
Closed
Posted
Paid on delivery
I need an experienced medical imaging freelancer to implement, run, and verify the workflow below for every patient and available time point in my longitudinal multiple sclerosis (MS) MRI dataset. You may use Claude or a comparable AI coding assistant to develop the pipeline. Perform image analysis using suitable neuroimaging software and an MS lesion segmentation method validated for the available sequences. Deliver the completed analysis, images, masks, Excel workbook, QC overlays, and reproducible code. **Dataset:** [Google Drive MRI dataset (90 pt with average of 6 procedures (time points for each))] Available sequences may include T1-weighted precontrast (T1pre), T1-weighted postcontrast (T1post), and FLAIR. Process downloaded copies and upload completed outputs to the source Google Drive folder. Preserve originals and maintain confidentiality using the agreed computing and storage environment. **1. Organize and identify scans** Create a folder named exactly **MS segmentation** inside the source directory: `MS segmentation/<existing patient folder name>/<existing time-point folder name>/` Preserve patient/time-point names and exclude the output folder from input searches. Match sequences from the same examination. Verify contrast status using available metadata, rather than filenames alone. Document missing sequences or ambiguous matches. Record scan date and patient age at each examination where available. Use the recorded examination age or calculate age from verified birth and scan dates. Enter NA if unavailable. **2. Preprocess and register** Apply N4 bias correction and intensity normalization appropriate for the segmentation method to each available sequence. Use compatible T1pre/T1post intensity matching that preserves genuine enhancement. Compare original and processed images to check that processing has not created or obscured enhancement. Rigidly coregister same-visit sequences and verify T1pre/T1post alignment before assessing enhancement. Keep patients and time points separate. Retain transformations and combine them where possible to minimize repeated interpolation. Use registered working copies for analysis. Save final preprocessed images on their respective original grids and transform masks back to each native grid. **3. Segment lesions and classify enhancement** Use a validated MS lesion segmentation method and document its model/version, required inputs, and validation evidence. Confirm that outputs represent MS lesions, rather than normal white matter or general brain tissue. Use FLAIR to establish total lesion extent, supported by T1pre where appropriate. Assess enhancement by comparing matched, aligned T1post and T1pre using a suitable enhancement-detection method. Cross-check enhancement candidates against FLAIR and original T1 images. Exclude obvious vessels, normally enhancing structures, intrinsic T1 hyperintensity, and processing artifacts. Classify whole lesions as: - Nonenhancing MS white-matter lesion. - Enhancing MS lesion. - Enhancement status indeterminate when assessment is unreliable or required sequences are missing. Missing T1post must not be interpreted as absence of enhancement. Flag uncertain findings for review. Assign focal or ring enhancement to the **whole lesion**; do not classify a ring lesion's center as a separate nonenhancing lesion. A FLAIR segmentation model does not automatically classify enhancement. Use a suitable method for each task. If a capability or sequence is unavailable, document the limitation and complete supported outputs. **4. Generate masks and NIfTI outputs** Create a binary FLAIR lesion mask: - 0 = background/nonlesion tissue. - 1 = MS lesion. Create separate multiclass masks on the original T1pre and T1post grids: - 0 = background/nonlesion tissue, including normal white matter. - 1 = nonenhancing MS white-matter lesion. - 2 = enhancing MS lesion. - 3 = MS lesion with indeterminate enhancement status. Determine classifications from the matched sequences, then export them to each available T1 native grid. T1pre/T1post masks must represent the same classifications in their respective spaces. These labels describe whole lesions categorized by enhancement status. If exact enhancing tissue can also be segmented, save it separately as a binary mask and report its volume separately. Save successfully generated outputs as **uncompressed .nii** files: ```text <Patient>_<Timepoint>[login to view URL] <Patient>_<Timepoint>[login to view URL] <Patient>_<Timepoint>[login to view URL] <Patient>_<Timepoint>[login to view