Simulation Method for the Physical Deformation of a Three-Dimensional Soft Body in Augmented Reality-Based External Ventricular Drainage.

OBJECTIVES: Intraoperative navigation reduces the risk of major complications and increases the likelihood of optimal surgical outcomes. This paper presents an augmented reality (AR)-based simulation technique for ventriculostomy that visualizes brain deformations caused by the movements of a surgical instrument in a three-dimensional brain model. This is achieved by utilizing a position-based dynamics (PBD) physical deformation method on a preoperative brain image. METHODS: An infrared camera-based AR surgical environment aligns the real-world space with a virtual space and tracks the surgical instruments. For a realistic representation and reduced simulation computation load, a hybrid geometric model is employed, which combines a high-resolution mesh model and a multiresolution tetrahedron model. Collision handling is executed when a collision between the brain and surgical instrument is detected. Constraints are used to preserve the properties of the soft body and ensure stable deformation. RESULTS: The experiment was conducted once in a phantom environment and once in an actual surgical environment. The tasks of inserting the surgical instrument into the ventricle using only the navigation information presented through the smart glasses and verifying the drainage of cerebrospinal fluid were evaluated. These tasks were successfully completed, as indicated by the drainage, and the deformation simulation speed averaged 18.78 fps. CONCLUSIONS: This experiment confirmed that the AR-based method for external ventricular drain surgery was beneficial to clinicians.

Artificial Intelligence in Gastric Cancer Imaging With Emphasis on Diagnostic Imaging and Body Morphometry.

Gastric cancer remains a significant global health concern, coercing the need for advancements in imaging techniques for ensuring accurate diagnosis and effective treatment planning. Artificial intelligence (AI) has emerged as a potent tool for gastric-cancer imaging, particularly for diagnostic imaging and body morphometry. This review article offers a comprehensive overview of the recent developments and applications of AI in gastric cancer imaging. We investigated the role of AI imaging in gastric cancer diagnosis and staging, showcasing its potential to enhance the accuracy and efficiency of these crucial aspects of patient management. Additionally, we explored the application of AI body morphometry specifically for assessing the clinical impact of gastrectomy. This aspect of AI utilization holds significant promise for understanding postoperative changes and optimizing patient outcomes. Furthermore, we examine the current state of AI techniques for the prognosis of patients with gastric cancer. These prognostic models leverage AI algorithms to predict long-term survival outcomes and assist clinicians in making informed treatment decisions. However, the implementation of AI techniques for gastric cancer imaging has several limitations. As AI continues to evolve, we hope to witness the translation of cutting-edge technologies into routine clinical practice, ultimately improving patient care and outcomes in the fight against gastric cancer.

Blending Low-Frequency Vibrations and Push-Pull Effects Affords Superior Photoacoustic Imaging Agents.

Photoacoustic imaging (PAI), a state-of-the-art noninvasive in vivo imaging technique, has been widely used in clinical disease diagnosis. However, the design of high-performance PAI agents with three key characteristics, i.e., near-infrared (NIR) absorption (λabs >800 nm), intense PA signals, and excellent photostability, remains a challenging goal. Herein, we present a facile but effective approach for engineering PAI agents by amplifying intramolecular low-frequency vibrations and enhancing the push-pull effect. As a demonstration of this blended approach, we constructed a PAI agent (BDP1-NEt2 ) based on the boron-dipyrromethene (BODIPY) scaffold. Compared with indocyanine green (ICG, an FDA-approved organic dye widely utilized in PAI studies; λabs =788 nm), BDP1-NEt2 exhibited a UV/Vis-NIR spectrum peaked at 825 nm, superior in vivo PA signal intensity and outstanding stability to offer improved tumor diagnostics. We believe this work provides a promising strategy to develop the next generation of PAI agents.

Functionally Masked Antibody to Uncouple Immune-Related Toxicities in Checkpoint Blockade Cancer Therapy.

