Accurate Segmentation Research Articles

Attention-Based Two-Branch Hybrid Fusion Network for Medical Image Segmentation

Accurate segmentation of medical images is vital for disease detection and treatment. Convolutional Neural Networks (CNN) and Transformer models are widely used in medical image segmentation due to their exceptional capabilities in image recognition and segmentation. However, CNNs often lack an understanding of the global context and may lose spatial details of the target, while Transformers struggle with local information processing, leading to reduced geometric detail of the target. To address these issues, this research presents a Global-Local Fusion network model (GLFUnet) based on the U-Net framework and attention mechanisms. The model employs a dual-branch network that utilizes ConvNeXt and Swin Transformer to simultaneously extract multi-level features from pathological images. It enhances ConvNeXt’s local feature extraction with spatial and global attention up-sampling modules, while improving Swin Transformer’s global context dependency with channel attention. The Attention Feature Fusion module and skip connections efficiently merge local detailed and global coarse features from CNN and Transformer branches at various scales. The fused features are then progressively restored to the original image resolution for pixel-level prediction. Comprehensive experiments on datasets of stomach and liver cancer demonstrate GLFUnet’s superior performance and adaptability in medical image segmentation, holding promise for clinical analysis and disease diagnosis.

Advanced Integration of Machine Learning Techniques for Accurate Segmentation and Detection of Alzheimer’s Disease

Alzheimer’s disease is a common type of neurodegenerative condition characterized by progressive neural deterioration. The anatomical changes associated with individuals affected by Alzheimer’s disease include the loss of tissue in various areas of the brain. Magnetic Resonance Imaging (MRI) is commonly used as a noninvasive tool to assess the neural structure of the brain for diagnosing Alzheimer’s disease. In this study, an integrated Improved Fuzzy C-means method with improved watershed segmentation was employed to segment the brain tissue components affected by this disease. These segmented features were fed into a hybrid technique for classification. Specifically, a hybrid Convolutional Neural Network–Long Short-Term Memory classifier with 14 layers was developed in this study. The evaluation results revealed that the proposed method achieved an accuracy of 98.13% in classifying segmented brain images according to different disease severities.

Accurate Segmentation Method for Roadside Lampposts Based on Vehicle-Mounted Lidar Point Clouds

Abstract. The extraction of roadside lampposts constitutes a significant research focus within the domain of vehicular LiDAR point cloud object retrieval. Addressing the complexities inherent in discerning lampposts amidst convoluted vegetation in diverse roadway settings, this study introduces an innovative, progressive technique for the individualized extraction of lampposts utilizing vehicular LiDAR point clouds. The proposed method initiates with a bifurcation of the primary point cloud into terrestrial and aerial subsets via the Cloth Simulation Filter (CSF) algorithm. Subsequent processes involve the extraction of distinct lamppost structures from aerial point clouds through a methodology integrating elevation-normalized spatial partitioning and directional coverage analysis, thereby facilitating precise lamppost localization. The culmination of this process involves the refinement of lamppost point clouds through supervoxel clustering complemented by a non-discretization filter grounded in Principal Component Analysis (PCA). The efficacy of this novel approach is substantiated through empirical studies employing a LiDAR dataset encompassing extensive adhesive scenarios, whereupon comparative analysis with extant methodologies reveals its enhanced proficiency in isolating individual lampposts in complex environments.

Interactive machine learning for segmenting pores of sandstone in computed tomography images

In the realm of gas field development and CO2/H2 geological storage, the precise characterization of reservoir parameters stands as a critical role. In recent years, digital rock technology has emerged as a cutting-edge tool for examining micro-pore structures, permeability parameter characteristics, and reservoir flow mechanisms. However, there are still certain defects in image segmentation, where low-density pore bodies in low-resolution images make it difficult to clearly distinguish between pores and solid minerals, affecting the accuracy of pore segmentation. This article aims to improve the accuracy of sandstone pore segmentation. We utilized the interactive machine learning segmentation method to segment pore structures and compare the segmented images obtained with the traditional ImageJ grayscale threshold segmentation methods. Furthermore, we evaluated the effectiveness of different segmentation methods quantitatively using the confusion matrix. The research results indicate that the segmentation quality (F1 score) of the machine learning method is higher than the grayscale methods, and the segmentation effectiveness of machine learning method is more stable. To further validate the accuracy of the machine learning method, we simulated the permeability and the results were compared with the experimental results, and the results show that the deviation in permeability segmented through machine learning methods is the smallest. Therefore, our results demonstrate the effective application of the machine learning method in segmenting sandstone pores in the digital rock images.

