Tc-99m MDP Bone Scan Research Articles

A Rare Case of Osteoid Osteoma of the Medial Cuneiform Bone at Tibialis Anterior Insertion Confirmed by Bone Scan SPECT/CT.

A 34-year-old man presented with progressive foot pain that was initially on the medial soft tissue but eventually localized to the medial side of midfoot. Despite undergoing various imaging tests and conservative treatments over 2 years, the patient remained undiagnosed. After 6 months, soft tissue and bone involvement were observed on the medial cuneiform. A needle biopsy was inconclusive. Since bone tumor is rare in the medial cuneiform, the patient was referred to our department for 99mTc-MDP bone scan. The imaging and clinical findings suggested osteoid osteoma as the likely diagnosis, which was confirmed as intraarticular nidus under tibialis anterior attachment, after surgical resection and pathological examination.

Diffuse Uptake of 68Ga-Pentixafor in the Breasts During the Ovulatory Phase in a Patient With SAPHO Syndrome.

We report a case of a woman with SAPHO syndrome who exhibited increased tracer uptake in the sternal angle on a 99mTc-MDP bone scan. This patient was enrolled in a 68Ga-pentixafor PET/CT trial for inflammatory diseases. The PET/CT showed no abnormal tracer uptake in the sternal angle. Unexpectedly, diffuse uptake of 68Ga-pentixafor was observed in both breasts, which might be due to hormonal stimulation because the woman underwent the 68Ga-pentixafor PET/CT scan during the ovulatory phase.

Prospective comparison of 68Ga-DOTA-ibandronate and bone scans for detecting bone metastases in breast cancer.

68Ga labeled DOTA-Ibandronate (68Ga-DOTA-IBA) positron emission tomography/computed tomography (PET/CT), is a novel bone-targeting imaging tracer and promising diagnostic method for bone metastases detection. Therefore, this study aimed to compare 68Ga-DOTA-IBA PET/CT to the 99mTc-MDP whole-body bone scan (WBBS) for detecting bone metastases in breast cancer (BC). In this prospective study, 45 women with BC underwent imaging via 68Ga-DOTA-IBA PET/CT and 99mTc-MDP WBBS. Clinical and demographic information as well as BC imaging features were recorded. The two methods were compared in terms of their detection rate for bone metastases and the number of lesions. The 45 women were aged 53.5 ± 11.0 years. The bone metastases detection rate with 68Ga-DOTA-IBA PET/CT was 100% (45/45) and with 99mTc-MDP WBBS was 95.6% (43/45). A total of 546 bone metastases lesions were detected. The lesion detection rate using 68Ga-DOTA-IBA PET/CT was 100% (546/546) and using 99mTc-MDP WBBS was 67.8% (370/546). More lesions were found at each site via 68Ga-DOTA-IBA than via 99mTc-MDP WBBS. 68Ga-DOTA-IBA PET/CT is a more sensitive method than 99mTc-MDP WBBS for assessing bone metastases in BC and may therefore represent a useful imaging technique for bone metastases, while offering a visual basis for 177Lu-DOTA-IBA diagnosis and therapy response assessments for BC. Further validation using a broader study cohort is warranted to confirm these findings. https://www.chictr.org.cn/showproj.html?proj=170163, identifier ChiCTR2200064487.

Correction: 99mTc-MDP Bone Scan and 18F-FDG PET/CT Imaging of Primary Hepatic Osteosarcoma.

Correction: 99mTc-MDP Bone Scan and 18F-FDG PET/CT Imaging of Primary Hepatic Osteosarcoma.

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.

18F-FDG PET/CT and 99mTc-MDP Bone Scintigraphy Findings of Multifocal Desmoid Fibromatosis.

Desmoid fibromatosis, also called desmoid tumors, is a group of locally aggressive fibromatous proliferative disorders. They represent less than 3% of all soft tissue sarcoma and are multifocal in approximately 10% of cases. However, there are only a few cases in the literature describing 18F-FDG PET/CT and 99mTc-MDP bone scan features of extra-abdominal desmoid fibromas, and all were solitary bone lesions. Herein, we presented a unique case of multifocal desmoid fibromatosis of bone illustrating the prospective value of 18F-FDG PET/CT and 99mTc-MDP bone scan in the evaluation of desmoid tumors.

