Accurate Tumor Localization Research Articles

Apple Vision Pro-guided Laparoscopic Radio Frequency Ablation for Liver Tumors: The Pioneer Experience.

Background: This study evaluates the feasibility of Apple Vision Pro goggles as an augmented reality (AR) surgical navigation tool for laparoscopic-assisted ultrasound-guided radiofrequency ablation (RFA) of liver tumors. Traditional RFA is effective but challenging due to the integration of multiple imaging modalities.Purpose: The primary aim of this research is to assess how Vision Pro goggles can enhance the surgical navigation process during RFA, improving tumor localization and the overall effectiveness of the procedure.Research Design: A feasibility study design was used to analyze the implementation of AR technologies in surgical navigation, focusing specifically on their application in laparoscopic surgeries.Study Sample: Participants included patients undergoing laparoscopic-assisted ultrasound-guided RFA, with pre-operative imaging workups involving CT and MRI scans followed by intraoperative laparoscopic sonography.Data Collection and/or Analysis: Data were collected through observations during surgical procedures using the Vision Pro goggles, which displayed various imaging inputs (MRI, 3D reconstruction, and laparoscopic sonography) in the surgeon's field of view. Image manipulation was assessed based on accuracy and effectiveness of tumor ablation.Results: The goggles enhanced tumor localization accuracy and facilitated real-time image manipulation, resulting in effective tumor ablation. Initial results show promising outcomes in the precision and efficiency of the RFA procedure.Conclusions: While the initial results are promising, larger studies are necessary to validate the technology's efficacy and safety. Future research should compare outcomes with traditional methods and explore its applicability to other surgeries, aiming to refine the system further. The Vision Pro goggles potentially represent a significant advancement in surgical technology by improving RFA precision and efficiency.

ATEDU-NET: An Attention-Embedded Deep Unet for multi-disease diagnosis in chest X-ray images, breast ultrasound, and retina fundus.

In image segmentation for medical image analysis, effective upsampling is crucial for recovering spatial information lost during downsampling. This challenge becomes more pronounced when dealing with diverse medical image modalities, which can significantly impact model performance. Plain and standard skip connections, widely used in most models, often fall short of maintaining high segmentation accuracy across different modalities, because essential spatial information transferred from the encoder to the decoder is lost. Inspired by these limitations, the Attention-Embedded Deep UNet (ATEDU-Net) is presented here, an innovative framework designed and tested on diverse medical image modalities, including X-ray, breast ultrasound, and retinal fundus images. ATEDU-Net features a unique architecture that combines progressive context refinement modules (PCRM) and global context modules (GCM) within a U-shaped network structure with Convgroup blocks which facilitate the integration of convolutional operations. This allows ATEDU-Net to autonomously capture rich spatial details and crucial contextual information from input images. The GCM captures essential contextual information for informed decision-making, while the PCRM enhances feature attention, resulting in precise and robust segmentation. The experimentation and analysis demonstrate that ATEDU-Net promises to be a powerful tool for medical professionals, aiding in the early detection of chest-related diseases, accurate localization of breast tumors, and early identification of eye diseases. This, in turn, contributes significantly to the formulation of optimal therapeutic strategies, enhancing patient care and outcomes. The versatility of ATEDU-Net is further highlighted by its ability to analyze medical images across various modalities, making it well-suited for the complex task of medical image analysis in diverse clinical scenarios.

