scholarly journals Assessment of glomerular morphological patterns by deep learning algorithms

2022 ◽  
Author(s):  
Cleo-Aron Weis ◽  
Jan Niklas Bindzus ◽  
Jonas Voigt ◽  
Marlen Runz ◽  
Svetlana Hertjens ◽  
...  
Keyword(s):  
Deep Learning ◽  
Structural Changes ◽  
Morphological Changes ◽  
Learning Algorithms ◽  
Clinical Information ◽  
Clear Cut ◽  
Promising Tool ◽  
Glomerular Lesions ◽  
Conventional Microscopy ◽  
Morphological Patterns

Abstract Background Compilation of different morphological lesion signatures is characteristic of renal pathology. Previous studies have documented the potential value of artificial intelligence (AI) in recognizing relatively clear-cut glomerular structures and patterns, such as segmental or global sclerosis or mesangial hypercellularity. This study aimed to test the capacity of deep learning algorithms to recognize complex glomerular structural changes that reflect common diagnostic dilemmas in nephropathology. Methods For this purpose, we defined nine classes of glomerular morphological patterns and trained twelve convolutional neuronal network (CNN) models on these. The two-step training process was done on a first dataset defined by an expert nephropathologist (12,253 images) and a second consensus dataset (11,142 images) defined by three experts in the field. Results The efficacy of CNN training was evaluated using another set with 180 consensus images, showing convincingly good classification results (kappa-values 0.838–0.938). Furthermore, we elucidated the image areas decisive for CNN-based decision making by class activation maps. Finally, we demonstrated that the algorithm could decipher glomerular disease patterns coinciding in a single glomerulus (e.g. necrosis along with mesangial and endocapillary hypercellularity). Conclusions In summary, our model, focusing on glomerular lesions detectable by conventional microscopy, is the first sui generis to deploy deep learning as a reliable and promising tool in recognition of even discrete and/or overlapping morphological changes. Our results provide a stimulus for ongoing projects that integrate further input levels next to morphology (such as immunohistochemistry, electron microscopy, and clinical information) to develop a novel tool applicable for routine diagnostic nephropathology.

scholarly journals Atrial fibrillation risk prediction from the 12-lead ECG using digital biomarkers and deep representation learning

2021 ◽  
Author(s):  
Shany Biton ◽  
Sheina Gendelman ◽  
Antônio H Ribeiro ◽  
Gabriela Miana ◽  
Carla Moreira ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Deep Learning ◽  
Risk Prediction ◽  
High Performance ◽  
Structural Changes ◽  
Model Performance ◽  
Clinical Information ◽  
Representation Learning ◽  
Patients At Risk ◽  
Single Modality

Abstract Aims This study aims to assess whether information derived from the raw 12-lead electrocardiogram (ECG) combined with clinical information is predictive of atrial fibrillation (AF) development. Methods We use a subset of the Telehealth Network of Minas Gerais (TNMG) database consisting of patients that had repeated 12-lead ECG measurements between 2010-2017 that is 1,130,404 recordings from 415,389 unique patients. Median and interquartile of age for the recordings were 58 (46-69) and 38% of the patients were males. Recordings were assigned to train-validation and test sets in an 80:20% split which was stratified by class, age and gender. A random forest classifier was trained to predict, for a given recording, the risk of AF development within 5-years. We use features obtained from different modalities, namely demographics, clinical information, engineered features, and features from deep representation learning. Results The best model performance on the test set was obtained for the model combining features from all modalities with an AUROC=0.909 against the best single modality model which had an AUROC=0.839. Conclusion Our study has important clinical implications for AF management. It is the first study integrating feature engineering, deep learning and EMR metadata to create a risk prediction tool for the management of patients at risk of AF. The best model that includes features from all modalities demonstrates that human knowledge in electrophysiology combined with deep learning outperforms any single modality approach. The high performance obtained suggest that structural changes in the 12-lead ECG are associated with existing or impending AF.