Skeletal involvement in Erdheim-Chester disease: Multimodality imaging features and association with the BRAFV600E mutation

ObjectiveThe aim of this study was to characterize the distribution of skeletal involvement in Erdheim-Chester disease (ECD) by using radiography, computed tomography (CT), 18F-FDG positron emission tomography/computed tomography (PET/CT), and bone scans, as well as looking for associations with the BRAFV600E mutation. Material and methodsProspective study of 50 consecutive patients with biopsy-confirmed ECD who had radiographs, CT, 18F-FDG PET/CT, and Tc-99m MDP bone scans. At least two experienced radiologists with expertise in the relevant imaging studies analyzed the images. Summary statistics were expressed as the frequency with percentages for categorical data. Fisher's exact test, as well as odds ratios (OR) with 95 % confidence intervals (CI), were used to link imaging findings to BRAFV600E mutation. The probability for co-occurrence of bone involvement at different locations was calculated and graphed as a heat map. ResultsAll 50 cases revealed skeletal involvement at different regions of the skeleton. The BRAFV600E mutation, which was found in 24 patients, was correlated with femoral and tibial involvement on 18F-FDG PET/CT and bone scan. The appearance of changes on the femoral, tibial, fibular, and humeral involvement showed correlation with each other based on heat maps of skeletal involvement on CT. ConclusionThis study reports the distribution of skeletal involvement in a cohort of patients with ECD. CT is able to detect the majority of ECD skeletal involvement. Considering the complementary nature of information from different modalities, imaging of ECD skeletal involvement is optimized by using a multi-modality strategy.

A rare clinical presentation of lung cancer: two cases of solitary digital metastasis on Tc-99m MDP bone scan

BackgroundAcrometastases are accounted for a very small proportion of bone metastases. Lung cancer is the most common acrometastasis origin, and it often has a poor prognosis. The aim of the present cases is to describe the probability of an acrometastasis in the differential diagnosis of finger lesions and to emphasize the importance of taking local views of extremity of complaint for proper interpretation in such patients.Case presentationHere we reported two patients with metastases to the fingers with occult primary lung carcinoma and a history of prior lung malignancy, respectively. First case was a 58-year-old man with history of pain and swelling in the fourth finger of his left hand. He underwent an amputation from the metacarpophalangeal level and the pathological diagnosis was metastatic NSCLC. The second case was a 65-year-old ex-smoker man with a history of prior lung cancer (adenocarcinoma) suffered from a swollen, erythematous, painful tip of the right third finger. Phalangectomy was performed and the histological examination of the amputated part revealed the presence of a metastatic differentiated carcinoma of pulmonary origin.ConclusionsWhen assessing the masses located at fingers, possibility of a solitary metastatic lung lesion should be considered.

A Unique Case of Familial Expansile Osteolysis: Findings on 99mTc-MDP Bone Scan.

Familial expansile osteolysis is an exceedingly rare autosomal dominant bone dysplasia, which can have overlapping features with Paget disease and expansile skeletal hyperphosphatasia. We present a novel case of familial expansile osteolysis evaluated on 99mTc-MDP bone scan with correlative radiographs and CT.

Comparison of Diagnostic Value between 99mTechnetium-Methylene Diphosphate Bone Scan and 99mTechnetium-Prostate-specific Membrane Antigen Scan in Patients with Prostate Cancer with Osseous Metastases.

Prostate cancer (PCa) ranks as the second most prevalent cancer among men globally. The utilization of efficient and cost-effective diagnostic and therapeutic approaches holds paramount importance in the diagnosis and treatment of these patients, significantly impacting treatment outcomes. This study focuses on the investigation and comparison of two commonly employed scans within the treatment process for these patients. In this prospective study, which spanned over 2 years, 40 patients diagnosed with PCa underwent examination using two scans: 99m Technetium-Prostate-specific Membrane Antigen (99mTC-PSMA) Scan and between Technetium-Methylene Diphosphate (99mTC-MDP) Bone Scan. The findings of these scans were then compared with each other, as well as with the results obtained from magnetic resonance imaging and the prostate-specific antigen level. The analysis of the results was conducted utilizing SPSS 22 software, and descriptive statistical methods were employed to present the findings. In this prospective study, the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the 99mTC-MDP Bone Scan were found to be 88.2%, 83.3%, 96.7%, 55.5%, and 87.5%, respectively. Similarly, for the 99mTC-PSMA Scan, the corresponding values were 94.1%, 83.3%, 96.4%, 83.3%, and 92.5%, respectively. Based on the findings of this study, it can be concluded that the diagnostic accuracy of the 99mTC-PSMA Scan is marginally higher compared to the 99mTC-MDP Bone Scan. Therefore, for patients who are limited to only one scan, the 99mTC-PSMA Scan appears to be the preferable choice.