Hybrid deep learning and optimal graph search method for optical coherence tomography layer segmentation in diseases affecting the optic nerve

Accurate segmentation of retinal layers in optical coherence tomography (OCT) images is critical for assessing diseases that affect the optic nerve, but existing automated algorithms often fail when pathology causes irregular layer topology, such as extreme thinning of the ganglion cell-inner plexiform layer (GCIPL). Deep LOGISMOS, a hybrid approach that combines the strengths of deep learning and 3D graph search to overcome their limitations, was developed to improve the accuracy, robustness and generalizability of retinal layer segmentation. The method was trained on 124 OCT volumes from both eyes of 31 non-arteritic anterior ischemic optic neuropathy (NAION) patients and tested on three cross-sectional datasets with available reference tracings: Test-NAION (40 volumes from both eyes of 20 NAION subjects), Test-G (29 volumes from 29 glaucoma subjects/eyes), and Test-JHU (35 volumes from 21 multiple sclerosis and 14 control subjects/eyes) and one longitudinal dataset without reference tracings: Test-G-L (155 volumes from 15 glaucoma patients/eyes). In the three test datasets with reference tracings (Test-NAION, Test-G, and Test-JHU), Deep LOGISMOS achieved very high Dice similarity coefficients (%) on GCIPL: 89.97±3.59, 90.63±2.56, and 94.06±1.76, respectively. In the same context, Deep LOGISMOS outperformed the Iowa reference algorithms by improving the Dice score by 17.5, 5.4, and 7.5, and also surpassed the deep learning framework nnU-Net with improvements of 4.4, 3.7, and 1.0. For the 15 severe glaucoma eyes with marked GCIPL thinning (Test-G-L), it demonstrated reliable regional GCIPL thickness measurement over five years. The proposed Deep LOGISMOS approach has potential to enhance precise quantification of retinal structures, aiding diagnosis and treatment management of optic nerve diseases.

Improved Real-Time Models for Object Detection and Instance Segmentation for Agaricus bisporus Segmentation and Localization System Using RGB-D Panoramic Stitching Images

The segmentation and localization of Agaricus bisporus is a precondition for its automatic harvesting. A. bisporus growth clusters can present challenges for precise localization and segmentation because of adhesion and overlapping. A low-cost image stitching system is presented in this research, utilizing a quick stitching method with disparity correction to produce high-precision panoramic dual-modal fusion images. An enhanced technique called Real-Time Models for Object Detection and Instance Segmentation (RTMDet-Ins) is suggested. This approach utilizes SimAM Attention Module’s (SimAM) global attention mechanism and the lightweight feature fusion module Space-to-depth Progressive Asymmetric Feature Pyramid Network (SPD-PAFPN) to improve the detection capabilities for hidden A. bisporus. It efficiently deals with challenges related to intricate segmentation and inaccurate localization in complex obstacles and adhesion scenarios. The technology has been verified by 96 data sets collected on a self-designed fully automatic harvesting robot platform. Statistical analysis shows that the worldwide stitching error is below 2 mm in the area of 1200 mm × 400 mm. The segmentation method demonstrates an overall precision of 98.64%. The planar mean positioning error is merely 0.31%. The method promoted in this research demonstrates improved segmentation and localization accuracy in a challenging harvesting setting, enabling efficient autonomous harvesting of A. bisporus.

An improved attention module based on nnU-Net for segmenting primary central nervous system lymphoma (PCNSL) in MRI images1.

