scholarly journals PathoFusion: An Open-Source AI Framework for Recognition of Pathomorphological Features and Mapping of Immunohistochemical Data

Cancers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 617
Author(s):  
Guoqing Bao ◽  
Xiuying Wang ◽  
Ran Xu ◽  
Christina Loh ◽  
Oreoluwa Daniel Adeyinka ◽  
...  
Keyword(s):  
Neural Network ◽  
Tumor Vasculature ◽  
Integrated System ◽  
Pathological Features ◽  
Adjacent Tissue ◽  
Tissue Sections ◽  
Contextual Feature ◽  
Hematoxylin And Eosin ◽  
Feature Information ◽  
Software Code

We have developed a platform, termed PathoFusion, which is an integrated system for marking, training, and recognition of pathological features in whole-slide tissue sections. The platform uses a bifocal convolutional neural network (BCNN) which is designed to simultaneously capture both index and contextual feature information from shorter and longer image tiles, respectively. This is analogous to how a microscopist in pathology works, identifying a cancerous morphological feature in the tissue context using first a narrow and then a wider focus, hence bifocal. Adjacent tissue sections obtained from glioblastoma cases were processed for hematoxylin and eosin (H&E) and immunohistochemical (CD276) staining. Image tiles cropped from the digitized images based on markings made by a consultant neuropathologist were used to train the BCNN. PathoFusion demonstrated its ability to recognize malignant neuropathological features autonomously and map immunohistochemical data simultaneously. Our experiments show that PathoFusion achieved areas under the curve (AUCs) of 0.985 ± 0.011 and 0.988 ± 0.001 in patch-level recognition of six typical pathomorphological features and detection of associated immunoreactivity, respectively. On this basis, the system further correlated CD276 immunoreactivity to abnormal tumor vasculature. Corresponding feature distributions and overlaps were visualized by heatmaps, permitting high-resolution qualitative as well as quantitative morphological analyses for entire histological slides. Recognition of more user-defined pathomorphological features can be added to the system and included in future tissue analyses. Integration of PathoFusion with the day-to-day service workflow of a (neuro)pathology department is a goal. The software code for PathoFusion is made publicly available.

scholarly journals Deep learning-based transformation of H&E stained tissues into special stains

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Kevin de Haan ◽  
Yijie Zhang ◽  
Jonathan E. Zuckerman ◽  
Tairan Liu ◽  
Anthony E. Sisk ◽  
...  
Keyword(s):  
Visual Inspection ◽  
Kidney Diseases ◽  
Periodic Acid ◽  
Needle Core Biopsy ◽  
Silver Stain ◽  
Periodic Acid Schiff ◽  
Tissue Sections ◽  
Biopsy Tissue ◽  
Hematoxylin And Eosin

AbstractPathology is practiced by visual inspection of histochemically stained tissue slides. While the hematoxylin and eosin (H&E) stain is most commonly used, special stains can provide additional contrast to different tissue components. Here, we demonstrate the utility of supervised learning-based computational stain transformation from H&E to special stains (Masson’s Trichrome, periodic acid-Schiff and Jones silver stain) using kidney needle core biopsy tissue sections. Based on the evaluation by three renal pathologists, followed by adjudication by a fourth pathologist, we show that the generation of virtual special stains from existing H&E images improves the diagnosis of several non-neoplastic kidney diseases, sampled from 58 unique subjects (P = 0.0095). A second study found that the quality of the computationally generated special stains was statistically equivalent to those which were histochemically stained. This stain-to-stain transformation framework can improve preliminary diagnoses when additional special stains are needed, also providing significant savings in time and cost.

Non-invasive intelligent monitoring system for fault detection in induction motor based on bio piezoelectric sensor using ANN

2022 ◽  
Author(s):  
Massine GANA ◽  
Hakim ACHOUR ◽  
Kamel BELAID ◽  
Zakia CHELLI ◽  
Mourad LAGHROUCHE ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Induction Motor ◽  
Vibration Analysis ◽  
Low Cost ◽  
Piezoelectric Sensor ◽  
Integrated System ◽  
Easy Access ◽  
Non Invasive ◽  
Artificial Neural