Investigation of the Effect of Tissue Differentiation of Cancerous Tissues on the Diagnostic Accuracy of 99mTc-PSMA Scan and 99mTc-MDP Bone Scan in Patients with Prostate Cancer with Bone Metastases

Background and Objective: Prostate cancer is currently the second most common cancer among men worldwide. Given the prevalence of this disease and the costs imposed on society for its diagnosis and treatment, awareness of diagnostic and therapeutic modalities, and factors influencing their outcomes is of particular importance. Materials and Methods: This prospective study aimed to investigate the diagnostic accuracy of 99mTc- PSMA scan and 99mTc-MDP Bone scan in 40 patients with prostate cancer and bone metastases. The study was conducted between 2020 and 2023, and the results were compared based on the tissue differentiation of cancerous tissues. Results: Data analysis revealed that the diagnostic accuracy of 99mTc- PSMA scan and 99mTc-MDP Bone scan for grade groups 1-5 ranged from 95.4% to 100% and 95.4% to 100%, respectively. However, none of the results were statistically significant. Specifically, the 99mTc- PSMA scan demonstrated diagnostic accuracy percentages of 100%, 98.7%, 96.1%, 96.6%, and 95.4%, respectively, for grade groups 1 to 5. Similarly, the diagnostic accuracy of 99mTc-MDP Bone scan for grade groups 1 to 5 was 100%, 96.3%, 98.7%, 96.6%, and 95.4%, respectively. Conclusion: The statistical analysis of the data suggests that tissue differentiation of prostate cancer does not impact the diagnostic accuracy of 99mTc- PSMA scan and 99mTc-MDP Bone scan. Moreover, the Gleason score of tissue samples did not affect the differentiation of cancerous tissues by the scans. Therefore, the findings suggest that 99mTc- PSMA scan and 99mTc-MDP Bone scan can provide accurate diagnostic results for prostate cancer patients with bone metastases, regardless of the tissue differentiation or Gleason score.

Head-to-head comparison of 68Ga-PSMA-11 PET with 99mTc-MDP bone scan for detection of bone disease in patients with prostate cancer with biochemical progression during ADT: A single center prospective study.

e17072 Background: 68Ga-PSMA-11 PET/CT (PSMA-PET) was approved by the U.S. Food and Drug Administration in patients with prostate cancer (PCa) at primary staging or biochemical recurrence. A head-to-head comparison between PSMA-PET and conventional imaging (99mTc-MDP bone scan [BS] and CT) in men with advanced prostate cancer was not performed. We aimed to compare the detection rate of bone disease for PSMA-PET vs BS in men with PCa and with biochemical progression during androgen deprivation therapy (ADT). Methods: This was a prospective single-center, open-label, single-arm, head-to-head comparison, prospective phase 2 study (NCT04928820). A sample size of 102 men was required to achieve an 80.3% power to detect a difference of 12% positivity rate of bone disease in favor of PSMA-PET vs BS (35% vs 23%). Men with i) biopsy-proved PCa, ii) who had rising PSA levels on 2 successive occasions ≥1 week apart, iii) were receiving treatment with hormonal therapy, iii) and had an absolute PSA value ≥1 ng/ml were eligible. Men who were enrolled received PSMA-PET and bone scan within 30 days. The primary endpoint was detection rate of bone disease for PSMA-PET vs BS. Secondary endpoint was the number of bone lesions detected by PSMA-PET vs BS. Number of lesions was categorized into: 0 vs 1 vs 2 vs 3 vs 4 vs 5 vs &gt; 5. A p value &lt; 0.05 was considered statistically significant. Results: 22 men were enrolled between July 8, 2021 and June 9, 2022. The median patients age was 71 years (range: 56-94). The median time between scans was 12 days (range: 1-29). The median PSA value was 9.5 ng/ml (range: 1.2 – 1717). 11/22 (11%) patients had hormone-sensitive PCa, while 11/22 (50%) had castration-resistant PCa prior to receiving the scans. The positivity rate for bone disease was equal for PSMA-PET and BS in all cases: 7/22 (32%) patients had negative scans on both imaging modalities and 15 (68%) had ≥1 bone lesion detected on both imaging modalities (p = 1.00). In 15/22 (68%) men, both imaging modalities showed equal number of bone lesions: 0 lesions in 7/22 (32%) men and &gt; 5 lesions in 8/22 (36%) men. In 3/22 (14%) men BS showed higher number of lesions, while in 4/22 (18%) men PSMA-PET showed higher number of lesions. No statistical difference was noticed between PSMA-PET and BS in number of bone lesions detected (p &gt; 0.05). The trial was terminated early since these preliminary results gave already a 95% confidence interval of 81-100% for equivalent positivity rate of bone disease between PSMA-PET and BS. Conclusions: In this prospective study of patients with prostate cancer with rising PSA levels under hormonal therapy, 68Ga-PSMA-11 PET and 99mTc-MDP bone scan had similar detection rate for bone disease. Further studies investigating similar comparison between PSMA-PET and BS in clinically-relevant selected patient population are warranted. Clinical trial information: NCT04928820 .