Accurate volumetric segmentation of primary central nervous system lymphoma (PCNSL) is essential for assessing and monitoring the tumor before radiotherapy and the treatment planning. The tedious manual segmentation leads to interindividual and intraindividual differences, while existing automatic segmentation methods cause under-segmentation of PCNSL due to the complex and multifaceted nature of the tumor. To address the challenges of small size, diffused distribution, poor inter-layer continuity on the same axis, and tendency for over-segmentation in brain MRI PCNSL segmentation, we propose an improved attention module based on nnUNet for automated segmentation. We collected 114 T1 MRI images of patients in the Huashan Hospital, Shanghai. Then randomly split the total of 114 cases into 5 distinct training and test sets for a 5-fold cross-validation. To efficiently and accurately delineate the PCNSL, we proposed an improved attention module based on nnU-Net with 3D convolutions, batch normalization, and residual attention (res-attention) to learn the tumor region information. Additionally, multi-scale dilated convolution kernels with different dilation rates were integrated to broaden the receptive field. We further used attentional feature fusion with 3D convolutions (AFF3D) to fuse the feature maps generated by multi-scale dilated convolution kernels to reduce under-segmentation. Compared to existing methods, our attention module improves the ability to distinguish diffuse and edge enhanced types of tumors; and the broadened receptive field captures tumor features of various scales and shapes more effectively, achieving a 0.9349 Dice Similarity Coefficient (DSC). Quantitative results demonstrate the effectiveness of the proposed method in segmenting the PCNSL. To our knowledge, this is the first study to introduce attention modules into deep learning for segmenting PCNSL based on brain magnetic resonance imaging (MRI), promoting the localization of PCNSL before radiotherapy.

Potato powdery scab segmentation using improved GrabCut algorithm

Potato powdery scab is a serious disease that affects potato yield and has widespread global impacts. Due to its concealed symptoms, it is difficult to detect and control the disease once lesions appear. This paper aims to overcome the drawbacks of interactive algorithms and proposes an optimized approach using object detection for the GrabCut algorithm. We design a YOLOv7-guided non-interactive GrabCut algorithm and combine it with image denoising techniques, considering the characteristics of potato powdery scab lesions. We successfully achieve effective segmentation of potato powdery scab lesions. Through experiments, the improved segmentation algorithm has an average accuracy of 88.05%, and the highest accuracy can reach 91.07%. This is an increase of 46.28% and 32.69% respectively compared to the relatively accurate K-means algorithm. Moreover, compared to the original algorithm which could not segment the lesions independently, the improvement is more significant. The experimental results indicate that the algorithm has a high segmentation accuracy, which provides strong support for further disease analysis and control.

A Novel Multi-Scale Feature Map Fusion for Oil Spill Detection of SAR Remote Sensing

The efficient and timely identification of oil spill areas is crucial for ocean environmental protection. Synthetic aperture radar (SAR) is widely used in oil spill detection due to its all-weather monitoring capability. Meanwhile, existing deep learning-based oil spill detection methods mainly rely on the classical U-Net framework and have achieved impressive results. However, SAR images exhibit high noise, blurry boundaries, and irregular shapes of target areas, as well as speckles and shadows, which lead to the loss of performance in existing algorithms. In this paper, we propose a novel network architecture to achieve more precise segmentation of oil spill areas by reintroducing rich semantic contextual information before obtaining the final segmentation mask. Specifically, the proposed architecture can re-fuse feature maps from different levels at the decoder end. We design a multi-convolutional layer (MCL) module to extract basic feature information from SAR images, and a feature extraction module (FEM) module further extracts and fuses feature maps generated by the U-Net decoder at different levels. Through these operations, the network can learn rich global and local contextual information, enable sufficient interaction of feature information at different stages, enhance the model’s contextual awareness, and improve its ability to recognize complex textures and blurry boundaries, thereby enhancing the segmentation accuracy of SAR images. Compared to many U-Net based segmentation networks, our method shows promising results and achieves state-of-the-art performance on multiple evaluation metrics.

Structural Analysis of Glazed Tubular Tiles of Oriental Architectures Based on 3D Point Clouds for Cultural Heritage

Abstract. Laser scanning, along with its resultant 3D point clouds, constitutes a prevalent method for the documentation of cultural heritage. This paper introduces a novel workflow for the structural analysis of glazed tubular tiles that adorn the roofs of historical buildings in the Orient, utilizing 3D point clouds. The workflow integrates a robust segmentation algorithm utilizing the maximum principal curvature and normal vectors. Moreover, clustering algorithms, including DBSCAN, are incorporated to refine the clusters and thus increase segmentation accuracy. Structural analysis is enabled by cylindrical model fitting, which allows for the estimation of parameters and residuals. While the results exhibit commendable performance in individual tile segmentation, it is imperative to address the impact of substantial variations in scanning range and incident angles before engaging in the structural analysis fitting process. The results of experiment demonstrate that under conditions of significantly large scanning angles, the root mean square error (RMSE) for inadequately fitted tiles can extend to 0.066 m, surpassing twice the RMSE observed for well-fitted tiles. The proposed workflow proves to be applicable and exhibits significant potential to advance practices in cultural heritage documentation.