Real-time CBCT imaging and motion tracking via a single arbitrarily-angled x-ray projection by a joint dynamic reconstruction and motion estimation (DREME) framework

Objective.Real-time cone-beam computed tomography (CBCT) provides instantaneous visualization of patient anatomy for image guidance, motion tracking, and online treatment adaptation in radiotherapy. While many real-time imaging and motion tracking methods leveraged patient-specific prior information to alleviate under-sampling challenges and meet the temporal constraint (<500 ms), the prior information can be outdated and introduce biases, thus compromising the imaging and motion tracking accuracy. To address this challenge, we developed a frameworkdynamicreconstruction andmotionestimation (DREME) for real-time CBCT imaging and motion estimation, without relying on patient-specific prior knowledge.Approach.DREME incorporates a deep learning-based real-time CBCT imaging and motion estimation method into a dynamic CBCT reconstruction framework. The reconstruction framework reconstructs a dynamic sequence of CBCTs in a data-driven manner from a standard pre-treatment scan, without requiring patient-specific prior knowledge. Meanwhile, a convolutional neural network-based motion encoder is jointly trained during the reconstruction to learn motion-related features relevant for real-time motion estimation, based on a single arbitrarily-angled x-ray projection. DREME was tested on digital phantom simulations and real patient studies.Main Results.DREME accurately solved 3D respiration-induced anatomical motion in real time (∼1.5 ms inference time for each x-ray projection). For the digital phantom studies, it achieved an average lung tumor center-of-mass localization error of 1.2 ± 0.9 mm (Mean ± SD). For the patient studies, it achieved a real-time tumor localization accuracy of 1.6 ± 1.6 mm in the projection domain.Significance.DREME achieves CBCT and volumetric motion estimation in real time from a single x-ray projection at arbitrary angles, paving the way for future clinical applications in intra-fractional motion management. In addition, it can be used for dose tracking and treatment assessment, when combined with real-time dose calculation.

Gadolinium oxide nanoparticles as a multimodal contrast enhancement agent for pre-clinical proton imaging

Orthotopic tumor models in pre-clinical translational research are becoming increasingly popular, raising the demands on accurate tumor localization prior to irradiation. This task remains challenging both in x-ray and proton computed tomography (xCT and pCT, respectively), due to the limited contrast of tumor tissue compared to the surrounding tissue. We investigate the feasibility of gadolinium oxide nanoparticles as a multimodal contrast enhancement agent for both imaging modalities. We performed proton radiographies at the experimental room of the Trento Proton Therapy Center using a MiniPIX-Timepix detector and dispersions of gadolinium oxide nanoparticles in sunflower oil with mass fractions up to 8wt%. To determine the minimum nanoparticle concentration required for the detectability of small structures, pCT images of a cylindrical water phantom with cavities of varying gadolinium oxide concentration were simulated using a dedicated FLUKA Monte Carlo framework. These findings are complemented by simulating pCT at dose levels from 80 mGy to 320 mGy of artificially modified murine xCT data, mimicking different levels of gadolinium oxide accumulation inside a fictitious tumor volume. To compare the results obtained for proton imaging to x-ray imaging, cone-beam CT images of a cylindrical PMMA phantom with cavities of dispersions of oil and gadolinium oxide nanoparticles with mass fractions up to 8wt% were acquired at a commercial pre-clinical irradiation setup. For proton radiography, considerable contrast enhancement was found for a mass fraction of 4wt%. Slightly lower values were found for the simulated pCT images at imaging doses below 200 mGy. In contrast, full detectability of small gadolinium oxide loaded structures in xCT at comparable imaging dose is already achieved for 0.5wt%. Achieving such concentrations required for pCT imaging inside a tumor volume inin-vivoexperiments may be challenging, yet it might be feasible using different targeting and/or injection strategies.

Accessible AI Diagnostics and Lightweight Brain Tumor Detection on Medical Edge Devices.

