
Closed
Posted
Paid on delivery
Project Domain / Category Artificial Intelligence / Computer Vision / Medical Image Processing / Deep Learning Abstract / Introduction Brain tumor detection from Magnetic Resonance Imaging (MRI) is an important medical image analysis task. Deep learning techniques can assist in identifying abnormal patterns in brain MRI images. Capsule Networks (CapsNet) offer an alternative to conventional Convolutional Neural Networks (CNNs) by learning spatial relationships among image features. Integrating a trained deep learning model into a web-based application can make MRI image analysis more accessible and convenient for demonstration and educational purposes. This project aims to develop a web-based brain tumor detection system using a Capsule Network (CapsNet). The publicly available Br35H Brain MRI dataset, containing Tumor and NoTumor images, will be used for model training and testing. The developed web application will allow users to upload MRI images, perform basic image-quality assessment, and obtain Tumor or No Tumor predictions using the trained CapsNet model. Functional Requirements: In this project, we will leverage image processing and deep learning techniques to address the following objectives: 1. Data Collection and Preprocessing: Gather a diverse dataset of brain MRI scans, ensuring data quality and integrity. Preprocess the images to enhance their suitability for further analysis. Apply image normalization, resizing, and suitable data augmentation. 2. Dataset Splitting: To facilitate model training and evaluation, we will split the dataset into distinct sets for training, validation, and testing. This step ensures that the deep learning model's performance is rigorously assessed and prevents overfitting. 3. Deep Learning Model Development: Implement and train a conventional Convolutional Neural Network (CNN) as a baseline model and a Capsule Network (CapsNet) as the primary model for classifying brain MRI images into Tumor and No Tumor categories. Conduct a comprehensive comparative performance analysis of both models using Accuracy, Precision, Recall, F1-Score, ROC-AUC, and Confusion Matrix. The comparison shall evaluate their classification effectiveness, ability to correctly identify tumor cases, and computational efficiency to determine the relative strengths and limitations of CapsNet compared with the conventional CNN. 4. Model Evaluation: We will establish robust evaluation metrics to assess the performance of the deep learning models, ensuring that the segmentation results are precise and reliable. Evaluate the model using Accuracy, Precision, Recall, F1-Score, ROC-AUC, and Confusion Matrix. Compare CapsNet with a basic CNN model to determine whether Capsule Networks provide any performance advantage. Analyze the performance drop of each model under different image-quality degradations. 5. DataSet: For this project you need to use BR35H Brain MRI dataset. 6. Model Deployment:Develop a user-friendly web interface that allows users to upload brain MRI images. The uploaded MRI image shall be processed using the trained CapsNet model. The system shall classify the image as Tumor or No Tumor and display the predicted class and model score
Project ID: 40791312
90 proposals
Remote project
Active 5 days ago
Set your budget and timeframe
Get paid for your work
Outline your proposal
It's free to sign up and bid on jobs
90 freelancers are bidding on average $138 USD for this job

Hello, I trust you're doing well. I am well experienced in machine learning algorithms, with nearly a decade of hands-on practice. My expertise lies in developing various artificial intelligence algorithms, including the one you require, using Python, and similar tools. I have worked with pytorch, and tensorflow to develop DL models, .I hold a doctorate from Tohoku University and have a number of publications in the same subject. My portfolio, which showcases my past work, is available for your review. Your project piqued my interest, and I would be delighted to be part of it. Let's connect to discuss in detail. Warm regards. please check my portfolio link: https://www.freelancer.com/u/sajjadtaghvaeifr
$250 USD in 7 days
6.7
6.7

CapsNet and CNN-based medical image classification align directly with my expertise in deep learning, computer vision, and image processing using Python, PyTorch, and TensorFlow. I can develop the MRI preprocessing and classification pipeline around the BR35H dataset, including resizing, normalization, augmentation, train/validation/test splitting, and a conventional CNN baseline for meaningful comparison. My experience with OpenCV and image-processing workflows supports the required image-quality assessment and degradation testing, while my model-training skills cover evaluation through Accuracy, Precision, Recall, F1-Score, ROC-AUC, and confusion matrices. I can also integrate the trained CapsNet into a Flask web application where users upload MRI images and receive a Tumor or No Tumor prediction with the model score. I focus on reliable, well-structured AI software from development through deployment, and I am ready to build this system as a clear educational and demonstration platform.
$140 USD in 7 days
6.6
6.6

