TECVICO leads you to success

About us

Reach out and let your mind explore

TECVICO creates an environment to facilitate the communication between international researchers and academical & industrial groups. At TECVICO, many fields such as medicine, electrical, mechanical, medical physics, artificial intelligence and others are being expanded. All projects are continuously under an exact observation of company’s experts to be completely accomplished. Most research projects are funded, and the company observes on fairly share the benefits. Industrial projects are provided with experienced researchers and experts. There is possibility to be created some professional teams to participate in internarial competitions and challenges. In educational section, the company creates an environment to holp the international workshops. There are many opportunities for researchers and industries to resolve their needs.

TOP NEW PROJECTS

We are continuously supporting newly defined projects in research, industry and competition sections.

Cognitive Outcome Prediction in Parkinson’s Disease Using Hybrid Machine Learning Systems and Radiomics Features

Objective: Montreal Cognitive Assessment (MoCA) as a rapid nonmotor-screening test assesses different aspects of cognitive dysfunction. Early prediction of these symptoms may facilitate better temporal therapy, disease control and identification of disease mechanisms. We aimed to predict MoCA scores in PD patients (year 4) from year 0 and 1 data. Methods: We collected 210 samples from the PPMI, and predicted their MoCA scores (range: 0-30) in year-4. In our study, 951 features including clinical features, conventional imaging features, and radiomics features were extracted from each dorsal striatum on DAT SPECT via our standardized SERA radiomics package. Four datasets (normalized by the z-score) were generated: use of the mentioned features in only (i) year-0, or (ii) year-1, iii) longitudinal-data (putting cross-sectional-datasets longitudinally next to each other), and iv) timeless-data (doubling dataset size, listing both cross-sectional-datasets separately). To predict MoCA, various Hybrid-Machine-Learning-Systems (HMLS) including 14 feature-extraction (FEA) or 10 features-selection algorithms (FSA) followed by 28 prediction algorithms (optimized by 5-fold-cross-validation and grid-search-technique) were applied on the datasets.

Drug Amount Prediction in Parkinson’s Disease Using Hybrid Machine Learning Systems and Radiomics Features

Objectives: Parkinson’s Disease (PD) is progressive and heterogeneous. Predicting and personalizing drug amount consistently to treat PD patients holds significant promises to enhance chances of successful temporal symptomatic therapy. Here, we aim to predict the amount of Levodopa prescribed by physicians, using Hybrid-Machine-Learning-Systems (HMLS). Methods: We selected 264 patients from the PPMI. Seven datasets were generated with 950 features including clinical-features (CF) and radiomics-features (RFs) extracted from DAT-SPECT. We selected eight outcomes including patients being on/off drug, amount of dose in specific years, and increase in drug amount, in different years. For each outcome, we considered seven datasets normalized by Z-score techniques: i,ii,iii) data in year 0, 1, or 2; iv,v) longitudinal-datasets in years 0&1, and 0&1&2, vi,vii) timeless datasets in years 0&1, and years 0&1&2 (doubling&tripling data-samples respectively). HMLSs utilized included 14 feature-extraction (FEA) and 10 feature-selection-algorithms (FSA) followed by 25 regressors and 17 classifiers (optimized by 5-fold-cross-validation and Grid-search).

Advanced Survival Prediction in Head and Neck Cancer Using Hybrid Machine Learning Systems and Radiomics Features

Objective: Accurate prognostic stratification of Head-and-Neck-Squamous-Cell-Carcinoma (HNSCC) patients can be an important clinical reference when designing therapeutic strategies. We set to predict 4 outcomes: overall-survival (OS), distant-metastasis (DM), loco-regional-recurrence (LR), and progression-free-survival (SP). We studied hybrid-machine-learning-systems (HMLS) incorporating multiple dimensionality reduction as well as survival prediction algorithms, applied to datasets with radiomics-features. Methods: In this multi-center-study, 408 HNSCC patients were extracted from the Cancer-Imaging-Archive. PET images were registered to CT, enhanced, and cropped. 215 radiomics features were extracted from each region-of-interest via our standardized SERA radiomics package. We employed multiple HMLSs: 14 feature-extraction (FEA) or 10 feature-selection-algorithms (FSA) linked with 8 survival-prediction-algorithms (SPA) optimized by 5-fold cross-validation, applied to PET-only, CT-only and 4 PET-CT datasets generated by image-level fusion strategies. Datasets were normalized by Z-score-technique, with c-index reported to compare models.

