Bone Scan Imaging Research Articles

Bone scintigraphy based on deep learning model and modified growth optimizer

Bone scintigraphy is recognized as an efficient diagnostic method for whole-body screening for bone metastases. At the moment, whole-body bone scan image analysis is primarily dependent on manual reading by nuclear medicine doctors. However, manual analysis needs substantial experience and is both stressful and time-consuming. To address the aforementioned issues, this work proposed a machine-learning technique that uses phases to detect Bone scintigraphy. The first phase in the proposed model is the feature extraction and it was conducted based on integrating the Mobile Vision Transformer (MobileViT) model in our framework to capture highly complex representations from raw medical imagery using two primary components including ViT and lightweight CNN featuring a limited number of parameters. In addition, the second phase is named feature selection, and it is dependent on the Arithmetic Optimization Algorithm (AOA) being used to improve the Growth Optimizer (GO). We evaluate the performance of the proposed FS model, named GOAOA using a set of 18 UCI datasets. Additionally, the applicability of Bone scintigraphy for real-world application is evaluated using 2800 bone scan images (1400 normal and 1400 abnormal). The results and statistical analysis revealed that the proposed GOAOA algorithm as an FS technique outperforms the other FS algorithms employed in this study.

Enhancing bone scan image quality: an improved self-supervised denoising approach.

Bone scans play an important role in skeletal lesion assessment, but gamma cameras exhibit challenges with low sensitivity and high noise levels. Deep learning (DL) has emerged as a promising solution to enhance image quality without increasing radiation exposure or scan time. However, existing self-supervised denoising methods, such as Noise2Noise (N2N), may introduce deviations from the clinical standard in bone scans. This study proposes an improved self-supervised denoising technique to minimize discrepancies between DL-based denoising and full scan images. 
Retrospective analysis of 351 whole-body bone scan data sets was conducted. In this study, we used N2N and Noise2FullCount (N2F) denoising models, along with an interpolated version of N2N (iN2N). Denoising networks were separately trained for each reduced scan time from 5 to 50%, and also trained for mixed training datasets, which include all shortened scans. We performed quantitative analysis and clinical evaluation by nuclear medicine experts.
The denoising networks effectively generated images resembling full scans, with N2F revealing distinctive patterns for different scan times, N2N producing smooth textures with slight blurring, and iN2N closely mirroring full scan patterns. Quantitative analysis showed that denoising improved with longer input times and mixed count training outperformed fixed count training. Traditional denoising methods lagged behind DL-based denoising. N2N demonstrated limitations in long-scan images. Clinical evaluation favored N2N and iN2N in resolution, noise, blurriness, and findings, showcasing their potential for enhanced diagnostic performance in quarter-time scans.
The improved self-supervised denoising technique presented in this study offers a viable solution to enhance bone scan image quality, minimizing deviations from clinical standards. The method's effectiveness was demonstrated quantitatively and clinically, showing promise for quarter-time scans without compromising diagnostic performance. This approach holds potential for improving bone scan interpretations, aiding in more accurate clinical diagnoses.

Multimodal Data-Driven Segmentation of Bone Metastasis Lesions in SPECT Bone Scans Using Deep Learning.