The timely and accurate detection of brain tumors is crucial for effective medical intervention, especially in resource-constrained settings. This study proposes a lightweight and efficient RetinaNet variant tailored for medical edge device deployment. The model reduces computational overhead while maintaining high detection accuracy by replacing the computationally intensive ResNet backbone with MobileNet and leveraging depthwise separable convolutions. The modified RetinaNet achieves an average precision (AP) of 32.1, surpassing state-of-the-art models in small tumor detection (APS: 14.3) and large tumor localization (APL: 49.7). Furthermore, the model significantly reduces computational costs, making real-time analysis feasible on low-power hardware. Clinical relevance is a key focus of this work. The proposed model addresses the diagnostic challenges of small, variable-sized tumors often overlooked by existing methods. Its lightweight architecture enables accurate and timely tumor localization on portable devices, bridging the gap in diagnostic accessibility for underserved regions. Extensive experiments on the BRATS dataset demonstrate the model robustness across tumor sizes and configurations, with confidence scores consistently exceeding 81%. This advancement holds the potential for improving early tumor detection, particularly in remote areas lacking advanced medical infrastructure, thereby contributing to better patient outcomes and broader accessibility to AI-driven diagnostic tools.

Complex Large-Deformation Multimodality Image Registration Network for Image-Guided Radiotherapy of Cervical Cancer.

In recent years, image-guided brachytherapy for cervical cancer has become an important treatment method for patients with locally advanced cervical cancer, and multi-modality image registration technology is a key step in this system. However, due to the patient's own movement and other factors, the deformation between the different modalities of images is discontinuous, which brings great difficulties to the registration of pelvic computed tomography (CT/) and magnetic resonance (MR) images. In this paper, we propose a multimodality image registration network based on multistage transformation enhancement features (MTEF) to maintain the continuity of the deformation field. The model uses wavelet transform to extract different components of the image and performs fusion and enhancement processing as the input to the model. The model performs multiple registrations from local to global regions. Then, we propose a novel shared pyramid registration network that can accurately extract features from different modalities, optimizing the predicted deformation field through progressive refinement. In order to improve the registration performance, we also propose a deep learning similarity measurement method combined with bistructural morphology. On the basis of deep learning, bistructural morphology is added to the model to train the pelvic area registration evaluator, and the model can obtain parameters covering large deformation for loss function. The model was verified by the actual clinical data of cervical cancer patients. After a large number of experiments, our proposed model achieved the highest dice similarity coefficient (DSC) metric compared with the state-of-the-art registration methods. The DSC index of the MTEF algorithm is 5.64% higher than that of the TransMorph algorithm. It will effectively integrate multi-modal image information, improve the accuracy of tumor localization, and benefit more cervical cancer patients.

Application of MRI imaging technology based on magnetic nanoparticles in diagnosis and prognosis evaluation of prostate cancer

Objective: Objective: Prostate cancer is one of the most common malignant tumors in men. Early diagnosis and prognosis evaluation are of great significance for the treatment and prevention of prostate cancer. The purpose of this study was to explore the application of magnetic nanoparticle-based MRI imaging technology in the diagnosis and prognosis assessment of prostate cancer. A total of 81 patients in our hospital from September 2018 to January 2021 were selected as the study objects, all suspected prostate cancer patients, and prostate detection was performed under the guidance of MRI and rectal ultrasound.According to the pathological results, the patients were divided into prostate cancer cluster group and benign prostatic hyperplasia group. Imaging of prostate cancer is achieved by the response of magnetic nanoparticles to magnetic fields. MRI images of patients were collected and analyzed using professional software. It can provide high-resolution images that enable accurate detection and localization of tumors, and the technology can also assess the severity of prostate cancer and predict a patient's prognosis.

A Framework for Multimodal Medical Image Interaction.