Of the existing immunotherapy drugs in oncology, monoclonal antibodies targeting the immune checkpoint axis are preferred because of the durable responses observed in selected patients. However, the associated immune-related adverse events (irAEs), causing uncommon fatal events, often require specialized management and medication discontinuation. The study aim was to investigate our hypothesis that masking checkpoint antibodies with tumor microenvironment (TME)-responsive polymer chains can mitigate irAEs and selectively target tumors by limiting systemic exposure to patients. We devised a broadly applicable strategy that functionalizes immune checkpoint-blocking antibodies with a mildly acidic pH-cleavable poly(ethylene glycol) (PEG) shell to prevent inflammatory side effects in normal tissues. Conjugation of pH-sensitive PEG to anti-CD47 antibodies (αCD47) minimized antibody-cell interactions by inhibiting their binding ability and functionality at physiological pH, leading to prevention of αCD47-induced anemia in tumor-bearing mice. When conjugated to anti-CTLA-4 and anti-PD-1 antibodies, double checkpoint blockade-induced colitis was also ameliorated. Notably, removal of the protective shell in response to an acidic TME restored the checkpoint antibody activities, accompanied by effective tumor regression and long-term survival in the mouse model. Our results support a feasible strategy for antibody-based therapies to uncouple toxicity from efficacy and show the translational potential for cancer immunotherapy.

Curvature-sensing peptide inhibits tumour-derived exosomes for enhanced cancer immunotherapy.

Tumour-derived exosomes (T-EXOs) impede immune checkpoint blockade therapies, motivating pharmacological efforts to inhibit them. Inspired by how antiviral curvature-sensing peptides disrupt membrane-enveloped virus particles in the exosome size range, we devised a broadly useful strategy that repurposes an engineered antiviral peptide to disrupt membrane-enveloped T-EXOs for synergistic cancer immunotherapy. The membrane-targeting peptide inhibits T-EXOs from various cancer types and exhibits pH-enhanced membrane disruption relevant to the tumour microenvironment. The combination of T-EXO-disrupting peptide and programmed cell death protein-1 antibody-based immune checkpoint blockade therapy improves treatment outcomes in tumour-bearing mice. Peptide-mediated disruption of T-EXOs not only reduces levels of circulating exosomal programmed death-ligand 1, but also restores CD8+ T cell effector function, prevents premetastatic niche formation and reshapes the tumour microenvironment in vivo. Our findings demonstrate that peptide-induced T-EXO depletion can enhance cancer immunotherapy and support the potential of peptide engineering for exosome-targeting applications.

Non-rigid registration based on hierarchical deformation of coronary arteries in CCTA images.

In this paper, we propose an accurate and rapid non-rigid registration method between blood vessels in temporal 3D cardiac computed tomography angiography images of the same patient. This method provides auxiliary information that can be utilized in the diagnosis and treatment of coronary artery diseases. The proposed method consists of the following four steps. First, global registration is conducted through rigid registration between the 3D vessel centerlines obtained from temporal 3D cardiac CT angiography images. Second, point matching between the 3D vessel centerlines in the rigid registration results is performed, and the corresponding points are defined. Third, the outliers in the matched corresponding points are removed by using various information such as thickness and gradient of the vessels. Finally, non-rigid registration is conducted for hierarchical local transformation using an energy function. The experiment results show that the average registration error of the proposed method is 0.987 mm, and the average execution time is 2.137 s, indicating that the registration is accurate and rapid. The proposed method that enables rapid and accurate registration by using the information on blood vessel characteristics in temporal CTA images of the same patient.

Computer-Aided Breast Surgery Framework Using a Markerless Augmented Reality Method.

