iiinova — where your digital self keeps evolving

Machine Learning for Biomedical Imaging

@melbajournal.bsky.social

67 followers 27 following 178 posts

Open-access, independent, minimum fee journal. Co-founded by Tal Arbel, @ja-schnabel.bsky.social, @msabuncu.bsky.social, William M. Wells III, Marc Niethammer, @adriandalca.bsky.social. Website: www.melba-journal.org

Posts Replies Media

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 7m

🎯 Authors introduce a public dataset of 129 CT scans from 91 patients with renal cell carcinoma, featuring voxel-level annotations of kidneys, tumors, and cysts, supporting reproducible AI research in renal cancer segmentation, detection, and classification. 🔎 Free to read: doi.org/10.59275/j.m...

RCC-AID: Renal Cell Carcinoma AI Dataset for Medical Imaging Research

S de Boer, H Häntze, S Ziegelmayer, T Russo, B van Ginneken, M Prokop, K Bressem, A Hering

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 7m

🚨 New publication alert: 📢 ”RCC-AID: Renal Cell Carcinoma AI Dataset for Medical Imaging Research.” 🖊️ S de Boer, H Häntze, S Ziegelmayer, T Russo, B van Ginneken, M Prokop, K Bressem, A Hering. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 13/10/2026

🎯 Authors introduce a longitudinal multimodal MRI dataset of 264 glioblastoma patients, with tumor delineations completed across 97% of available timepoints and treatment-response labels, brain masks, and radiomic features to support reproducible modeling. 🔎 Free to read: doi.org/10.59275/j.m...

CFB-GBM v2.0: An Augmented Longitudinal Dataset for Multi-Modal Glioblastoma Segmentation, Radiomics, and RANO Progression Tracking

A G Leclercq, N N Moreau, H Audebert, A Nassar, T Cochin, T Leleu, L Le Henaff, A Desmonts, Y Poirier, A Dubru, L Guillemette, P Lecoeur, K Lemasson, C Jaudet, S Bougleux, R Hérault, C Brunaud, S Val...

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 13/10/2026

🚨 New publication alert: 📢 ”CFB-GBM v2.0: An Augmented Longitudinal Dataset for Multi-Modal Glioblastoma Segmentation, Radiomics, and RANO Progression Tracking.” 🖊️ A G Leclerq, N N Moreau, H Audebert, A Nassar, T Cochin, T Leleu, ..., A Batalla, J Lacroix, R Rouzier, A Corroyer-Dulmont ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 12/10/2026

🎯 Authors introduce an expert-labeled histopathology dataset for oral squamous cell carcinoma detection, with 1,714 images from 115 patients and paired low- and high-magnification images supporting multi-scale analysis. 🔎 Free to read: doi.org/10.59275/j.m...

A Histopathological Image Dataset for Oral Squamous Cell Carcinoma and Normal Tissue Analysis

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 12/10/2026

🚨 New publication alert: 📢 ”A Histopathological Image Dataset for Oral Squamous Cell Carcinoma and Normal Tissue Analysis.” 🖊️ S Bahaa. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 12/10/2026

🎯 Authors introduce CT-Bench, a multimodal CT lesion resource and visual question answering benchmark with over 20,000 annotated lesions. It supports seven tasks for evaluating image–text alignment, localization, attributes, and lesion-level reasoning. 🔎 Free to read: doi.org/10.59275/j.m...

CT-Bench: A Comprehensive Benchmark for Multimodal AI in Computed Tomography Analysis

Q Zhu, Q Jin, T S Mathai, Y Fang, Z Wang, Y Yang, M Sarfo-Gyamfi, B Hou, R Gu, P T S Balamuralikrishna, K C Wang, R M Summers, Z Lu

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 12/10/2026

🚨 New publication alert: 📢 ”CT-Bench: A Comprehensive Benchmark for Multimodal AI in Computed Tomography Analysis.” 🖊️ Q Zhu, Q Jin, T S Mathai, Y Fang, …, P T S Balamuralikrishna, K C Wang, R M Summers, Z Lu. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 09/10/2026

🎯 Authors propose an approach combining anatomically adaptive brain representations with Kolmogorov–Arnold Networks to reduce atlas-related bias in functional connectivity analysis, improving downstream classification. 🔎 Free to read: doi.org/10.59275/j.m...

ABFR-KAN: Kolmogorov-Arnold Networks for Functional Brain Analysis

T Ward, A Imran

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 09/10/2026

🚨 New publication alert: 📢 ”ABFR-KAN: Kolmogorov-Arnold Networks for Functional Brain Analysis.” 🖊️ T Ward, A Imran. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 08/10/2026

🎯 Authors introduce a diffusion framework that generates images through topology-preserving geodesic deformations, explicitly modeling shape changes. The approach produces realistic images while preserving anatomical structure. 🔎 Free to read: doi.org/10.59275/j.m...

