Fine-Tuning U-Net for Ultrasound Image Segmentation: Different Layers, Different Outcomes

Amiri, Mina; Brooks, Rupert; Rivaz, Hassan

doi:10.1109/tuffc.2020.3015081

Cited by 84 publications

(42 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several approaches to fine-tuning to train the network model [27], but two fine-tuning approaches (ResNet-FC and ResNet-Conv+FC) were shown in this study. Although it is not included in this paper, the full network was trained using initial pretrained weights and was also compared with various layers selected for training.…”

Section: Discussionmentioning

confidence: 94%

“…Owing to the limited training data size, the transfer learning technique was employed instead of training from scratch [21,22,[25][26][27]. The idea of transfer learning is to reuse the trained weights learned from a similar task.…”

Section: Deep Learning Approach 221 Deep Learning Network Architecturementioning

confidence: 99%

“…The idea of transfer learning is to reuse the trained weights learned from a similar task. There are several fine-tuning strategies in transfer learning, including determining whether to freeze or to train the selected layers [27]. The level of fine-tuning in transfer learning can be decided based on the similarity between the pre-training task and the target task and also the characteristics of the data to be utilized.…”

Section: Deep Learning Approach 221 Deep Learning Network Architecturementioning

confidence: 99%

See 2 more Smart Citations

Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography

et al. 2021

View full text Add to dashboard Cite

Mucinous cystic neoplasms (MCN) and serous cystic neoplasms (SCN) account for a large portion of solitary pancreatic cystic neoplasms (PCN). In this study we implemented a convolutional neural network (CNN) model using ResNet50 to differentiate between MCN and SCN. The training data were collected retrospectively from 59 MCN and 49 SCN patients from two different hospitals. Data augmentation was used to enhance the size and quality of training datasets. Fine-tuning training approaches were utilized by adopting the pre-trained model from transfer learning while training selected layers. Testing of the network was conducted by varying the endoscopic ultrasonography (EUS) image sizes and positions to evaluate the network performance for differentiation. The proposed network model achieved up to 82.75% accuracy and a 0.88 (95% CI: 0.817–0.930) area under curve (AUC) score. The performance of the implemented deep learning networks in decision-making using only EUS images is comparable to that of traditional manual decision-making using EUS images along with supporting clinical information. Gradient-weighted class activation mapping (Grad-CAM) confirmed that the network model learned the features from the cyst region accurately. This study proves the feasibility of diagnosing MCN and SCN using a deep learning network model. Further improvement using more datasets is needed.

show abstract

Section: Discussionmentioning

confidence: 94%

Section: Deep Learning Approach 221 Deep Learning Network Architecturementioning

confidence: 99%

Section: Deep Learning Approach 221 Deep Learning Network Architecturementioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Amiri et al. ( 36 ) fine-tuned the U-Net on breast US images and got a mean DSC of 0.80 ± 0.03. Similarly, a DSC of 0.83 to 0.90 was achieved on US images of ovarian cancer using different U-net models in this study.…”

Section: Discussionmentioning

confidence: 99%

Multiple U-Net-Based Automatic Segmentations and Radiomics Feature Stability on Ultrasound Images for Patients With Ovarian Cancer

et al. 2021

View full text Add to dashboard Cite

Few studies have reported the reproducibility and stability of ultrasound (US) images based radiomics features obtained from automatic segmentation in oncology. The purpose of this study is to study the accuracy of automatic segmentation algorithms based on multiple U-net models and their effects on radiomics features from US images for patients with ovarian cancer. A total of 469 US images from 127 patients were collected and randomly divided into three groups: training sets (353 images), validation sets (23 images), and test sets (93 images) for automatic segmentation models building. Manual segmentation of target volumes was delineated as ground truth. Automatic segmentations were conducted with U-net, U-net++, U-net with Resnet as the backbone (U-net with Resnet), and CE-Net. A python 3.7.0 and package Pyradiomics 2.2.0 were used to extract radiomic features from the segmented target volumes. The accuracy of automatic segmentations was evaluated by Jaccard similarity coefficient (JSC), dice similarity coefficient (DSC), and average surface distance (ASD). The reliability of radiomics features were evaluated by Pearson correlation and intraclass correlation coefficients (ICC). CE-Net and U-net with Resnet outperformed U-net and U-net++ in accuracy performance by achieving a DSC, JSC, and ASD of 0.87, 0.79, 8.54, and 0.86, 0.78, 10.00, respectively. A total of 97 features were extracted from the delineated target volumes. The average Pearson correlation was 0.86 (95% CI, 0.83–0.89), 0.87 (95% CI, 0.84–0.90), 0.88 (95% CI, 0.86–0.91), and 0.90 (95% CI, 0.88–0.92) for U-net++, U-net, U-net with Resnet, and CE-Net, respectively. The average ICC was 0.84 (95% CI, 0.81–0.87), 0.85 (95% CI, 0.82–0.88), 0.88 (95% CI, 0.85–0.90), and 0.89 (95% CI, 0.86–0.91) for U-net++, U-net, U-net with Resnet, and CE-Net, respectively. CE-Net based segmentation achieved the best radiomics reliability. In conclusion, U-net based automatic segmentation was accurate enough to delineate the target volumes on US images for patients with ovarian cancer. Radiomics features extracted from automatic segmented targets showed good reproducibility and for reliability further radiomics investigations.

show abstract

“…The pre-trained 3D model (model-A) was trained on the large calcium scoring NCCT datasets. The key to the success of the transfer learning with 3D U-Net is to fine-tune only the shallow layers (contracting path) ( Amiri, Brooks & Rivaz, 2020 ) instead of the whole network. This contracting path represents the more low-level features in the network ( Amiri, Brooks & Rivaz, 2020 ).…”

Section: Methodsmentioning

confidence: 99%

A 3D deep learning approach to epicardial fat segmentation in non-contrast and post-contrast cardiac CT images

Siriapisith

Kusakunniran

Haddawy

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Epicardial fat (ECF) is localized fat surrounding the heart muscle or myocardium and enclosed by the thin-layer pericardium membrane. Segmenting the ECF is one of the most difficult medical image segmentation tasks. Since the epicardial fat is infiltrated into the groove between cardiac chambers and is contiguous with cardiac muscle, segmentation requires location and voxel intensity. Recently, deep learning methods have been effectively used to solve medical image segmentation problems in several domains with state-of-the-art performance. This paper presents a novel approach to 3D segmentation of ECF by integrating attention gates and deep supervision into the 3D U-Net deep learning architecture. The proposed method shows significant improvement of the segmentation performance, when compared with standard 3D U-Net. The experiments show excellent performance on non-contrast CT datasets with average Dice scores of 90.06%. Transfer learning from a pre-trained model of a non-contrast CT to contrast-enhanced CT dataset was also performed. The segmentation accuracy on the contrast-enhanced CT dataset achieved a Dice score of 88.16%.

show abstract

Fine-Tuning U-Net for Ultrasound Image Segmentation: Different Layers, Different Outcomes

Cited by 84 publications

References 35 publications

Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography

Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography

Multiple U-Net-Based Automatic Segmentations and Radiomics Feature Stability on Ultrasound Images for Patients With Ovarian Cancer

A 3D deep learning approach to epicardial fat segmentation in non-contrast and post-contrast cardiac CT images

Contact Info

Product

Resources

About