Skeletal standardized uptake values obtained using quantitative SPECT/CT for the detection of bone metastases in patients with lung adenocarcinoma.

To assess the utility of skeletal standardized uptake values (SUVs) obtained using quantitative single-photon emission computed tomography/computed tomography (SPECT/CT) in differentiating bone metastases from benign lesions, particularly in patients with lung adenocarcinoma. Patients with lung adenocarcinoma who had undergone whole-body Tc-99m methyl-diphosphonate (99mTc-MDP) bone scans and received late phase SPECT/CT were retrospectively analyzed in this study. The maximum SUV (SUVmax); Hounsfield units (HUs); and volumes of osteoblastic, osteolytic, mixed, CT-negative metastatic and benign bone lesions, and normal vertebrae were compared. Receiver operating characteristic curves were used to determine the optimal cutoff SUVmax between metastatic and benign lesions as well as the cutoff SUVmax between CT-negative metastatic lesions and normal vertebrae. The linear correlation between SUVmax and HUs of metastatic lesions as well as that between SUVmax and the volume of all bone lesions were investigated. A total of 252 bone metastatic lesions, 140 benign bone lesions, and 199 normal vertebrae from 115 patients with lung adenocarcinoma were studied (48 males, 67 females, median age: 59 years). Metastatic lesions had a significantly higher SUVmax (23.85 ± 14.34) than benign lesions (9.67 ± 7.47) and normal vertebrae (6.19 ± 1.46; P < 0.0001). The SPECT/CT hotspot of patients with bone metastases could be distinguished from benign lesions using a cutoff SUVmax of 11.10, with a sensitivity of 87.70% and a specificity of 80.71%. The SUVmax of osteoblastic (29.16 ± 16.63) and mixed (26.62 ± 14.97) lesions was significantly greater than that of osteolytic (15.79 ± 5.57) and CT-negative (16.51 ± 6.93) lesions (P < 0.0001, P = 0.0003, and 0.002). SUVmax at the cutoff value of 8.135 could distinguish CT-negative bone metastases from normal vertebrae, with a sensitivity of 100.00% and a specificity of 91.96%. SUVmax showed a weak positive linear correlation with HUs in all bone metastases and the volume of all bone lesions. SUVmax of quantitative SPECT/CT is a useful index for distinguishing benign bone lesions from bone metastases in patients with lung adenocarcinoma, particularly in the diagnosis of CT-negative bone metastases, but other factors that may affect SUVmax should be considered.