This study proposes a markerless Augmented Reality (AR) surgical framework for breast lesion removal using a depth sensor and 3D breast Computed Tomography (CT) images. A patient mesh in the real coordinate system is acquired through a patient 3D scan using a depth sensor for registration. The patient mesh on the virtual coordinate system is obtained by contrast-based skin segmentation in 3D mesh generated from breast CT scans. Then, the nipple area is detected based on the gradient in the segmented skin area. The region of interest (ROI) is set based on the detection result to select the vertices in the virtual coordinate system. The mesh on the real and virtual coordinate systems is first aligned by matching the center of mass, and the Iterative Closest Point (ICP) method is applied to perform more precise registration. Experimental results of 20 patients' data showed 98.35 ± 0.71% skin segmentation accuracy in terms of Dice Similarity Coefficient (DSC) value, 2.79 ± 1.54 mm nipple detection error, and 4.69 ± 1.95 mm registration error. Experiments using phantom and patient data also confirmed high accuracy in AR visualization. The proposed method in this study showed that the 3D AR visualization of medical data on the patient's body is possible by using a single depth sensor without having to use markers.

Evading Doxorubicin-Induced Systemic Immunosuppression Using Ultrasound-Responsive Liposomes Combined with Focused Ultrasound.

Doxorubicin (DOX) is a representative anticancer drug with a unique ability to induce immunogenic cell death of cancer cells. However, undesired toxicity on immune cells has remained a significant challenge, hindering the usage of DOX in cancer immunotherapy. Here, we report a combined therapy to avoid the off-target toxicity of DOX by adapting ultrasound-responsive liposomal doxorubicin and focused ultrasound exposure. Histological analysis demonstrated that the combined therapy induced less hemosiderosis of splenocytes and improved tumor infiltration of cytotoxic T lymphocytes. Additionally, in vivo therapeutic evaluation results indicate that the combined therapy achieved higher efficacy when combined with PD-1 immune-checkpoint blockade therapy by improving immunogenicity.

Self-immolative nanosensitizer for glutathione depletion- assisted sonodynamic therapy.

Background: Despite remarkable advances in sonodynamic therapy (SDT) of cancer, the low reactive oxygen species (ROS) quantum yield of the sonosensitizer remains a critical concern in glutathione (GSH)-overexpressing cancer cells. Methods: For enhanced SDT, we report hydrophilized self-immolative polymer (SIP)-decorated TiO2 nanoparticles (HSIPT-NPs) to achieve on-demand GSH depletion and ROS generation. Results: Upon intracellular delivery of HSIPT-NPs into hydrogen peroxide-rich cancer cells, SIP is degraded through electron transfer to produce GSH-depleting quinone methide, reprogramming GSH high cancer cells into GSH low phenotype. In the presence of ultrasound, compared to conventional TiO2 NPs, HSIPT-NPs induce significantly higher oxidative stress to cancer cells by incapacitating their antioxidant effects. SDT with HSIPT-NPs effectively inhibit tumor growth in mice via the synergistic effects of GSH depletion and ROS generation. Conclusion: On the basis of their ability to reprogram cancer cells, HSIPT-NPs offer considerable potential as a nanosensitizer for enhanced SDT.

Prognostic Value of Sarcopenia and Myosteatosis in Patients with Resectable Pancreatic Ductal Adenocarcinoma.

