Machine Learning for Biomedical Imaging

We have a new low-frequency email list. Please consider signing up if you want to hear about our important announcements. melba-journal.org/contact.html

🎯 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.mel…

🚨 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, ..., K T Wilson, Y Huo, B A Landman. ⬇️

🎯 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.mel…

🚨 New publication alert: 📢 ”From Prompts to Pipelines: Evaluating LLM-Generated Medical Image Segmentation Baselines.” 🖊️ J Arjomandi, L Neubig, F Mathis-Ullrich, A M Kist. ⬇️

🎯 Authors propose a physics-regularized neural representation for respiratory motion modeling in radiotherapy, providing continuous, trajectory-aware motion estimation with improved extrapolation and physiologically plausible predictions. 🔎 Free to read: doi.org/10.59275/j.mel…

🚨 New publication alert: 📢 “Biophysics-Enhanced Neural Representations for Patient-Specific Respiratory Motion Modeling.” 🖊️ J Boysen, H Uzunova, H Handels, J Ehrhardt. ⬇️

🎯 Authors study human–AI interaction in pathology and show that while AI improves performance, it also introduces automation and anchoring biases. As reliance on AI increases, authors highlight risks in clinical decision support systems. 🔎 Free to read: doi.org/10.59275/j.mel…

🚨 New publication alert: 📢 “Stuck on Suggestions: Automation Bias, the Anchoring Effect, and the Factors That Shape Them in Computational Pathology.” 🖊️ E Rosbach, J Ammeling, J Ganz, C A Bertram, T Conrad, A Riener, M Aubreville. ⬇️

🎯 Authors present a multi-objective framework for evaluating fairness–utility trade-offs in ML, enabling systematic comparison of models across fairness and performance metrics in medical imaging. 🔎 Free to read: doi.org/10.59275/j.mel…

🚨 New publication alert: 📢 ”A Multi-Objective Evaluation Framework for Analyzing Utility-Fairness Trade-Offs in Machine Learning Systems.” 🖊️ G Özbulak, O Jimenez-del-Toro, M Fatoretto, L Berton, A Anjos. ⬇️

🎯 Authors propose a self-supervised contrastive framework for medical image segmentation that learns from unlabeled data and integrates SAM-based refinement. It enables efficient segmentation in low-data and cross-domain settings. 🔎 Free to read: doi.org/10.59275/j.mel…

🚨 New publication alert: 📢 “Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image Segmentation.” 🖊️ T B Ward, A Moseley, A-A-Z Imran. ⬇️

🎯 Authors present a benchmark for atypical mitosis classification using DL models, evaluated across in- and out-of-domain datasets, showing that transfer learning and fine-tuning effectively address this challenging, imbalanced task. 🔎 Free to read: doi.org/10.59275/j.mel…

🚨 New publication alert: 📢 “Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation.” 🖊️ @SwetaBioX, V Weiss, T A Donovan, R HJ Fick, T Conrad, ..., K Breininger, M Aubreville, C A Bertram. ⬇️

🎯 Authors propose resolution-agnostic frameworks using implicit neural representations for dense 3D analysis of anisotropic retinal OCT volumes, enabling improved volumetric evaluation across imaging protocols. 🔎 Free to read: doi.org/10.59275/j.mel…

🚨 New publication alert: 📢 “Don’t Mind the Gaps: Implicit Neural Representations for Resolution-Agnostic Retinal OCT Analysis.” 🖊️ B Kahrs, J Andresen, F Falta, M Santarossa, H Handels, T Kepp. ⬇️

🎯 Authors present a low-cost 3D breast reconstruction pipeline from monocular RGB video using a neural parametric shape model, achieving high-quality, accurate geometry without specialized hardware. 🔎 Free to read: doi.org/10.59275/j.mel…

🚨 New publication alert: 📢 “Learning Neural Parametric 3D Breast Shape Models for Metrical Surface Reconstruction From Monocular RGB Videos.” 🖊️ M Weiherer, A von Riedheim, V Brébant, B Egger, C Palm. ⬇️

🎯 Authors introduce a domain-specific AutoML system for cellular image analysis that automates pipeline design and training using meta-learning and multi-fidelity optimization. 🔎 Free to read: doi.org/10.59275/j.mel…

🚨 New publication alert: 📢 “AIxCell: A Domain-Specific and Meta-Learning based AutoML System for Cellular Image Segmentation.” 🖊️ J-H Roberg, L Leyendecker, S Schönleben, R H Schmitt. ⬇️