An Ultrasonic Image Recognition Method for Papillary Thyroid Carcinoma Based on Depth Convolution Neural Network

2017 ◽  
pp. 82-91
Author(s):  
Wei Ke ◽  
Yonghua Wang ◽  
Pin Wan ◽  
Weiwei Liu ◽  
Hailiang Li
Keyword(s):  
Neural Network ◽  
Papillary Thyroid Carcinoma ◽  
Thyroid Carcinoma ◽  
Image Recognition ◽  
Convolution Neural Network ◽  
Papillary Thyroid ◽  
Recognition Method ◽  
Ultrasonic Image

Classification of papillary thyroid carcinoma histological images based on deep learning

2021 ◽  
pp. 1-11
Author(s):  
Yaning Liu ◽  
Lin Han ◽  
Hexiang Wang ◽  
Bo Yin
Keyword(s):  
Neural Network ◽  
Differential Diagnosis ◽  
Deep Learning ◽  
Papillary Thyroid Carcinoma ◽  
Thyroid Carcinoma ◽  
Image Features ◽  
Papillary Thyroid ◽  
Histological Image ◽  
Histological Images

Papillary thyroid carcinoma (PTC) is a common carcinoma in thyroid. As many benign thyroid nodules have the papillary structure which could easily be confused with PTC in morphology. Thus, pathologists have to take a lot of time on differential diagnosis of PTC besides personal diagnostic experience and there is no doubt that it is subjective and difficult to obtain consistency among observers. To address this issue, we applied deep learning to the differential diagnosis of PTC and proposed a histological image classification method for PTC based on the Inception Residual convolutional neural network (IRCNN) and support vector machine (SVM). First, in order to expand the dataset and solve the problem of histological image color inconsistency, a pre-processing module was constructed that included color transfer and mirror transform. Then, to alleviate overfitting of the deep learning model, we optimized the convolution neural network by combining Inception Network and Residual Network to extract image features. Finally, the SVM was trained via image features extracted by IRCNN to perform the classification task. Experimental results show effectiveness of the proposed method in the classification of PTC histological images.

Artificial Neural Network Analysis of Geo Database in Diagnosing Papillary Thyroid Carcinoma

2021 ◽  
Author(s):  
zhoujing zhang ◽  
di xu ◽  
Ozioma Akakuru ◽  
wenjing xu ◽  
yewei zhang
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Artificial Neural Network ◽  
Papillary Thyroid Carcinoma ◽  
Thyroid Carcinoma ◽  
Network Models ◽  
Papillary Thyroid ◽  
Neural Network Models ◽  
Artificial Neural ◽  
Artificial Neural Network Models

The diagnosis of papillary thyroid carcinoma has always been a concerned and challenging issue and it is very important and meaningful to have a definite diagnosis before the operation. In this study, we tried to use an artificial intelligence algorithm instead of medical statistics to analyze the genetic fingerprint from gene chip results to identify papillary thyroid carcinoma. We trained 20 artificial neural network models with differential genes and other important genes related to the cell metabolic cycle as the list of input features, and apply them to the diagnosis of papillary thyroid cancer in the independent validation data set. The results showed that when we used the DEGs and all genes lists as input features the models got the best diagnostic performance with AUC=98.97% and 99.37% and the accuracy were both 96%. This study revealed that the proposed artificial neural network models constructed with genetic fingerprints could achieve a prediction of papillary thyroid carcinoma. Such models can support clinicians to make more accurate clinical diagnoses. At the same time, it provides a novel idea for the application of artificial intelligence in clinical medicine.

scholarly journals Vegetable Pest Image Recognition Method Based on Improved VGG Convolution Neural Network

2019 ◽  
Vol 1237 ◽  
pp. 032018
Author(s):  
Haijian Ye ◽  
Hang Han ◽  
Linna Zhu ◽  
Qingling Duan
Keyword(s):  
Neural Network ◽  
Image Recognition ◽  
Convolution Neural Network ◽  
Recognition Method

scholarly journals Mapping Driver Mutations to Histopathological Subtypes in Papillary Thyroid Carcinoma: Applying a Deep Convolutional Neural Network

2019 ◽  
Vol 8 (10) ◽  
pp. 1675 ◽  
Author(s):  
Peiling Tsou ◽  
Chang-Jiun Wu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Papillary Thyroid Carcinoma ◽  
Thyroid Carcinoma ◽  
Convolutional Neural Network ◽  
The Cancer Genome Atlas ◽  
Driver Mutations ◽  
Papillary Thyroid ◽  
Validation Data ◽  
Ras Mutations