OBJECTIVE: The clinical relevance of myosteatosis has not been well evaluated in patients with pancreatic ductal adenocarcinoma (PDAC), although sarcopenia has been extensively researched. Therefore, we evaluated the prognostic value of muscle quality, including myosteatosis, in patients with resectable PDAC treated surgically. MATERIALS AND METHODS: We retrospectively evaluated 347 patients with resectable PDAC who underwent curative surgery (mean age ± standard deviation, 63.6 ± 9.6 years; 202 male). Automatic muscle segmentation was performed on preoperative computed tomography (CT) images using an artificial intelligence program. A single axial image of the portal phase at the inferior endplate level of the L3 vertebra was used for analysis in each patient. Sarcopenia was evaluated using the skeletal muscle index, calculated as the skeletal muscle area (SMA) divided by the height squared. The mean SMA attenuation was used to evaluate myosteatosis. Diagnostic cutoff values for sarcopenia and myosteatosis were devised using the Contal and O'Quigley methods, and patients were classified according to normal (nMT), sarcopenic (sMT), myosteatotic (mMT), or combined (cMT) muscle quality types. Multivariable Cox regression analyses were conducted to assess the effects of muscle type on the overall survival (OS) and recurrence-free survival (RFS) after surgery. RESULTS: Eighty-four (24.2%), 73 (21.0%), 75 (21.6%), and 115 (33.1%) patients were classified as having nMT, sMT, mMT, and cMT, respectively. Compared to nMT, mMT and cMT were significantly associated with poorer OS, with hazard ratios (HRs) of 1.49 (95% confidence interval, 1.00-2.22) and 1.68 (1.16-2.43), respectively, while sMT was not (HR of 1.40 [0.94-2.10]). Only mMT was significantly associated with poorer RFS, with an HR of 1.59 (1.07-2.35), while sMT and cMT were not. CONCLUSION: Myosteatosis was associated with poor OS and RFS in patients with resectable PDAC who underwent curative surgery.

Spatially variant immune infiltration scoring in human cancer tissues.

The Immunoscore is a method to quantify the immune cell infiltration within cancers to predict the disease prognosis. Previous immune profiling approaches relied on limited immune markers to establish patients' tumor immunity. However, immune cells exhibit a higher-level complexity that is typically not obtained by the conventional immunohistochemistry methods. Herein, we present a spatially variant immune infiltration score, termed as SpatialVizScore, to quantify immune cells infiltration within lung tumor samples using multiplex protein imaging data. Imaging mass cytometry (IMC) was used to target 26 markers in tumors to identify stromal, immune, and cancer cell states within 26 human tissues from lung cancer patients. Unsupervised clustering methods dissected the spatial infiltration of cells in tissue using the high-dimensional analysis of 16 immune markers and other cancer and stroma enriched labels to profile alterations in the tumors' immune infiltration patterns. Spatially resolved maps of distinct tumors determined the spatial proximity and neighborhoods of immune-cancer cell pairs. These SpatialVizScore maps provided a ranking of patients' tumors consisting of immune inflamed, immune suppressed, and immune cold states, demonstrating the tumor's immune continuum assigned to three distinct infiltration score ranges. Several inflammatory and suppressive immune markers were used to establish the cell-based scoring schemes at the single-cell and pixel-level, depicting the cellular spectra in diverse lung tissues. Thus, SpatialVizScore is an emerging quantitative method to deeply study tumor immunology in cancer tissues.

Sex-specific Cutoff Values of Visceral Fat Area for Lean vs. Overweight/Obese Nonalcoholic Fatty Liver Disease in Asians.

Background and Aims: Visceral obesity is a risk factor for nonalcoholic fatty liver disease (NAFLD). We investigated sex-specific optimal cutoff values for visceral fat area (VFA) associated with lean and overweight/obese NAFLD in an Asian population. Methods: This retrospective study included 678 potential living liver donors (mean age, 30.8±9.4 years; 434 men and 244 women) who had undergone abdominal computed tomography (CT) imaging and liver biopsy between November 2016 and October 2017. VFA was measured using single-slice abdominal CT. NAFLD was evaluated by liver biopsy (≥5% hepatic steatosis). Receiver operating characteristic curve analysis was used to determine cutoff values for VFA associated with lean (body mass index [BMI] <23 kg/m2) and overweight/obese (BMI ≥23 kg/m2) NAFLD. Results: Area under the curve (AUC) values with 95% confidence intervals (CI) for VFA were 0.82 (95% CI, 0.75-0.88) for lean and 0.74 (95% CI, 0.69-0.79) for overweight/obese men with NAFLD. The AUC values were 0.67 (95% CI, 0.58-0.75) for lean and 0.71 (95% CI, 0.62-0.80) for overweight/obese women with NAFLD. The cutoff values for VFA associated with lean NAFLD were 50.2 cm2 in men and 40.5 cm2 in women. The optimal cutoff values for VFA associated with overweight/obese NAFLD were 100.6 cm2 in men and 68.0 cm2 in women. Conclusions: Sex-specific cutoff values for VFA may be useful for identifying subjects at risk of lean and overweight/obese NAFLD.