URL] <Patient>_<Timepoint>[login to view URL] <Patient>_<Timepoint>[login to view URL] ``` Optional, when successfully generated: `<Patient>_<Timepoint>[login to view URL]` Use existing patient/time-point names in filenames. Preserve each original scan's dimensions, voxel spacing, orientation, and spatial coordinates in its corresponding preprocessed image and mask. Use nearest-neighbor interpolation for masks and integer labels. Report missing or failed outputs. **5. Create [login to view URL]** Save the workbook inside **MS segmentation**, with these worksheets: **A. Lesion_Summary** One row per patient, time point, enhancement group, and anatomical category. Columns: Patient ID; Time point; Scan date; Patient age at scan (years); Enhancement group; Anatomical category; Lesion count; Lesion volume (cm³); Lesion volume (% of ICV); Lesion burden (% of WM); Measurement reference space; Corresponding mask paths; QC status/comments. Enhancement groups: - All lesions. - Enhancing lesions. - Nonenhancing white-matter lesions. - Enhancement status indeterminate. For each group, report: Total, Periventricular, Deep white matter, Juxtacortical, Infratentorial, and Unclassified where necessary. Use an anatomical segmentation or atlas-based method. Document one consistent classification rule, assign each lesion to one anatomical category, and avoid double counting lesions spanning regions. Total rows are aggregates, not additional categories to sum. **B. Individual_Lesions** One row per lesion. Columns: Patient ID; Time point; Scan date; Age at scan (years); Lesion ID; Anatomical category; Enhancement status; Voxel count; Volume (mm³); Volume (cm³); Volume (% of ICV); Lesion burden (% of WM); Measurement reference space; QC comments. When available, add **Enhancing tissue volume (cm³)**. Keep this separate from the full volume of a lesion classified as enhancing. Lesion IDs are specific to each time point unless reliable longitudinal matching has been performed and documented. **C. Reference_Volumes** Columns: Patient ID; Time point; Age at scan (years); Intracranial volume (cm³); Total white-matter volume including lesions (cm³); Measurement source/method; QC comments. Calculations: - Lesion volume (cm³) = lesion voxel count × voxel volume (mm³) ÷ 1000. - Lesion volume (% of ICV) = lesion volume (cm³) ÷ intracranial volume (cm³) × 100. - Lesion burden (% of WM) = lesion volume (cm³) ÷ total white-matter volume including lesions (cm³) × 100. Use the same reference volumes for all enhancement groups within each patient/time point. Calculate primary lesion counts and whole-lesion volumes once on a clearly identified reference grid, preferably native FLAIR. Do not count exported T1 copies as additional lesions. Keep measurements in separate numeric columns. Display volumes and percentages to four decimal places and counts as integers. Use Excel formulas where appropriate. Use NA for unavailable/unreliable measurements and explain why. Use 0 only when processing succeeded and the category was absent. Do not fabricate measurements or infer reference volumes from example values. **6. Quality control and completion report** Save overlays in each patient/time-point folder: - Total lesion mask over FLAIR. - Classified lesions over T1pre, where available. - Classified lesions over T1post, where available. Legend: green = nonenhancing; red = enhancing; yellow = indeterminate. Use a clearly labeled single color for the binary total-lesion overlay. Check registration, native-space geometry, label values, anatomical classification, obvious false positives/missed lesions, and agreement between masks and Excel measurements. Confirm that enhancing, nonenhancing, and indeterminate groups reconcile with total lesion counts and volumes without overlap or double counting. Provide a completion report covering patients/time points processed, available/missing sequences, successful outputs, missing measurements, failures with reasons, findings requiring expert review, and the output folder/workbook locations. Verify that delivered files are present and readable. **7. Reproducibility and execution** Deliver executable scripts, configuration files, parameters, software/dependency versions, model versions and weight sources, registration transformations, processing logs, a completion/failure manifest, and reproduction instructions.
Project ID: 40795997
94 proposals
Remote project
Active 2 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
94 freelancers are bidding on average $460 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
$500 USD in 7 days
8.0
8.0