Geodesic-informed Generative Diffusion Model For Topology-preserved Image Video Generation

N Wu, N Jayakumar, J Xing, M Zhang

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 08/10/2026

🚨 New publication alert: 📢 ”Geodesic-informed Generative Diffusion Model For Topology-preserved Image Video Generation.” 🖊️ N Wu, N Jayakumar, J Xing, M Zhang. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 08/10/2026

🎯 Authors introduce SSIBench, an open-source framework benchmarking 21 self-supervised MRI reconstruction methods across seven realistic scenarios without fully sampled ground truth. 🔎 Free to read: doi.org/10.59275/j.m...

Benchmarking Self-Supervised Learning Methods for Accelerated MRI Reconstruction

A Wang, S McDonagh, M Davies

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 08/10/2026

🚨 New publication alert: 📢 ”Benchmarking Self-Supervised Learning Methods for Accelerated MRI Reconstruction.” 🖊️ A Wang, S McDonagh, M Davies. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 07/10/2026

🎯 Authors present the MYOSAIQ challenge, benchmarking myocardial infarct segmentation across a large multicenter cardiac MRI dataset. Results show that well-designed U-Net methods outperform fully automated foundation models. 🔎 Free to read: doi.org/10.59275/j.m...

The MYOSAIQ Challenge: Myocardial Segmentation with Automated Infarct Quantification

O Bernard, W A Romero R., C Bouton, C Goujat, H J Ling, P Jodoin, F Guo, C Sheagren, G Wright, A Qayyum, M Mazher, S A Niederer, H Wang, X Wu, F Thaler, G Plank, M Urschler, R M Rosales, E Pueyo, N Du...

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 07/10/2026

🚨 New publication alert: 📢 ”The MYOSAIQ Challenge: Myocardial Segmentation with Automated Infarct Quantification.” 🖊️ O Bernard, W A Romero R, C Bouton, C Goujat, H Jung Ling, P-M Jodoin, ..., P Clarysse, L Belle, T Bochaton, N Mewton, M Viallon, P Croisille. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 07/10/2026

🎯 Authors propose a framework to generate synthetic depth images from CT scans for AI-based patient positioning in radiography. Pretraining on synthetic data improves pose assessment on real radiographs by up to 11 percentage points. 🔎 Free to read: doi.org/10.59275/j.m...

Patient Pose Assessment Using a CT-Based Framework for Synthetic Data Generation

M Laufer, D Mairhöfer, M Sieren, H Gerdes, F Leal dos Reis, A Bischof, T Käster, E Barth, J Barkhausen, T Martinetz

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 07/10/2026

🚨 New publication alert: 📢 ”Patient Pose Assessment Using a CT-Based Framework for Synthetic Data Generation.” 🖊️ M Laufer, D Mairhöfer, M Sieren, H Gerdes, F Leal dos Reis, A Bischof, T Käster, E Barth, J Barkhausen, T Martinetz. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 02/10/2026

🎯 Authors introduce a dataset for predicting ejection fraction from parasternal long-axis echocardiography, with over 25,000 labeled videos, showing clinically relevant performance and further improvements by combining multiple echocardiographic views. 🔎 Free to read: doi.org/10.59275/j.m...

Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction

Z Gao, D Yurk, Y S Abu-Mostafa

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 02/10/2026

🚨 New publication alert: 📢 ”Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction.” 🖊️ Z Gao, D Yurk, Y S Abu-Mostafa. ⬇️

Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction

Z Gao, D Yurk, Y S Abu-Mostafa

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 23/09/2026

📢 New MELBA Special Issue: MICCAI Open Data 2026 Featuring 16 open datasets across diverse populations, diseases, imaging modalities, and clinical settings, advancing more accessible and representative medical AI research. 🔗 : www.melba-journal.org/issues/micca...

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 31/08/2026

🎯 Authors introduce a new dataset of 25,000+ echocardiography videos for ejection fraction prediction, showing clinically relevant performance and further improvements by combining multiple echocardiographic views. 🔎 Free to read: doi.org/10.59275/j.m...

Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction

Z Gao, D Yurk, Y S Abu-Mostafa

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 31/08/2026

🚨 New publication alert: 📢 ”Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction.” 🖊️ Z Gao, D Yurk, Y S Abu-Mostafa. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 28/08/2026

🎯 Authors propose a framework that predicts the 3D locations and shapes of 41 anatomical structures from a single 2D depth image, enabling automated patient positioning, reducing setup time and improving radiology workflow efficiency. 🔎 Free to read: doi.org/10.59275/j.m...