Patients with malignant tumors often develop bone metastases. SPECT bone scintigraphy is an effective tool for surveying bone metastases due to its high sensitivity, low-cost equipment, and radiopharmaceutical. However, the low spatial resolution of SPECT scans significantly hinders manual analysis by nuclear medicine physicians. Deep learning, a promising technique for automated image analysis, can extract hierarchal patterns from images without human intervention. To enhance the performance of deep learning-based segmentation models, we integrate textual data from diagnostic reports with SPECT bone scans, aiming to develop an automated analysis method that outperforms purely unimodal data-driven segmentation models. We propose a dual-path segmentation framework to extract features from bone scan images and diagnostic reports separately. In the first path, an encoder-decoder network is employed to learn hierarchical representations of features from SPECT bone scan images. In the second path, the Chinese version of the MacBERT model is utilized to develop a text encoder for extracting features from diagnostic reports. The extracted textual features are then fused with image features during the decoding stage in the first path, enhancing the overall segmentation performance. Experimental evaluation conducted on real-world clinical data demonstrated the superior performance of the proposed segmentation model. Our model achieved a 0.0209 increase in the DSC (Dice Similarity Coefficient) score compared to the well-known U-Net model. The proposed multimodal data-driven method effectively identifies and isolates metastasis lesions in SPECT bone scans, outperforming existing classical deep learning models. This study demonstrates the value of incorporating textual data in the deep learning-based segmentation of lowresolution SPECT bone scans.

Appropriateness of Imaging for Low-Risk Prostate Cancer-Real World Data from the Pennsylvania Urologic Regional Collaboration (PURC).

Imaging for prostate cancer defines the extent of disease. Guidelines recommend against imaging low-risk prostate cancer patients with a computed tomography (CT) scan or bone scan due to the low probability of metastasis. We reviewed imaging performed for men diagnosed with low-risk prostate cancer across the Pennsylvania Urologic Regional Collaborative (PURC), a physician-led data sharing and quality improvement collaborative. The data of 10 practices were queried regarding the imaging performed in men diagnosed with prostate cancer from 2015 to 2022. The cohort included 13,122 patients with 3502 (27%) low-risk, 2364 (18%) favorable intermediate-risk, 3585 (27%) unfavorable intermediate-risk, and 3671 (28%) high-risk prostate cancer, based on the AUA guidelines. Amongst the low-risk patients, imaging utilization included pelvic MRI (59.7%), bone scan (17.8%), CT (16.0%), and PET-based imaging (0.5%). Redundant imaging occurred in 1022 patients (29.2%). There was variability among the PURC sites for imaging used in the low-risk patients, and iterative education reduced the need for CT and bone scans. Approximately 15% of low-risk patients had staging imaging performed using either a CT or bone scan, and redundant imaging occurred in almost one-third of men. Such data underscore the need for continued guideline-based education to optimize the stewardship of resources and reduce unnecessary costs to the healthcare system.

Sex estimation from mandibular morphometry using discriminant analysis–CT scan based retrospective study

It is well known that skeletal characteristics vary among different populations. Sex dimorphic characteristics of the mandible have been reported from studies using either mandible bone or computer tomography (CT) scan images of the mandible to test its efficacy in estimating sex. Mandibular studies for estimating sex in any particular population group may not hold well for different populations owing to inherent geographical variations. With this background, we assessed the validity of mandible measurements from CT scan images to determine sex in the South Indian population. As a part of our study, 11 metric parameters and 1 angular parameter were measured and analyzed. The mean values of all the parameters were significantly higher for males as compared to females. Bigonial breadth indicated the best discriminatory ability of the study. Mandibular angle had the least predictive accuracy among all the discriminant functions studied. We further observed that a combination of parameters gave the best overall classification rate (92.3 %). When the same functions were tested on an independent testing data set, a combination of parameters and bigonial breadth gave the best classification rate (82.1 %) which was consistent. We concluded that the mandible has a high accuracy for sex estimation. All the parameters studied demonstrated statistically significant differences between the two sexes except the mandibular angle.

MSegResRF-SPECT: A Novel Joint Classification Model of Whole Body Bone Scan Images for Bone Metastasis Diagnosis.