My 7+ years of medical data analysis and research, combined with hands-on image processing, deep learning, and machine learning skills, make me well suited to this MS MRI lesion segmentation workflow. I can work across longitudinal patient/time-point data, structure outputs consistently, and produce the required Excel summaries, masks, QC overlays, and reproducible Python/R code. My background in biostatistics and medical research supports careful handling of patient-level data, missing sequences, age and scan-date fields, classification records, and quality-control documentation. I can use image-processing and deep-learning methods to support FLAIR lesion segmentation, preserve separate patient examinations, and clearly document limitations where enhancement assessment depends on unavailable or unreliable T1post data. My Python, R, Excel, and data-processing experience is also directly relevant to validating outputs and maintaining an auditable workflow. I would be glad to apply my medical imaging and analytical skills to this dataset and deliver well-organized, documented results while preserving the original files.
$750 USD in 7 days
7.0
7.0

My expertise in deep learning, image processing, and machine learning is directly aligned with building an automated MRI lesion-segmentation workflow for a longitudinal MS dataset. I can develop and run the processing pipeline in Python or MATLAB, handling the available T1pre, T1post, and FLAIR images while keeping patient and time-point data separated. My image-processing background supports preprocessing, registration, intensity analysis, lesion-mask generation, enhancement comparison, and QC visualization. I can also structure the outputs consistently across examinations, produce the requested NIfTI masks and Excel summaries, and provide reproducible code documenting processing decisions, model usage, missing sequences, ambiguous matches, and limitations. I would be glad to apply my deep learning and medical image-analysis skills to deliver a thoroughly documented, verifiable MS segmentation workflow and its associated outputs.
$750 USD in 15 days
6.5
6.5

Hi, This project requires a robust, reproducible pipeline for longitudinal MS MRI lesion segmentation with precise preprocessing, registration, and lesion classification. The main engineering risk lies in ensuring accurate coregistration and enhancement classification across multiple sequences and time points while preserving native spatial references. I usually structure pipelines with clear separation of preprocessing, segmentation, and postprocessing layers, enabling traceability and quality control at each step. My experience extending complex systems and delivering well-documented, reproducible code suits the detailed workflow and reporting requirements here. I would first validate the segmentation model compatibility and registration accuracy before automating lesion classification and mask generation. Embedding thorough QC overlays and Excel reporting ensures reliable outputs for clinical review. Systems like this benefit from stable, maintainable pipelines designed for iterative review and expert feedback. I can outline the ingestion, processing, and reporting architecture to meet these goals. Thanks, Hercules
$500 USD in 7 days
6.5
6.5

⭐⭐⭐⭐⭐ Medical Imaging Workflow for Longitudinal MS MRI Dataset ❇️ Hi My Friend, I hope you are doing well. I checked all of your project requirements and I can see you are looking for an experienced medical imaging freelancer. You have no need to look any further as Zohaib is here to help you! My team is already doing 50+ similar projects for neuroimaging pipelines. I will build a reproducible pipeline using Python, NiPy, and a validated MS lesion model. I will run the full workflow on each patient, generate all masks, Excel sheets, QC overlays, and upload results to the same Google Drive folder, all within your budget. ➡️ Why Me? I can easily do your MS MRI analysis as I have 5 years of experience in Python, MRI preprocessing, lesion segmentation, and data management. Not only this, I have a strong grip on N4 bias correction, image registration, and Excel automation. ➡️ Let's have a quick chat to discuss your project in detail and let me show you samples of my previous work. Looking forward to discussing with you in chat. ➡️ Skills & Experience: ✅ Python ✅ NiPy ✅ FSL ✅ ANTs ✅ N4 Bias Correction ✅ Image Registration ✅ MS Lesion Segmentation ✅ Excel Automation ✅ QC Overlay Creation ✅ Google Drive API ✅ Reproducible Scripts ✅ Data Confidentiality Waiting for your response! Best Regards, Zohaib
$350 USD in 2 days
6.4
6.4

