Deep Learning-Based Segmentation of 3D Volumetric Image and Microstructural Analysis

Multiview two-dimensional (2D) convolutional neural networks (CNNs) and three-dimensional (3D) CNNs have been successfully used for analyzing volumetric data in many state-of-the-art medical imaging applications. We propose an alternative modular framework that analyzes volumetric data with an approach that is analogous to radiologists' interpretation, and apply the framework to reduce false positives that are generated in computer-aided detection (CADe) systems for pulmonary nodules in thoracic computed tomography (CT) scans. In our approach, a deep network consisting of 2D CNNs first processes slices individually. The features extracted in this stage are then passed to a recurrent neural network (RNN), thereby modeling consecutive slices as a sequence of temporal data and capturing the contextual information across all three dimensions in the volume of interest. Outputs of the RNN layer are weighed before the final fully connected layer, enabling the network to scale the importance of different slices within a volume of interest in an end-to-end training framework. We validated the proposed architecture on the false positive reduction track of the lung nodule analysis (LUNA) challenge for pulmonary nodule detection in chest CT scans, and obtained competitive results compared to 3D CNNs. Our results show that the proposed approach can encode the 3D information in volumetric data effectively by achieving a sensitivity >0.8 with just 1/8 false positives per scan. Our experimental results demonstrate the effectiveness of temporal analysis of volumetric images for the application of false positive reduction in chest CT scans and show that state-of-the-art 2D architectures from the literature can be directly applied to analyzing volumetric medical data. As newer and better 2D architectures are being developed at a much faster rate compared to 3D architectures, our approach makes it easy to obtain state-of-the-art performance on volumetric data using new 2D architectures.

Image registration is an important problem for image processing and computer vision with many proposed applications in medical image analysis.^{1, 2} Image registration techniques attempt to map corresponding features between two images. The problem is particularly difficult as anatomy is subject to elastic deformations. This paper considers this problem in the context of graph matching. Firstly, weighted Region Adjacency Graphs (RAGs) are constructed from each image using an approach based on watershed saliency. ³ The vertices of the RAG represent salient regions in the image and the (weighted) edges represent the relationship (bonding) between each region. Correspondences between images are then determined using a weighted graph matching method. Graph matching is considered to be one of the most complex problems in computer vision, due to its combinatorial nature. Our approach uses a multi-spectral technique to graph matching first proposed by Umeyama⁴ to find an approximate solution to the weighted graph matching problem (WGMP) based on the singular value decomposition of the adjacency matrix. Results show the technique is successful in co-registering 2-D MRI images and the method could be useful in co-registering 3-D volumetric data (e.g. CT, MRI, SPECT, PET etc.).

Introduction: Precise segmentation of the liver from computed tomography (CT) scans is an essential component in the diagnosis and treatment of liver diseases such as hepatocellular carcinoma. Manual segmentation can be time-consuming and subject to variability, spurring the application of automated systems based on deep learning. We introduce a 3D U-Net-based convolutional neural network for end-to-end segmentation of the liver from volumetric CT images. The model is trained and tested on the LiTS dataset using a standard preprocessing pipeline and an in-house composite loss function—AdvancedComboLoss—combining Dice Loss, Binary Cross-Entropy, and Focal Tversky Loss to balance class imbalance and boundary accuracy. The network handles entire 3D volumes with spatial context retained between anatomical planes and is trained on a GPU-enabled setup with the PyTorch environment. Objectives: To develop a highly accurate and computationally efficient 3D U-Net-based deep learning model for automated liver segmentation from volumetric CT scans, addressing challenges like class imbalance, anatomical variability, and low tissue contrast, using a custom loss function (AdvancedComboLoss) and a standardized preprocessing pipeline. Methods: The methodology adopted is volumetric liver segmentation from a specially designed 3D U-Net architecture specific to medical CT scans. The process entails preprocessing of raw CT scans into a common shape and intensity range and training a fully convolutional 3D neural network that learns the spatial relationships among all three anatomical planes. The model uses an encoder-decoder architecture with skip connections to maintain fine-grained structural information, allowing for accurate delineation of liver regions. A hybrid loss function—integrating Dice, Binary Cross-Entropy, and Focal Tversky losses—is used to direct the learning process to optimize overlap of regions, accuracy of classification, and class imbalance. Results: Experimental outcomes demonstrate that the model has a Dice score of 0.9604 and voxel-wise accuracy of 0.9979, indicating excellent performance in segmentation as well as strong agreement with expert annotations. The model presented in this paper presents a solid, scalable, and clinically valuable approach to automated liver segmentation with future potential to integrate into multi-stage liver and tumor analysis workflows. Conclusions: Herein, we built and tested a 3D U-Net deep learning architecture for unsupervised liver segmentation from abdominal CT volumes. Through utilization of volumetric convolutions as well as through a well-engineered composite loss function, the model was successful in capturing complicated liver anatomy as well as being able to hold high performance even on varied CT volumes. The power of the method is not just in its quantitative performance but also in its capability to generate anatomically consistent and visually plausible segmentations, making it extremely relevant to actual clinical workflows. Although there are some limitations—constrained batch size and absence of data augmentation—there is room for improvement, the findings affirm that deep learning can be an effective tool for automating key tasks in medical image analysis. As a whole, this paper adds a robust and effective segmentation model that would be potentially embedded in wider diagnostic workflows, ending up improving the accuracy, speed, and scalability of liver evaluation in clinical practice. In brief, this paper adds a high-fidelity, scalable, and computationally effective solution for computer-aided liver segmentation, pushing the application of artificial intelligence in clinical decision-making and medical image analysis.