Whole-body bone scanning is a nuclear medicine technique with high sensitivity used for the diagnosis of bone-related diseases [e.g., bone metastases] that can be obtained by positron emission tomography[PET] or single-photon emission computed tomography[SPECT] imaging, depending on the different radiopharmaceuticals used. In contrast to the high sensitivity of the bone scan, it has low specificity, which leads to misinterpretation, causing adverse effects of unwarranted intervention or interruption to timely treatment. To address this problem, this paper proposes a joint model called mSegResRF-SPECT, which accomplishes for the first time the task of classifying whole-body bone scan images on a public SPECT dataset [BS-80K] for the diagnosis of bone metastases. The mSegResRF-SPECT adopts a multi-bone region segmentation algorithm to segment the whole body image into 13 regions, ResNet34 as an extractor to extract the regional features, and a random forest algorithm as a classifier. The experimental results of the proposed model show that the average accuracy, sensitivity, and F1 score of the model on the BS-80K dataset reached SOTA. The proposed method presents a promising solution for better bone scan classification methods.

Leveraging Model Scaling and Butterfly Network in the Bone Scan Image Segmentation

As we all know, cancer is one of the leading causes of death worldwide and the second leading cause of death overall. This is why regular screenings or health checks are necessary to detect cancer lesions early. Since bone scan images have become the primary means of detecting the emergence of cancer lesions on bone, high segmentation accuracy is essential for establishing the model of some predefined regions in bone scan images where cancer metastasis was predicted to appear. Consequently, robust localization and identification of the specific region in bone scan images are required for automated metastasis detection. To this end, we propose Efficient-BtrflyNet, a new deep learning-based architecture for skeleton segmentation of whole-body bone scan images. The proposed architecture exploits the benefits of EfficientNet’s model scaling and the encoder–decoder design of butterfly-type networks. We added EfficientNetB7 to the encoder section to obtain more specific features. The proposed architecture simultaneously processes anterior and posterior whole-body bone scan images. Using 37 bone scan images, we evaluated the performance of our proposed skeleton segmentation system using the Dice score. Efficient-BtrflyNet achieves superior segmentation performance compared to the existing representative method.

Bone scan findings of Paget’s disease of bone in patients with VCP Multisystem Proteinopathy 1

Multisystem Proteinopathy 1 (MSP1) disease is a rare genetic disorder caused by mutations in the Valosin-Containing Protein (VCP) gene with clinical features of inclusion body myopathy (IBM), frontotemporal dementia (FTD), and Paget’s disease of bone (PDB). We performed bone scan imaging in twelve patients (6 females, 6 males) with confirmed VCP gene mutation six (50%) of which has myopathy alone, four (33%) with both PDB and myopathy, and two (15%) were presymptomatic carriers. We aim to characterize the PDB in diagnosed individuals, and potentially identify PDB in the myopathy and presymptomatic groups. Interestingly, two patients with previously undiagnosed PDB had positive diagnostic findings on the bone scan and subsequent radiograph imaging. Among the individuals with PDB, increased radiotracer uptake of the affected bones were of typical distribution as seen in conventional PDB and those reported in other MSP1 cohorts which are the thoracic spine and ribs (75%), pelvis (75%), shoulder (75%) and calvarium (15%). Overall, we show that technetium-99m bone scans done at regular intervals are a sensitive screening tool in patients with MSP1 associated VCP variants at risk for PDB. However, diagnostic confirmation should be coupled with clinical history, biochemical analysis, and skeletal radiographs to facilitate early treatment and prevention complications, acknowledging its limited specificity.

Circulating and Imaging Biomarkers of Radium-223 Response in Metastatic Castration-Resistant Prostate Cancer.