Hello, I have a research background in biomedical image analysis, deep learning-based segmentation, and reproducible clinical AI pipelines, including research on brain tumour histopathology and model evaluation across heterogeneous clinical datasets. For your longitudinal MS MRI project, I recommend beginning with a paid validation pilot on a representative subset of examinations before processing the complete dataset of approximately 540 time points. This would allow us to establish a reliable workflow for the available MRI sequences and identify limitations before full-scale execution. My proposed approach is to: - Audit the patient/time-point structure, MRI metadata, sequence availability, and native image geometry. - Evaluate suitable, research-validated MS lesion segmentation methods, such as LST-AI or FLAMeS, depending on available sequences. - Implement registration, preprocessing, native-space mask exports, and independent enhancement assessment using matched T1pre/T1post images. - Generate anatomical lesion classifications, volumetric measurements, QC overlays, and the requested Excel worksheets. - Implement automated consistency checks, processing logs, failure reporting, and reproducible execution scripts. I would be happy to discuss the dataset format, available MRI sequences, computing environment, and validation expectations. Best regards, Naga Raju
$500 USD in 7 days
6.1
6.1

I can implement and execute this longitudinal MS MRI lesion-segmentation workflow across the available patients and time points, with careful separation of input data, native-space outputs, and quality-control deliverables. The pipeline will organize examinations, verify sequence matching and contrast status, apply N4 correction and suitable normalization, register same-visit images, and use validated MS lesion-segmentation methods with documented model versions and limitations. Enhancement classification will be handled separately from FLAIR lesion detection, with explicit indeterminate labels where T1post or image quality is insufficient. I will provide uncompressed NIfTI images and masks on the correct native grids, registration transforms, QC overlays, processing logs, manifests, configuration files, dependency/model documentation, and reproducibility instructions. The Excel workbook will include lesion-level and summary measurements, anatomical categories, reference volumes, formulas, QC comments, and transparent NA handling without fabricating values. I will also reconcile masks, classifications, volumes, and workbook totals, then provide a completion report identifying missing sequences, failures, and cases requiring expert review. Confidentiality, preservation of originals, and verification that all delivered files are readable will be maintained throughout execution.
$250 USD in 2 days
5.4
5.4

Hello, I have carefully reviewed your project requirements, and I am confident that my experience with medical image processing, MRI segmentation, image registration, and quantitative analysis makes me a strong candidate for this project. I can work through the complete workflow, including: 1. **Dataset organization and sequence identification** - Organize patient and time-point folders while preserving the original structure. - Identify and match T1pre, T1post, and FLAIR sequences. - Check available metadata and document missing or ambiguous sequences. 2. **MRI preprocessing and registration** - Apply N4 bias-field correction and appropriate intensity normalization. - Perform rigid registration of same-examination sequences. - Verify T1pre/T1post alignment and preserve native-space geometry. - Retain registration transformations and preprocessing parameters. 3. **MS lesion segmentation and enhancement classification** - Apply an appropriate MS lesion segmentation approach validated for the available MRI sequences. - Use FLAIR to establish total lesion extent. - Assess enhancement using aligned precontrast and postcontrast T1 images. - Classify whole lesions as enhancing, nonenhancing, or indeterminate. 4. **NIfTI masks and image outputs** - Generate binary FLAIR lesion masks. - Generate separate multiclass T1pre and T1post lesion-label masks. Looking forward to working with you. Best regards
$500 USD in 3 days
5.3
5.3

Hello, Your longitudinal MS set is really a production job: roughly ninety patients and several visits each, with a fixed folder layout, native-space masks, enhancement labels, and an Excel workbook that has to add up without double counting. I would run it as a batch pipeline with a clear audit trail, not a pile of one-off scripts. First I match sequences from the same exam using metadata, not filenames alone, and log anything missing or ambiguous. Then N4 and intensity prep suited to a validated FLAIR lesion method, rigid same-visit alignment of T1pre, T1post, and FLAIR, and a quick check that prep did not invent or hide real enhancement. FLAIR sets total lesion extent; enhancement only comes from aligned T1post vs T1pre, with cross-checks against FLAIR and the originals so vessels and normal bright structures stay out. Each whole lesion gets one label: nonenhancing, enhancing, or indeterminate when the postcontrast scan is missing or unreliable. Missing T1post never means no enhancement. You get uncompressed NIfTI on the original grids, green/red/yellow QC overlays, the three-sheet workbook with volumes to four decimals, plus runnable code, versions, transforms, and a completion report. I suggest a small pilot batch first so we lock the method before the full Drive run.
$570 USD in 14 days
4.9
4.9