Oral effervescent agent improving magnetic resonance cholangiopancreatography.

Background: The purpose of our study was to validate the oral effervescent agent improving magnetic resonance cholangiopancreatography (MRCP) in patients with suspicious pancreatobiliary disease. Methods: One hundred and eleven consecutive patients with alleged or suspected pancreatobiliary tree problems who had undergone two-dimensional (2D) MRCP imaging both before and after oral effervescent enhancement (conventional-MRCP and enhanced-MRCP) were included. Two radiologists independently scored overall image quality, visualization of ten ductal segments, and gastroduodenal fluid signal intensity score. In consensus, they assessed the presence of gastroduodenal fluids and pancreatobiliary tree overlapping. The data were analyzed using Wilcoxon's signed-rank test, McNemar test, and paired t-test. Results: The grades of overall image quality and individual biliary duct visualization for ten targeted ductal segments, and gastroduodenal fluid signal intensity scores increased significantly on enhanced-MRCP by both readers (P≤0.02), but there was no significant increase for pancreatic duct (PD) at head and tail. On enhanced-MRCP, gastroduodenal fluids except for gastric fundus were less detected rather than those on conventional-MRCP. Anatomic structures of gastroduodenal fluids overlapping extrahepatic bile duct were mainly gastric antrum, duodenal bulb, and 2nd portion on conventional-MRCP. However, these fluids were less overlapped on enhanced-MRCP (P<0.001). Gastric body and antrum were main anatomic structures of gastroduodenal fluids overlapping PD on conventional-MRCP, and fluid in these locations significantly less overlapped PD on enhanced-MRCP (P≤0.02). Conclusions: Oral administration of effervescent agent provided effective elimination of gastroduodenal fluid overlapping pancreatobiliary ductal system at MRCP and can improve the quality of the examination in the patients with known or suspected pancreatobiliary disease.

GWAS Reveals a Novel Candidate Gene CmoAP2/ERF in Pumpkin (Cucurbita moschata) Involved in Resistance to Powdery Mildew.

Pumpkin (Cucurbita moschata Duchesne ex Poir.) is a multipurpose cash crop rich in antioxidants, minerals, and vitamins; the seeds are also a good source of quality oils. However, pumpkin is susceptible to the fungus Podosphaera xanthii, an obligate biotrophic pathogen, which usually causes powdery mildew (PM) on both sides of the leaves and reduces photosynthesis. The fruits of infected plants are often smaller than usual and unpalatable. This study identified a novel gene that involves PM resistance in pumpkins through a genome-wide association study (GWAS). The allelic variation identified in the CmoCh3G009850 gene encoding for AP2-like ethylene-responsive transcription factor (CmoAP2/ERF) was proven to be involved in PM resistance. Validation of the GWAS data revealed six single nucleotide polymorphism (SNP) variations in the CmoAP2/ERF coding sequence between the resistant (IT 274039 [PMR]) and the susceptible (IT 278592 [PMS]). A polymorphic marker (dCAPS) was developed based on the allelic diversity to differentiate these two haplotypes. Genetic analysis in the segregating population derived from PMS and PMR parents provided evidence for an incomplete dominant gene-mediated PM resistance. Further, the qRT-PCR assay validated the elevated expression of CmoAP2/ERF during PM infection in the PMR compared with PMS. These results highlighted the pivotal role of CmoAP2/ERF in conferring resistance to PM and identifies it as a valuable molecular entity for breeding resistant pumpkin cultivars.