Abstract This paper presents a design of a low-cost integrated system for the preventive detection of unbalance faults in an induction motor. In this regard, two non-invasive measurements have been collected then monitored in real time and transmitted via an ESP32 board. A new bio-flexible piezoelectric sensor developed previously in our laboratory, was used for vibration analysis. Moreover an infrared thermopile was used for non-contact temperature measurement. The data is transmitted via Wi-Fi to a monitoring station that intervenes to detect an anomaly. The diagnosis of the motor condition is realized using an artificial neural network algorithm implemented on the microcontroller. Besides, a Kalman filter is employed to predict the vibrations while eliminating the noise. The combination of vibration analysis, thermal signature analysis and artificial neural network provides a better diagnosis. It ensures efficiency, accuracy, easy access to data and remote control, which significantly reduces human intervention.

scholarly journals Forest Fire Detection via Feature Entropy Guided Neural Network

Entropy ◽  
2022 ◽  
Vol 24 (1) ◽  
pp. 128
Author(s):  
Zhenwei Guan ◽  
Feng Min ◽  
Wei He ◽  
Wenhua Fang ◽  
Tao Lu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Forest Fire ◽  
State Of The Art ◽  
Fire Detection ◽  
High Entropy ◽  
Training Samples ◽  
Feature Information ◽  
Forest Fire Detection ◽  
Entropy Source

Forest fire detection from videos or images is vital to forest firefighting. Most deep learning based approaches rely on converging image loss, which ignores the content from different fire scenes. In fact, complex content of images always has higher entropy. From this perspective, we propose a novel feature entropy guided neural network for forest fire detection, which is used to balance the content complexity of different training samples. Specifically, a larger weight is given to the feature of the sample with a high entropy source when calculating the classification loss. In addition, we also propose a color attention neural network, which mainly consists of several repeated multiple-blocks of color-attention modules (MCM). Each MCM module can extract the color feature information of fire adequately. The experimental results show that the performance of our proposed method outperforms the state-of-the-art methods.

scholarly journals Role of S-100 Immunostain as An Auxiliary Diagnostic Aid in Leprosy

2017 ◽  
Vol 56 (205) ◽  
pp. 141-144 ◽  
Author(s):  
Ramesh Dhakhwa ◽  
Sneh Acharya ◽  
Sailesh Pradhan ◽  
Sanju Babu Shrestha ◽  
Tomoo Itoh
Keyword(s):  
Erythema Nodosum ◽  
Lupus Vulgaris ◽  
Common Pattern ◽  
Tissue Sections ◽  
Histopathologic Diagnosis ◽  
S 100 ◽  
Skin Biopsies ◽  
Hematoxylin And Eosin ◽  
Hematoxylin And Eosin Stain

Introduction: Histopathologic diagnosis of leprosy is difficult when Bacillary Index (BI) is zero and neural involvement are not easily identifiable on routine Hematoxylin and Eosin stain. This study was undertaken to study the role of S-100 immunostaining in demonstrating different patterns of nerve involvement in various types of leprosy. Methods: Thirty one skin biopsies with clinico-histopathologic diagnoses of leprosy over a period of two years were included in the study. Ten cases of non-lepromatous granulomatous dermatoses (including eight cases of lupus vulgaris and two cases of erythema nodosum) were used as controls. Tissue sections from all cases and controls were stained with Hematoxylin and Eosin (H&E) stain, Fite stain and S-100 immunostain. The H&E stained slides were used to study the histopathological features, Fite stained slides for Bacillary Index and S-100 for nerve changes. Results: Neural changes could be demonstrated in the entire spectrum of leprosy using S-100 immunostaining. The most common pattern of nerve destruction in the tuberculoid spectrum was fragmented and infiltrated whereas lepromatous spectrum showed mostly fragmented nerve twigs. Intact nerves were not detected in any of the leprosy cases. Conclusions:  S-100 immunostain is a useful auxiliary aid to the routine  H&E stain in the diagnosis of leprosy especially tuberculoid spectrum and intermediate leprosy.  Keywords: bacillary index; leprosy; S-100 immunostain.

scholarly journals High Dimensional Electromagnetic Interference Signal Clustering Based On SOM Neural Network

2016 ◽  
Vol 20 (1) ◽  
pp. 27
Author(s):  
Hongyi Li ◽  
Di Zhao ◽  
Shaofeng Xu ◽  
Pidong Wang ◽  
Jiaxin Chen
Keyword(s):  
Neural Network ◽  
Electromagnetic Interference ◽  
Large Scale ◽  
Spectral Characteristics ◽  
Simulation Models ◽  
Integrated System ◽  
Interference Signal ◽  
Global Features ◽  
Strongly Nonlinear ◽  
Emc Design

In this paper, we study the spectral characteristics and global representations of strongly nonlinear, non-stationary electromagnetic interferences (EMI), which is of great significance in analysing the mathematical modelling of electromagnetic capability (EMC) for a large scale integrated system. We firstly propose to use Self-Organizing Feature Map Neural Network (SOM) to cluster EMI signals. To tackle with the high dimensionality of EMI signals, we combine the dimension reduction and clustering approaches, and find out the global features of different interference factors, in order to finally provide precise mathematical simulation models for EMC design, analysis, forecasting and evaluation. Experimental results have demonstrated the validity and effectiveness of the proposed method.