Medical doctors rely on images of the human anatomy, such as magnetic resonance imaging (MRI), to localize regions of interest in the patient during diagnosis and treatment. Despite advances in medical imaging technology, the information conveyance remains unimodal. This visual representation fails to capture the complexity of the real, multisensory interaction with human tissue. However, perceiving multimodal information about the patient's anatomy and disease in real-time is critical for the success of medical procedures and patient outcome. We introduce a Multimodal Medical Image Interaction (MMII) framework to allow medical experts a dynamic, audiovisual interaction with human tissue in three-dimensional space. In a virtual reality environment, the user receives physically informed audiovisual feedback to improve the spatial perception of anatomical structures. MMII uses a model-based sonification approach to generate sounds derived from the geometry and physical properties of tissue, thereby eliminating the need for hand-crafted sound design. Two user studies involving 34 general and nine clinical experts were conducted to evaluate the proposed interaction framework's learnability, usability, and accuracy. Our results showed excellent learnability of audiovisual correspondence as the rate of correct associations significantly improved (p < 0.001) over the course of the study. MMII resulted in superior brain tumor localization accuracy (p < 0.05) compared to conventional medical image interaction. Our findings substantiate the potential of this novel framework to enhance interaction with medical images, for example, during surgical procedures where immediate and precise feedback is needed.

Progression in Near-Infrared Fluorescence Imaging Technology for Lung Cancer Management.

Lung cancer is a major threat to human health and a leading cause of death. Accurate localization of tumors in vivo is crucial for subsequent treatment. In recent years, fluorescent imaging technology has become a focal point in tumor diagnosis and treatment due to its high sensitivity, strong selectivity, non-invasiveness, and multifunctionality. Molecular probes-based fluorescent imaging not only enables real-time in vivo imaging through fluorescence signals but also integrates therapeutic functions, drug screening, and efficacy monitoring to facilitate comprehensive diagnosis and treatment. Among them, near-infrared (NIR) fluorescence imaging is particularly prominent due to its improved in vivo imaging effect. This trend toward multifunctionality is a significant aspect of the future advancement of fluorescent imaging technology. In the past years, great progress has been made in the field of NIR fluorescence imaging for lung cancer management, as well as the emergence of new problems and challenges. This paper generally summarizes the application of NIR fluorescence imaging technology in these areas in the past five years, including the design, detection principles, and clinical applications, with the aim of advancing more efficient NIR fluorescence imaging technologies to enhance the accuracy of tumor diagnosis and treatment.

Brain Tumor Segmentation from Optimal MRI Slices Using a Lightweight U-Net

The timely detection and accurate localization of brain tumors is crucial in preserving people’s quality of life. Thankfully, intelligent computational systems have proven invaluable in addressing these challenges. In particular, the UNET model can extract essential pixel-level features to automatically identify the tumor’s location. However, known deep learning-based works usually directly feed the 3D volume into the model, which causes excessive computational complexity. This paper presents an approach to boost the UNET network, reducing computational workload while maintaining superior efficiency in locating brain tumors. This concept could benefit portable or embedded recognition systems with limited resources for operating in real time. This enhancement involves an automatic slice selection from the MRI T2 modality volumetric images containing the most relevant tumor information and implementing an adaptive learning rate to avoid local minima. Compared with the original model (7.7 M parameters), the proposed UNET model uses only 2 M parameters and was tested on the BraTS 2017, 2020, and 2021 datasets. Notably, the BraTS2021 dataset provided outstanding binary metric results: 0.7807 for the Intersection Over the Union (IoU), 0.860 for the Dice Similarity Coefficient (DSC), 0.656 for the Sensitivity, and 0.9964 for the Specificity compared to vanilla UNET.

MA-VoxelMorph: Multi-scale attention-based VoxelMorph for nonrigid registration of thoracoabdominal CT images

This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement. However, fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging. To deal with this problem, we propose a 3D multi-scale attention VoxelMorph (MA-VoxelMorph) registration network. To alleviate the large deformation problem, a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction, and position-aware axial attention for long-distance dependencies between pixels capture. To further improve the large deformation and fine structure registration results, a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers. Our method was evaluated on four public lung datasets (DIR-Lab dataset, Creatis dataset, Learn2Reg dataset, OASIS dataset) and a local dataset. Results proved that the proposed method achieved better registration performance than current state-of-the-art methods, especially in handling the registration of large deformations and fine structures. It also proved to be fast in 3D image registration, using about 1.5 s, and faster than most methods. Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries.