A two-step concept for 3D segmentation on 5 abdominal organs inside volumetric CT images is presented. Firsteach relevant organ’s volume of interest is extracted as bounding box. The extracted volume acts as input for asecond stage, wherein two compared U-Nets with different architectural dimensions re-construct an organ segmen-tation as label mask. In this work, we focus on comparing 2D U-Nets vs. 3D U-Net counterparts. Our initial resultsindicate Dice improvements of about 6% at maximum. In this study to our surprise, liver and kidneys for instancewere tackled significantly better using the faster and GPU-memory saving 2D U-Nets. For other abdominal keyorgans, there were no significant differences, but we observe highly significant advantages for the 2D U-Net interms of GPU computational efforts for all organs under study.

The science of solving clinical problems by analyzing images generated in clinical practice is known as medical image analysis. The aim is to extract information in an affective and efficient manner for improved clinical diagnosis. The recent advances in the field of biomedical engineering have made medical image analysis one of the top research and development area. One of the reasons for this advancement is the application of machine learning techniques for the analysis of medical images. Deep learning is successfully used as a tool for machine learning, where a neural network is capable of automatically learning features. This is in contrast to those methods where traditionally hand crafted features are used. The selection and calculation of these features is a challenging task. Among deep learning techniques, deep convolutional networks are actively used for the purpose of medical image analysis. This includes application areas such as segmentation, abnormality detection, disease classification, computer aided diagnosis and retrieval. In this study, a comprehensive review of the current state-of-the-art in medical image analysis using deep convolutional networks is presented. The challenges and potential of these techniques are also highlighted.

Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: An empirical study of 2.5D solutions.

The current standard for assessing neonatal pain is discontinuous and suffers from inter-observer variations, which can result in delayed intervention and inconsistent treatment of pain. Therefore, it is critical to address the shortcomings of the current standard and develop continuous and less subjective pain assessment tools. Convolutional Neural Networks have gained much popularity in the last decades due to the wide range of its successful applications in medical image analysis, object recognition, and emotion recognition. In this paper, we propose a Neonatal Convolutional Neural Network, designed and trained end-to-end to detect neonatal pain. We evaluated the proposed network in two data sets of neonates and compared its performance to the performance of ResNet architecture in the same data sets. Our proposed method outperformed ResNet in recognizing neonates’ pain and achieved around 91.00% accuracy. While further research is needed, our preliminary results suggest that the presented network can be used for automatic pain assessment, and possibly similar applications. It also suggests that the automatic recognition of neonatal pain provides a viable and more efficient alternative to the current standard of pain assessment.