My deep learning, image processing, Python, and web application skills align directly with your MRI brain tumor detection system. I can develop the requested Tumor/No Tumor classification workflow around the BR35H dataset, including preprocessing, normalization, resizing, augmentation, and a web interface for uploading MRI images and displaying the predicted class with its model score. My broader experience includes completing 150+ freelance projects since 2014 across data analysis, automation, technical work, and web/app development. That combination supports the project’s full scope—from implementing a baseline CNN and CapsNet to evaluating both with Accuracy, Precision, Recall, F1-Score, ROC-AUC, and confusion matrices, including analysis under image-quality degradation. I communicate reliably, work carefully with structured data and technical requirements, and can deliver a clear educational demonstration rather than an unsupported medical claim. I would be glad to build this system and compare the two models rigorously.
$140 USD in 7 days
6.2
6.2

Hi there, I can help develop an MRI brain tumor detection system using Python, deep learning, and CNN-based image classification. I’ll focus on preprocessing MRI scans, training or fine-tuning a suitable model, evaluating its performance, and building a reliable prediction workflow. Do you already have a labeled MRI dataset and a trained model, or would you like me to handle the complete pipeline from dataset preparation to evaluation? Do you also need tumor classification by type or simply tumor detection? I’ll keep the code clean and documented and provide clear instructions for running the system. You can check my profile for my experience and previous work. Portfolio: https://www.freelancer.com/u/sf264 Let’s discuss your requirements so I can recommend the right model and implementation approach for your project.
$100 USD in 1 day
5.3
5.3

Br35H contains near-duplicate MRI slices, so a random train/test split will leak data and inflate CapsNet accuracy past 99%. That won't survive academic review, so I'd dedupe with perceptual hashing before splitting. Quick questions - should this be built in TensorFlow or PyTorch, given CapsNet dynamic routing gets memory-heavy above 128x128? And which degradations matter for the robustness study, such as Gaussian noise, blur, or low contrast? Here is the architectural approach: - DATA PIPELINE: OpenCV normalization, resizing and augmentation, with hash-based dedup before a stratified train/validation/test split. - MODEL BENCHMARKING: Train a CNN baseline and CapsNet, reporting Accuracy, Precision, Recall, F1-Score, ROC-AUC and Confusion Matrix. - FLASK DEPLOYMENT: Upload flow with blur and contrast quality checks, returning Tumor or No Tumor with the model score. I've built medical imaging pipelines under HIPAA constraints where leakage-free validation was non-negotiable. Let's align on the evaluation protocol before training starts.
$130 USD in 3 days
5.5
5.5

**Can start on this today and get the CapsNet training pipeline and web demo moving fast** I am Anand, a Full-Stack Developer and IT Systems Specialist, and I can build this in Python end to end 1. Data Collection and Preprocessing: I will use the Br35H Tumor and NoTumor images, check them for corrupt or low quality files, then apply resizing, normalization, and augmentation such as rotation, flipping, and brightness changes 2. Dataset Splitting: I will create stratified training, validation, and test splits so both classes stay balanced and the final results are not biased 3. Deep Learning Model Development: I will build a conventional CNN as the baseline and a CapsNet as the primary model for Tumor vs No Tumor classification 4. Model Evaluation: I will compare both models on Accuracy, Precision, Recall, F1-Score, ROC-AUC, and Confusion Matrix, and also test how performance drops under blur, noise, and contrast degradation 5. DataSet: Confirmed, I will use only the BR35H Brain MRI dataset as specified 6. Model Deployment: I will deploy the trained CapsNet into a simple web app where users can upload an MRI image, get a basic image quality check, and see the Tumor or No Tumor prediction Recent work: Built a dashboard app that replaced an ops team's spreadsheets, and a booking platform still running two years later Should I start with the data preprocessing and CNN vs CapsNet comparison first, then build the web interface around the better performing setup
$110 USD in 7 days
4.8
4.8

Python is the key skill I can apply to build the web-based MRI brain tumor detection system you described, including image upload handling and a clear Tumor/No Tumor prediction interface. My profile also focuses on UI/UX design and responsive front-end development, allowing me to create a clean, accessible application for presenting image-quality feedback, model scores, and results. I can combine Python with my experience in user-focused interface design, HTML, CSS, JavaScript, and responsive layouts to deliver a practical demonstration platform around the trained model. The interface can be designed to make the workflow straightforward while clearly distinguishing predictions and evaluation information. I understand the importance of presenting this as an educational/demo tool rather than a clinical diagnosis system. My background in Figma, web development, usability, and cross-device compatibility makes me well suited to turn the technical MRI classification project into a polished, user-friendly application. Choose me to create an effective interface and Python-based web experience for your CapsNet system.
$100 USD in 6 days
4.7
4.7