Achieving sub-millisievert CT colonography for accurate colorectal tumor detection using smart examination protocols: a prospective self-controlled study.

To assess the feasibility of combining Auto-kVp selection technique, higher preset ASIR-V and noise index (NI) to realize individualized sub-mSv CT colonography (CTC) for accurate colorectal tumor detection and localization. Ninety patients with suspected colorectal cancer (CRC) were prospectively enrolled to undergo standard dose CTC (SDCTC) in the prone and ultra-low dose CTC (ULDCTC) in the supine position. SDCTC used 120 kVp, preset ASIR-V of 30%, SmartmA for a NI of 13; ULDCTC used Auto-kVp selection technique with 80 or 100 kVp, preset ASIR-V of 60%, SmartmA for a NI of 13 for 80 kVp, and NI of 15 for 100 kVp. The effective dose (ED), image quality [signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of colorectal neoplasms] between the two protocols were compared and the accuracies of tumor locations were evaluated for CTC in comparison with the surgery results. The mean ED of the ULDCTC-80 kVp subgroup was 0.70 mSv, 71.43% lower than the 2.45mSv for the 120 kVp group, while that of the ULDCTC-100 kVp subgroup was 0.98mSv, 73.00% lower than the 3.63mSv for the 120 kVp group (P < 0.001). The tumor SNR and CNR of the ULDCTC were higher than those of SDCTC (P < 0.05), while there was no difference in the subjective image quality between them with good inter-observer agreement (Kappa: 0.805-0.923). Both SDCTC and ULDCTC groups had high detection rate of colorectal tumors, along with good consistency in determining tumor location compared with surgery reports (Kappa: 0.718-0.989). The combination of Auto-kVp selection, higher preset ASIR-V and NI achieves individualized sub-mSv CTC with good performance in detecting and locating CRC with surgery and consistent results between SDCTC and ULDCTC.

Deep Location Soft-Embedding-Based Network With Regional Scoring for Mammogram Classification.

Early detection and treatment of breast cancer can significantly reduce patient mortality, and mammogram is an effective method for early screening. Computer-aided diagnosis (CAD) of mammography based on deep learning can assist radiologists in making more objective and accurate judgments. However, existing methods often depend on datasets with manual segmentation annotations. In addition, due to the large image sizes and small lesion proportions, many methods that do not use region of interest (ROI) mostly rely on multi-scale and multi-feature fusion models. These shortcomings increase the labor, money, and computational overhead of applying the model. Therefore, a deep location soft-embedding-based network with regional scoring (DLSEN-RS) is proposed. DLSEN-RS is an end-to-end mammography image classification method containing only one feature extractor and relies on positional embedding (PE) and aggregation pooling (AP) modules to locate lesion areas without bounding boxes, transfer learning, or multi-stage training. In particular, the introduced PE and AP modules exhibit versatility across various CNN models and improve the model's tumor localization and diagnostic accuracy for mammography images. Experiments are conducted on published INbreast and CBIS-DDSM datasets, and compared to previous state-of-the-art mammographic image classification methods, DLSEN-RS performed satisfactorily.

Generation and Characterization of Novel Pan-Cancer Anti-uPAR Fluorescent Nanobodies as Tools for Image-Guided Surgery.