Radium-223 improves overall survival (OS) and reduces skeletal events in patients with bone metastatic castration-resistant prostate cancer (CRPC), but relevant biomarkers are lacking. We evaluated automated bone scan index (aBSI) and circulating tumor cell (CTC) analyses as potential biomarkers of prognosis and activity. Patients with bone metastatic CRPC were enrolled on a prospective single-arm study of standard radium-223. 99mTc-MDP bone scan images at baseline, 2 months, and 6 months were quantitated using aBSI. CTCs at baseline, 1 month, and 2 months were enumerated and assessed for RNA expression of prostate cancer-specific genes using microfluidic enrichment followed by droplet digital polymerase chain reaction. The median OS was 21.3 months in 22 patients. Lower baseline aBSI and minimal change in aBSI (<+0.7) from baseline to 2 months were each associated with better OS (P = .00341 and P = .0139, respectively). The higher baseline CTC count of ≥5 CTC/7.5 mL was associated with worse OS (median, 10.1 v 32.9 months; P = .00568). CTCs declined at 2 months in four of 15 patients with detectable baseline CTCs. Among individual genes in CTCs, baseline expression of the splice variant AR-V7 was significantly associated with worse OS (hazard ratio, 5.20 [95% CI, 1.657 to 16.31]; P = .00195). Baseline detectable AR-V7, higher aBSI, and CTC count ≥5 CTC/7.5 mL continued to have a significant independent negative impact on OS after controlling for prostate-specific antigen or alkaline phosphatase. Quantitative bone scan assessment with aBSI and CTC analyses are prognostic markers in patients treated with radium-223. AR-V7 expression in CTCs is a particularly promising prognostic biomarker and warrants validation in larger cohorts.

A Case Report on Avascular Necrosis of Right Femoral Head in a 20-years Old Male

Avascular necrosis of the femoral head is a condition which causes cellular destruction of bone material due to interruption of blood supply. Necrosis is caused by inadequate blood supply, resulting in bone tissue destruction with collapsing of that segment. The disease usually occurs in young adults, and femoral head is one of the commonest sites. Avascular necrosis may be traumatic or non-traumatic and causes major musculoskeletal disability. Initially patients remain asymptomatic. In untreated cases the disease progresses and causes joint destruction, requiring surgical intervention and in later stages need total hip replacement. Plain X-ray, isotope bone scan and magnetic resonance imaging (MRI) play important role in making the diagnosis. MRI is highly accurate method for the diagnosis of avascular necrosis of the femoral head.

Diffuse Cardiac Uptake Misdiagnosed as Cardiac Amyloidosis in Bone Scan.

In this presented case, a 77-year-old woman with an implanted prosthesis and ongoing knee pain underwent a bone scan using 99mTc-hydroxydiphosphonate (HDP) in suspicion for bone infection. An incidental finding from this scan revealed diffuse cardiac uptake, necessitating further diagnostic procedures to exclude the possibility of cardiac amyloidosis. In the subsequent 99mTc-3,3-diphosphono-1,2-propanodicarboxylic acid (DPD) scan and SPECT images, no perceptible cardiac uptake was observed at all. Upon retrospective review of the patient's medical records, she received 1000 mg of ferric carboxymaltose for iron-deficient anemia the day before the 99mTc-HDP bone scan. Therefore, it was assumed that the diffuse and temporary cardiac activity was due to the transient iron overload. We present and share these bone scan images in order to avoid possible future misinterpretation of cardiac amyloidosis.

IMPLEMENTASI INDONESIAN DIAGNOSTIC REFERENCE LEVEL (I-DRL) PADA PELAYANAN DIAGNOSTIK IN VIVO KEDOKTERAN NUKLIR DI RSUP DR. SARDJITO TAHUN 2022-2023