Interactive system for registering adjacent tissue sections

1998 ◽  
Author(s):  
Stephen J. Lockett ◽  
Carlos Fernandez ◽  
Enrique G. Rodriguez ◽  
Ulrich Wesselmann ◽  
Boris C. Bastian ◽  
...  
Keyword(s):  
Interactive System ◽  
Adjacent Tissue ◽  
Tissue Sections

scholarly journals Non-Tumor Cystic Lesions of the Adrenal Gland

PRILOZI ◽  
2015 ◽  
Vol 36 (3) ◽  
pp. 51-59 ◽  
Author(s):  
Vesna Janevska ◽  
Vlado Janevski ◽  
Oliver Stankov ◽  
Liljana Spasevska ◽  
Slavica Kostadinova-Kunovska ◽  
...  
Keyword(s):  
Imaging Techniques ◽  
Cystic Lesions ◽  
Pathological Features ◽  
Radiological Findings ◽  
Tissue Sections ◽  
Male Ratio ◽  
Radiologic Imaging ◽  
Vascular Origin ◽  
The Mean ◽  
Material Standard

Abstract Adrenal cystic lesions are uncommon but due to the improved radiologic imaging techniques their appearance seems to increase. Material and Methods: We analyzed the clinical and radiological findings of 10 patients with adrenal cysts and the pathological features of the operative material. Standard dissection procedure and paraffin embedded tissue sections were made, stained by HE and immunohistochemically with CD34, CD 31, Factor 8, Podoplanin, CKWS and AE1/AE3 Results: The mean age of the patients was 40.6 years; female to male ratio was 2.3:1. All the cysts were diagnosed as cystic lesions radiologically except one. The most present clinical symptom was abdominal pain. The diameter of the cysts measured from 2 to 7 cm. Four of the cysts were diagnosed as pseudocysts and six as endothelial. Six cysts were lined by CD34+ and CD31+ cells, four were lined by Factor 8+ and podoplanin+ cells and four had no lining. Conclusion: Endothelial cysts were more common cysts in our study and the immunohistochemical results suggested common vascular origin to all endothelial cysts and supported additional separation of angiomatous and lymphangiomathous adrenal vascular cysts.

Eccentricity of Rotor Prediction of Aero-Engine Rotor Based on Image Identification and Machine Learning

2019 ◽  
Author(s):  
Zihao Zhang ◽  
Junkang Guo ◽  
Yanhui Sun ◽  
Jun Hong
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Rbf Neural Network ◽  
Engineering Application ◽  
Direction Error ◽  
Rotor Eccentricity ◽  
The Neural Network ◽  
Aero Engine ◽  
Feature Information ◽  
Engine Rotor

Abstract The eccentricity of rotor seriously affect the vibration and reliability of aero-engine. Due to the machining error of parts, it is very important to accurately predict the error propagation in assembly. A method based on image recognition and machine learning is proposed to predict the eccentricity of rotor. Firstly, by analyzing and calculating the axial and radial runout error data, the error is mainly concentrated in the first 30 orders of the Fourier series. Secondly, based on the mapping relationship between profile trajectory and eccentricity of rotor, the feature information of the profile trajectory is extracted by constructing the complex domain autoregressive (CAR) model for the radial and axial direction error profile trajectory. Then use the finite element method to calculate the rotor eccentricity. Using the feature information as the input of the neural network, the rotor eccentricity is assembled as the output of the neural network, and the radial basis function (RBF) neural network is built to predict the rotor eccentricity. Theoretical and experimental results show that the proposed method has good enforceability, high accuracy, short calculation time and high engineering application value. In addition, this method can not only be applied to predict the eccentricity of aero-engine rotor flange assembly, but also can be used in the general field of interference fit of assembly.

Sign in / Sign up

Export Citation Format

Share Document