Hi, I can develop your brain tumor detection project using the BR35H MRI dataset, training a conventional CNN baseline and a CapsNet model for comparative evaluation. I’ll implement preprocessing, augmentation, proper train/validation/test splits, and evaluate Accuracy, Precision, Recall, F1-score, ROC-AUC, confusion matrices, computational efficiency, and robustness under image-quality degradation. I’ll also build a user-friendly web application for MRI uploads and prediction scores, with documented code, trained model files, and evaluation visualizations. The system will be presented as an educational prototype, not a substitute for clinical diagnosis. Best regards, Shakila Naz
$100 USD in 1 day
5.1
5.1

I'd train the CapsNet on Br35H with normalization, resizing and augmentation, then wrap it in a Flask app with upload, image-quality check and Tumor/No Tumor output. I have built FastAPI sites on VPS and Flask apps before. I can start today.
$140 USD in 7 days
4.9
4.9

Hi there, I am a medical researcher, biostatistician, and deep learning developer with extensive experience in medical image processing, computer vision architectures, and academic reporting. Grounded in medical ethics and clinical imaging standards, I approach diagnostic AI with the methodological rigor necessary to build transparent, reproducible models. For your project, I will preprocess and augment the Br35H MRI dataset, train a baseline CNN alongside a Capsule Network (CapsNet) to capture spatial hierarchies, and benchmark both architectures across Accuracy, Recall, F1-Score, ROC-AUC, and confusion matrices. I will also conduct systematic perturbation tests to analyze performance drops under image degradation. Finally, I will package the trained CapsNet model into a responsive web application allowing users to upload brain MRI scans, perform automated quality checks, and obtain real-time Tumor or No Tumor predictions with confidence scores. Deliverables include clean, documented Python notebooks, saved model weights, an academic report with an abstract and literature references. What are your preferred hosting framework (such as Streamlit or Flask) and target deadline for deployment? Payment will be discussed over chat. Wishing you all the best.
$140 USD in 10 days
4.7
4.7

Hi, I can deliver a professional result tailored to the specific requirements in your project brief. I’ll review the scope, references, required formats, and final use first, then focus the work on the deliverables and details that matter for this project rather than applying a generic workflow. You’ll receive the agreed final files in the requested formats and dimensions, with editable source files where specified and reasonable revisions against the brief. Portfolio: https://www.freelancer.com/u/karimatchoo I can start immediately and will follow your brief and references closely. Best regards, Karim Mohamed
$133 USD in 1 day
3.9
3.9

Hi, I notice that training a Capsule Network on the BR35H Brain MRI dataset requires careful data preprocessing to enhance image quality. I'd approach this by applying image normalization and suitable data augmentation techniques. My goal is to develop a robust web-based brain tumor detection system using the trained CapsNet model. In my experience, a common mistake in deep learning model development is overfitting, which can be mitigated by splitting the dataset into distinct sets for training, validation, and testing. I'll set up a comparative performance analysis of the CapsNet and CNN models using metrics like Accuracy and F1-Score to determine their classification effectiveness. The client can expect a reliable and precise brain tumor detection system with a user-friendly web interface for uploading and processing MRI images.
$110 USD in 7 days
4.2
4.2

Hi, Your project needs more than just a trained CapsNet model—it requires a reliable comparison with CNN, image-quality assessment, and a working MRI classification web application. I'd use Python, PyTorch, and OpenCV to preprocess the Br35H dataset, implement CNN and CapsNet architectures, and evaluate both using Accuracy, Precision, Recall, F1, ROC-AUC, and confusion matrices. I'll also test performance under blur, noise, and resolution degradation. For deployment, I'd recommend FastAPI with a Streamlit interface supporting MRI uploads, quality checks, predictions, and confidence scores. Two quick questions: 1. Should image-quality assessment automatically reject poor-quality scans or simply display warnings? 2. Do you need a detailed comparative research report with training graphs and performance analysis? I'm ready to discuss the implementation and get started. Best regards, Jeff Chong
$140 USD in 7 days
4.1
4.1

Tumor detection from MRI scans, I would build this with a U-Net or CNN classifier in Keras, OpenCV for preprocessing and slicing, then wrap it in a Flask app with a simple upload and result view. I can start today and have a working prototype in 4 days. The budget and timeline here are initial estimates from the post, final numbers after we go over the dataset and accuracy targets you need. Want me to send a quick scope doc?
$150 USD in 7 days
3.7
3.7

Hey there, Python-based computer vision and deep learning are the core skills this MRI tumor detection system requires. I can develop the CapsNet-based binary classifier using the BR35H dataset, while also implementing a conventional CNN baseline for a meaningful comparison. My image-processing experience aligns with the required normalization, resizing, augmentation, and image-quality assessment. I can evaluate both models with accuracy, precision, recall, F1-score, ROC-AUC, and confusion matrices, including analysis under image-quality degradation. My Python skills also support integrating the trained model into a practical web interface using FastAPI or Django, allowing MRI uploads and displaying the Tumor/No Tumor prediction with its model score. I would be glad to build this as a clear, educational demonstration system with a reliable computer-vision pipeline and polished web integration. Choose me to develop your MRI analysis project.
$500 USD in 7 days
3.8
3.8