Comparing Deep Learning and MCWST Approaches for Individual Tree Crown Segmentation

Abstract. Accurate segmentation of individual tree crowns (ITC) segmentation is essential for investigating tree-level based growth trends and assessing tree vitality. ITC segmentation using remote sensing data faces challenges due to crown heterogeneity, overlapping crowns and data quality. Currently, both classical and deep learning methods have been employed for crown detection and segmentation. However, the effectiveness of deep learning based approaches is limited by the need for high-quality annotated datasets. Benefiting from the BaKIM project, a high-quality annotated dataset can be provided and tested with a Mask Region-based Convolutional Neural Network (Mask R-CNN). In addition, we have used the deep learning based approach to detect the tree locations thus refining the previous Marker controlled Watershed Transformation (MCWST) segmentation approach. The experimental results show that the Mask R-CNN model exhibits better model performance and less time cost compared to the MCWST algorithm for ITC segmentation. In summary, the proposed framework can achieve robust and fast ITC segmentation, which has the potential to support various forest applications such as tree vitality estimation.

MFAFNet: An innovative crack intelligent segmentation method based on multi-layer feature association fusion network

The regular and timely detection and segmentation of cracks in asphalt pavements is very important for road evaluation. However, certain problems remain to be solved, such as the difficulty of crack detection under interference from zebra stripes and dark light. A novel intelligent crack segmentation method based on a multi-layer feature association fusion network (MFAFNet) is therefore proposed in this study. Firstly, a fusion convolution with a Transformer called a feature coupling encoder (FC-Encoder) is developed in MFAFNet to enhance the model's global feature awareness and ability to capture local details. Secondly, a two-branch feature association module (TFBA-module) is proposed to obtain strong correlation information for global and local features. Next, a hybrid MLP architecture for lightweight feature decoder (H-MLP Decoder) is constructed to achieve feature recombination of the multi-level fusion information. The accuracy of crack segmentation under interference from zebra stripes and dark light is improved through the use of these three modules. Our model is compared with some well-known existing segmentation networks such as U-Net, DeepLabv3+, PSPNet, HRNet and SegFormer, and the segmentation accuracy, F1-score and IoU of the proposed MFAFNet are found to be 94.39 %, 93.26 % and 89.46 %, respectively. In addition, the segmentation efficiency reaches 21.87FPS. Our experimental results show that the proposed MFAFNet yields more effective performance in the field of asphalt pavement crack segmentation than the alternatives.

STF-Net: sparsification transformer coding guided network for subcortical brain structure segmentation.

Subcortical brain structure segmentation plays an important role in the diagnosis of neuroimaging and has become the basis of computer-aided diagnosis. Due to the blurred boundaries and complex shapes of subcortical brain structures, labeling these structures by hand becomes a time-consuming and subjective task, greatly limiting their potential for clinical applications. Thus, this paper proposes the sparsification transformer (STF) module for accurate brain structure segmentation. The self-attention mechanism is used to establish global dependencies to efficiently extract the global information of the feature map with low computational complexity. Also, the shallow network is used to compensate for low-level detail information through the localization of convolutional operations to promote the representation capability of the network. In addition, a hybrid residual dilated convolution (HRDC) module is introduced at the bottom layer of the network to extend the receptive field and extract multi-scale contextual information. Meanwhile, the octave convolution edge feature extraction (OCT) module is applied at the skip connections of the network to pay more attention to the edge features of brain structures. The proposed network is trained with ahybrid loss function. The experimental evaluation on two public datasets: IBSR and MALC, shows outstanding performance in terms of objective and subjective quality.

Fully automatic AI segmentation of oral surgery-related tissues based on cone beam computed tomography images

Accurate segmentation of oral surgery-related tissues from cone beam computed tomography (CBCT) images can significantly accelerate treatment planning and improve surgical accuracy. In this paper, we propose a fully automated tissue segmentation system for dental implant surgery. Specifically, we propose an image preprocessing method based on data distribution histograms, which can adaptively process CBCT images with different parameters. Based on this, we use the bone segmentation network to obtain the segmentation results of alveolar bone, teeth, and maxillary sinus. We use the tooth and mandibular regions as the ROI regions of tooth segmentation and mandibular nerve tube segmentation to achieve the corresponding tasks. The tooth segmentation results can obtain the order information of the dentition. The corresponding experimental results show that our method can achieve higher segmentation accuracy and efficiency compared to existing methods. Its average Dice scores on the tooth, alveolar bone, maxillary sinus, and mandibular canal segmentation tasks were 96.5%, 95.4%, 93.6%, and 94.8%, respectively. These results demonstrate that it can accelerate the development of digital dentistry.

