Refined tooth and pulp segmentation using U-Net in CBCT image

2021 ◽  
pp. 20200251
Author(s):  
Wei Duan ◽  
Yufei Chen ◽  
Qi Zhang ◽  
Xiang Lin ◽  
Xiaoyu Yang
Keyword(s):  
Deep Learning ◽  
Dental Pulp ◽  
Small Data ◽  
Two Phase ◽  
Valuable Data ◽  
Pulp Cavity ◽  
Structural Problems ◽  
Single Tooth ◽  
Cbct Image ◽  
Feature Pyramid

Objectives The aim of this study was extracting any single tooth from a CBCT scan and performing tooth and pulp cavity segmentation to visualize and to have knowledge of internal anatomy relationships before undertaking endodontic therapy. Methods: We propose a two-phase deep learning solution for accurate tooth and pulp cavity segmentation. First, the single tooth bounding box is extracted automatically for both single-rooted tooth (ST) and multirooted tooth (MT). It is achieved by using the Region Proposal Network (RPN) with Feature Pyramid Network (FPN) method from the perspective of panorama. Second, U-Net model is iteratively performed for refined tooth and pulp segmentation against two types of tooth ST and MT, respectively. In light of rough data and annotation problems for dental pulp, we design a loss function with a smoothness penalty in the network. Furthermore, the multi-view data enhancement is proposed to solve the small data challenge and morphology structural problems. Results: The experimental results show that the proposed method can obtain an average dice 95.7% for ST, 96.2% for MT and 88.6% for pulp of ST, 87.6% for pulp of MT. Conclusions This study proposed a two-phase deep learning solution for fast and accurately extracting any single tooth from a CBCT scan and performing accurate tooth and pulp cavity segmentation. The 3D reconstruction results can completely show the morphology of teeth and pulps, it also provides valuable data for further research and clinical practice.

scholarly journals Automated Counting Grains on the Rice Panicle Based on Deep Learning Method

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 281
Author(s):  
Ruoling Deng ◽  
Ming Tao ◽  
Xunan Huang ◽  
Kemoh Bangura ◽  
Qian Jiang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Model Performance ◽  
Rice Breeding ◽  
Grain Number ◽  
Lighting Condition ◽  
Detection Model ◽  
Grain Moisture ◽  
Feature Pyramid ◽  
Moisture Conditions ◽  
Rice Panicles

Grain number per rice panicle, which directly determines grain yield, is an important agronomic trait for rice breeding and yield-related research. However, manually counting grains of rice per panicle is time-consuming, laborious, and error-prone. In this research, a grain detection model was proposed to automatically recognize and count grains on primary branches of a rice panicle. The model used image analysis based on deep learning convolutional neural network (CNN), by integrating the feature pyramid network (FPN) into the faster R-CNN network. The performance of the grain detection model was compared to that of the original faster R-CNN model and the SSD model, and it was found that the grain detection model was more reliable and accurate. The accuracy of the grain detection model was not affected by the lighting condition in which images of rice primary branches were taken. The model worked well for all rice branches with various numbers of grains. Through applying the grain detection model to images of fresh and dry branches, it was found that the model performance was not affected by the grain moisture conditions. The overall accuracy of the grain detection model was 99.4%. Results demonstrated that the model was accurate, reliable, and suitable for detecting grains of rice panicles with various conditions.

scholarly journals Hierarchical Recognition System for Target Recognition from Sparse Representations

2015 ◽  
Vol 2015 ◽  
pp. 1-6 ◽  
Author(s):  
Zongyong Cui ◽  
Zongjie Cao ◽  
Jianyu Yang ◽  
Hongliang Ren
Keyword(s):  
Deep Learning ◽  
Deep Structure ◽  
Target Recognition ◽  
Recognition System ◽  
Automatic Target Recognition ◽  
Feature Representation ◽  
Small Data ◽  
Learning Method ◽  
Classification Problems ◽  
Restricted Boltzmann Machines

A hierarchical recognition system (HRS) based on constrained Deep Belief Network (DBN) is proposed for SAR Automatic Target Recognition (SAR ATR). As a classical Deep Learning method, DBN has shown great performance on data reconstruction, big data mining, and classification. However, few works have been carried out to solve small data problems (like SAR ATR) by Deep Learning method. In HRS, the deep structure and pattern classifier are combined to solve small data classification problems. After building the DBN with multiple Restricted Boltzmann Machines (RBMs), hierarchical features can be obtained, and then they are fed to classifier directly. To obtain more natural sparse feature representation, the Constrained RBM (CRBM) is proposed with solving a generalized optimization problem. Three RBM variants,L1-RNM,L2-RBM, andL1/2-RBM, are presented and introduced to HRS in this paper. The experiments on MSTAR public dataset show that the performance of the proposed HRS with CRBM outperforms current pattern recognition methods in SAR ATR, like PCA + SVM, LDA + SVM, and NMF + SVM.