F.N.A.C. AS DIAGNOSTIC TOOL OF PAROTID TUMORS AND ASSOCIATED PITFALLS IN CORRELATION WITH HISTOPATHOLOGY

2020 ◽  
Vol 4 (1) ◽  
Author(s):  
Bhawana Pant ◽  
Sanjay Gaur ◽  
Prabhat Pant
Keyword(s):  
Preoperative Diagnosis ◽  
Histopathological Examination ◽  
Clinical Information ◽  
Final Diagnosis ◽  
Needle Aspiration ◽  
Histopathological Diagnosis ◽  
Cytological Diagnosis ◽  
Tertiary Referral Centre ◽  
Clear Cut ◽  
Parotid Tumors

F.NA.C has been used for ages as a safe and economical tool for fast preoperative diagnosis of parotid tumors. It has certain pitfall which sometimes leads to misdiagnosis and consequently it may have affect on treatment of the tumors. Keeping in view of the diverse classification of parotid tumors’ information from cytology should be combined with radiology as well as clinical diagnosis. Aim: To discuss some cases where there was discrepancy between cytological diagnosis and histopathological result and also suggest measures to improve the efficacy of F.N.A.C. Material and methods: The study includes 50 cases of parotid tumours who presented to the  department of ENT at Government medical college Haldwani which is a tertiary referral centre during 2009 to 2016. Only adult patients were included and inflammatory swelling were excluded from the study. All patients evaluated  Contrast enhanced computerized tomography(CECT) and  Magnetic resonance imaging (MRI) followed by Fine needle aspiration cytology .Preoperative diagnosis was made upon the findings of the above investigations and different types of  parotid surgeries  were done. . Final diagnosis was made on  histopathological  examination. Result :The most common tumour  came out to be pleomorphic adenoma (23 cases-46%) followed by mucoepidermoid carcinoma(12cases-24%). In ten  cases there was no clear cut  association between cytological diagnosis and final histopathological diagnosis. Conclusion: FNAC is highly sensitive and specific technique for diagnosis of many salivary gland swellings. FNAC can be used preoperatively to avoid unnecessary surgery and biopsy. Details of clinical information and radiologic features may help the pathologist to arrive at the appropriate diagnosis and reduce false interpretation. Pitfalls may also occur with improper technique of FNAC which can be overcome by proper caution.

Developing an Artificial Intelligence Project in your Radiology Department

2020 ◽  
Vol 2 ◽  
pp. 58-61 ◽  
Author(s):  
Syed Junaid ◽  
Asad Saeed ◽  
Zeili Yang ◽  
Thomas Micic ◽  
Rajesh Botchu
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Health Care ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Radiology Department ◽  
Short Article ◽  
Computing Power ◽  
Road Map ◽  
Key Concepts

The advances in deep learning algorithms, exponential computing power, and availability of digital patient data like never before have led to the wave of interest and investment in artificial intelligence in health care. No radiology conference is complete without a substantial dedication to AI. Many radiology departments are keen to get involved but are unsure of where and how to begin. This short article provides a simple road map to aid departments to get involved with the technology, demystify key concepts, and pique an interest in the field. We have broken down the journey into seven steps; problem, team, data, kit, neural network, validation, and governance.

Structural changes in uterine tissues after uterine artery embolization in patients with leiomyoma complicated by uterine bleeding

GYNECOLOGY ◽  
2018 ◽  
Vol 20 (1) ◽  
pp. 78-82
Author(s):  
G P Titova ◽  
M M Damirov ◽  
L S Kokov ◽  
O N Oleynikova ◽  
G E Belozerov
Keyword(s):  
Uterine Artery Embolization ◽  
Uterine Artery ◽  
Structural Changes ◽  
Morphological Changes ◽  
Uterine Bleeding ◽  
Small Scale ◽  
Artery Embolization ◽  
Vessel Occlusion ◽  
Uterine Arteries ◽  
Uterine Tumors

Uterine leiomyoma (UL) is often complicated by the development of uterine bleeding. In urgent gynecology for the implementation of endovascular hemostasis, uterine artery embolization (UAE) is used. Performing UAE allows to stop and/or significantly reduce the intensity of bleeding and prepare a patient for surgical intervention. At the same time, the morphological changes that occur in uterine tissues in operated UL patients after performing the UAE are not studied. The aim was to study the peculiarities of pathomorphological changes in uterine tumors and tissues in operated UL patients complicated by uterine bleeding after performing UAE. Material and methods. The results of morphological changes appearing in tumors and tissues of the uterus in 39 operated UL patients, who were used for stopping uterine bleeding, were analyzed. Results. After applying different types of embolizing agents in macroscopic study of the uterus, signs of ischemia of its tissues were revealed, and the most pronounced disorders were detected in the UL nodes. Morphologically it was established that UAE microemboli resulted in vessel occlusion with increasing thrombosis in their distal sections. UAE was not accompanied by occlusal occlusion of the arteries and resulted in small-scale necrosis of the tumor with complete regeneration of the endometrium. Conclusions. The results of the morphological study showed that after the UAE was performed, the myomatous nodes underwent dystrophic, necrobiotic and necrotic changes. Depending on the nature of occlusion of the uterine arteries, various variants of necrosis (scale and completeness of the process) developed in the tumor tissue, which was aseptic in nature.