The Indonesian Diagnostic Reference Level (I-DRL) value in nuclear medicine was only published in November 2022 by the Nuclear Energy Regulatory Agency (BAPETEN). Implementing I-DRL in in-vivo diagnostic services in nuclear medicine at Sardjito Hospital, which has been running so far, needs ongoing evaluation to help realize an increase in the ratio of benefits to risks of radiation to patients. This research aims to apply I-DRL nuclear medicine at Dr. Sardjito Hospital while still applying the principles of optimizing medical exposure. Optimization focuses on maintaining guaranteed image quality, namely images that are readable or not readable by nuclear medicine specialists, while still implementing radiation protection against medical exposure. The research is a retrospective descriptive method from bone scan patient data from 2022-2023. The selection of 299 bone scan data was based on the most frequently performed examinations. The bone scan imaging tool used was a GE brand single-photon emission computed tomography (SPECT-CT) gamma camera type NM/CT 870 DR. Image processing uses a comparison of region of interest (ROI) values from the target and background on the femur bone using Xeleris software. Based on the image analysis results, the target and background's lowest, average, and highest comparison values were respectively 1.15, 2.1, and 3.75. Spearman statistical testing was also carried out between the dose per Body Mass Index (BMI) and the target/background value ratio, obtaining an R-value of -0.046, which means the two variables have a weak relationship. This research provides information that I-DRL Bone scan can be implemented without affecting the image quality results. Implementing I-DRL is a form of optimizing radiation protection for patients, preventing unnecessary radiation exposure, and ensuring the quality of nuclear medicine services will improve in the future. Keywords: I-DRL, in vivo diagnostics, optimization, radiation protection, bone scan.

Bone Metastases Lesion Segmentation on Breast Cancer Bone Scan Images with Negative Sample Training.

The use of deep learning methods for the automatic detection and quantification of bone metastases in bone scan images holds significant clinical value. A fast and accurate automated system for segmenting bone metastatic lesions can assist clinical physicians in diagnosis. In this study, a small internal dataset comprising 100 breast cancer patients (90 cases of bone metastasis and 10 cases of non-metastasis) and 100 prostate cancer patients (50 cases of bone metastasis and 50 cases of non-metastasis) was used for model training. Initially, all image labels were binary. We used the Otsu thresholding method or negative mining to generate a non-metastasis mask, thereby transforming the image labels into three classes. We adopted the Double U-Net as the baseline model and made modifications to its output activation function. We changed the activation function to SoftMax to accommodate multi-class segmentation. Several methods were used to enhance model performance, including background pre-processing to remove background information, adding negative samples to improve model precision, and using transfer learning to leverage shared features between two datasets, which enhances the model's performance. The performance was investigated via 10-fold cross-validation and computed on a pixel-level scale. The best model we achieved had a precision of 69.96%, a sensitivity of 63.55%, and an F1-score of 66.60%. Compared to the baseline model, this represents an 8.40% improvement in precision, a 0.56% improvement in sensitivity, and a 4.33% improvement in the F1-score. The developed system has the potential to provide pre-diagnostic reports for physicians in final decisions and the calculation of the bone scan index (BSI) with the combination with bone skeleton segmentation.

Bone metastasis detection method based on improving golden jackal optimization using whale optimization algorithm

This paper presents a machine learning-based technique for interpreting bone scintigraphy images, focusing on feature extraction and introducing a new feature selection method called GJOW. GJOW enhances the effectiveness of the golden jackal optimization (GJO) algorithm by integrating operators from the whale optimization algorithm (WOA). The technique’s performance is evaluated through extensive experiments using 18 benchmark datasets and 581 bone scan images obtained from a gamma camera, including 362 abnormal and 219 normal cases. The results highlight the superior predictive effectiveness of the GJOW algorithm in bone metastasis detection, achieving an accuracy of 71.79% and specificity of 91.14%. The contributions of this study include the introduction of a new machine learning-based approach for detecting bone metastasis using gamma camera scans, leading to improved accuracy in identifying bone metastases. The findings have practical implications for early detection and intervention, potentially improving patient outcomes.

