Machine Learning: Using Xception, a Deep Convolutional Neural Network Architecture, to Implement Pectus Excavatum Diagnostic Tool from Frontal-View Chest X-rays

Fan, Yu-Jiun; Tzeng, I‐Shiang; Huang, Yanbo; Hsu, Yuan-Yu; Wei, Bo-Chun; Hung, Shuo-Ting; Cheng, Yeung-Leung

doi:10.3390/biomedicines11030760

Cited by 4 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the classification of angiographic images (i.e., 170 images) was achieved with five pretrained CNN models as shown in Tables 5-9. Several studies have already used pretrained models such as DenseNet, EfficientNet and Xception to classify medical images efficiently which is in line with the result achieved [48,72,73].…”

Section: Discussionsupporting

confidence: 55%

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries

Kaba¹,

Hacı²,

Işın

et al. 2023

Diagnostics

View full text Add to dashboard Cite

In recent years, the prevalence of coronary artery disease (CAD) has become one of the leading causes of death around the world. Accurate stenosis detection of coronary arteries is crucial for timely treatment. Cardiologists use visual estimations when reading coronary angiography images to diagnose stenosis. As a result, they face various challenges which include high workloads, long processing times and human error. Computer-aided segmentation and classification of coronary arteries, as to whether stenosis is present or not, significantly reduces the workload of cardiologists and human errors caused by manual processes. Moreover, deep learning techniques have been shown to aid medical experts in diagnosing diseases using biomedical imaging. Thus, this study proposes the use of automatic segmentation of coronary arteries using U-Net, ResUNet-a, UNet++, models and classification using DenseNet201, EfficientNet-B0, Mobilenet-v2, ResNet101 and Xception models. In the case of segmentation, the comparative analysis of the three models has shown that U-Net achieved the highest score with a 0.8467 Dice score and 0.7454 Jaccard Index in comparison with UNet++ and ResUnet-a. Evaluation of the classification model’s performances has shown that DenseNet201 performed better than other pretrained models with 0.9000 accuracy, 0.9833 specificity, 0.9556 PPV, 0.7746 Cohen’s Kappa and 0.9694 Area Under the Curve (AUC).

show abstract

Section: Discussionsupporting

confidence: 55%

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries

Kaba¹,

Hacı²,

Işın

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Consequently, the correlation of each channel is captured via a regular 3×3 or 5×5 convolution. This idea goes to the extreme of doing 1×1 to each channel, then doing 3×3 to each output [26]. This is identical to replacing the inception module with depth wise separable convolutions.…”

Section: Introductionmentioning

confidence: 99%

Identification of lung disease types using convolutional neural network and VGG-16 architecture

Bukhori,

Verdy,

Windi Eka

et al. 2023

SRIT

View full text Add to dashboard Cite

Pneumonia, tuberculosis, and Covid-19 are different lung diseases but have similar characteristics. One of the reasons for the worsening of disease in lung sufferers is a diagnosis that takes a long time. Another factor, the results of the X-ray photos look blurry and lack contracture, causing different diagnostic results of X-ray photos. This research classifies lung images into four categories: normal lungs, tuberculosis, pneumonia, and Covid-19 using the Convolutional Neural Network method and VGG-16 architecture. The results of the research with models and scenarios without pre-trained use data with a ratio of 9:1 at epoch 50, an accuracy of 94%, while the lowest results are in scenarios using data with a ratio of 8:2 at epoch 50, non-pre-trained models, accuracy by 87%.

show abstract

Pectus excavatum diagnosis redefined: A fully automatic tool for batch evaluation of chest computed tomography images

Fan,

Ng,

Tzeng

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

We aimed to implement a fully automatic computed tomography (CT) image-detection programming algorithm as a pectus excavatum (PE) diagnostic tool, facilitating comprehensive chest wall deformity evaluation. We developed our algorithm using MATLAB®, leveraging the Hounsfield unit threshold and region growing methods. The MATLAB graphical user interface enables the direct use of our program. We validated the model using CT images of anthropomorphic phantoms. The measurement values obtained by our algorithm demonstrated very small difference compared to known anthropomorphic phantom model data. For algorithm testing, 17,214 chest CT images of 57 patients were processed by algorithm and reviewed independently by a radiologist and a thoracic surgeon. The measurements of transverse, anteroposterior, and sternum-to-vertebral distance of the thoracic cavity, and the calculation data of four indices exhibited high positive correlation (0.94 ~ 0.99); asymmetry index and maximum anteroposterior hemithorax distance exhibited moderate correlation (0.40 ~ 0.83). Our automatic PE diagnostic tool demonstrated high accuracy; four chest wall deformity indices were obtained simultaneously without any initial manual marking, which correlated with manual measurements.

show abstract

Machine Learning: Using Xception, a Deep Convolutional Neural Network Architecture, to Implement Pectus Excavatum Diagnostic Tool from Frontal-View Chest X-rays

Cited by 4 publications

References 34 publications

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries

Identification of lung disease types using convolutional neural network and VGG-16 architecture

Pectus excavatum diagnosis redefined: A fully automatic tool for batch evaluation of chest computed tomography images

Contact Info

Product

Resources

About