Rapid multi-catheter segmentation for magnetic resonance image-guided catheter-based interventions.

Magnetic resonance imaging (MRI) is the gold standard for delineating cancerous lesions in soft tissue. Catheter-based interventions require the accurate placement of multiple long, flexible catheters at the target site. The manual segmentation of catheters in MR images is a challenging and time-consuming task. There is a need for automated catheter segmentation to improve the efficiency of MR-guided procedures. To develop and assess a machine learning algorithm for the detection of multiple catheters in magnetic resonance images used during catheter-based interventions. In this work, a 3D U-Net was trained to retrospectively segment catheters in scans acquired during clinical MR-guided high dose rate (HDR) prostate brachytherapy cases. To assess confidence in segmentation, multiple AI models were trained. On clinical test cases, average segmentation results were used to plan the brachytherapy delivery. Dosimetric parameters were compared to the original clinical plan. Data was obtained from 35 patients who underwent HDR prostate brachytherapy for focal disease with a total of 214 image volumes. 185 image volumes from 30 patients were used for training using a five-fold cross validation split to divide the data for training and validation. To generate confidence measures of segmentation accuracy, five trained models were generated. The remaining five patients (29 volumes) were used to test the performance of the trained model by comparison to manual segmentations of three independent observers and assessment of dosimetric impact on the final clinical brachytherapy plans. The network successfully identified 95% of catheters in the test set at a rate of 0.89s per volume. The multi-model method identified the small number of cases where AI segmentation of individual catheters was poor, flagging the need for user input. AI-based segmentation performed as well as segmentations by independent observers. Plan dosimetry using AI-segmented catheters was comparable to the original plan. The vast majority of catheters were accurately identified by AI segmentation, with minimal impact on plan outcomes. The use of multiple AI models provided confidence in the segmentation accuracy and identified catheter segmentations that required further manual assessment. Real-time AI catheter segmentation can be used during MR-guided insertions to assess deflections and for rapid planning of prostate brachytherapy.

An Evaluation Method of Dental Treatment Quality Combined with Deep Learning and Multi-index Decomposition

ABSTRACT Dentists judge that the quality of dental treatment for each patient is very time-consuming and inefficient, lacks quantitative evaluation criteria, and is easy to cause errors. At the same time, the traditional method of extracting tooth and root canal image features based on experience is difficult to accurately extract the tooth area and root canal filling area, resulting in low accuracy of tooth and root canal segmentation, which in turn affects the accuracy of tooth treatment quality evaluation. In this paper, a deep learning convolutional neural network is used to segment the root canal filling area, tooth boundary, and the boundary between tooth and soft tissue for the real patient ‘s root canal treatment and filling image. Finally, the segmented image is quantitatively evaluated according to the multi-evaluation index of professional doctors. The experimental results show that the intelligent evaluation method of dental treatment quality combined with deep learning and multi-index decomposition proposed in this paper not only unifies the evaluation criteria of dental treatment quality but also the therapeutic effect of quantitative scoring can effectively improve the work efficiency of doctors, which has reference significance for the application of artificial intelligence in the medical field.

Comparative assessment of established and deep learning-based segmentation methods for hippocampal volume estimation in brain magnetic resonance imaging analysis.

In this study, our objective was to assess the performance of two deep learning-based hippocampal segmentation methods, SynthSeg and TigerBx, which are readily available to the public. We contrasted their performance with that of two established techniques, FreeSurfer-Aseg and FSL-FIRST, using three-dimensional T1-weighted MRI scans (n = 1447) procured from public databases. Our evaluation focused on the accuracy and reproducibility of these tools in estimating hippocampal volume. The findings suggest that both SynthSeg and TigerBx are on a par with Aseg and FIRST in terms of segmentation accuracy and reproducibility, but offer a significant advantage in processing speed, generating results in less than 1 min compared with several minutes to hours for the latter tools. In terms of Alzheimer's disease classification based on the hippocampal atrophy rate, SynthSeg and TigerBx exhibited superior performance. In conclusion, we evaluated the capabilities of two deep learning-based segmentation techniques. The results underscore their potential value in clinical and research environments, particularly when investigating neurological conditions associated with hippocampal structures.