scholarly journals Deep Network Guided Proof Search

10.29007/8mwc ◽  
2018 ◽  
Author(s):  
Sarah Loos ◽  
Geoffrey Irving ◽  
Christian Szegedy ◽  
Cezary Kaliszyk
Keyword(s):  
Deep Learning ◽  
Program Analysis ◽  
Network Models ◽  
Theorem Prover ◽  
Neural Network Models ◽  
Two Phase ◽  
First Order ◽  
Proof Search ◽  
System Verification ◽  
Theory Reasoning

Deep learning techniques lie at the heart of several significant AI advances in recent years including object recognition and detection, image captioning, machine translation, speech recognition and synthesis, and playing the game of Go.Automated first-order theorem provers can aid in the formalization and verification of mathematical theorems and play a crucial role in program analysis, theory reasoning, security, interpolation, and system verification.Here we suggest deep learning based guidance in the proof search of the theorem prover E. We train and compare several deep neural network models on the traces of existing ATP proofs of Mizar statements and use them to select processed clauses during proof search. We give experimental evidence that with a hybrid, two-phase approach, deep learning based guidance can significantly reduce the average number of proof search steps while increasing the number of theorems proved.Using a few proof guidance strategies that leverage deep neural networks, we have found first-order proofs of 7.36% of the first-order logic translations of the Mizar Mathematical Library theorems that did not previously have ATP generated proofs. This increases the ratio of statements in the corpus with ATP generated proofs from 56% to 59%.

scholarly journals Evaluation of secondary dentin formation for forensic age assessment by means of semi-automatic segmented ultrahigh field 9.4 T UTE MRI datasets

2020 ◽  
Vol 134 (6) ◽  
pp. 2283-2288
Author(s):  
Maximilian Timme ◽  
Jens Borkert ◽  
Nina Nagelmann ◽  
Andreas Schmeling
Keyword(s):  
Dental Pulp ◽  
Automatic Segmentation ◽  
Tooth Pulp ◽  
Human Teeth ◽  
Age Assessment ◽  
Ultrahigh Field ◽  
Tooth Structure ◽  
Pulp Cavity ◽  
Magnetic Resonance Imaging Mri ◽  
Dentin Formation

Abstract Dental methods are an important element of forensic age assessment of living persons. After the development of all the teeth, including third molars, is completed, degenerative characteristics can be used to assess age. The radiologically detectable reduction of the dental pulp cavity has been described as such a feature. We investigated the suitability of ultrahigh field 9.4 T ultrashort time echo (UTE) magnetic resonance imaging (MRI) for the evaluation of pulp cavity volume in relation to the total tooth volume in 4 extracted human teeth. The volume calculations were performed after semi-automatic segmentation by software AMIRA using the different intensities of the structures in the MRI dataset. The automatically selected intensity range was adjusted manually to the structures. The visual distinction of pulp and tooth structure was possible in all cases with in-plane resolution < 70 μm. Ratios of tooth/pulp volume were calculated, which could be suitable for age estimation procedures. Intensity shifts within the pulp were not always correctly assigned by the software in the course of segmentation. 9.4 T UTE-MRI technology is a forward-looking, radiation-free procedure that allows the volume of the dental pulp to be determined at high spatial resolution and is thus potentially a valuable instrument for the age assessment of living persons.

scholarly journals Unveiling COVID-19 from CHEST X-Ray with Deep Learning: A Hurdles Race with Small Data

2020 ◽  
Vol 17 (18) ◽  
pp. 6933 ◽  
Author(s):  
Enzo Tartaglione ◽  
Carlo Alberto Barbano ◽  
Claudio Berzovini ◽  
Marco Calandri ◽  
Marco Grangetto
Keyword(s):  
Deep Learning ◽  
Scientific Community ◽  
Northern Italy ◽  
Medium Size ◽  
Small Data ◽  
Early Screening ◽  
X Ray ◽  
Chest X Ray ◽  
Statistical Results

The possibility to use widespread and simple chest X-ray (CXR) imaging for early screening of COVID-19 patients is attracting much interest from both the clinical and the AI community. In this study we provide insights and also raise warnings on what is reasonable to expect by applying deep learning to COVID classification of CXR images. We provide a methodological guide and critical reading of an extensive set of statistical results that can be obtained using currently available datasets. In particular, we take the challenge posed by current small size COVID data and show how significant can be the bias introduced by transfer-learning using larger public non-COVID CXR datasets. We also contribute by providing results on a medium size COVID CXR dataset, just collected by one of the major emergency hospitals in Northern Italy during the peak of the COVID pandemic. These novel data allow us to contribute to validate the generalization capacity of preliminary results circulating in the scientific community. Our conclusions shed some light into the possibility to effectively discriminate COVID using CXR.

Sign in / Sign up

Export Citation Format

Share Document