Fine-tuning Pre-trained Convolutional Neural Networks for Gastric Precancerous Disease Classification on Magnification Narrow-band Imaging Images

Liu, Xiaoqi; Wang, Cheng-Liang; Bai, Jianying; Liao, Guobin

doi:10.1016/j.neucom.2018.10.100

Cited by 54 publications

(31 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea is that the convolutional neural network (CNN) layers [ 15 ] are trained so that the model can be used for other tasks. In the transfer learning [ 16 ] used below, only the dense layers (fully connected layer) are trained, but the CNN layers are kept constant. This is often combined with a fine-tuning step [ 17 ].…”

Section: Methodsmentioning

confidence: 99%

Use of deep learning for structural analysis of computer tomography images of soil samples

et al. 2021

View full text Add to dashboard Cite

Soil samples from several European countries were scanned using medical computer tomography (CT) device and are now available as CT images. The analysis of these samples was carried out using deep learning methods. For this purpose, a VGG16 network was trained with the CT images (X). For the annotation (y) a new method for automated annotation, ‘surrogate’ learning, was introduced. The generated neural networks (NNs) were subjected to a detailed analysis. Among other things, transfer learning was used to check whether the NN can also be trained to other y-values. Visually, the NN was verified using a gradient-based class activation mapping (grad-CAM) algorithm. These analyses showed that the NN was able to generalize, i.e. to capture the spatial structure of the soil sample. Possible applications of the models are discussed.

show abstract

Section: Methodsmentioning

confidence: 99%

Use of deep learning for structural analysis of computer tomography images of soil samples

et al. 2021

View full text Add to dashboard Cite

show abstract

“…accuracy of 95% when using transfer learning. [30] Here, we trained both ResNet-50 and VGG-16 using transfer learning for predicting EGC, and their combined results achieved an accuracy of 92.5% in still images. The results of two types of CNNs were combined to reduce the rate of miss-selection of a single classifier.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial

Liu

et al. 2021

Endoscopy

102

View full text Add to dashboard Cite

Background and study aims: Qualified esophagogastroduodenoscopy (EGD) is a prerequisite for detecting upper gastrointestinal lesions especially early gastric cancer (EGC). Our previous report showed that artificial intelligence system could monitor blind spots during EGD. Here, we updated the system to a new one (named ENDOANGEL), verified its effectiveness on improving endoscopy quality and pre-tested its performance on detecting EGC in a multi-center randomized controlled trial. Patients and methods: ENDOANGEL was developed using deep convolutional neural networks and deep reinforcement learning. Patients undergoing EGD examination in 5 hospitals were randomly assigned to ENDOANGEL-assisted (EA) group or normal control (NC) group. The primary outcome was the number of blind spots. The second outcome includes performance of ENDOANGEL on predicting EGC in clinical setting. Results: 1,050 patients were recruited and randomized. 498 and 504 patients in EA and NC groups were respectively analyzed. Compared with NC, the number of blind spots was less (5.382±4.315 vs. 9.821±4.978, p<0.001) and the inspection time was prolonged (5.400±3.821 min vs. 4.379±3.907 min, p<0.001) in EA group. In the 498 patients from EA group, 196 gastric lesions with pathological results were identified. ENDOANGEL correctly predicted all 3 EGC (1 mucosal carcinoma and 2 high-grade neoplasia) and 2 advanced gastric cancer, with a per-lesion accuracy of 84.69%, sensitivity of 100% and specificity of 84.29% for detecting GC. Conclusions: The results of the multi-center study confirmed that ENDOANGEL is an effective and robust system to improve the quality of EGD and has the potential to detect EGC in real time.

show abstract

“…The weakly supervised neural model has been utilized for stomach ulcer detection. The extracted features from [43] VGG model and transferred as input to the classifiers for gastric ulcers classification [44]. Classical deep model has been utilized for stomach ulcer classification on 5560 images of WCE into ulcers, erosions/normal classes and its achieved accuracy of 90.8% [45].…”

Section: Related Workmentioning

confidence: 99%

3D-semantic segmentation and classification of stomach infections using uncertainty aware deep neural networks

Amin

Sharif

Gul

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Wireless capsule endoscopy (WCE) might move through human body and captures the small bowel and captures the video and require the analysis of all frames of video due to which the diagnosis of gastrointestinal infections by the physician is a tedious task. This tiresome assignment has fuelled the researcher’s efforts to present an automated technique for gastrointestinal infections detection. The segmentation of stomach infections is a challenging task because the lesion region having low contrast and irregular shape and size. To handle this challenging task, in this research work a new deep semantic segmentation model is suggested for 3D-segmentation of the different types of stomach infections. In the segmentation model, deep labv3 is employed as a backbone of the ResNet-50 model. The model is trained with ground-masks and accurately performs pixel-wise classification in the testing phase. Similarity among the different types of stomach lesions accurate classification is a difficult task, which is addressed in this reported research by extracting deep features from global input images using a pre-trained ResNet-50 model. Furthermore, the latest advances in the estimation of uncertainty and model interpretability in the classification of different types of stomach infections is presented. The classification results estimate uncertainty related to the vital features in input and show how uncertainty and interpretability might be modeled in ResNet-50 for the classification of the different types of stomach infections. The proposed model achieved up to 90% prediction scores to authenticate the method performance.

show abstract

Fine-tuning Pre-trained Convolutional Neural Networks for Gastric Precancerous Disease Classification on Magnification Narrow-band Imaging Images

Cited by 54 publications

References 14 publications

Use of deep learning for structural analysis of computer tomography images of soil samples

Use of deep learning for structural analysis of computer tomography images of soil samples

Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial

3D-semantic segmentation and classification of stomach infections using uncertainty aware deep neural networks

Contact Info

Product

Resources

About