning reports higher AUC than a supervised baseline on the PCam histopathology dataset.