Fluorescence molecular imaging plays a vital role in image-guided surgery. In this context, the urokinase plasminogen activator receptor (uPAR) is an interesting biomarker enabling the detection and delineation of various tumor types due to its elevated expression on both tumor cells and the tumor microenvironment. In this study, anti-uPAR Nanobodies (Nbs) are generated through llama immunization with human and murine uPAR protein. Extensive in vitro characterization and in vivo testing with radiolabeled variants are conducted to assess their pharmacokinetics and select lead compounds. Subsequently, the selected Nbs are converted into fluorescent agents, and their application for fluorescence-guided surgery is evaluated in various subcutaneous and orthotopic tumor models. The study yields a panel of high-affinity anti-uPAR Nbs, showing specific binding across multiple types of cancer cells in vitro and in vivo. Lead fluorescently-labeled compounds exhibit high tumor uptake with high contrast at 1h after intravenous injection across all assessed uPAR-expressing tumor models, outperforming a non-targeting control Nb. Additionally, rapid and accurate tumor localization and demarcation are demonstrated in an orthotopic human glioma model. Utilizing these Nbs can potentially enhance the precision of surgical tumor resection and, consequently, improve survival rates in the clinic.

18F-AlF-NOTA-octreotide PET/CT in the localization of tumor-induced osteomalacia: case series and literature review.

This study explores tumor-induced osteomalacia (TIO) through a case series and literature review, assessing the diagnostic potential of 18F-AlF-NOTA-octreotide (18F-OC) positron emission tomography/computed tomography (PET/CT). We analyzed TIO patients who underwent 18F-OC PET/CT. Parameters such as tumor dimension, the maximum standardized uptake value (SUVmax), the mean standardized uptake value (SUVmean) and metabolic tumor volume (MTV) were meticulously assessed. Clinical features and imaging characteristics pertinent to TIO were reviewed. 6 patients with clinical suspicion of TIO exhibited hypophosphatemia (0.25 to 0.64 mmol/L), elevated alkaline phosphatase (ALP) levels (142 to 506 U/L), and increased parathyroid hormone (PTH) levels (92.9 to 281.7 pg/mL). Of these patients, two underwent FGF-23 testing, with results of 3185.00 pg/ml and 17.56 pg/ml, respectively. Conventional imaging modalities depicted widespread osteoporosis, with several cases demonstrating fractures indicative of osteomalacic and associated pathological fractures. Subsequent 18F-OC PET/CT facilitated the accurate localization of causative tumors, with histopathological examination confirming the diagnosis of phosphaturic mesenchymal tumor (PMT). The interval from initial clinical presentation to definitive TIO diagnosis spanned approximately 2.5 years (range: 1 - 4 years), with tumors varying in size (maximum diameter: 7.8 to 40.0mm), SUVmax (5.47 to 25.69), SUVmean (3.43 to 7.26), and MTV (1.27 to 18.59 cm3). The implementation of whole-body 18F-OC PET/CT imaging emerges as a critical tool in the identification of occult tumors causing TIO. Future investigations incorporating a broader cohort are imperative to further delineate the diagnostic and therapeutic implications of 18F-OC PET/CT in managing TIO.

A Dual-Cascade Activatable Near-Infrared Fluorescent Probe for Precise Intraoperative Imaging of Tumor.

Accurate intraoperative tumor delineation is critical to achieving successful surgical outcomes. However, conventional techniques typically suffer from poor specificity and low sensitivity and are time-consuming, which greatly affects intraoperative decision-making. Here, we report a cascade activatable near-infrared fluorescent (NIRF) probe IR780SS@CaP that can sequentially respond to tumor acidity and elevated glutathione levels for accurate intraoperative tumor localization. Compared with nonactivatable and single-factor activatable probes, IR780SS@CaP with a cascade strategy can minimize nonspecific activation and false positive signals in a complicated biological environment, affording a superior tumor-to-normal tissue ratio to facilitate the delineation of abdominal metastases. Small metastatic lesions that were less than 1 mm in diameter can be precisely identified by IR780SS@CaP and completely excised under NIRF imaging guidance. This study could benefit tumor diagnosis and image-guided tumor surgery by providing real-time information and reliable decision support, thus reducing the risk of both recurrence and complications to improve patient outcomes.