Osteopoikilosis mimicking osteoblastic bone mets: A Case report

Background: Osteopoikilosis is a benign, uncommon disorder that is inherited by the autosomal dominant gene. Multiple benign enostoses are present in this specific kind of sclerosing skeletal dysplasia, which can be mistaken for osteoblastic skeletal metastases. Case Presentation: We present here a case of 50-year-old male patient with pain in lower back for 3 months. His pelvic X-ray showed few sclerotic rounded lesions in ilium, acetabulum and proximal femur. His MRI pelvis showed T1WI and T2WI hypo intense focal lesions in ilium and acetabulum. His 99mTc MDP bone scan was done showing no focal abnormal uptake in lesion reported on pelvic X-ray and MRI. These features are suggestive of Osteopoikilosis, ruling out osteoblastic skeletal metastasis. Conclusion: Osteopoikilosis is usually an incidental finding on radiograph. Both x-ray and MRI findings can mimic skeletal metastasis, but a normal bone scan can rule out metastasis and is useful if metastatic disease is thought to be a possibility.

99mTc-MDP bone scan in the diagnosis of Erdheim-Chester disease

nil

99m-Tc MDP Bone Scan Image Enhancement using Pipeline Application of Dynamic Stochastic Resonance Algorithm and Block-Matching 3D Filter.

In this pilot study, we have proposed and evaluated pipelined application of the dynamic stochastic resonance (DSR) algorithm and block-matching 3D (BM3D) filter for the enhancement of nuclear medicine images. The enhanced images out of the pipeline were compared with the corresponding enhanced images obtained using individual applications of DSR and BM3D algorithm. Twenty 99m-Tc MDP bone scan images acquired on SymbiaT6 SPECT/CT gamma camera system fitted with low-energy high-resolution collimators were exported in DICOM format to a personal computer and converted into PNG format. These PNG images were processed using the proposed algorithm in MATLAB. Two nuclear medicine physicians visually compared each input and its corresponding three enhanced images to select the best-enhanced image. The image quality metrics (Brightness, Global Contrast Factor (GCF), Contrast per pixel (CPP), and Blur) were used to assess the image quality objectively. The Wilcoxon signed test was applied to find a statistically significant difference in Brightness, GCF, CPP, and Blur of enhanced and its input images at a level of significance. Images enhanced using the pipelined application of SR and BM3D were selected as the best images by both nuclear medicine physicians. Based on Brightness, Global Contrast Factor (GCF), CPP, and Blur, the image quality of our proposed pipeline was significantly better than enhanced images obtained using individual applications of DSR and BM3D algorithm. The proposed method was found to be very successful in enhancing details in the low count region of input images. The enhanced images were bright, smooth, and had better target-to-background ratio compared to input images. The pipelined application of DSR and BM3D algorithm produced enhancement in nuclear medicine images having following characteristics: bright, smooth, better target-to-background ratio, and improved visibility of details in the low count regions of the input image, as compared to individual enhancements by application of DSR or BM3D algorithm.

Compression of 99mTc Methylene Diphosphonate Bone Scan Images using Discrete Cosine Transformation.

The objective of this study was to find the optimum value of threshold for compression of 99mTc-methylene diphosphonate (MDP) bone scan images using discrete cosine transformation (DCT). DCT was applied to 51 99mTc-MDP bone scan images and then the image of logarithmic value of DCT coefficients was inspected to determine the threshold. After inspecting the number of images of DCT coefficients, we estimated the appropriate value of the threshold to be 10. After the application of threshold = 10, compressed image was reconstructed by applying the inverse DCT. Compression factor was calculated by dividing the nonzero element after thresholding to the nonzero element before thresholding DCT coefficients. Nuclear medicine physicians compared the compressed images with its input images and labeled them as acceptable or unacceptable. During comparison of input and compressed images, we considered points such as smoothening, blocking artifacts, body contour, gap between closely placed lesions, and detectability of lesion. Forty-four compressed images (out of 51 images) obtained at threshold 10 were acceptable to Nuclear Medicine Physician (NMP). Compressed images were less noisy compared to its input image. Compression factor was found to be 13.03 ± (minimum = 2.71, maximum = 42.92). The optimum value of threshold for compression of 99mTc-MDP bone scan images was found to be 10, and the average compression factor achieved was equal to 13.03 (92.30%).