Clinical outcomes of surgical treatment for Copenhagen syndrome: a case series

BackgroundCopenhagen syndrome (CS) is a rare disorder mostly observed in adolescent. The onset of the disease, with a progressive anterior vertebral ankylosis in the thoracic and/or lumbar areas often clinically revealed by thoracolumbar kyphosis. We report a series of three patients of CS with good outcome.Case presentationThe mean age of patients were 14.0 (SD = 3.6) years at admission time. Patients underwent clinical and radiological examination (MRI, CT scan, and bone scan) before surgery and revealed Copenhagen syndrome. Case 2 received conservative treatment braces and regular follow-up. Finally, all patients were treated according to their clinical conditions through a combined surgical approach such as pedicle subtraction osteotomy (PSO), ponte osteotomy, hook, pedicular screw insertion, and fusion. In postoperative follow-up, the deformity correction was achieved with proper alignment in all the cases.ConclusionThe treatment of CS with PSO plus ponte osteotomy seems to result in an excellent surgical procedure and outcome for our patients based on deformity severity. Bone scan imaging could be considered as an aid to differential diagnosis, which is an effective method.

Deep learning enhanced ultra-fast SPECT/CT bone scan in patients with suspected malignancy: quantitative assessment and clinical performance

Objectives. To evaluate the clinical performance of deep learning-enhanced ultrafast single photon emission computed tomography/computed tomography (SPECT/CT) bone scans in patients with suspected malignancy. Approach. In this prospective study, 102 patients with potential malignancy were enrolled and underwent a 20 min SPECT/CT and a 3 min SPECT scan. A deep learning model was applied to generate algorithm-enhanced images (3 min DL SPECT). The reference modality was the 20 min SPECT/CT scan. Two reviewers independently evaluated general image quality, Tc-99m MDP distribution, artifacts, and diagnostic confidence of 20 min SPECT/CT, 3 min SPECT/CT, and 3 min DL SPECT/CT images. The sensitivity, specificity, accuracy, and interobserver agreement were calculated. The lesion maximum standard uptake value (SUVmax) of the 3 min DL and 20 min SPECT/CT images was analyzed. The peak signal-to-noise ratio (PSNR) and structure similarity index measure (SSIM) were evaluated. Main results. The 3 min DL SPECT/CT images showed significantly superior general image quality, Tc-99m MDP distribution, artifacts, and diagnostic confidence than the 20 min SPECT/CT images (P < 0.0001). The diagnostic performance of the 20 min and 3 min DL SPECT/CT images was similar for reviewer 1 (paired X 2 = 0.333, P = 0.564) and reviewer 2 (paired X 2 = 0.05, P = 0.823). The diagnosis results for the 20 min (kappa = 0.822) and 3 min DL (kappa = 0.732) SPECT/CT images showed high interobserver agreement. The 3 min DL SPECT/CT images had significantly higher PSNR and SSIM than the 3 min SPECT/CT images (51.44 versus 38.44, P < 0.0001; 0.863 versus 0.752, P < 0.0001). The SUVmax of the 3 min DL and 20 min SPECT/CT images showed a strong linear relationship (r = 0.991; P < 0.0001). Significance. Ultrafast SPECT/CT with a 1/7 acquisition time can be enhanced by a deep learning method to achieve comparable image quality and diagnostic value to those of standard acquisition.

Automatic prediction model of overall survival in prostate cancer patients with bone metastasis using deep neural networks

Abstract Objectives Bone is the most common site of metastasis in prostate cancer (PCa) patients and is correlated with poor prognosis and increasing economic burden. Few studies have analyzed the prognostic prediction for metastatic PCa patients with the assistance of neural networks. Methods Four convolutional neural network (CNN) models are developed and evaluated to predict the overall survival (OS) of PCa patients with bone metastasis. All the CNN models are first trained with 64 samples and evaluated with 10 samples; two models use only bone scan images and two models use both bone scan images and clinical parameters (CPs). The predictions of the best models are compared with those by two urology surgeons on 20 test samples. Results Our best models can predict OS of PCa patients with bone metastasis with AUC=0.8022 by using only bone scan images and AUC=0.8132 by using both bone scan images and CPs on 20 test samples. The best Youden indexes of the two models are 0.6263 and 0.7142, respectively, which are 0.3077 and 0.3131 higher than that of the urologists’ average Youden index, which indicate that CNN models exhibit significant advantages. Conclusions CNN models are suitable to predict OS in PCa patients with bone metastasis using bone scan images and CPs. Our models show better performance in terms of accuracy and stability than urology surgeons.