Depth to Anatomy: Organ Localization from Depth Images for Automated Patient Table Positioning in Radiology Workflow

E Kats, K Geissler, J G Hirsch, D Mensing, J Senegas, S Heldman, M P Heinrich

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 28/08/2026

🚨 New publication alert: 📢 ”Depth to Anatomy: Organ Localization from Depth Images for Automated Patient Table Positioning in Radiology Workflow.” 🖊️ E Kats, K Geissler, J G Hirsch, D Mensing, J Senegas, S Heldman, M P Heinrich. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 18/08/2026

🎯 Authors compare loss functions for learning from partially labeled echocardiography datasets across multiple domains, identifying the most effective strategies for different labeling scenarios and improving multi-structure cardiac segmentation. 🔎 Free to read: doi.org/10.59275/j.m...

Comparison of Loss Functions for Robust Deep Learning-based Echocardiography Segmentation when Learning with Partially Labelled Data from Multiple Domains

I Islam, B Ruijsink, E Puyol-Antón, A J Reader, A P King

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 18/08/2026

🚨 New publication alert: 📢 ”Comparison of Loss Functions for Robust Deep Learning-based Echocardiography Segmentation when Learning with Partially Labelled Data from Multiple Domains.” 🖊️ I Islam, B Ruijsink, E Puyol-Antón, A J Reader, A P King. ⬇️

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 05/08/2026

🎯 Authors evaluate Shift-Variant FBP for cone-beam CT reconstruction across challenging acquisition settings, showing robustness to irregular trajectories and efficient reconstruction while revealing limitations under severe undersampling. 🔎 Free to read: doi.org/10.59275/j.m...

Robustness and Stability Analysis of Differentiable Shift-Variant FBP for Cone-Beam CT under Challenging Acquisition Settings

C Ye, L Schneider, Y Sun, M Thies, S Mei, P A Pérez-Toro, S Bayer, A Maier

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 05/08/2026

🚨 New publication alert: 📢 ”Robustness and Stability Analysis of Differentiable Shift-Variant FBP for Cone-Beam CT under Challenging Acquisition Settings.” 🖊️ C Ye, L-S Schneider, Y Sun, M Thies, S Mei, P A Pérez-Toro, S Bayer, A Maier. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 13/07/2026

🎯 Authors explore how to maximize domain generalization for fetal brain MRI segmentation using FetalSynthSeg, showing that simple intensity modeling improves robustness across scanners and MRI contrasts, achieving SOTA performance on out-of-domain datasets. 🔎 Free to read: doi.org/10.59275/j.m...

Evaluating Synthetic Data Generation for Domain Generalization in Fetal Brain MRI Segmentation

V Zalevskyi, T Sanchez, M Roulet, B Bulut, H Lajous, J Aviles Verdera, S Neves Silva, G Langs, G Kasprian, R Licandro, J Hutter, H Kebiri, M Bach Cuadra

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 13/07/2026

🚨 New publication alert: 📢 ”Evaluating Synthetic Data Generation for Domain Generalization in Fetal Brain MRI Segmentation.” 🖊️ V Zalevskyi, T Sanchez, M Roulet, B Bulut, H Lajous, J Aviles Verdera, S Neves Silva, G Langs, G Kasprian, R Licandro, J Hutter, H Kebiri, M Bach Cuadra. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 09/07/2026

🎯 Authors benchmark deep learning models for predicting cell cycle dynamics from label-free brightfield microscopy, enabling accurate prediction of continuous cell cycle progression without fluorescent reporters. 🔎 Free to read: doi.org/10.59275/j.m...

Sequence models for continuous cell cycle stage prediction from brightfield images

A Salati, L Leger, M Leonardi, M Weigert, F Naef

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 09/07/2026

🚨 New publication alert: 📢 ”Sequence models for continuous cell cycle stage prediction from brightfield images.” 🖊️ A Salati, L-A Leger, M Leonardi, M Weigert, F Naef. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 08/07/2026

🎯 Authors introduce a spectral generative framework to model 3D dental crown shapes from compact intrinsic representations. Synchronizing spectral embeddings enables robust and efficient shape generation from limited datasets with varying mesh connectivity. 🔎 Free to read: doi.org/10.59275/j.m...

Deep Spectral Models for Robust Dental Shape Generation

T Kubı́k, F Guibault, M Španěl, H Lombaert

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 08/07/2026

🚨 New publication alert: 📢 ”Deep Spectral Models for Robust Dental Shape Generation.” 🖊️ T Kubı́k, F Guibault, M Španěl, H Lombaert. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 07/07/2026

🎯 Authors propose a graph-based framework for multi-label chest CT classification that models inter-slice relationships through spectral graph convolution, achieving strong cross-dataset generalization. 🔎 Free to read: doi.org/10.59275/j.m...

Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans

T Di Piazza, C Lazarus, O Nempont, L Boussel

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 07/07/2026

🚨 New publication alert: 📢 ”Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans.” 🖊️ T Di Piazza, C Lazarus, O Nempont, L Boussel. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 06/07/2026

🎯 Authors introduce a lightweight framework that restores anatomically plausible segmentation maps on out-of-distribution medical images. by learning geometric priors from small in-distribution datasets. 🔎 Free to read: doi.org/10.59275/j.m...

Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation

J B Pal, S P Awate

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 06/07/2026

🚨 New publication alert: 📢 ”Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation.” 🖊️ J B Pal, S P Awate. ⬇️

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 02/07/2026

🎯 Authors introduce a ML pipeline using multi-modal fetal MRI to predict gestational age at birth. The study highlights cervical length and placental T2* as key predictors of preterm birth risk. 🔎 Free to read: doi.org/10.59275/j.m...

Predicting gestational age at birth in the context of preterm birth from multi-modal fetal MRI

D Fajardo-Rojas, M Hall, D Cromb, M A Rutherford, L Story, E Robinson, J Hutter

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 02/07/2026

🚨 New publication alert: 📢 ”Predicting gestational age at birth in the context of preterm birth from multi-modal fetal MRI.” 🖊️ D Fajardo-Rojas, M Hall, D Cromb, M A Rutherford, L Story, E Robinson, J Hutter. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 23/06/2026

🎯 Authors propose a Bayesian framework for T1 mapping using a novel spatial prior that improves spatial consistency and uncertainty quantification, producing more reliable parameter estimates than existing Bayesian and maximum-likelihood approaches. 🔎 Free to read: doi.org/10.59275/j.m...

Generalized TV–ℓp Structured Priors for Bayesian T1 Mapping

D Lin, M Berggren, T Löfstedt

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 23/06/2026

🚨 New publication alert: 📢 ”Generalized TV–ℓp Structured Priors for Bayesian T1 Mapping.” 🖊️ D Lin, M Berggren, T Löfstedt. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 12/06/2026

🎯 Authors investigate how sex and age biases in training data affect skin lesion classification models, highlighting the need for targeted fairness strategies and robust evaluation across populations. 🔎 Free to read: doi.org/10.59275/j.m...

Effect of Demographic Bias on Skin Lesion Classification

R Raumanns, G Schouten, V Cheplygina, J P Pluim

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 12/06/2026

🚨 New publication alert: 📢 ”Effect of Demographic Bias on Skin Lesion Classification.” 🖊️ R Raumanns, G Schouten, V Cheplygina, J PW Pluim. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 10/06/2026

🎯 Authors present a kidney and renal mass segmentation model built on nnU-Net, demonstrating robust generalization to external cohorts and consistent performance across patient and imaging subgroups. 🔎 Free to read: doi.org/10.59275/j.m...

Robust Renal Mass Segmentation on CT: A Validation Study of an AI-Based Framework

S de Boer, H Häntze, K V Venkadesh, M A D Buser, G E Humpire Mamani, L Xu, L C Adams, J Nawabi, K K Bressem, B van Ginneken, M Prokop, A Hering

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 10/06/2026

🚨 New publication alert: 📢 ”Robust Renal Mass Segmentation on CT: A Validation Study of an AI-Based Framework.” 🖊️ S de Boer, H Häntze, K V Venkadesh, …, K K Bressem, B van Ginneken, M Prokop, A Hering. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 20/05/2026

🎯 Authors propose a deformable registration method for multiplexed immunofluorescence imaging that improves nucleus alignment across staining rounds, increasing reliable cell classification for downstream analysis. 🔎 Free to read: doi.org/10.59275/j.m...

Quantifying the Efficacy of Deep Learning-Driven Deformable Registra- tion in Multiplexed-Immunofluorescence Imaging for Nucleus Subtype Classification

G Rudravaram, S Bao, L W Remedios, A R Krishnan, M E Kim, Y Liu, C Gao, R Zhang, B Jiang, Q Liu, K S Lau, J T Roland, M K Washington, L A Coburn, K T Wilson, Y Huo, B A Landman

000

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 20/05/2026

🚨 New publication alert: 📢 ”Quantifying the Efficacy of Deep Learning-Driven Deformable Registration in Multiplexed-Immunofluorescence Imaging for Nucleus Subtype Classification.” 🖊️ G Rudravaram, S Bao, L W Remedios, A R Krishnan, ..., L A Coburn, K T Wilson, Y Huo, B A Landman. ⬇️

100

Machine Learning for Biomedical Imaging @melbajournal.bsky.social · 19/05/2026

🎯 Authors evaluate LLMs for automatically generating medical image segmentation pipelines, showing that reasoning-enabled models improve accuracy, stability, and code quality across modalities. 🔎 Free to read: doi.org/10.59275/j.m...

From Prompts to Pipelines: Evaluating LLM-Generated Medical Image Segmentation Baselines

J Arjomandi, L Neubig, F Mathis-Ullrich, A M Kist

000