Papillary thyroid carcinoma (PTC) is the most common subtype of thyroid cancers and informative biomarkers are critical for risk stratification and treatment guidance. About half of PTCs harbor BRAFV600E and 10%–15% have RAS mutations. In the current study, we trained a deep learning convolutional neural network (CNN) model (Google Inception v3) on histopathology images obtained from The Cancer Genome Atlas (TCGA) to classify PTCs into BRAFV600E or RAS mutations. We aimed to answer whether CNNs can predict driver gene mutations using images as the only input. The performance of our method is comparable to that of recent publications of other cancer types using TCGA tumor slides with area under the curve (AUC) of 0.878–0.951. Our model was tested on separate tissue samples from the same cohort. On the independent testing subset, the accuracy rate using the cutoff of truth rate 0.8 was 95.2% for BRAF and RAS mutation class prediction. Moreover, we showed that the image-based classification correlates well with mRNA-derived expression pattern (Spearman correlation, rho = 0.63, p = 0.002 on validation data and rho = 0.79, p = 2 × 10−5 on final testing data). The current study demonstrates the potential of deep learning approaches for histopathologically classifying cancer based on driver mutations. This information could be of value assisting clinical decisions involving PTCs.

Papillary Thyroid Carcinoma: How Radical Lymphadenectomy Should be Performed?

Swiss Surgery ◽  
2003 ◽  
Vol 9 (2) ◽  
pp. 63-68
Author(s):  
Schweizer ◽  
Seifert ◽  
Gemsenjäger
Keyword(s):  
High Risk ◽  
Papillary Thyroid Carcinoma ◽  
Thyroid Carcinoma ◽  
Low Risk ◽  
Papillary Thyroid ◽  
Sentinel Nodes ◽  
Fand Sich ◽  
Radical Lymphadenectomy ◽  
N Status

Fragestellung: Die Bedeutung von Lymphknotenbefall bei papillärem Schilddrüsenkarzinom und die optimale Lymphknotenchirurgie werden kontrovers beurteilt. Methodik: Retrospektive Langzeitstudie eines Operateurs (n = 159), prospektive Dokumentation, Nachkontrolle 1-27 (x = 8) Jahre, Untersuchung mit Bezug auf Lymphknotenbefall. Resultate: Staging. Bei 42 Patienten wurde wegen makroskopischem Lymphknotenbefall (cN1) eine therapeutische Lymphadenektomie durchgeführt, mit pN1 Status bei 41 (98%) Patienten. Unter 117 Patienten ohne Anhalt für Lymphknotenbefall (cN0) fand sich okkulter Befall bei 5/29 (17%) Patienten mit elektiver (prophylaktischer) Lymphadenektomie, und bei 2/88 (2.3%) Patienten ohne Lymphadenektomie (metachroner Befall) (p < 0.005). Lymphknotenrezidive traten (1-5 Jahre nach kurativer Primärtherapie) bei 5/42 (12%) pN1 und bei 3/114 (2.6%) cN0, pN0 Tumoren auf (p = 0009). Das 20-Jahres-Überleben war bei TNM I + II (low risk) Patienten 100%, d.h. unabhängig vom N Status; pN1 vs. pN0, cN0 beeinflusste das Überleben ungünstig bei high risk (>= 45-jährige) Patienten (50% vs. 86%; p = 0.03). Diskussion: Der makroskopische intraoperative Lymphknotenbefund (cN) hat Bedeutung: - Befall ist meistens richtig positiv (pN1) und erfordert eine ausreichend radikale, d.h. systematische, kompartiment-orientierte Lymphadenektomie (Mikrodissektion) zur Verhütung von - kurablem oder gefährlichem - Rezidiv. - Okkulter Befall bei unauffälligen Lymphknoten führt selten zum klinischen Rezidiv und beeinflusst das Überleben nicht. Wir empfehlen eine weniger radikale (sampling), nur zentrale prophylaktische Lymphadenektomie, ohne Risiko von chirurgischer Morbidität. Ein empfindlicherer Nachweis von okkultem Befund (Immunhistochemie, Schnellschnitt von sampling Gewebe oder sentinel nodes) erscheint nicht rational. Bei pN0, cN0 Befund kommen Verzicht auf 131I Prophylaxe und eine weniger intensive Nachsorge in Frage.

Sign in / Sign up

Export Citation Format

Share Document