Meningioma Mimicking Bone Metastasis in Breast Cancer.

Meningiomas constitute 37% of primary central nervous system tumors and are more common in women. Also may occur with other primary malignancies, which can cause confusion with the metastasis in whole body bone scan (WBBS) imaging. A 58-year-old woman diagnosed with breast cancer was referred to the WBBS for the investigation of possible bone metastases. In the planar images, radiotracer uptake at multiple sites was detected on the anterior side of the skull base and the posterior side of the vertex of the cranium. Single photon emission computed tomography/computed tomography was performed for anatomical localization of possible metastatic lesions, and it revealed that detected accumulations of radiotracer did not belong to the bone metastases; uptakes were located at the cerebral parenchyma and the lesions in the falx cerebri. Patient history explained that she had been diagnosed with meningioma five years ago, which mimicked bone metastases in this study.

Evaluation of the role of vertebral augmentation in chronic vertebral compression fractures: A retrospective study

ObjectivesVertebral augmentation is recommended for acute or subacute vertebral compression fractures (VCFs); few studies claim its usefulness in chronic VCFs also. Use of radionuclide imaging may improvise identification of chronic VCFs that may benefit from vertebral augmentation; hence we have evaluated efficacy of vertebral augmentation procedures in chronic VCFs with incomplete fracture healing suggested either by MRI or Tc99m- MDP bone scan. Materials and MethodsPatients with chronic osteoporotic VCFs (>12 weeks) during the period of June 2013 to June 2019 were included in this retrospective study; patients with evidence of incomplete fracture healing either by MRI or bone scan imaging with Tc 99m-MDP underwent vertebroplasty or kyphoplasty. Primary outcome measure was patient’s pain score measured by numerical rating scale (NRS); secondary outcome measures were patient’s disability assessed by Roland Morris Disability questionnaire (RDQ); quality of life assessed by Quality of life questionnaire of European Foundation of Osteoporosis (QUALLEFO) and analgesic usage. P ​< ​0.050 was considered as significant. Results34 patients were enrolled for the study with median fracture age of 36 months. The median NRS pain scores, RDQ scores, QUALEFFO scores and analgesic usage were significantly reduced at all-time points as compared to the baseline value over the follow up period of 1 year after vertebral augmentation procedure (P ​< ​0.050). Cement leakage was seen in 5 patients (15%). ConclusionVertebral augmentation procedures provided significant improvements in pain scores, disability and quality of life in patients of chronic osteoporotic VCFs with median fracture age of 36 months.

Artificial Intelligence of Object Detection in Skeletal Scintigraphy for Automatic Detection and Annotation of Bone Metastases.

When cancer has metastasized to bone, doctors must identify the site of the metastases for treatment. In radiation therapy, damage to healthy areas or missing areas requiring treatment should be avoided. Therefore, it is necessary to locate the precise bone metastasis area. The bone scan is a commonly applied diagnostic tool for this purpose. However, its accuracy is limited by the nonspecific character of radiopharmaceutical accumulation. The study evaluated object detection techniques to improve the efficacy of bone metastases detection on bone scans. We retrospectively examined the data of 920 patients, aged 23 to 95 years, who underwent bone scans between May 2009 and December 2019. The bone scan images were examined using an object detection algorithm. After reviewing the image reports written by physicians, nursing staff members annotated the bone metastasis sites as ground truths for training. Each set of bone scans contained anterior and posterior images with resolutions of 1024 × 256 pixels. The optimal dice similarity coefficient (DSC) in our study was 0.6640, which differs by 0.04 relative to the optimal DSC of different physicians (0.7040). Object detection can help physicians to efficiently notice bone metastases, decrease physician workload, and improve patient care.