A Transfer Learning Evaluation of Deep Neural Networks for Image Classification

Baker, Nermeen Abou; Zengeler, Nico; Handmann, Uwe

doi:10.3390/make4010002

Cited by 38 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By leveraging the pre-trained model's learned features, the newly-trained model can benefit from the general knowledge captured during the pre-training phase, which can lead to enhanced performance, quicker convergence, and a reduced need for training data. The weights of the pre-trained model are typically kept constant 25 . This enables the model to learn task-specific characteristics while retaining the valuable information acquired during pre-training.…”

Section: Methodsmentioning

confidence: 99%

Transfer learning of pre-treatment quantitative ultrasound multi-parametric images for the prediction of breast cancer response to neoadjuvant chemotherapy

Falou,

Sannachi,

Haque

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Locally advanced breast cancer (LABC) is a severe type of cancer with a poor prognosis, despite advancements in therapy. As the disease is often inoperable, current guidelines suggest upfront aggressive neoadjuvant chemotherapy (NAC). Complete pathological response to chemotherapy is linked to improved survival, but conventional clinical assessments like physical exams, mammography, and imaging are limited in detecting early response. Early detection of tissue response can improve complete pathological response and patient survival while reducing exposure to ineffective and potentially harmful treatments. A rapid, cost-effective modality without the need for exogenous contrast agents would be valuable for evaluating neoadjuvant therapy response. Conventional ultrasound provides information about tissue echogenicity, but image comparisons are difficult due to instrument-dependent settings and imaging parameters. Quantitative ultrasound (QUS) overcomes this by using normalized power spectra to calculate quantitative metrics. This study used a novel transfer learning-based approach to predict LABC response to neoadjuvant chemotherapy using QUS imaging at pre-treatment. Using data from 174 patients, QUS parametric images of breast tumors with margins were generated. The ground truth response to therapy for each patient was based on standard clinical and pathological criteria. The Residual Network (ResNet) deep learning architecture was used to extract features from the parametric QUS maps. This was followed by SelectKBest and Synthetic Minority Oversampling (SMOTE) techniques for feature selection and data balancing, respectively. The Support Vector Machine (SVM) algorithm was employed to classify patients into two distinct categories: nonresponders (NR) and responders (RR). Evaluation results on an unseen test set demonstrate that the transfer learning-based approach using spectral slope parametric maps had the best performance in the identification of nonresponders with precision, recall, F1-score, and balanced accuracy of 100, 71, 83, and 86%, respectively. The transfer learning-based approach has many advantages over conventional deep learning methods since it reduces the need for large image datasets for training and shortens the training time. The results of this study demonstrate the potential of transfer learning in predicting LABC response to neoadjuvant chemotherapy before the start of treatment using quantitative ultrasound imaging. Prediction of NAC response before treatment can aid clinicians in customizing ineffectual treatment regimens for individual patients.

show abstract

Section: Methodsmentioning

confidence: 99%

Transfer learning of pre-treatment quantitative ultrasound multi-parametric images for the prediction of breast cancer response to neoadjuvant chemotherapy

Falou,

Sannachi,

Haque

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The paper explores the process of selecting the most suitable pre-trained model for image classification tasks using transfer learning. The study involves refining the output layers and network parameters of eleven pretrained image processing models (8) on ImageNet and applying them to five different target domain datasets.…”

Section: Summary Of Previous Workmentioning

confidence: 99%

HybridTransferNet: Advancing Soil Image Classification through Comprehensive Evaluation of Hybrid Transfer Learning

R¹,

Ashoka²,

2023

Preprint

View full text Add to dashboard Cite

Soil image classification is an important task in agricultural and environmental applications. With the advent of deep learning, image-based soil classification has become a popular research topic. Transfer learning is a widely used approach in image classification, where a pre-trained model is fine-tuned on a new dataset. However, traditional transfer learning approaches only fine-tune the last layer of the pre-trained model, which may not be sufficient for achieving high performance on a new task. In this paper, we propose HybridTransferNet, a novel hybrid transfer learning approach for image-based soil classification. HybridTransferNet fine-tunes a small number of earlier layers in addition to the last layer of a pre-trained ResNet50 model, resulting in improved classification performance compared to traditional transfer learning approaches. We evaluate HybridTransferNet on a soil classification dataset and report multiple performance metrics, including accuracy, precision, recall, and F1 score. Our experimental results show that HybridTransferNet outperforms traditional transfer learning approaches and achieves state-of-the-art performance on the soil classification task.

show abstract

“…A collection of automated learning techniques known as deep learning that are built from several layers of artificial neural networks. Therefore, the most accurate learning models of deep learning techniques are automatic feature extraction [4,5].…”

Section: Introductionmentioning

confidence: 99%

The Novel of Using Transfer Learning Approach for Seatbelts Automated Surveillance

Salih,

Alkhalid

2024

IJTDI

View full text Add to dashboard Cite

The number of cars on the road has increased significantly as a result of the development of society, and this is one of the problems that traffic officials have focused on when diagnosing seat belts. With the increase in traffic accidents in recent years due to drivers not adhering to safety rules, it has become necessary to focus on this area. Seat belt diagnosis is an important rule that must be followed in the field of deep learning. In this paper, transfer learning is applied in seat belt diagnosis to reduce the number of risks and to protect passengers and drivers from traffic accidents when the seat belt is not used. The Xception model is proposed because this model has very deep hidden layers which leads to good metrics, the model is trained on the ImagNet dataset using fine-tuning learning. We find that previous training on ImageNet leads to a significant increase in the efficiency of the proposed architecture and extracts the important feature in a variety of situations to determine whether the driver has fastened his seat belt or not. The results show that the model can inspect seat belts with a high accuracy of 99.42% and a loss function of 8.15%.

show abstract

A Transfer Learning Evaluation of Deep Neural Networks for Image Classification

Cited by 38 publications

References 31 publications

Transfer learning of pre-treatment quantitative ultrasound multi-parametric images for the prediction of breast cancer response to neoadjuvant chemotherapy

Transfer learning of pre-treatment quantitative ultrasound multi-parametric images for the prediction of breast cancer response to neoadjuvant chemotherapy

HybridTransferNet: Advancing Soil Image Classification through Comprehensive Evaluation of Hybrid Transfer Learning

The Novel of Using Transfer Learning Approach for Seatbelts Automated Surveillance

Contact Info

Product

Resources

About