Impact of Baseline Muscle Mass and Myosteatosis on the Development of Early Toxicity During First-Line Chemotherapy in Patients With Initially Metastatic Pancreatic Cancer.

Objectives: Although chemotherapy is the only treatment option for metastatic pancreatic cancer (PDAC), patients frequently encounter adverse events during chemotherapy leading deterioration of patients' quality of life and treatment interruption. We evaluated the role of baseline CT-assessed body composition in predicting early toxicity during first cycle of the first-line chemotherapy in patients with metastatic PDAC. Methods: This retrospective study included 636 patients with initially metastatic PDAC who underwent first-line chemotherapy from January 2009 to December 2019. Chemotherapy regimen, baseline laboratory data, and body composition parameters acquired from baseline CT were obtained. The skeletal muscle index (SMI) was used to identify patients with a low muscle mass (SMI < 41 cm2/m2 for women, and < 43 cm2/m2 [body mass index < 25 cm/kg2] or < 53 cm2/m2 [body mass index ≥ 25 cm/kg2] for men), and myosteatosis was defined as low-attenuated muscle area divided by skeletal muscle area (LAMA/SMA index) ≥ 20%. Univariate and multivariable binary logistic regression analyses were performed using bootstrapping with 500 interactions to identify predictors of grade 3-4 toxicity and any treatment-modifying toxicity which led to a dose reduction, delayed administration, drug skip or discontinuation. Results: During the first cycle of the first-line chemotherapy, grade 3-4 toxicity and treatment-modifying toxicity occurred in 160 patients (25.2%) and in 247 patients (38.8%), respectively. The presence of both low muscle mass and myosteatosis was significantly associated with the occurrence of both grade 3-4 toxicity (odd ratio [OR], 1.73; 95% confidence interval [CI], 1.14-2.63) and treatment-modifying toxicity (OR, 1.83; 95% CI, 1.26-2.66) whereas low muscle mass alone did not. Conclusions: The presence of both low muscle mass and myosteatosis assessed on baseline CT may be used to predict early chemotherapy-related toxicity in patients with metastatic PDAC.

Relationship of body mass index and abdominal fat with radiation dose received during preoperative liver CT in potential living liver donors: a cross-sectional study.

Background: Although contrast-enhanced computed tomography (CT) is currently the most widely-used imaging modality for the preoperative evaluation of potential living liver donors, radiation exposure remains a major concern. The present study aimed to determine the relationship of body mass index (BMI) and abdominal fat with the effective radiation dose received during liver CT scans as part of a pre-donation work-up in potential living donors. Methods: This retrospective cross-sectional study included 695 potential living donors (mean age, 30.5±9.7 years; 445 men and 250 women) who had undergone preoperative liver CT scans between 2017 and 2018. The following measures were evaluated: BMI, abdominal fat as measured at the level of the third lumbar vertebra, and effective dose based on the dose length product (DLP). Correlations between the effective dose and other variables were evaluated using Pearson's correlation coefficient. Results: The mean BMI, total fat area (TFA), and effective dose were 23.6±3.3 kg/m2, 218.7±110.0 cm2, and 9.4±3.3 mSv, respectively. The effective dose during liver CT scans had a strong positive correlation with both BMI (r=0.715; P<0.001) and TFA (r=0.792; P<0.001). As BMI and TFA increased, so did the effective dose. Conclusions: Higher BMI and TFA significantly increased the radiation dose received during liver CT scans in potential living donors.

Deep Learning Segmentation in 2D X-ray Images and Non-Rigid Registration in Multi-Modality Images of Coronary Arteries.