Abstract PO3-22-10: 3D-CT mapping with a photo-translucent application using iPad delineates tumor lesions on patient breast skin in breast-conserving surgery: Preliminary results

Abstract Objective: The aim of this study was to evaluate the feasibility and efficacy of a 3D-CT mapping technique with a photo-translucent application using an iPad for tumor localization on the patient's breast skin in breast-conserving surgery (BCS). We also compared the accuracy of tumor localization between conventional methods and 3D-CT mapping. Methods: Between February and July 2023, 20 female patients with early-stage (0 to 2) breast cancer scheduled for BCS were enrolled in this study. Preoperative enhanced CT scans were performed, and a 3D-CT image was generated by incorporating the patient's skin and manually marking the contrast-enhanced lesion using SYNAPSE VINCENT software. The 3D-CT images, adjusted to individual rotation angles to match the horizontal skin position above the tumor, were imported into an iPad equipped with a photo-translucent application. Using a securely fixed iPad holder, the translucent image was superimposed on the patient's breast, and the enhanced lesion was marked on the skin using a blue pen. Conventional tumor marking was performed based on ultrasound imaging, CT, and MRI findings using a black pen. Photographs were taken to simulate BCS based on the 3D-CT blue marking. All patients underwent BCS with resection margins of 1.5-2 cm from the black marking, and intraoperative frozen section analysis was performed to assess the resection margins. Results: The majority of patients had hormone receptor-positive breast cancers, and neoadjuvant chemotherapy was administered in three patients (Table 1). The extent of tumor involvement assessed by pathological assessment and imaging findings showed the least discrepancy with MRI, with an average error of 4.2 mm. MRI also had the lowest rate of missed tumor detection compared to other imaging modalities. The initial positive margin rate was 20%, and the simulation conducted in this study did not alter that value. Furthermore, the simulation demonstrated more effective excision of the tumor's center compared to conventional surgical methods (Table 2). Conclusion: The use of 3D-CT mapping with a photo-translucent application on an iPad offers a promising approach for accurate tumor localization in BCS. This technique provides a simplified and efficient method, and it can also be applied to cases where lesions have completely disappeared after neoadjuvant chemotherapy. XX- XX XX- XX Citation Format: Gou Watanabe, Akihiko Suzuki. 3D-CT mapping with a photo-translucent application using iPad delineates tumor lesions on patient breast skin in breast-conserving surgery: Preliminary results [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO3-22-10.

An augmented reality surgical navigation system based on co-axial projection of surgical paths for open liver tumor surgery

The traditional surgical navigation system for open liver tumor resection has some problems, such as low tumor localization accuracy, high complexity of system operation, and heavy surgical burden on surgeons. To solve these problems, this paper proposes an augmented reality surgical navigation system based on coaxial projection of surgical paths. Firstly, the intraoperative tumor localization module is used to locate the tumor. An augmented reality coaxial projection module for surgical path projection has been developed. In addition, a unified view of the camera and projector in the module is designed. Secondly, we propose an algorithm for image registration and fusion. The actual scene image of the liver captured by the augmented reality coaxial projection module is registered and fused with the model image to determine the tumor’s location in the surgical image. Then, surgical path planning is carried out for the tumors in the surgical images. An augmented reality coaxial projection module projects the surgical path onto the surface of the liver to assist surgeons in tumor resection. Finally, we validate the performance of our proposed surgical navigation system through multiple sets of experiments on tumor resection. The experimental results show that the average error and time of tumor resection based on this system are 2.95 mm and 59 s, respectively. It can be seen that the system proposed in this study achieved better results under laboratory conditions. The development of this system lays the foundation for our future research in clinical surgical navigation systems.

AI-assisted Analysis to Facilitate Detection of Humeral Lesions on Chest Radiographs.

