ASCEND
BY NTHRYS

NTHRYS › Internships

Ai Radiomics

Ai Radiomics
Category
Focused area
Variant
Pay · Join
Step 2 of 5Choose category
Field
▾
Category
▾
Focused area
▾

Ai Radiomics

Choose a category below to begin. Each category opens into focused areas, and selecting a focused area lets you pick your final internship variant (your preferred track, mode and duration).

Internship Types — tap to learn more
Mode — tap to learn more
Duration — tap to learn more
🔍

Showing 1–20 of 50

AI Radiomic Feature Extraction & Selection Research
Internship extracting and selecting radiomic features with AI pipelines that survive scanner change. Interns work with realistic case datasets.
5 focused areasClick to view more details →
Machine Learning for Radiomics Reproducibility
Internship testing radiomic reproducibility with ML analysis across repeat scans and protocols. Guided practice with real datasets throughout.
Academic (A)Tech (T)Research (R)
1 Month
A · ₹7,670
T · ₹22,079
R · ₹32,115
3 Months
A · ₹29,032
T · ₹35,484
R · ₹51,613
6 Months
A · ₹64,517
T · ₹78,854
R · ₹1,14,696
14 more durations from 5 days to 1 year
5 focused areasClick to view more details →
AI Radiogenomics Correlation Studies Research
Internship correlating imaging features with tumour genomics through AI radiogenomic analysis. Practical exercises anchor every concept taught.
5 focused areasClick to view more details →
Deep Learning for Tumor Radiomics Research
Internship characterising tumours with deep radiomic models trained across imaging cohorts. Applied sessions reinforce each technique.
5 focused areasClick to view more details →
AI Longitudinal Radiomics Change Detection
Internship measuring imaging change over time with AI registration that tracks lesions scan after scan. Guided practice with real datasets throughout.
5 focused areasClick to view more details →
AI Multi-Modal Radiomics Fusion Research
Internship fusing radiomic features across CT, MRI, and PET with AI into unified predictive models. Includes mentored hands-on analysis sessions.
5 focused areasClick to view more details →
AI Radiomics Treatment Response Research
Internship assessing treatment response with AI radiomics that reads change earlier than size criteria. Interns practise on genuine research problems.
5 focused areasClick to view more details →
AI Radiomics Standardization Framework Research
Internship standardising radiomic workflows so features stay comparable across sites and vendors. Hands-on work runs alongside theory modules.
5 focused areasClick to view more details →
AI Radiomics for Immunotherapy Response Research
Internship predicting immunotherapy response from imaging with AI radiomic signatures. Mentor-led sessions build applied skill.
5 focused areasClick to view more details →
AI Federated Radiomics Multi-Center Research
Internship running federated radiomics across centres so imaging models train without moving scans. Interns work with realistic case datasets.
5 focused areasClick to view more details →
Radiomics Texture Analysis Deep Learning
Develop convolutional neural networks to extract and classify textural patterns from medical imaging for tumor characterization and disease progression.
5 focused areasClick to view more details →
AI Radiomics Prognostic Model Development
Build machine learning models combining radiomic features with clinical variables to predict patient survival outcomes and treatment efficacy.
5 focused areasClick to view more details →
Radiomics Robustness Segmentation Validation
Investigate how different segmentation algorithms affect radiomic feature stability and develop methods to ensure consistent feature extraction.
5 focused areasClick to view more details →
Adversarial Attack Radiomics Model Security
Research adversarial vulnerabilities in AI radiomics models and develop defense mechanisms to enhance clinical deployment safety.
5 focused areasClick to view more details →
Radiomics Image Harmonization Cross-Scanner
Develop normalization techniques to reduce scanner and acquisition protocol variability in radiomic features across healthcare institutions.
5 focused areasClick to view more details →
Explainable AI Radiomics Feature Interpretation
Create interpretability frameworks using SHAP, LIME, and attention mechanisms to understand which radiomic features drive AI predictions.
5 focused areasClick to view more details →
Radiomics Lung Cancer Risk Stratification
Develop AI models leveraging radiomic features from CT scans to stratify lung nodule malignancy risk and guide clinical management.
5 focused areasClick to view more details →
Radiomics Breast Cancer Subtype Prediction
Build machine learning classifiers using mammography and MRI radiomics to predict hormone receptor and HER2 status non-invasively.
5 focused areasClick to view more details →
Radiomics Glioma Grade Classification Neural Networks
Train deep learning models on MRI radiomic features to automatically classify glioma grades and support neurosurgical planning.
5 focused areasClick to view more details →
Radiomics Liver Fibrosis Stage Detection
Develop AI algorithms using ultrasound and CT radiomics to non-invasively detect and stage hepatic fibrosis progression.
5 focused areasClick to view more details →