arXiv subjects

Gernot Kronreif

Publications and source records attributed to Gernot Kronreif.

9 recordsLinked to original sources

arXiv2026

Less Contouring, More Accuracy: Lesion-Guided ROI Deep Learning for Ovarian Ultrasound Classification

Ovarian lesion classification using transvaginal ultrasound remains challenging due to overlapping imaging characteristics and the dependence on expert interpretation. This study investigates whether lesion-guided region-of-interest (ROI) deep learning can achieve competitive diagnostic performance while reducing the annotation burden associated with pixel-level lesion segmentation. Two publicly available ovarian ultrasound datasets were evaluated: the Multi-Modality Ovarian Tumor Ultrasound (MMOTU) dataset for eight-class classification and the Ovarian Ultrasound Dataset (OUD) for binary classification. Four strategies were compared under a unified framework: global image-based deep learning, lesion-guided ROI-based deep learning, lesion contour-based deep learning, and contour-based radiomics with machine learning classifiers. Four deep learning architectures, MaxViT-Tiny, Swin Transformer, EfficientNet-B7, and ResNet18, were evaluated. Radiomics models were developed using support vector machine, k-nearest neighbors, and artificial neural network classifiers, with ANOVA-based feature selection applied for the lower-sample OUD dataset. The lesion-guided ROI strategy achieved the strongest overall performance, with MaxViT-Tiny obtaining 93.10% accuracy and an AUC of 0.99 on MMOTU and 97.56% accuracy and an AUC of 0.99 on OUD. The contour-based approach achieved comparable accuracy but required substantially higher annotation effort. These findings demonstrate that lesion-guided ROI deep learning provides an effective balance between diagnostic performance and annotation efficiency, offering a practical approach for scalable AI-assisted ovarian ultrasound analysis

cs.CV↗

arXiv2026

Current validation practice undermines surgical AI development

Surgical data science (SDS) is rapidly advancing, yet clinical adoption of artificial intelligence (AI) in surgery remains limited, with inadequate validation as an important contributing factor. Existing validation practices often neglect the temporal and hierarchical structure of intraoperative videos, yielding misleading or clinically irrelevant results. We introduce a comprehensive catalogue of validation pitfalls in AI-based surgical video analysis, derived from a multi-stage Delphi process with 92 international experts. Pitfalls span three categories: (1) data, (2) metric selection/configuration, and (3) aggregation and reporting. A systematic review of surgical AI papers reveals that these pitfalls are widespread. Experiments on surgical video datasets show that ignoring temporal and hierarchical data structures can understate uncertainty, obscure critical failure modes, and alter algorithm rankings. To address these shortcomings, we provide consensus-based best practices compiled. Together, this work provides an evidence-based framework for rigorous validation of surgical video analysis algorithms, guiding benchmarking, reporting, regulatory review, and clinical translation.

q-bio.OT↗

arXiv2026

CBCT-IQ: A Publicly Available Annotated Cone-Beam CT Dataset for Image Quality Assessment and Benchmarking

Medical image quality plays a critical role in diagnostic accuracy, especially in X-ray-based imaging modalities such as cone-beam computed tomography (CBCT), where image quality must be balanced against radiation dose. While expert visual evaluation remains the clinical standard for image quality evaluation, it is time-consuming, subjective and affected by inter-observer variability, emphasizing the need for reliable quantitative image quality assessment (IQA) methods. However, the development and validation of such IQA methods have been limited by the lack of publicly available CBCT datasets with expert image quality annotations. In this study, we provide the first open-access CBCT IQA dataset containing 1,764 annotated image slices acquired using systematic variations in image acquisition and reconstruction parameters. Three clinical experts graded the overall image quality and a predefined regions of interest (ROI) using a four-level scoring scheme. In addition, we benchmark 26 full reference- and no reference-based IQA measures against expert annotations and introduce an exploratory IQA measure-based ranking capable of distinguishing subtle image quality differences. This dataset introduced a standardized benchmark for future CBCT IQA research and provides a valuable resource for the development and validation of new IQA methods, enabling reproducible research and advancing CBCT IQA.

physics.med-ph↗

arXiv2026

A deep learning pipeline for PAM50 subtype classification using histopathology images and multi-objective patch selection

