Semi-supervised learning for cancer detection of lymph node metastases

Amit Kumar Jaiswal; Ivan Panshin; Dimitrij Shulkin; Nagender Aneja; Samuel Abramov

doi:10.5281/zenodo.3251086

Semi-supervised learning for cancer detection of lymph node metastases

Amit Kumar Jaiswal
, Ivan Panshin
, Dimitrij Shulkin
, Nagender Aneja
, Samuel Abramov

Institute for Research in Applicable Computing (IRAC)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Downloads (Pure)

Abstract

Pathologists find tedious to examine the status of the sentinel lymph node on a large number of pathological scans. The examination process of such lymph node which encompasses metastasized cancer cells is histopathologically organized. However, the task of finding metastatic tissues is gradual which is often challenging. In this work, we present our deep convolutional neural network based model validated on PatchCamelyon (PCam) benchmark dataset for fundamental machine learning research in histopathology diagnosis. We find that our proposed model trained with a semi-supervised learning approach by using pseudo labels on PCam-level significantly leads to better performances to strong CNN baseline on the AUC metric.

Original language	English
Title of host publication	nan
DOIs	https://doi.org/10.5281/zenodo.3251086
Publication status	Published - 14 Jun 2019
Event	CVPR - Towards Causal, Explainable and Universal Medical Visual Diagnosis - Long Beach Duration: 16 Jun 2019 → … http://s1155026040.github.io/mvd-2019-cvpr-workshop/

Conference

Conference	CVPR - Towards Causal, Explainable and Universal Medical Visual Diagnosis
City	Long Beach
Period	16/06/19 → …
Other	CVPR - Towards Causal, Explainable and Universal Medical Visual Diagnosis (16/06/2019, Long Beach)
Internet address	http://s1155026040.github.io/mvd-2019-cvpr-workshop/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Neural Networks
cancer detection
semi-supervised learning

Access to Document

10.5281/zenodo.3251086

MVD CVPRAccepted author manuscript, 400 KBLicence: CC BY-NC-ND

https://zenodo.org/record/3246577

Handle.net

Persistent link

Cite this

@inproceedings{b402ffb32c134ac9a2459da03937b276,

title = "Semi-supervised learning for cancer detection of lymph node metastases",

abstract = "Pathologists find tedious to examine the status of the sentinel lymph node on a large number of pathological scans. The examination process of such lymph node which encompasses metastasized cancer cells is histopathologically organized. However, the task of finding metastatic tissues is gradual which is often challenging. In this work, we present our deep convolutional neural network based model validated on PatchCamelyon (PCam) benchmark dataset for fundamental machine learning research in histopathology diagnosis. We find that our proposed model trained with a semi-supervised learning approach by using pseudo labels on PCam-level significantly leads to better performances to strong CNN baseline on the AUC metric.",

keywords = "Neural Networks, cancer detection, semi-supervised learning",

author = "Jaiswal, \{Amit Kumar\} and Ivan Panshin and Dimitrij Shulkin and Nagender Aneja and Samuel Abramov",

year = "2019",

month = jun,

day = "14",

doi = "10.5281/zenodo.3251086",

language = "English",

booktitle = "nan",

note = "CVPR - Towards Causal, Explainable and Universal Medical Visual Diagnosis ; Conference date: 16-06-2019",

url = "http://s1155026040.github.io/mvd-2019-cvpr-workshop/",

}

TY - GEN

T1 - Semi-supervised learning for cancer detection of lymph node metastases

AU - Jaiswal, Amit Kumar

AU - Panshin, Ivan

AU - Shulkin, Dimitrij

AU - Aneja, Nagender

AU - Abramov, Samuel

PY - 2019/6/14

Y1 - 2019/6/14

N2 - Pathologists find tedious to examine the status of the sentinel lymph node on a large number of pathological scans. The examination process of such lymph node which encompasses metastasized cancer cells is histopathologically organized. However, the task of finding metastatic tissues is gradual which is often challenging. In this work, we present our deep convolutional neural network based model validated on PatchCamelyon (PCam) benchmark dataset for fundamental machine learning research in histopathology diagnosis. We find that our proposed model trained with a semi-supervised learning approach by using pseudo labels on PCam-level significantly leads to better performances to strong CNN baseline on the AUC metric.

AB - Pathologists find tedious to examine the status of the sentinel lymph node on a large number of pathological scans. The examination process of such lymph node which encompasses metastasized cancer cells is histopathologically organized. However, the task of finding metastatic tissues is gradual which is often challenging. In this work, we present our deep convolutional neural network based model validated on PatchCamelyon (PCam) benchmark dataset for fundamental machine learning research in histopathology diagnosis. We find that our proposed model trained with a semi-supervised learning approach by using pseudo labels on PCam-level significantly leads to better performances to strong CNN baseline on the AUC metric.

KW - Neural Networks

KW - cancer detection

KW - semi-supervised learning

U2 - 10.5281/zenodo.3251086

DO - 10.5281/zenodo.3251086

M3 - Conference contribution

BT - nan

T2 - CVPR - Towards Causal, Explainable and Universal Medical Visual Diagnosis

Y2 - 16 June 2019

ER -

Semi-supervised learning for cancer detection of lymph node metastases

Abstract

Conference

UN SDGs

Keywords

Access to Document

Handle.net

Fingerprint

Cite this