Thermal characterization of ABS-Graphene blended three dimensional printed functional prototypes for electro chemical energy storage

2018 ◽  
Vol 1 (1) ◽  
pp. 1-11 ◽  
Author(s):  
Kamaljit Singh Boparai ◽  
Rupinder Singh
Keyword(s):  
Energy Storage ◽  
Structural Changes ◽  
Fused Deposition Modeling ◽  
Morphological Changes ◽  
Three Dimensional ◽  
Thermal Characterization ◽  
Chemical Energy ◽  
Flow Index ◽  
Fused Deposition

This study highlights the thermal characterization of ABS-Graphene blended three dimensional (3D) printed functional prototypes by fused deposition modeling (FDM) process. These functional prototypes have some applications as electro-chemical energy storage devices (EESD). Initially, the suitability of ABS-Graphene composite material for FDM applications has been examined by melt flow index (MFI) test. After establishing MFI, the feedstock filament for FDM has been prepared by an extrusion process. The fabricated filament has been used for printing 3D functional prototypes for printing of in-house EESD. The differential scanning calorimeter (DSC) analysis was conducted to understand the effect on glass transition temperature with the inclusion of Graphene (Gr) particles. It has been observed that the reinforced Gr particles act as a thermal reservoir (sink) and enhances its thermal/electrical conductivity. Also, FT-IR spectra realized the structural changes with the inclusion of Gr in ABS matrix. The results are supported by scanning electron microscopy (SEM) based micrographs for understanding the morphological changes.

A Study on the Auxiliary Diagnosis of Thyroid Disease Images Based on Multiple Dimensional Deep Learning Algorithms

2020 ◽  
Vol 16 (3) ◽  
pp. 199-205
Author(s):  
Yuejun Liu ◽  
Yifei Xu ◽  
Xiangzheng Meng ◽  
Xuguang Wang ◽  
Tianxu Bai
Keyword(s):  
Deep Learning ◽  
Learning Algorithms ◽  
Region Of Interest ◽  
Classification Performance ◽  
Thyroid Diseases ◽  
Great Success ◽  
Learning Models ◽  
Good Classification Performance ◽  
Spect Images

Background: Medical imaging plays an important role in the diagnosis of thyroid diseases. In the field of machine learning, multiple dimensional deep learning algorithms are widely used in image classification and recognition, and have achieved great success. Objective: The method based on multiple dimensional deep learning is employed for the auxiliary diagnosis of thyroid diseases based on SPECT images. The performances of different deep learning models are evaluated and compared. Methods: Thyroid SPECT images are collected with three types, they are hyperthyroidism, normal and hypothyroidism. In the pre-processing, the region of interest of thyroid is segmented and the amount of data sample is expanded. Four CNN models, including CNN, Inception, VGG16 and RNN, are used to evaluate deep learning methods. Results: Deep learning based methods have good classification performance, the accuracy is 92.9%-96.2%, AUC is 97.8%-99.6%. VGG16 model has the best performance, the accuracy is 96.2% and AUC is 99.6%. Especially, the VGG16 model with a changing learning rate works best. Conclusion: The standard CNN, Inception, VGG16, and RNN four deep learning models are efficient for the classification of thyroid diseases with SPECT images. The accuracy of the assisted diagnostic method based on deep learning is higher than that of other methods reported in the literature.

scholarly journals Cumulative infiltration and infiltration rate prediction using optimized deep learning algorithms: A study in Western Iran

2021 ◽  
Vol 35 ◽  
pp. 100825
Author(s):  
Mahdi Panahi ◽  
Khabat Khosravi ◽  
Sajjad Ahmad ◽  
Somayeh Panahi ◽  
Salim Heddam ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Algorithms ◽  
Infiltration Rate ◽  
Western Iran ◽  
Rate Prediction ◽  
Cumulative Infiltration

scholarly journals Semantic segmentation of PolSAR image data using advanced deep learning model

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Rajat Garg ◽  
Anil Kumar ◽  
Nikunj Bansal ◽  
Manish Prateek ◽  
Shashi Kumar
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Urban Area ◽  
Urban Areas ◽  
Learning Algorithms ◽  
Semantic Segmentation ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Deep Learning Model

AbstractUrban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.

Sign in / Sign up

Export Citation Format

Share Document