You will get Image Segmentation using Machine Learning with Annotation and Report
Project details
This project stands out by offering a fully automated and highly accurate tumor segmentation system for CT volumes, addressing a critical need in medical imaging and cancer diagnostics. Unlike conventional methods that rely heavily on manual annotation and struggle with tumor variability, this approach integrates intelligent liver ROI detection, advanced slice-wise segmentation, and enhanced visualization through post-processing and watershed algorithms. Achieving 99.50% mAP50 and 94.91% Dice score on the LiTS17 dataset, it outperforms existing solutions. The inclusion of volumetric tumor analysis further supports clinical decision-making, making this a powerful tool for improving diagnosis, monitoring tumor progression, and evaluating treatment response.
Machine Learning Tools
MATLAB, OpenCV, Python, Python Scikit-Learn, TensorFlowWhat's included
| Service Tiers |
Starter
$100
|
Standard
$200
|
Advanced
$1,000
|
|---|---|---|---|
| Delivery Time | 2 days | 7 days | 20 days |
Number of Revisions | 3 | 5 | 9 |
Number of Model Variations | 2 | 4 | 10 |
Number of Graphs/Charts | 10 | 15 | 20 |
Model Validation/Testing | |||
Model Documentation | - | ||
Data Source Connectivity | - | ||
Source Code |
Optional add-ons
You can add these on the next page.
Additional Revision
+$1
Additional Graph/Chart
+$1
Journal Project
(+ 10 Days)
+$1,000Frequently asked questions
About Md Abu
Expert Machine Learning Engineer
Ullapara, Bangladesh - 5:05 pm local time
🔬 Core Competencies:
1. Machine Learning & Deep Learning: Proficient in developing supervised and unsupervised models using Python (TensorFlow, Keras, Scikit-learn) tailored for healthcare data.
2. Biomedical Image Processing: Expertise in analyzing medical imaging modalities such as MRI, CT, and X-ray using OpenCV, MATLAB, and Python to extract clinically relevant features.
3. Signal Processing: Hands-on experience with EEG, EMG, and fNIRS data analysis, including preprocessing, artifact removal, feature extraction, and classification.
4. Neural Engineering: Skilled in interpreting brain signal patterns and correlating them with cognitive/clinical conditions, grounded by both coursework and lab experience in neurology.
5. Healthcare AI Applications: Interest in clinical decision support systems, disease prediction models, brain-computer interfaces (BCI), and prosthetic control using biosignals.
🎓 Academic Background:
MS in Biomedical Physics and Technology, University of Dhaka
Focus: Image processing, Signal processing, Medical instrumentation
B.Sc. in Biomedical Engineering, Khulna University of Engineering & Technology (KUET)
Focus: Medical imaging, Bioinstrumentation, Machine learning applications in health
🧠 Research Interests:
Medical image detection, segmentation and classification using CNNs
Brain-computer interface (BCI) systems using EEG and machine learning
Machine learning for drug discovery
💡 Projects & Achievements:
Medical Image Classification and Segmentation: Built CNN models for disease detection and segmentation (e.g., pneumonia, brain tumors) from X-ray/MRI images, achieving high diagnostic accuracy.
EEG-based Mental State Classification: Developed ML pipelines to classify attention, relaxation, and stress levels from EEG datasets, enhancing BCI interface control strategies.
fNIRS Signal Analysis: Implemented signal preprocessing and statistical modeling to detect cortical activation during cognitive tasks.
EMG-controlled Prosthetic Hand: Designed a cost-effective prototype integrated with microcontroller-based control and signal classification algorithms.
Publication & Lab Work: Participated in collaborative research and published work related to biosignal and medical image processing.
🛠️ Technical Skills:
Programming: Python, MATLAB, R (Expert)
Libraries & Tools: TensorFlow, Keras, Scikit-learn, OpenCV, Numpy, MNE, EEGLAB
Data Handling: Experience with clinical datasets, biosignal archives (e.g., PhysioNet), and DICOM imaging
Hardware: Arduino, Raspberry Pi, Biopac systems, fNIR devices
🌍 What I Offer:
Whether it’s designing ML models for disease detection, classification and segmentation, developing signal processing pipelines, or working on cutting-edge healthtech innovations, I bring a deep interdisciplinary understanding, hands-on experience, and a problem-solving mindset. I strive to contribute to research and development that has real-world impact—transforming data into life-saving solutions.
Steps for completing your project
After purchasing the project, send requirements so Md Abu can start the project.
Delivery time starts when Md Abu receives requirements from you.
Md Abu works on your project following the steps below.
Revisions may occur after the delivery date.
Let's arrange a Zoom meeting to discuss and finalize your project.