Nuclear atypia grading in breast cancer histopathological images based on CNN feature extraction and LSTM classification

Early diagnosis of breast cancer,the most common disease among women around the world,increases the chance of treatment and is highly important.Nuclear atypia grading in histopathological images plays an important role in the final diagnosis and grading ofbreast cancer.Grading images by pathologists is a time consuming and subjective task.Therefore,the existence of a computer-aided system for nuclear atypia grading is very useful and necessary;In this stud%two automatic systems for grading nuclear atypia in breast cancer histopathological images based on deep learning methods are proposed.A patch-based approach is introduced due to the large size of the histopathological images and restriction of the training data.In the proposed system I,the most important patches in the image are detected first and then a three-hidden-layer convolutional neural network(CNN)is designed and trained for feature extraction and to classify the patches individually.The proposed system II is based on a combination of the CNN for feature extraction and a two-layer Long short-term memoty(LSTM)network for classification.The LSTM network is utilised to consider all patches of an image simultaneously for image grading.The simulation results show the efficiency of the proposed systems for automatic nuclear atypia grading and outperform the current related studies in the literature.

Image Tamper Detection and Multi-Scale Self-Recovery Using Reference Embedding with Multi-Rate Data Protection

This paper proposes a multi-scale self-recovery(MSSR)approach to protect images against content forgery.The main idea is to provide more resistance against image tampering while enabling the recovery process in a multi-scale quality manner.In the proposed approach,the reference data composed of several parts and each part is protected by a channel coding rate according to its importance.The first part,which is used to reconstruct a rough approximation of the original image,is highly protected in order to resist against higher tampering rates.Other parts are protected with lower rates according to their importance leading to lower tolerable tampering rate(TTR),but the higher quality of the recovered images.The proposed MSSR approach is an efficient solution for the main disadvantage of the current methods,which either recover a tampered image in low tampering rates or fails when tampering rate is above the TTR value.The simulation results on 10000 test images represent the efficiency of the multi-scale self-recovery feature of the proposed approach in comparison with the existing methods.