Batch Similarity Based Triplet Loss Assembled into Light-Weighted Convolutional Neural Networks for Medical Image Classification

Huang, Zhiwen; Zhou, Quan; Zhu, Xingxing; Zhang, Xuming

doi:10.3390/s21030764

Cited by 9 publications

(6 citation statements)

References 46 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is not able to measure the similarity of intraclass and inter-class of samples [12], which prevents CL from learning discriminative features of the samples. Therefore, several other loss functions are proposed in deep learning models, such as the contrastive loss, the triplet loss, the triplet lifted structure loss and the triplet hard loss, which are able to learn discriminative features, suppress intra-class change [51], and maximize the gap between different classes [13]. However, they also have some drawbacks.…”

Section: Mixed Lossmentioning

confidence: 99%

Residual neural network with mixed loss based on batch training technique for identification of EGFR mutation status in lung cancer

Jia

Hou

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

Epidermal growth factor receptor (EGFR) is the key to targeted therapy with tyrosine kinase inhibitors in lung cancer. Traditional identification of EGFR mutation status requires biopsy and sequence testing, which may not be suitable for certain groups who cannot perform biopsy. In this paper, using easily accessible and non-invasive CT images, the residual neural network (ResNet) with mixed loss based on batch training technique is proposed for identification of EGFR mutation status in lung cancer. In this model, the ResNet is regarded as the baseline for feature extraction to avoid the gradient disappearance. Besides, a new mixed loss based on the batch similarity and the cross entropy is proposed to guide the network to better learn the model parameters. The proposed mixed loss utilizes the similarity among batch samples to evaluate the distribution of training data, which can reduce the similarity of different classes and the difference of the same classes. In the experiments, VGG16Net, DenseNet, ResNet18, ResNet34 and ResNet50 models with the mixed loss are trained on the public CT dataset with 155 patients including EGFR mutation status from TCIA. The trained networks are employed to the collected preoperative CT dataset with 56 patients from the cooperative hospital for validating the efficiency of the proposed models. Experimental results show that the proposed models are more appropriate and effective on the lung cancer dataset for identifying the EGFR mutation status. In these models, the ResNet34 with mixed loss is optimal (accuracy = 81.58%, AUC = 0.8861, sensitivity = 80.02%, specificity = 82.90%).

show abstract

Section: Mixed Lossmentioning

confidence: 99%

Residual neural network with mixed loss based on batch training technique for identification of EGFR mutation status in lung cancer

Jia

Hou

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…To overcome the problem of imbalance of images in the dataset, Lei et al [28] proposed a novel class-centre involving triplet loss for the classification of skin disease. Huang et al [29] proposed novel batch similarity-based triplet loss, which takes into account the similarity among the input images to group images of the same class and separate images of a different class, along with crossentropy loss to improve the performance of light-weighted CNN models for the problem of medical image classification.…”

Section: B Deep Metric Learning On Medical Images Classificationmentioning

confidence: 99%

Biceph-Net: A robust and lightweight framework for the diagnosis of Alzheimer's disease using 2D-MRI scans and deep similarity learning

Rashid,

Gupta,

Gupta

et al. 2022

Preprint

View full text Add to dashboard Cite

Alzheimer's Disease (AD) is a neurodegenerative disease that is one of the significant causes of death in the elderly population. Many deep learning techniques have been proposed to diagnose AD using Magnetic Resonance Imaging (MRI) scans. Predicting AD using 2D slices extracted from 3D MRI scans is challenging as the inter-slice information gets lost. To this end, we propose a novel and lightweight framework termed 'Biceph-Net' for AD diagnosis using 2D MRI scans that model both the intra-slice and inter-slice information. 'Biceph-Net' has been experimentally shown to perform similar to other Spatio-temporal neural networks while being computationally more efficient. Biceph-Net is also superior in performance compared to vanilla 2D convolutional neural networks (CNN) for AD diagnosis using 2D MRI slices. Biceph-Net also has an inbuilt neighbourhood-based model interpretation feature that can be exploited to understand the classification decision taken by the network. Biceph-Net experimentally achieves a test accuracy of 100% in the classification of Cognitively Normal (CN) vs AD, 98.16% for Mild Cognitive Impairment (MCI) vs AD, and 97.80% for CN vs MCI vs AD.

show abstract

“…To capture information from the third axis, most studies in VMI analysis utilize global average pooling [7]. However, in fine-grained image recognition (FGIR) community, bilinear encoding is widely used as an aggregation function [12].…”

Section: Introductionmentioning

confidence: 99%

Moving from 2D to 3D: Volumetric Medical Image Classification for Rectal Cancer Staging

Lee

Shin

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Volumetric images from Magnetic Resonance Imaging (MRI) provide invaluable information in preoperative staging of rectal cancer. Above all, accurate preoperative discrimination between T2 and T3 stages is arguably both the most challenging and clinically significant task for rectal cancer treatment, as chemo-radiotherapy is usually recommended to patients with T3 (or greater) stage cancer. In this study, we present a volumetric convolutional neural network to accurately discriminate T2 from T3 stage rectal cancer with rectal MR volumes. Specifically, we propose 1) a custom ResNet-based volume encoder that models the inter-slice relationship with late fusion (i.e., 3D convolution at the last layer), 2) a bilinear computation that aggregates the resulting features from the encoder to create a volume-wise feature, and 3) a joint minimization of triplet loss and focal loss. With MR volumes of pathologically confirmed T2/T3 rectal cancer, we perform extensive experiments to compare various designs within the framework of residual learning. As a result, our network achieves an AUC of 0.831, which is higher than the reported accuracy of the professional radiologist groups. We believe this method can be extended to other volume analysis tasks.

show abstract

Batch Similarity Based Triplet Loss Assembled into Light-Weighted Convolutional Neural Networks for Medical Image Classification

Cited by 9 publications

References 46 publications

Residual neural network with mixed loss based on batch training technique for identification of EGFR mutation status in lung cancer

Residual neural network with mixed loss based on batch training technique for identification of EGFR mutation status in lung cancer

Biceph-Net: A robust and lightweight framework for the diagnosis of Alzheimer's disease using 2D-MRI scans and deep similarity learning

Moving from 2D to 3D: Volumetric Medical Image Classification for Rectal Cancer Staging

Contact Info

Product

Resources

About