Diagnostic &amp; prognostic impact of 18F-NaF PET/CT versus 99mTc-MDP bone scan in detection of bone metastases

Purpose: To assess the role of 18F-NaF PET/CT in the detection of metastatic bone disease compared to 99mTc-MDP bone scan (+/-SPECT/CT). Methods: 64 adult patients with locally advanced primary tumor were enrolled in this study. All patients underwent pretherapy 18F-NaF PET/CT and 99mTc-MDP bone scan. Results: Among the 64 patients 18F-NaF PET/CT revealed positive bone metastases in 26 patients, only 19 of them have positive results in 99mTc-MDP bone scan, while the remaining 7 patients were falsely negative in 99mTc-MDP bone scan. On the other hand 18F-NaF PET/CT diagnosed 38 patients free of osseous metastases, 5 patients of them were falsely diagnosed having osseous metastases by 99mTc-MDP bone scan. None of patient has positive bone metastases by 99mTc-MDP &amp; negative 18F-NaF PET/CT for bone metastases in our study group. The overall results revealed significant higher sensitivity for 18F-NaF PET/CT (100%) compared to 99mTc-MDP bone scan (73.08%) (P&lt;0.05) as well as higher specificity for 18F-NaF PET/CT (100%) compared to 99mTc-MDP bone scan (86.8%) (P&lt;0.05). Conclusion: 18F-NaF PET/CT is a high-quality skeletal imaging with convenient diagnostic performance in either lytic or sclerotic bone lesions surpassing that of Tc99m MDP, with lower equivocal interpretations.

Clinical value of ultrasound for the evaluation of local recurrence of primary bone tumors.

BackgroundEarly detection of local recurrence would improve the survival rate of patients with recurrent bone tumors. There is still no consensus on how to follow up after surgery of primary malignant bone tumors. Therefore, the purpose of this study is to evaluate the diagnostic value of ultrasound (US) for local recurrence after limb salvage by comparing it with other imaging modalities.MethodsWe retrospectively reviewed the medical records of patients who were regularly examined by US in our hospital after primary bone tumor surgery from January 2016 to December 2019, some of which underwent x-ray, computed tomography (CT), or 99mTc-MDP bone scan. Recurrence was determined by pathologic confirmation. The cases were considered a true negative for no recurrence if no clinical or pathologic evidence for recurrence was found at least 6 months after the US examination. The Chi-square test or Fisher exact test was used to compare categorical data. p-values < 0.0083 were considered statistically significant.ResultsA total of 288 cases were finally enrolled in our research, including 66 cases with pathologic results. The sensitivity of US was 95.0%, higher than that of x-ray (29.6%) (p = 0.000). The accuracy of US was 96.9%, higher than that of x-ray (85.6%) (p = 0.000).ConclusionAs a nonradiative and cost-effective examination, US may be used as a routine imaging method for postoperative surveillance of primary bone tumors, especially those with metal implants, if more multicenter prospective studies can be done in the future.

Automated Detection of Poor-Quality Scintigraphic Images Using Machine Learning.

Objective In the present study, we have used machine learning algorithm to accomplish the task of automated detection of poor-quality scintigraphic images. We have validated the accuracy of our machine learning algorithm on 99m Tc-methyl diphosphonate ( 99m Tc-MDP) bone scan images. Materials and Methods Ninety-nine patients underwent 99mTC-MDP bone scan acquisition twice at two different acquisition speeds, one at low speed and another at double the speed of the first scan, with patient lying in the same position on the scan table. The low-speed acquisition resulted in good-quality images and the high-speed acquisition resulted in poor-quality images. The principal component analysis (PCA) of all the images was performed and the first 32 principal components (PCs) were retained as feature vectors of the image. These 32 feature vectors of each image were used for the classification of images into poor or good quality using machine learning algorithm (multivariate adaptive regression splines [MARS]). The data were split into two sets, that is, training set and test set in the ratio of 60:40. Hyperparameter tuning of the model was done in which five-fold cross-validation was performed. Receiver operator characteristic (ROC) analysis was used to select the optimal model using the largest value of area under the ROC curve. Sensitivity, specificity, and accuracy for the classification of poor- and good-quality images were taken as metrics for the performance of the algorithm. Result Accuracy, sensitivity, and specificity of the model in classifying poor-quality and good-quality images were 93.22, 93.22, and 93.22%, respectively, for the training dataset and 86.88, 80, and 93.7%, respectively, for the test dataset. Conclusion Machine learning algorithms can be used to classify poor- and good-quality images with good accuracy (86.88%) using 32 PCs as the feature vector and MARS as the classification model.