Fusing enhanced Transformer and large kernel CNN for malignant thyroid nodule segmentation

Li, Geng; Chen, Ruyue; Zhang, Jun; Liu, Kailin; Geng, Chong; Lyu, Lei

doi:10.1016/j.bspc.2023.104636

Cited by 19 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Koundal et al [ 18 ] introduced a method called “Spatial Neutrosophic Distance Regularized Level Set” (SNDRLS) for the identification of thyroid nodules. Li et al [ 19 , 20 ] proposed a deep active contour model for nodule segmentation. Li et al [ 19 , 20 ] introduced a Transformer and CNN-based method for the segmentation of malignant thyroid lesions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Deep-Learning-Based CADx Architecture for Classification of Thyroid Nodules Using Ultrasound Images

Göreke

2023

Interdiscip Sci Comput Life Sci

View full text Add to dashboard Cite

Nodules of thyroid cancer occur in the cells of the thyroid as benign or malign types. Thyroid sonographic images are mostly used for diagnosis of thyroid cancer. The aim of this study is to introduce a computer-aided diagnosis system that can classify the thyroid nodules with high accuracy using the data gathered from ultrasound images. Acquisition and labeling of sub-images were performed by a specialist physician. Then the number of these sub-images were increased using data augmentation methods. Deep features were obtained from the images using a pre-trained deep neural network. The dimensions of the features were reduced and features were improved. The improved features were combined with morphological and texture features. This feature group was rated by a value called similarity coefficient value which was obtained from a similarity coefficient generator module. The nodules were classified as benign or malignant using a multi-layer deep neural network with a pre-weighting layer designed with a novel approach. In this study, a novel multi-layer computer-aided diagnosis system was proposed for thyroid cancer detection. In the first layer of the system, a novel feature extraction method based on the class similarity of images was developed. In the second layer, a novel pre-weighting layer was proposed by modifying the genetic algorithm. The proposed system showed superior performance in different metrics compared to the literature. Graphical Abstract Supplementary Information The online version contains supplementary material available at 10.1007/s12539-023-00560-4.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Li et al [ 19 , 20 ] proposed a deep active contour model for nodule segmentation. Li et al [ 19 , 20 ] introduced a Transformer and CNN-based method for the segmentation of malignant thyroid lesions. Koundal et al [ 21 ] introduced a CAD system for segmentation of thyroid lesions on ultrasound images.…”

Section: Introductionmentioning

confidence: 99%

A Novel Deep-Learning-Based CADx Architecture for Classification of Thyroid Nodules Using Ultrasound Images

Göreke

2023

Interdiscip Sci Comput Life Sci

View full text Add to dashboard Cite

show abstract

“…Using ViT helps to explore global features and provide a more accurate classification model. Geng Li et al proposed a deep-learning-based CAD system and transformer fusing CNN network to segment the malignant thyroid nodule automatically [26].…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Framework for the Characterization of Thyroid Nodules from Ultrasound Images Using Improved Inception Network and Multi-Level Transfer Learning

2023

View full text Add to dashboard Cite

In the past few years, deep learning has gained increasingly widespread attention and has been applied to diagnosing benign and malignant thyroid nodules. It is difficult to acquire sufficient medical images, resulting in insufficient data, which hinders the development of an efficient deep-learning model. In this paper, we developed a deep-learning-based characterization framework to differentiate malignant and benign nodules from the thyroid ultrasound images. This approach improves the recognition accuracy of the inception network by combining squeeze and excitation networks with the inception modules. We have also integrated the concept of multi-level transfer learning using breast ultrasound images as a bridge dataset. This transfer learning approach addresses the issues regarding domain differences between natural images and ultrasound images during transfer learning. This paper aimed to investigate how the entire framework could help radiologists improve diagnostic performance and avoid unnecessary fine-needle aspiration. The proposed approach based on multi-level transfer learning and improved inception blocks achieved higher precision (0.9057 for the benign class and 0.9667 for the malignant class), recall (0.9796 for the benign class and 0.8529 for malignant), and F1-score (0.9412 for benign class and 0.9062 for malignant class). It also obtained an AUC value of 0.9537, which is higher than that of the single-level transfer learning method. The experimental results show that this model can achieve satisfactory classification accuracy comparable to experienced radiologists. Using this model, we can save time and effort as well as deliver potential clinical application value.

show abstract

ETSVF-COVID19: efficient two-stage voting framework for COVID-19 detection

Akyol

2024

Neural Comput & Applic

View full text Add to dashboard Cite

COVID-19 disease, an outbreak in the spring of 2020, reached very alarming dimensions for humankind due to many infected patients during the pandemic and the heavy workload of healthcare workers. Even though we have been saved from the darkness of COVID-19 after about three years, the importance of computer-aided automated systems that support field experts in the fight against with global threat has emerged once again. This study proposes a two-stage voting framework called ETSVF-COVID19 that includes transformer-based deep features and a machine learning approach for detecting COVID-19 disease. ETSVF-COVID19, which offers 99.2% and 98.56% accuracies on computed tomography scan and X-radiation images, respectively, could compete with the related works in the literature. The findings demonstrate that this framework could assist field experts in making informed decisions while diagnosing COVID-19 with its fast and accurate classification role. Moreover, ETSVF-COVID19 could screen for chest infections and help physicians, particularly in areas where test kits and specialist doctors are inadequate.

show abstract

Fusing enhanced Transformer and large kernel CNN for malignant thyroid nodule segmentation

Cited by 19 publications

References 32 publications

A Novel Deep-Learning-Based CADx Architecture for Classification of Thyroid Nodules Using Ultrasound Images

A Novel Deep-Learning-Based CADx Architecture for Classification of Thyroid Nodules Using Ultrasound Images

A Deep Learning Framework for the Characterization of Thyroid Nodules from Ultrasound Images Using Improved Inception Network and Multi-Level Transfer Learning

ETSVF-COVID19: efficient two-stage voting framework for COVID-19 detection

Contact Info

Product

Resources

About