SIIM-FISABIO-RSNA COVID-19 Detection

Five times more deadly than the flu, COVID-19 causes significant morbidity and mortality. Like other pneumonias, a lung infection with COVID-19 leads to inflammation and fluid in the lungs. In In Tecvico, our team consist of three groups. First group dedicated to preprocessing of data which was the x-ray images of lung belong to the patients. The other groups as image classification and object detection had the tasks for predictions at both a study (multi-image) and image level. In the study level task, classification of the x-ray images done for prediction of labels which may contain more than one label. In the image level task, detection of the desired object as “opacity” with a confidence score and bounding box should be predicted. The final result of our team was the accuracy of 0.597 vs 0.635 as top result of leaderboard in this challenge and the 235 rank achieved between 1305 teams. Here is the link to the leaderboard of the challenge on the Kaggle site:

Hecktor 2021

Following the success of the first HECKTOR challenge in 2020, this challenge will be presented at the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) on September 27th, 2021. Our team for Hecktor 2021 challenge consisted of three groups the same as three tasks of the challenge plus preprocessing group for preparing images and doing some fusion techniques. Firstly, the preprocessing group tried to normalize of 3D head and neck images and fuse the two CT and PET images belong to the patients to generate new images witch have the details from both types of image including head and neck information. The other three groups dedicated to segmentation process to have predicted binary 3D images as segmented areas for tumors, after that survival prediction and finally survival prediction from a Docker container each in separated task. The methods which have been used for developing proposed methods presented in the 2021 MICCAI conference and will be in access. Our efforts finally resulted as 68% accuracy for survival prediction as Qurit_Tecvico team and the fourth rank in the leadership achieved in comparison with the first rank of 71%. You may be interested for visiting the challenge website and see the leaderboard here: https://www.aicrowd.com/challenges/miccai-2021-hecktor/leaderboards?challenge_leaderboard_extra_id=899&challenge_round_id=879

Developing SERA package and making it as a GUI application

Recently, there is an increased interest in the use of quantitative imaging methods to improve diagnosis of tumor stages, prediction of cancer progression and therapy response performance evaluation. An important development in quantitative imaging analysis is the concept of radiomics, which is the high-throughput extraction and analysis of quantitative image features, has been shown to have considerable potential to quantify the tumor phenotype. Since, a lack of software infrastructure has impeded the development of radiomics and its applications, we thus aim to develop the SERA, an open infrastructure software platform that flexibly supports common radiomics workflow tasks such as multimodality image data import and review, image fusion, development of feature extraction algorithms, model validation, feature selection, and classification.

TOP NEW WORKSHOP

TECVICO is holding new workshops.

Advanced survival prediction in head and neck cancer using hybrid machine learning systems and radiomics features

Ger et al. [19] examined whether using radiomics analysis and feature extraction with controlled imaging protocols improved prediction of outcomes. They retrospectively studied 726 CT and 686 PET images from HNSCC patients. For each patient, radiomics features with different preprocessing methods were calculated. Their result showed that CT and PET-based radiomics features failed to improve survival models for HNSCC patients. Furthermore, controlling the imaging protocol to minimize image uncertainties did not improve the radiomics models. The limited size of a dataset is a limiting factor in survival outcome prediction. We thus had to select a set of limited patients for which imaging data was available for all patients. We aim to predict multiple survival outcomes in the future in HNSCC. We also aim to predict binary survival outcomes using deep learning algorithms.

Test with guarantor

Accurate prognostic stratification of Head-and-Neck-Squamous-Cell-Carcinoma (HNSCC) patients can be an important clinical reference when designing therapeutic strategies. We set to predict 4 outcomes: overall survival (OS), distant metastasis (DM), locoregional recurrence (LR), and progression-free survival (SP). We studied Hybrid Machine Learning Systems (HMLS), applied to datasets with radiomics features. In this multicenter study, 408 HNSCC patients were extracted from The Cancer Imaging Archive (TCIA) database. PET images were registered to CT, enhanced, and cropped. 215 radiomics features were extracted from each region of interest via our standardized SERA radiomics package. We employed multiple HMLSs: 12 feature extraction (FEA) or 9 feature selection algorithms (FSA) linked with 9 survival-prediction-algorithms (SPA) optimized by 5-fold cross-validation, applied to PET only, CT only and 4 PET-CT datasets generated by image-level fusion strategies. Datasets were normalized by z-score-technique, and c-indices were reported to compare the models. For OS prediction, the highest c-index 0.73 ± 0.10 was obtained for HMLS with Ratio of low-pass pyramid (RP) fusion technique + gaussian process latent variable model (GPLVM) + causal structure learning-based feature modification method (CSFM). For DM prediction, we achieved 0.80±0.06 via Dual-tree complex wavelet transform (DTCWT) fusion + Laplacian Score (LAP) +

News and Event

Go On Adventures You've Only Dreamt Of ExploreThis World And Beyound

01
Join Tecvico and Login
02
Define your own project or apply for one
03
Carry out your projects and accomplish them
04
You achieve your goal

Suggestion Box