I understand you require a robust and reproducible MS lesion segmentation workflow. My experience with similar longitudinal datasets, particularly in developing automated processing pipelines for [mention a specific technique or software, e.g., T1-weighted and FLAIR sequence registration and segmentation], positions me to efficiently deliver accurate and verifiable results for your 90-patient cohort. I'm proficient in handling the scale and complexity of such datasets. My proposed approach will leverage a combination of established neuroimaging tools. I will employ FSL or ANTs for image registration and normalization, ensuring precise co-alignment across all time points. For lesion segmentation, I will implement a validated method such as Lesion-TOOLS or a deep learning model trained on relevant sequences, depending on the optimal performance for your specific data. The entire pipeline will be scripted using Python and NiBabel for seamless execution, data handling, and reproducible code generation. I will also implement rigorous QC checks, including overlay visualization on original T1 and FLAIR images. To ensure the best fit, could you clarify if you have any preferred segmentation software or specific validation metrics you'd like to prioritize? I’m available for a brief call to discuss your dataset in more detail and refine the technical plan.
$607 USD in 21 days
4.7
4.7

Affordable, Early Delivery. ★★★★★★★★★★★★★★I hold a Masters degree which gives me the requisite background to handle writing from various subjects. I am a highly committed person towards my work. You can rely on QualityXenter for quality and consistency in writing. We never violate copyright rules. I have vast amount of experience in this industry since I am working from 2015 as a professional writer. I provide many modifications till to get your satisfactions. I have access to enough journals to use in your research project. I always produce quality work at VERY LOW RATES so, don't worry if you have a low budget for your work, I will be very happy to make a new client like you. I am producing quality work for my clients including ARTICLE WRITING, REPORT WRITING, ESSAY WRITING, RESEARCH PAPERS, BUSINESS PLAN, TECHNICAL WRITING, MATLAB, THESIS, ACCOUNTING & FINANCE work ETC. Go through my profile link https://www.freelancer.com/u/qualityxenter
$250 USD in 1 day
4.1
4.1

Hi there, This is Dev Singh from Bengaluru, India. I checked your project description and understand you want a reproducible MS MRI analysis pipeline that produces reliable lesion measurements, enhancement classifications, native-space masks, and quality-controlled patient-level reports across the longitudinal dataset. I've built something very similar recently, where the hardest challenge was maintaining consistent lesion classification and spatial accuracy across sequences and time points. I'd suggest Python, 3D Slicer, and validated MS lesion segmentation models, with registration and expert QC before batch processing. A few quick questions so I get this right: Q1 –, Which MRI sequences and acquisition protocols are consistently available across the approximately 540 examinations? Q2 –, Is a neuroradiologist or MS imaging specialist available to review uncertain lesion and enhancement classifications? Q3 –, Do you have a preferred validated segmentation model, or should model selection and validation evidence be part of the project? Happy to discuss a pilot on a few representative patients before estimating the full workload on a quick call, if that works for you. Looking forward to hearing from you. Best, Dev Singh
$1,000 USD in 15 days
4.3
4.3

Hi there, I see you need to implement a comprehensive workflow for MS lesion segmentation using the supplied MRI dataset. I can take charge of organizing scans into the specified folder structure while ensuring proper preprocessing, registration, and segmentation of lesions. For this, I would utilize validated MS lesion segmentation methods and generate the required masks and analysis files as outlined in your project. I will ensure a systematic approach to each step, maintaining confidentiality and the data's integrity. I am prepared to deliver an Excel workbook containing comprehensive lesion data and the necessary quality control overlays as part of the final output. This approach will allow for reproducibility and clarity in your analysis. Regards, Ali
$340 USD in 7 days
3.7
3.7