Cervical cancer ranks as the second most common cancer in women worldwide. In clinical practice, colposcopy is an indispensable part of screening for cervical intraepithelial neoplasia (CIN) grades and cervical cancer but exhibits high misdiagnosis rate. Existing computer-assisted algorithms for analyzing cervigram images have neglected that colposcopy is a sequential and multistate process, which is unsuitable for clinical applications. In this work, we construct a cervigram-based recurrent convolutional neural network (C-RCNN) to classify different CIN grades and cervical cancer. Convolutional neural networks are leveraged to extract spatial features. We develop a sequence-encoding module to encode discriminative temporal features and a multistate-aware convolutional layer to integrate features from different states of cervigram images. To train and evaluate the performance of C-RCNN, we leveraged a dataset of 4,753 real cervigrams and obtained 96.13% test accuracy with a specificity and sensitivity of 98.22% and 95.09%, respectively. Areas under each receiver operating characteristic curves are above 0.94, proving that visual representations and sequential dynamics can be jointly and effectively optimized in the training phase. Comparative analysis demonstrated the effectiveness of the proposed C-RCNN against competing methods, showing significant improvement over only focusing on a single frame. This architecture can be extended to other applications in medical image analysis.

Automatic detection of breast lesions in automated 3D breast ultrasound with cross-organ transfer learning

Along with the development of medical imaging technology, medical image analysis has become a crucial part of clinical diagnosis. However, traditional image analysis methods rely on manual feature extraction and expert evaluation, triggering problems such as low efficiency and lack of accuracy. Deep learning techniques, especially convolutional neural networks (CNNs), have made significant breakthroughs in medical image analysis in recent years. The aim of this paper is to study the application of deep learning in medical imaging, and explore the advantages and development potential in early disease diagnosis, image segmentation and feature extraction. This paper reviews the basic principles of deep learning and analyses the applicability of deep learning in medical imaging by combining the characteristics of medical imaging. Through systematic analysis of existing literature, this paper summarises the remarkable achievements of deep learning in processing, analysing and applying it to various medical images, such as Optical Coherence Tomography (OCT), Magnetic Resonance Imaging (MRI) and so on. It has been shown that deep learning methods can significantly improve the accuracy and efficiency of medical image processing and demonstrate performance due to traditional methods in tasks such as classification. However, how to improve the interpretability of models and the generalisability of clinical applications are still current research hotspots and challenges.

Shape modeling is an important area in computer vision and medical imaging. Shape models have proved valuable in the tasks of object representation, recognition, and classification. This thesis focuses on shape models of 3D surfaces extracted from volumetric images and their applications in medical image analysis. This thesis presents a new framework for classification of 3D neuroanatomic structures using shape features, with the goal of deriving a shape-based medical classifier that has clinical value. This framework combines a powerful 3D surface modeling method, the spherical harmonics (SPHARM) description, with a set of effective pattern classification, feature selection, evaluation, and visualization techniques. This approach is shown to be effective using simulated shape data. It is also applied to real hippocampal data, and achieves good cross-validation accuracy (>90%) in detecting hippocampal shape changes in schizophrenia, which is competitive with the best results in previous studies. To help medical diagnosis in practice, a threshold-free receiver operating characteristic approach is employed as a means of evaluating the potential of a classifier. In addition, a new visualization approach is proposed for localizing discriminative patterns. This thesis also considers two extensions of the above work. In one extension, the left and right hippocampi are treated as a single shape configuration, and a new multi-surface alignment algorithm is developed for aligning configurations of multiple surfaces simultaneously. This alignment algorithm is incorporated into our classification for hippocampal data. The best cross-validation accuracy achieved is 92%, supporting the idea that the shape configuration of the two hippocampi provides valuable information in detecting schizophrenia. In the other extension, we focus on spherical parameterization, which is the key step for deriving a SPHARM description for a 3D object. Earlier techniques can be applied only to voxel surfaces. We propose CALD, a new spherical parameterization algorithm which makes our framework applicable to general triangle meshes. This new algorithm can be used for shape representation and manipulation purposes in different areas, including medical image analysis, computer vision, graphics, and multimedia databases.