Purpose To develop an artificial intelligence (AI) system for humeral tumor detection on chest radiographs (CRs) and evaluate the impact on reader performance. Materials and Methods In this retrospective study, 14 709 CRs (January 2000 to December 2021) were collected from 13 468 patients, including CT-proven normal (n = 13 116) and humeral tumor (n = 1593) cases. The data were divided into training and test groups. A novel training method called false-positive activation area reduction (FPAR) was introduced to enhance the diagnostic performance by focusing on the humeral region. The AI program and 10 radiologists were assessed using holdout test set 1, wherein the radiologists were tested twice (with and without AI test results). The performance of the AI system was evaluated using holdout test set 2, comprising 10 497 normal images. Receiver operating characteristic analyses were conducted for evaluating model performance. Results FPAR application in the AI program improved its performance compared with a conventional model based on the area under the receiver operating characteristic curve (0.87 vs 0.82, P = .04). The proposed AI system also demonstrated improved tumor localization accuracy (80% vs 57%, P < .001). In holdout test set 2, the proposed AI system exhibited a false-positive rate of 2%. AI assistance improved the radiologists' sensitivity, specificity, and accuracy by 8.9%, 1.2%, and 3.5%, respectively (P < .05 for all). Conclusion The proposed AI tool incorporating FPAR improved humeral tumor detection on CRs and reduced false-positive results in tumor visualization. It may serve as a supportive diagnostic tool to alert radiologists about humeral abnormalities. Keywords: Artificial Intelligence, Conventional Radiography, Humerus, Machine Learning, Shoulder, Tumor Supplemental material is available for this article. © RSNA, 2024.

3D cine-magnetic resonance imaging using spatial and temporal implicit neural representation learning (STINR-MR).

Objective. 3D cine-magnetic resonance imaging (cine-MRI) can capture images of the human body volume with high spatial and temporal resolutions to study anatomical dynamics. However, the reconstruction of 3D cine-MRI is challenged by highly under-sampled k-space data in each dynamic (cine) frame, due to the slow speed of MR signal acquisition. We proposed a machine learning-based framework, spatial and temporal implicit neural representation learning (STINR-MR), for accurate 3D cine-MRI reconstruction from highly under-sampled data.Approach. STINR-MR used a joint reconstruction and deformable registration approach to achieve a high acceleration factor for cine volumetric imaging. It addressed the ill-posed spatiotemporal reconstruction problem by solving a reference-frame 3D MR image and a corresponding motion model that deforms the reference frame to each cine frame. The reference-frame 3D MR image was reconstructed as a spatial implicit neural representation (INR) network, which learns the mapping from input 3D spatial coordinates to corresponding MR values. The dynamic motion model was constructed via a temporal INR, as well as basis deformation vector fields (DVFs) extracted from prior/onboard 4D-MRIs using principal component analysis. The learned temporal INR encodes input time points and outputs corresponding weighting factors to combine the basis DVFs into time-resolved motion fields that represent cine-frame-specific dynamics. STINR-MR was evaluated using MR data simulated from the 4D extended cardiac-torso (XCAT) digital phantom, as well as two MR datasets acquired clinically from human subjects. Its reconstruction accuracy was also compared with that of the model-based non-rigid motion estimation method (MR-MOTUS) and a deep learning-based method (TEMPEST).Main results. STINR-MR can reconstruct 3D cine-MR images with high temporal (<100 ms) and spatial (3 mm) resolutions. Compared with MR-MOTUS and TEMPEST, STINR-MR consistently reconstructed images with better image quality and fewer artifacts and achieved superior tumor localization accuracy via the solved dynamic DVFs. For the XCAT study, STINR reconstructed the tumors to a mean ± SD center-of-mass error of 0.9 ± 0.4 mm, compared to 3.4 ± 1.0 mm of the MR-MOTUS method. The high-frame-rate reconstruction capability of STINR-MR allows different irregular motion patterns to be accurately captured.Significance. STINR-MR provides a lightweight and efficient framework for accurate 3D cine-MRI reconstruction. It is a 'one-shot' method that does not require external data for pre-training, allowing it to avoid generalizability issues typically encountered in deep learning-based methods.