SRMA: a dual-branch parallel multi-scale attention network for remote sensing images sea-land segmentation

ABSTRACT The use of deep learning-based high resolution remote sensing image sea and land segmentation method has become prevalent in various fields such as environmental monitoring, resource assessment, and urban planning. However, the segmentation process faces challenges due to the complex coastline and the similarity in spectral colour difference between the sea and land in certain areas. The remote sensing images obtained from satellites often exhibit unclear boundaries between the sea and land, as well as intricate coastlines. Consequently, the segmentation of sea and land becomes a difficult task. The existing sea-land segmentation methods have limitations in accurately segmenting long and narrow waters, as well as areas with low differentiation between sea and land. In this paper, we propose a new sea-land segmentation method called SRMA (Swin-Res-Multi-Attention). SRMA performs parallel feature extraction using a dual-branch parallel: Swin-Transformer branch and ResNet branch. The combination of Swin-Transformer’s self-attention and ResNet’s residual design helps reduce the loss of feature information, thereby avoiding incorrect segmentation in regions with low distinctness. To improve overall stability, we introduce the MCA (Multiscale channel attention module) module, which combines feature information from different scales. The multi-scale pyramid design of MCA module ensures stability and improves segmentation accuracy in narrow waters. Experimental results on a public dataset demonstrate that our model outperforms existing methods. Additionally, we evaluate the model’s performance in complex scenarios by creating a new dataset that includes a complex urban water body and cloud interference. The results showcase the robustness and superiority of our model.

Smart traffic management of vehicles using faster R-CNN based deep learning method

With constant growth of civilization and modernization of cities all across the world since past few centuries smart traffic management of vehicles is one of the most sorted after problem by research community. Smart traffic management basically involves segmentation of vehicles, estimation of traffic density and tracking of vehicles. The vehicle segmentation from videos helps realization of niche applications such as monitoring of speed and estimation of traffic. When occlusions, background with clutters and traffic with density variations, this problem becomes more intractable in nature. Keeping this motivation in this research work, we investigate Faster R-CNN based deep learning method towards segmentation of vehicles. This problem is addressed in four steps viz minimization with adaptive background model, Faster R-CNN based subnet operation, Faster R-CNN initial refinement and result optimization with extended topological active nets. The computational framework uses adaptive background modeling. It also addresses shadow and illumination issues. Higher segmentation accuracy is achieved through topological active net deformable models. The topological and extended topological active nets help to achieve stated deformations. Mesh deformation is achieved with minimization of energy. The segmentation accuracy is improved with modified version of extended topological active net. The experimental results demonstrate superiority of this framework with respect to other methods.

VINNA for Neonates – Orientation Independence through Latent Augmentations

Abstract A robust, fast, and accurate segmentation of neonatal brain images is highly desired to better understand and detect changes during development and disease, specifically considering the rise in imaging studies for this cohort. Yet, the limited availability of ground truth datasets, lack of standardized acquisition protocols, and wide variations of head positioning in the scanner pose challenges for method development. A few automated image analysis pipelines exist for newborn brain MRI segmentation, but they often rely on time-consuming non-linear spatial registration procedures and require resampling to a common resolution, subject to loss of information due to interpolation and down-sampling. Without registration and image resampling, variations with respect to head positions and voxel resolutions have to be addressed differently. In deep-learning, external augmentations such as rotation, translation, and scaling are traditionally used to artificially expand the representation of spatial variability, which subsequently increases both the training dataset size and robustness. However, these transformations in the image space still require resampling, reducing accuracy specifically in the context of label interpolation. We recently introduced the concept of resolution-independence with the Voxel-size Independent Neural Network framework, VINN. Here, we extend this concept by additionally shifting all rigid-transforms into the network architecture with a four degree of freedom (4-DOF) transform module, enabling resolution-aware internal augmentations (VINNA) for deep learning. In this work we show that VINNA (i) significantly outperforms state-of-the-art external augmentation approaches, (ii) effectively addresses the head variations present specifically in newborn datasets, and (iii) retains high segmentation accuracy across a range of resolutions (0.5-1.0mm). Furthermore, the 4-DOF transform module together with internal augmentations is a powerful, general approach to implement spatial augmentation without requiring image or label interpolation. The specific network application to newborns will be made publicly available as VINNA4neonates.