• Corpus ID: 195345090

Semi-Supervised Learning for Cancer Detection of Lymph Node Metastases

  title={Semi-Supervised Learning for Cancer Detection of Lymph Node Metastases},
  author={Amit Kumar Jaiswal and Ivan Panshin and D. Shulkin and Nagender Aneja and Samuel Abramov},
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… 

Figures and Tables from this paper

An Enhanced Deep Learning Architecture for the Classification of Cancerous Lymph Node Images

A novel architecture aimed at classifying sections of lymph node scans and incorporating the successful enhancement features with a ResNet-50 leads to a new strategy to identify the presence of metastatic cancer in lymph node patch images.

A novel attention fusion network-based framework to ensemble the predictions of CNNs for lymph node metastasis detection

The proposed ensemble framework comprises different pre-trained CNN models such as DenseNet201, InceptionV3 and ResNeXt-50 and achieves an AUC-ROC of 0.9816 which surpasses the highest A UC-R OC achieved by the conventional approaches on the PCam benchmark dataset.

Dynamic Learning Rate in Deep CNN Model for Metastasis Detection and Classification of Histopathology Images

This work emphasizes the relevance of the dynamic learning rate than the fixed learning rate during the training of networks, which is the crucial hyperparameter used during theTraining of deep convolutional neural networks (DCNN) to improve model accuracy.

Optimized Light-Weight Convolutional Neural Networks for Histopathologic Cancer Detection

EfficientNet-B6 CNN model for histopathologic cancer detection is considered and different activation functions as well as gradient descent optimization algorithms are applied, to analyze its effects on diagnosis accuracy.

3D Texture Feature-Based Lymph Node Automated Detection in Head and Neck Cancer Analysis

A systematic machine learning approach to detect lymph node region from computed tomography (CT) scans based on 3D texture features and it is demonstrated that gradient boosting model with feature agglomeration and low variance threshold achieves the test accuracy of 94.48%.


The survey focuses on two major issues usually faced by CNN-based methods namely the design of an appropriate CNN architecture and the lack of a sufficient labelled dataset for training the model.

Semi-supervised learning in cancer diagnostics

This review provides a comprehensive overview of essential functionalities and assumptions of SSL, highlights current state-of-the-art models in histopathology, radiology and radiotherapy, as well as genomics and point out future directions for SSL in oncology.

Towards label-efficient automatic diagnosis and analysis: a comprehensive survey of advanced deep learning-based weakly-supervised, semi-supervised and self-supervised techniques in histopathological image analysis

A comprehensive and systematic review of the latest studies on weakly supervised learning, semi-supervised learning, and self-super supervised learning in the field of computational pathology from both technical and methodological perspectives is presented.

Deep Learning-Based Smart IoT Health System for Blindness Detection Using Retina Images

This paper proposes an optimized technique on top of recently released pre-trained EfficientNet models for blindness identification in retinal images along with a comparative analysis among various other neural network models that outperforms CNN and ResNet50 models.



Detecting Cancer Metastases on Gigapixel Pathology Images

This work presents a framework to automatically detect and localize tumors as small as 100 x 100 pixels in gigapixel microscopy images sized 100,000 x100,000 pixels and achieves image-level AUC scores above 97% on both the Camelyon16 test set and an independent set of 110 slides.

Deep Learning for Identifying Metastatic Breast Cancer

The power of using deep learning to produce significant improvements in the accuracy of pathological diagnoses is demonstrated, by combining the deep learning system's predictions with the human pathologist's diagnoses.

Using Transfer Learning to Detect Breast Cancer without Network Training

A method to complete the breast cancer detection by incomplete sampling of the features of the transfer learning output without network training is proposed and verified on Camelyon16 dataset.

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer

In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints.

Impact of Deep Learning Assistance on the Histopathologic Review of Lymph Nodes for Metastatic Breast Cancer

The potential of a deep learning algorithm to improve pathologist accuracy and efficiency in a digital pathology workflow is demonstrated by a multireader multicase study utilizing a proof of concept assistant tool.

Rotation Equivariant CNNs for Digital Pathology

This work proposes a new model for digital pathology segmentation, based on the observation that histopathology images are inherently symmetric under rotation and reflection, and presents a novel derived dataset to enable principled comparison of machine learning models, in combination with an initial benchmark.

Histopathological Breast Cancer Image Classification by Deep Neural Network Techniques Guided by Local Clustering

A Convolutional Neural Network, a Long-Short-Term-Memory (LSTM), and a combination of CNN and LSTM are proposed for breast cancer image classification using novel DNN techniques guided by structural and statistical information derived from the images.

Prostate Histopathology: Learning Tissue Component Histograms for Cancer Detection and Classification

This system represents a first step toward automated cancer quantification on prostate digital histopathology imaging, which could pave the way for more accurately informed postprostatectomy patient care.

Computer aided lung cancer diagnosis with deep learning algorithms

This study tested the feasibility of using deep learning algorithms for lung cancer diagnosis with the cases from Lung Image Database Consortium (LIDC) database, including Convolutional Neural Network, Deep Belief Networks, and Stacked Denoising Autoencoder.

A Dataset for Breast Cancer Histopathological Image Classification

A dataset of 7909 breast cancer histopathology images acquired on 82 patients, which is now publicly available from http://web.ufpr.br/vri/breast-cancer-database, aimed at automated classification of these images in two classes, which would be a valuable computer-aided diagnosis tool for the clinician.