← All publications

preprint · 2025 · Under internal review · no results disclosed

Towards Improving Mammography Quality: CNN Models for Skin Fold Positioning Error Classification

Adarsh Bhandary Panambur · Andreas Fieselmann · Reza Biniazan · Christian Hummer · Steffen Kappler · Siming Bayer · Andreas Maier

Not peer reviewed.

01 / SUMMARY

What this paper does

A skin fold in a mammogram is a positioning error: it can obscure tissue, degrade the read, and force a repeat exposure. This work trains convolutional neural networks to detect that error automatically, so quality control happens at acquisition rather than at reporting. It comes out of the Siemens Healthineers part of my doctoral work with the mammography systems team. The manuscript is under internal review, no venue has been assigned, and no quantitative results are publicly available, so this page deliberately contains no numbers.

02 / METHOD

How

Convolutional neural network classification of mammography images for the presence of skin-fold positioning errors. Methodological detail is withheld while the manuscript is under review.

03 / FINDINGS

Reported results

  • Under internal review. No quantitative results are publicly disclosed and none are reproduced here.
04 / WHY IT MATTERS

Relevance

Positioning quality is upstream of every downstream AI claim — a model trained or deployed on badly positioned images inherits the problem, and a repeat exposure has a real dose and cost.

05 / LIMITATION

What it does not show

Not peer reviewed, no venue, and no public results. Listed for completeness only.

06 / REFERENCE

Citation

A. Bhandary Panambur, A. Fieselmann, R. Biniazan, C. Hummer, S. Kappler, S. Bayer, A. Maier. Towards Improving Mammography Quality: CNN Models for Skin Fold Positioning Error Classification. Journal submission, under internal review, 2025.

View original abstract

A skin fold in a mammogram is a positioning error that can obscure tissue and force a repeat acquisition. This work develops convolutional neural network models to classify skin-fold positioning errors automatically as a mammography quality-control step. The manuscript is under internal review and no quantitative results are publicly available.

Related work

Connected publications

BE-WISE architecture: pre-contrast, post-contrast and subtraction MRI volumes stacked into a (32, 3, 224, 224) tensor, encoded by a shared Swin-Tiny slice encoder into (32, 768) embeddings, then split into a slice-level lesion predictor producing a per-slice probability curve and a breast-level classifier producing normal, benign or malignant

Bildverarbeitung für die Medizin (BVM) 2026, 10–17

BE-WISE: Breast MRI Evaluation with Weakly-Informed Slice-Level Explanation

Published

Breast MRI models usually need lesions outlined voxel by voxel, which does not scale. BE-WISE asks how far one annotated slice per exam gets you. Pre-contrast, post-contrast and subtraction volumes are stacked and encoded slice by slice with a shared Swin-Tiny transformer. One branch predicts a per-slice lesion probability against a Gaussian target centred on the radiologist's slice; the other pools the same embeddings by attention into a normal / benign / malignant decision. On the multicenter ODELIA dataset this reached test AUC 0.8683 and an ODELIA score of 0.7098, against 0.7968 and 0.5695 for a medical slice transformer baseline.

Explainable AIMedical ImagingDetection / Localization
1 min read → Paper ↗
BE-WISER architecture: pre-contrast, post-contrast and subtraction inputs go through a SwinV2-Tiny slice encoder into slice embeddings, which split into a breast-level classifier module with ABMIL attention, feature aggregation, global head and global logits, and a weak slice-level lesion localization branch with a slice head, slice logits and per-slice class probabilities over normal, benign and malignant

Research Square preprint (in review)

BE-WISER: Class-Aware Weak Slice-Level Supervision for Breast MRI

Preprint · in review

BE-WISE could say which slice contained something; BE-WISER says what that something is. Each slice inside the Gaussian region around the radiologist's marked slice inherits the exam's class — benign or malignant — while the rest are labelled normal, so the slice head becomes three-class instead of binary. On the latest multicenter ODELIA release (926 / 230 / 292 examinations from six institutions) this reached breast-level AUC 0.864 and an ODELIA score of 0.699, against 0.807 and 0.591 for a breast-level baseline. Localization also improved: Hit@1 rose from 0.554 to 0.632 and the mean slice distance fell from 2.838 to 2.505 slices.

Explainable AIDetection / LocalizationMedical Imaging
1 min read → Paper ↗
conference 2026 Vision-Language Models · Foundation Models

European Congress of Radiology (ECR) 2026, scientific exhibit C-15780

Lesion-Aware AI for Mammography: Multi-Dataset Pretraining with ROI-Guided Contrastive Learning and Clinical Image Retrieval

Accepted

Global contrastive pretraining lets a mammography model align on breast density or view rather than on the lesion, because those cues are enough to match an image to its report. This work adds region-of-interest guidance to multi-dataset contrastive pretraining, so localized pathology has to contribute to the representation, and then tests the embeddings on clinical image retrieval — finding visually and diagnostically similar prior cases. Accepted as a scientific exhibit at ECR 2026; quantitative results are not yet publicly available.

Vision-Language ModelsFoundation ModelsMedical Imaging
Details → DOI ↗