Medical image segmentation is a crucial and intricate process in medical image processing and analysis. With the advancements in artificial intelligence, deep learning techniques have been widely used in recent years for medical image segmentation. One such technique is the U-Net framework based on the U-shaped convolutional neural networks (CNN) and its variants. However, these methods have limitations in simultaneously capturing both the global and the remote semantic information due to the restricted receptive domain caused by the convolution operation’s intrinsic features. Transformers are attention-based models with excellent global modeling capabilities, but their ability to acquire local information is limited. To address this, we propose a network that combines the strengths of both CNN and Transformer, called CoTrFuse. The proposed CoTrFuse network uses EfficientNet and Swin Transformer as dual encoders. The Swin Transformer and CNN Fusion module are combined to fuse the features of both branches before the skip connection structure. We evaluated the proposed network on two datasets: the ISIC-2017 challenge dataset and the COVID-QU-Ex dataset. Our experimental results demonstrate that the proposed CoTrFuse outperforms several state-of-the-art segmentation methods, indicating its superiority in medical image segmentation. The codes are available at https://github.com/BinYCn/CoTrFuse.

Medical image analysis plays a pivotal role in modern healthcare, aiding clinicians in accurate diagnosis and treatment planning. However, the complexity and diversity of medical images pose significant challenges for traditional image processing methods. Existing methods often struggle to precisely delineate structures in medical images, leading to suboptimal diagnostic accuracy. The demand for automated and accurate segmentation tools in medical imaging has grown, highlighting the necessity for robust and efficient algorithms capable of handling diverse anatomical variations and pathologies. While CNNs have shown promise in image analysis, their application to medical images requires customization to accommodate unique challenges. The literature lacks comprehensive studies that bridge the gap between general-purpose CNNs and the specific demands of medical image segmentation, especially concerning the diverse and intricate structures present in medical imagery. This study addresses the need for advanced techniques by leveraging Convolutional Neural Networks (CNNs) for semantic segmentation in medical image analysis. Our approach involves the design and implementation of a specialized CNN architecture tailored to the nuances of medical image data. We employ state-of-the-art techniques for data preprocessing, model training, and validation. The model is trained on a diverse dataset encompassing various medical imaging modalities, ensuring its adaptability and generalizability. The proposed CNN-based semantic segmentation model demonstrates superior performance in accurately delineating anatomical structures compared to traditional methods. Evaluation metrics, including Dice coefficient and sensitivity, indicate the model efficacy in achieving precise segmentation. The results underscore the potential of CNNs in advancing medical image analysis for improved clinical outcomes.

Medical image registration is crucial in medical image analysis applications. Recently, U-Net-style networks have been commonly used for unsupervised image registration, predicting dense displacement fields in full-resolution space. However, this process is resource-intensive and time-consuming for high-resolution volumetric image data. To address this challenge, this paper proposes a novel model named RegFSC-Net, which utilizes Fourier transform with spatial reorganization (SR) and channel refinement (CR) network for registration. We embed efficient feature extraction modules SR and CR modules into the encoder, and adopt a parameter-free model to drive the decoder to improve the U-shaped network. Precisely, RegFSC-Net does not directly predict the full-resolution displacement field in space but learns the low-dimensional representation of the displacement field in the bandlimited Fourier domain, which is beneficial in reducing network parameters, memory usage, and computational costs. Experimental results show that RegFSC-Net outperforms various state-of-the-art methods. Specifically, in comparison to the widely recognized Transformer-based method TransMorph, RegFSC-Net utilizes only around 8.2% of its parameters, resulting in a 1.95% higher Dice score and significantly faster inference speeds of 126.67% and 419.99% on GPU and CPU, respectively. Furthermore, we also designed three variants of RegFSC-Net and demonstrated their potential applications in computer-aided diagnosis.

Over the past five years, artificial intelligence (AI) has introduced new models and methods for addressing the challenges associated with the broader adoption of AI models and systems in medicine. This paper reviews recent advances in AI for medical image and video analysis, outlines emerging paradigms, highlights pathways for successful clinical translation, and provides recommendations for future work. Hybrid Convolutional Neural Network (CNN) Transformer architectures now deliver state-of-the-art results in segmentation, classification, reconstruction, synthesis, and registration. Foundation and generative AI models enable the use of transfer learning to smaller datasets with limited ground truth. Federated learning supports privacy-preserving collaboration across institutions. Explainable and trustworthy AI approaches have become essential to foster clinician trust, ensure regulatory compliance, and facilitate ethical deployment. Together, these developments pave the way for integrating AI into radiology, pathology, and wider healthcare workflows.