The utility of a deep learning-based algorithm for bone scintigraphy in patient with prostate cancer

Evaluation of jaw pathologies of patients with medication-related osteonecrosis of the jaw using a computer program to assess the bone scan index: comparison of standardized uptake values with bone SPECT/CT

OBJECTIVES

The aim of this study is to investigate the jaw pathologies of patients with medication-related osteonecrosis of the jaw (MRONJ) using a computer program to assess the bone scan index (BSI), especially comparison of standardized uptake values (SUVs) with bone single-photon emission-computed tomography/computed tomography (SPECT/CT).

METHODS

Sixty-three patients with MRONJ underwent bone SPECT/CT in this prospective study. BSI and high-risk hot spot as bone metastases in the patients with MRONJ were evaluated using a computer program for BSI that scanned SPECT/CT and automatically defined the data. The maximum and mean SUVs with SPECT/CT were obtained using commercially available software. Statistical analyses were performed by Pearson chi-square test, Mann-Whitney U -test, or one-way analysis of variance with Tukey's honestly significant difference test. A P value lower than 0.05 was considered statistically significant.

RESULTS

The maximum and mean SUVs for a high-risk hot spot of the jaw with MRONJ [28.2 ± 10.2 and 11.7 ± 3.8; n  = 6 (6/63 : 9.5%)] were significantly higher than those for a low-risk hot spot [18.5 ± 6.4 and 6.2 ± 1.9; n  = 23 (23/63 : 36.5%)] and no-risk hot spot [14.2 ± 9.4 and 5.3 ± 5.1; n  = 34 (34/63 : 54.0%)], respectively.

CONCLUSION

The computer program for BSI indicated that 9.5% of the jaw with MRONJ were false positive of bone metastases. The study suggests that high-risk hot spots of the jaw with MRONJ depend on the SUVs.

Artificial Intelligence in Detection, Management, and Prognosis of Bone Metastasis: A Systematic Review

BACKGROUND

Metastasis commonly occur in the bone tissue. Artificial intelligence (AI) has become increasingly prevalent in the medical sector as support in decision-making, diagnosis, and treatment processes. The objective of this systematic review was to assess the reliability of AI systems in clinical, radiological, and pathological aspects of bone metastases.

METHODS

We included studies that evaluated the use of AI applications in patients affected by bone metastases. Two reviewers performed a digital search on 31 December 2023 on PubMed, Scopus, and Cochrane library and extracted authors, AI method, interest area, main modalities used, and main objectives from the included studies.

RESULTS

We included 59 studies that analyzed the contribution of computational intelligence in diagnosing or forecasting outcomes in patients with bone metastasis. Six studies were specific for spine metastasis. The study involved nuclear medicine (44.1%), clinical research (28.8%), radiology (20.4%), or molecular biology (6.8%). When a primary tumor was reported, prostate cancer was the most common, followed by lung, breast, and kidney.

CONCLUSIONS

Appropriately trained AI models may be very useful in merging information to achieve an overall improved diagnostic accuracy and treatment for metastasis in the bone. Nevertheless, there are still concerns with the use of AI systems in medical settings. Ethical considerations and legal issues must be addressed to facilitate the safe and regulated adoption of AI technologies. The limitations of the study comprise a stronger emphasis on early detection rather than tumor management and prognosis as well as a high heterogeneity for type of tumor, AI technology and radiological techniques, pathology, or laboratory samples involved.

Evaluation of two-dimensional total bone uptake (2D-TBU) and bone scan index (BSI) extracted from active bone metastatic burden on the bone scintigraphy in patients with radium-223 treatment

OBJECTIVE

Radium-223 is a first alpha-emitting radionuclide treatment for metastatic castration-resistant prostate cancer (mCRPC) patients with bone metastases. Although the spread-based bone scan index (BSI) and novel index of the intensity-based two-dimensional total bone uptake (2D-TBU) from bone scintigraphy may provide useful input in radium-223 treatment, they have not been evaluated in detail yet. This study aimed to fill this gap by evaluating BSI and 2D-TBU in patients treated with radium-223.