My MATLAB expertise is the strongest match for developing and running a reproducible processing workflow for your longitudinal MS MRI dataset. I can use MATLAB to organize patient and time-point data, manage sequence matching, perform image-processing operations, generate structured outputs, and support verification across the available examinations. I can also prepare the requested Excel workbook and reproducible code, while documenting missing sequences, ambiguous matches, processing limitations, and QC findings. The workflow can preserve the original dataset and produce the requested lesion masks, transformed outputs, and review records where the available imaging and validated methods support them. I will keep the analysis organized consistently within the required patient/time-point folder structure. My MATLAB and Mathematica skills make me well suited to implement a controlled, auditable imaging workflow for this project, and I would be glad to complete the analysis and deliver the associated outputs and documentation.
$258 USD in 2 days
3.3
3.3

You need an experienced medical imaging freelancer to implement, run, and verify a longitudinal MS MRI lesion segmentation workflow for 90 patients across multiple time points, delivering organized preprocessed images, validated lesion masks, enhancement classifications, QC overlays, an Excel workbook, and reproducible code uploaded to your Google Drive. I will create the exact `MS segmentation/<patient>/<timepoint>/` folder structure, match sequences per examination using DICOM metadata (not filenames), and record scan dates and patient ages from available tags. For preprocessing, I will apply N4 bias correction (ANTs) and intensity normalization (Nyúl or histogram matching) per sequence, then rigidly coregister same-visit T1pre/T1post/FLAIR with ANTs/FLIRT, verifying alignment visually and via mutual information before enhancement assessment. Transformations will be combined to minimize interpolation; preprocessed images saved on original grids. For segmentation, I will use a validated deep-learning model (e.g., nnU-Net trained on MS lesion challenges, or FSL's BIANCA with FLAIR+T1pre) documenting model/version and validation evidence. FLAIR defines total lesion extent; enhancement is assessed by subtracting aligned T1pre from T1post with a thresholded difference map, cross-checked against FLAIR and raw T1s to exclude vessels, choroid plexus, and artifacts. Whole lesions are classified as nonenhancing (1), enhancing (2), or indeterminate (3); missing T1post flags indeterminate, not absent. Outputs: binary FLAIR lesion mask (0/1) and multiclass T1pre/T1post masks (0-3) transformed to each native grid, saved as uncompressed .nii with your exact naming convention. Optional enhancing-tissue binary mask and volume reported when feasible. All code (Python, nibabel, nilearn, torch, ANTsPy, pandas) delivered as a reproducible pipeline with config and requirements. QC overlays (mask contours on preprocessed images) generated per time point. Results aggregated into an Excel workbook with patient, time point, sequences present, lesion counts, volumes, enhancement status, and QC flags. On Freelancer.com I hold 4.9 stars from 153 reviews. - Adnan
$450 USD in 14 days
3.4
3.4

Hello, "MS Lesion Segmentation Processing" - the challenge is producing consistent lesion and enhancement classifications across hundreds of longitudinal MRI examinations without confusing missing sequences or processing artifacts with true findings. I'll establish a reproducible pipeline for registration, validated lesion segmentation, enhancement assessment, native-space masks, anatomical classification, Excel measurements and QC. I'll preserve scan geometry, flag unreliable cases and document every model, parameter and failure. Can we agree on a representative pilot batch before processing the full dataset? Looking forward to working with you.
$750 USD in 60 days
3.4
3.4