Breast cancer is a highly heterogeneous disease with diverse molecular profiles. The PAM50 gene signature is widely recognized as a standard for classifying breast cancer into intrinsic subtypes, enabling more personalized treatment strategies. In this study, we introduce a novel optimization-driven deep learning framework that aims to reduce reliance on costly molecular assays by directly predicting PAM50 subtypes from H&E-stained whole-slide images (WSIs). Our method jointly optimizes patch informativeness, spatial diversity, uncertainty, and patch count by combining the non-dominated sorting genetic algorithm II (NSGA-II) with Monte Carlo dropout-based uncertainty estimation. The proposed method can identify a small but highly informative patch subset for classification. We used a ResNet18 backbone for feature extraction and a custom CNN head for classification. For evaluation, we used the internal TCGA-BRCA dataset as the training cohort and the external CPTAC-BRCA dataset as the test cohort. On the internal dataset, an F1-score of 0.8812 and an AUC of 0.9841 using 627 WSIs from the TCGA-BRCA cohort were achieved. The performance of the proposed approach on the external validation dataset showed an F1-score of 0.7952 and an AUC of 0.9512. These findings indicate that the proposed optimization-guided, uncertainty-aware patch selection can achieve high performance and improve the computational efficiency of histopathology-based PAM50 classification compared to existing methods, suggesting a scalable imaging-based replacement that has the potential to support clinical decision-making.

cs.CV↗

arXiv2026

Deep learning based Non-Rigid Volume-to-Surface Registration for Brain Shift compensation Using Point Cloud

Soft-tissue deformation remains a major limitation in image-guided neurosurgery, where intra-operative anatomy can deviate substantially from pre-operative imaging due to brain shift, compromising navigation accuracy and surgical safety. Existing compensation methods often rely on intra-operative MRI, CT, or ultrasound, which are disruptive and difficult to integrate repeatedly into the surgical workflow. In contrast, partial 3D cortical surfaces can be reconstructed as point clouds from stereoscopic microscopes or laser range scanners (LRS), capturing only a limited portion of the exposed cortex. This makes point cloud registration a practical alternative without interrupting surgery; however, such partial and noisy observations make deformation estimation highly challenging. In this study, we propose a deep learning-based framework for non-rigid volume-to-surface registration, enabling dense displacement field estimation from sparse intra-operative surface observations without explicit point correspondences or volumetric intra-operative imaging. The network leverages multi-scale point-based feature extraction and a hierarchical deformation decoder to capture both global and local deformations. The key contribution lies in integrating partial intra-operative surface information into the full pre-operative point cloud domain, enabling implicit correspondence learning and dense deformation recovery under limited visibility. Quantitative results demonstrate accurate recovery of fine-scale deformations, achieving an Endpoint Error (EPE) of 1.13 +/- 0.75 mm and RMSE of 1.33 +/- 0.81 mm under challenging partial-surface conditions. The proposed approach supports automatic, workflow-compatible brain-shift compensation from sparse surface observations.

cs.CV↗

arXiv2024

An Integrated Optimization and Deep Learning Pipeline for Predicting Live Birth Success in IVF Using Feature Optimization and Transformer-Based Models

In vitro fertilization (IVF) is a widely utilized assisted reproductive technology, yet predicting its success remains challenging due to the multifaceted interplay of clinical, demographic, and procedural factors. This study develops a robust artificial intelligence (AI) pipeline aimed at predicting live birth outcomes in IVF treatments. The pipeline uses anonymized data from 2010 to 2018, obtained from the Human Fertilization and Embryology Authority (HFEA). We evaluated the prediction performance of live birth success as a binary outcome (success/failure) by integrating different feature selection methods, such as principal component analysis (PCA) and particle swarm optimization (PSO), with different traditional machine learning-based classifiers including random forest (RF) and decision tree, as well as deep learning-based classifiers including custom transformer-based model and a tab transformer model with an attention mechanism. Our research demonstrated that the best performance was achieved by combining PSO for feature selection with the TabTransformer-based deep learning model, yielding an accuracy of 99.50% and an AUC of 99.96%, highlighting its significant performance to predict live births. This study establishes a highly accurate AI pipeline for predicting live birth outcomes in IVF, demonstrating its potential to enhance personalized fertility treatments.

cs.AI↗

arXiv2024

Advanced Hybrid Deep Learning Model for Enhanced Classification of Osteosarcoma Histopathology Images