X-ray angiography is commonly used in the diagnosis and treatment of coronary artery disease with the advantage of visualization of the inside of blood vessels in real-time. However, it has several disadvantages that occur in the acquisition process, which causes inconvenience and difficulty. Here, we propose a novel segmentation and nonrigid registration method to provide useful real-time assistive images and information. A convolutional neural network is used for the segmentation of coronary arteries in 2D X-ray angiography acquired from various angles in real-time. To compensate for errors that occur during the 2D X-ray angiography acquisition process, 3D CT angiography is used to analyze the topological structure. A novel energy function-based 3D deformation and optimization is utilized to implement real-time registration. We evaluated the proposed method for 50 series from 38 patients by comparing the ground truth. The proposed segmentation method showed that Precision, Recall, and F1 score were 0.7563, 0.6922, and 0.7176 for all vessels, 0.8542, 0.6003, and 0.7035 for markers, and 0.8897, 0.6389, and 0.7386 for bifurcation points, respectively. In the nonrigid registration method, the average distance of 0.8705, 1.06, and 1. 5706 mm for all vessels, markers, and bifurcation points was achieved. The overall process execution time was 0.179 s.

Change of Computed Tomography-Based Body Composition after Adrenalectomy in Patients with Pheochromocytoma.

Despite the potential biological importance of the sympathetic nervous system on fat and skeletal muscle metabolism in animal and in vitro studies, its relevance in humans remains undetermined. To clarify the influence of catecholamine excess on human body composition, we performed a retrospective longitudinal cohort study including 313 consecutive patients with histologically confirmed pheochromocytoma who underwent repeat abdominal computed tomography (CT) scans before and after adrenalectomy. Changes in CT-determined visceral fat area (VFA), subcutaneous fat area (SFA), skeletal muscle area (SMA), and skeletal muscle index (SMI) were measured at the level of the third lumbar vertebra. The mean age of all patients was 50.6 ± 13.6 years, and 171/313 (54.6%) were women. The median follow-up duration for repeat CTs was 25.0 months. VFA and SFA were 14.5% and 15.8% higher, respectively (both p < 0.001), after adrenalectomy, whereas SMA and SMI remained unchanged. Similarly, patients with visceral obesity significantly increased from 103 (32.9%) at baseline to 138 (44.1%) following surgery (p < 0.001); however, the prevalence of sarcopenia was unchanged. This study provides important clinical evidence that sympathetic hyperactivity can contribute to lipolysis in visceral and subcutaneous adipose tissues, but its impact on human skeletal muscle is unclear.

Automated segmentation of the fractured vertebrae on CT and its applicability in a radiomics model to predict fracture malignancy.

Although CT radiomics has shown promising results in the evaluation of vertebral fractures, the need for manual segmentation of fractured vertebrae limited the routine clinical implementation of radiomics. Therefore, automated segmentation of fractured vertebrae is needed for successful clinical use of radiomics. In this study, we aimed to develop and validate an automated algorithm for segmentation of fractured vertebral bodies on CT, and to evaluate the applicability of the algorithm in a radiomics prediction model to differentiate benign and malignant fractures. A convolutional neural network was trained to perform automated segmentation of fractured vertebral bodies using 341 vertebrae with benign or malignant fractures from 158 patients, and was validated on independent test sets (internal test, 86 vertebrae [59 patients]; external test, 102 vertebrae [59 patients]). Then, a radiomics model predicting fracture malignancy on CT was constructed, and the prediction performance was compared between automated and human expert segmentations. The algorithm achieved good agreement with human expert segmentation at testing (Dice similarity coefficient, 0.93-0.94; cross-sectional area error, 2.66-2.97%; average surface distance, 0.40-0.54 mm). The radiomics model demonstrated good performance in the training set (AUC, 0.93). In the test sets, automated and human expert segmentations showed comparable prediction performances (AUC, internal test, 0.80 vs 0.87, p = 0.044; external test, 0.83 vs 0.80, p = 0.37). In summary, we developed and validated an automated segmentation algorithm that showed comparable performance to human expert segmentation in a CT radiomics model to predict fracture malignancy, which may enable more practical clinical utilization of radiomics.