Hello, I am Chang Liu, an AI researcher with a PhD from the University of Science and Technology of China. My research is in deep learning for images and video, with papers in IEEE TIP and IEEE TCSVT. For your MS dataset I would: 1. Organize all patients and time points in the MS segmentation folder, verify contrast status from metadata, and log missing or ambiguous sequences, scan dates and ages. 2. Apply N4 correction and normalization, rigidly coregister same-visit sequences with ANTs, and keep all transforms so masks return to each native grid by nearest neighbor. 3. Segment lesions on FLAIR with a published, validated MS method such as LST-AI, documenting its version, then classify enhancement by comparing aligned T1post and T1pre, labelling unreliable cases indeterminate. 4. Derive ICV and white matter volumes from an anatomical segmentation such as SynthSeg, assign each lesion to one category by a documented rule, and build MS_Lesion_Analysis.xlsx. 5. Deliver QC overlays, the completion report, scripts, versions and logs. One honest note: I am not a radiologist, so findings needing expert review will be flagged, not decided by me. No public tool is fully validated for enhancement classification, so I will document my method and its limits. We should agree the computing environment for the patient data before I start. My profile: https://www.freelancer.com/u/AlonzoLeeeooo I can first process one patient end to end for your review. Chang
$750 USD in 21 days
3.6
3.6

Hi, the part I'd watch closest is enhancement. LST-AI will give you the FLAIR lesions, but it won't tell you which ones enhance. So I'd run that as its own step: N4, rigid T1pre/T1post registration, intensity matching, then a subtraction map checked against FLAIR so vessels and T1-bright spots don't get counted. I'll build it in Python with ANTsPy, nibabel and SynthSeg. SynthSeg gives ICV, white matter, and the ventricle, cortex and brainstem labels behind the four location rules. Each lesion gets one category and one status. It's counted once on native FLAIR, then moved to each T1 grid with nearest-neighbor. On the imaging side, I built a Radiology Information System with a DICOM viewer on fo-dicom. I also built a lab tool that measures marks in camera images with OpenCV and calibration. I have 159 reviews on Freelancer. I'd split it into 3 milestones: 1) scan inventory, sequence matching and full outputs for 3 patients for you to check 2) the run over all 90 patients and their visits 3) the workbook, QC overlays, completion report and the scripts to rerun it Message me and we'll set the timeline together. If you want a different order, that's easy to change. I've assumed you or a radiologist will review the flagged lesions. I'll flag them clearly but won't make the clinical call. Are the scans DICOM or already NIfTI?
$300 USD in 20 days
3.0
3.0

Dataset organization: Automatically identify patients, time points, and matching T1pre, T1post, and FLAIR sequences. Record missing or ambiguous scans, examination dates, and available age information. Preprocessing and registration: Use N4 bias-field correction, appropriate intensity normalization, and rigid registration of same-examination sequences. Preserve transformations and native-space geometry. Lesion segmentation: Select an established MS lesion segmentation method compatible with the available MRI sequences. Document its model version, input requirements, and validation evidence. Use FLAIR to establish lesion extent. Enhancement classification: Compare aligned T1pre and T1post images, cross-check candidates against FLAIR, and classify whole lesions as enhancing, nonenhancing, or indeterminate. Missing postcontrast imaging will never be treated as evidence of absent enhancement. Native-space outputs: Generate the requested binary FLAIR masks and multiclass T1pre/T1post masks, preserving dimensions, orientation, voxel spacing, and spatial coordinates.
$500 USD in 7 days
3.2
3.2

Hi, I have built large-scale data processing pipelines that generate reproducible outputs and structured workbooks from imaging-like datasets. I’ll implement the end-to-end MS segmentation workflow: folder organization, N4 bias correction, coregistration, validated lesion segmentation, label export to native grids, QC overlays, and MS_Lesion_Analysis.xlsx. I deliver dependable, scriptable pipelines with versioned configuration and execution logs that support repeatable verification. Best, Razmik
$300 USD in 5 days
2.6
2.6

Riyadh, Saudi Arabia
Payment method verified
Member since Mar 6, 2023
$250-750 USD
$250-750 USD
₹750-1250 INR / hour
₹750-1250 INR / hour
$30-250 USD
$8-15 USD / hour
$15-25 USD / hour
$250-750 USD
₹12500-37500 INR
$10-11 USD
₹12500-37500 INR
$30-250 USD
₹750-1250 INR / hour
$10-30 USD
$30-250 USD
$30-250 AUD
$10-30 USD
$30-250 USD
$15-25 USD / hour
$15-25 USD / hour
$4-50 USD / hour
$250-750 USD