Recent advances in machine learning are transforming medical image analysis, particularly in cancer detection and classification. Techniques such as deep learning, especially convolutional neural networks (CNNs) and vision transformers (ViTs), are now enabling the precise analysis of complex histopathological images, automating detection, and enhancing classification accuracy across various cancer types. This study focuses on osteosarcoma (OS), the most common bone cancer in children and adolescents, which affects the long bones of the arms and legs. Early and accurate detection of OS is essential for improving patient outcomes and reducing mortality. However, the increasing prevalence of cancer and the demand for personalized treatments create challenges in achieving precise diagnoses and customized therapies. We propose a novel hybrid model that combines convolutional neural networks (CNN) and vision transformers (ViT) to improve diagnostic accuracy for OS using hematoxylin and eosin (H&E) stained histopathological images. The CNN model extracts local features, while the ViT captures global patterns from histopathological images. These features are combined and classified using a Multi-Layer Perceptron (MLP) into four categories: non-tumor (NT), non-viable tumor (NVT), viable tumor (VT), and none-viable ratio (NVR). Using the Cancer Imaging Archive (TCIA) dataset, the model achieved an accuracy of 99.08%, precision of 99.10%, recall of 99.28%, and an F1-score of 99.23%. This is the first successful four-class classification using this dataset, setting a new benchmark in OS research and offering promising potential for future diagnostic advancements.

eess.IV↗

arXiv2022

Silicone phantoms fabricated with multi-material extrusion 3D printing technology mimicking imaging properties of soft tissues in CT

Recently, 3D printing has been widely used to fabricate medical imaging phantoms. So far, various rigid 3D printable materials have been investigated for their radiological properties and efficiency in imaging phantom fabrication. However, flexible, soft tissue materials are also needed for imaging phantoms, which are used in various scenarios, such as anatomical deformations to improve dynamic treatments and various needle-based surgeries and training. Recently, various silicone additive manufacturing technologies have been used to produce anatomical models based on extrusion techniques that allow the fabrication of soft tissue materials. To date, there is no systematic study in the literature investigating the radiological properties of silicone rubber materials/fluids for imaging phantoms fabricated directly by extrusion using 3D printing techniques. The aim of this study was to investigate the radiological properties of 3D printed phantoms made of silicone in CT imaging. The radiodensity as described as Hounsfield Units (HU) of several test phantoms composed of three different silicone printing materials were evaluated by changing the infill density to adjust their radiological properties. A comparison of HU values with a Gammex Tissue Characterization Phantom was performed. A scaled down anatomical model derived from an abdominal CT was also fabricated and the resulting HU values were evaluated. For the three different silicone materials, a spectrum ranging from -639 to +780 HU was obtained on CT at a scan setting of 120 kVp. A good agreement was observed between the HU target values in abdominal CT and the HU values of the 3D-printed anatomical phantom in all tissues. Moreover, using different infill densities, the printed materials were able to achieve a similar radiodensity range as obtained in different tissue-equivalent inserts in the Gammex phantom (238 HU to -673 HU).

physics.med-ph↗

arXiv2022

Realistic 3D printed imaging tumor phantoms for validation of image processing algorithms

Medical imaging phantoms are widely used for validation and verification of imaging systems and algorithms in surgical guidance and radiation oncology procedures. Especially, for the performance evaluation of new algorithms in the field of medical imaging, manufactured phantoms need to replicate specific properties of the human body, e.g., tissue morphology and radiological properties. Additive manufacturing (AM) technology provides an inexpensive opportunity for accurate anatomical replication with customization capabilities. In this study, we proposed a simple and cheap protocol to manufacture realistic tumor phantoms based on the filament 3D printing technology. Tumor phantoms with both homogenous and heterogenous radiodensity were fabricated. The radiodensity similarity between the printed tumor models and real tumor data from CT images of lung cancer patients was evaluated. Additionally, it was investigated whether a heterogeneity in the 3D printed tumor phantoms as observed in the tumor patient data had an influence on the validation of image registration algorithms. A density range between -217 to 226 HUs was achieved for 3D printed phantoms; this range of radiation attenuation is also observed in the human lung tumor tissue. The resulted HU range could serve as a lookup-table for researchers and phantom manufactures to create realistic CT tumor phantoms with the desired range of radiodensities. The 3D printed tumor phantoms also precisely replicated real lung tumor patient data regarding morphology and could also include life-like heterogeneity of the radiodensity inside the tumor models. An influence of the heterogeneity on accuracy and robustness of the image registration algorithms was not found.

physics.med-ph↗