Hi! I have already completed a similar project using deep learning for medical image analysis. I’d be happy to give you a live demo and walk you through the model, results, and web application. We can schedule a short meeting at your convenience to discuss your requirements and see how my existing work aligns with your project.
$240 USD in 7 days
3.8
3.8

The integration of a Capsule Network for brain tumor detection from MRI scans is a critical aspect of this project. I would ensure the model is trained effectively using the Br35H dataset, focusing on preprocessing techniques like normalization and augmentation to enhance image quality before analysis. The plan involves first developing both a baseline CNN and the CapsNet model for comparison, followed by rigorous evaluation using metrics such as Accuracy and F1-Score. Before starting, I’d confirm the preferred framework for deployment, whether Flask or another, to ensure a smooth web application experience. With a Master's degree in AI and machine learning, I've successfully implemented deep learning models in various projects. What specific features do you envision for the user interface of the web application?
$120 USD in 7 days
3.2
3.2

A Python-based MRI classification system with both CapsNet and CNN models requires careful implementation and a reliable web application layer, and Python is the core skill I bring to this project. I can build the Br35H dataset preprocessing pipeline, including resizing, normalization, augmentation, and training/validation/testing separation for Tumor and No Tumor MRI images. My full-stack background includes 8+ years of developing web applications, custom systems, integrations, and AI automation solutions. This supports the complete delivery of a usable upload interface connected to the trained model, with image-quality checks, predicted class, and model confidence score displayed clearly. I can also implement the requested comparative evaluation using accuracy, precision, recall, F1-score, ROC-AUC, confusion matrices, and testing under image-quality degradation, while keeping the application suitable for educational and demonstration use rather than clinical diagnosis. I would be glad to develop this Python-based CapsNet brain tumor detection system and deliver a practical, well-integrated application.
$140 USD in 7 days
3.2
3.2

You want to develop a web-based brain tumor detection system using a Capsule Network (CapsNet) on the Br35H Brain MRI dataset with a comparative CNN baseline and a deployed web interface for Tumor or No Tumor predictions. - Data Collection and Preprocessing: I will load the BR35H dataset, apply normalization, resizing, and data augmentation to ensure data quality and integrity for training. - Dataset Splitting: I will split the data into distinct training, validation, and testing sets to prevent overfitting and enable rigorous assessment. - Deep Learning Model Development: I will implement and train a basic CNN baseline and a CapsNet primary model for classifying images into Tumor and No Tumor categories. - Comparative Performance Analysis: I will evaluate both models using Accuracy, Precision, Recall, F1-Score, ROC-AUC, and Confusion Matrix to determine CapsNet's relative strengths and limitations. - Performance Analysis Under Image-Quality Degradations: I will analyze the performance drop of each model under different image-quality degradations to measure robustness. - Model Deployment: I will develop a user-friendly Flask web interface for MRI upload, basic image-quality assessment, CapsNet inference, and display of the predicted class and model score. On Freelancer.com I hold 4.9 stars from 153 reviews. Price: USD 200, Timeline: 14 days (50% model training and comparison report / 50% web deployment and final delivery) - Adnan
$129.52 USD in 14 days
3.4
3.4

IF YOU ARE NOT HAPPY YOU DON'T PAY! Br35H has near-duplicate scans, so a random split can leak them across train and test and inflate both models toward 99%. CapsNet routing is also memory-heavy, so it usually trains at around 64-128px, and that resolution has to match what the web app feeds it. I'd do a deduplicated split, train the CNN baseline and the CapsNet, and report all six metrics. I'd also rerun them under blur, noise, low contrast and JPEG compression, then build a Flask upload page with a quality check that shows Tumor/No Tumor and the score. Point 4 mentions segmentation, but the dataset only supports classification. Is classification only okay? Send me a message and I'll explain exactly how I'd approach your project.
$250 USD in 3 days
2.9
2.9

Taxila Rawalpindi, Pakistan
Payment method verified
Member since Aug 2, 2026
$30-250 USD
$30-250 USD
$30-250 USD
$2-8 USD / hour
$1500-3000 USD
$30-250 USD
$30-250 USD
$30-250 USD
€140 EUR
₹750-1250 INR / hour
$30-250 USD
$25-50 USD / hour
₹75000-150000 INR
€8-30 EUR
£150-250 GBP
$30-250 AUD
$15-25 USD / hour
₹600-650 INR
$250-750 USD
$250-750 USD
$10-30 USD
$30-250 USD
$10-30 USD
$25 USD
$250-750 USD