METHODS

Twenty-seven Japanese patients with mCRPC treated with radium-223 were retrospectively analyzed. The patients were evaluated via blood tests and bone scans at baseline and 3 cycles intervals of treatment. BSI and 2D-TBU were analyzed via VSBONE BSI in terms of correlations, response to radium-223 treatment, association with treatment completion, and the Kaplan-Meier survival analysis was performed.

RESULTS

Nineteen patients (70.4%) completed six cycles of radium-223 treatment, whereas eight patients (29.6%) did not complete the treatment regimen. A significant difference in baseline BSI and 2D-TBU was observed between these groups of patients. Both BSI and 2D-TBU were highly correlated (r = 0.96, p < 0.001). Univariate analysis showed an association between radium-223 completion in median BSI and 2D-TBU values (p = 0.015) and completion percentage differences (91.7% vs. 45.5%; p = 0.027). The Kaplan-Meier product limit estimator showed that the median overall survival was 25.2 months (95% CI 14.0-33.6 months) in the completion group and 7.5 months (95% CI 3.3-14.2 months) in the without completion group (p < 0.001). The overall survival based on median cutoff levels showed a significant difference in 2D-TBU (p = 0.007), but not in BSI (p = 0.15).

CONCLUSIONS

The 2D-TBU may offer advantages over BSI in classifying patients towards radium-223 treatment based on the degree of progression of bone metastases. This study supports the importance of preliminary assessment of bone metastasis status using BSI and 2D-TBU extracted from VSBONE BSI for radium-223 treatment decisions.

Artificial intelligence-based analysis of whole-body bone scintigraphy: The quest for the optimal deep learning algorithm and comparison with human observer performance

PURPOSE

Whole-body bone scintigraphy (WBS) is one of the most widely used modalities in diagnosing malignant bone diseases during the early stages. However, the procedure is time-consuming and requires vigour and experience. Moreover, interpretation of WBS scans in the early stages of the disorders might be challenging because the patterns often reflect normal appearance that is prone to subjective interpretation. To simplify the gruelling, subjective, and prone-to-error task of interpreting WBS scans, we developed deep learning (DL) models to automate two major analyses, namely (i) classification of scans into normal and abnormal and (ii) discrimination between malignant and non-neoplastic bone diseases, and compared their performance with human observers.

MATERIALS AND METHODS

After applying our exclusion criteria on 7188 patients from three different centers, 3772 and 2248 patients were enrolled for the first and second analyses, respectively. Data were split into two parts, including training and testing, while a fraction of training data were considered for validation. Ten different CNN models were applied to single- and dual-view input (posterior and anterior views) modes to find the optimal model for each analysis. In addition, three different methods, including squeeze-and-excitation (SE), spatial pyramid pooling (SPP), and attention-augmented (AA), were used to aggregate the features for dual-view input models. Model performance was reported through area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity and was compared with the DeLong test applied to ROC curves. The test dataset was evaluated by three nuclear medicine physicians (NMPs) with different levels of experience to compare the performance of AI and human observers.

RESULTS

DenseNet121_AA (DensNet121, with dual-view input aggregated by AA) and InceptionResNetV2_SPP achieved the highest performance (AUC = 0.72) for the first and second analyses, respectively. Moreover, on average, in the first analysis, Inception V3 and InceptionResNetV2 CNN models and dual-view input with AA aggregating method had superior performance. In addition, in the second analysis, DenseNet121 and InceptionResNetV2 as CNN methods and dual-view input with AA aggregating method achieved the best results. Conversely, the performance of AI models was significantly higher than human observers for the first analysis, whereas their performance was comparable in the second analysis, although the AI model assessed the scans in a drastically lower time.

CONCLUSION

Using the models designed in this study, a positive step can be taken toward improving and optimizing WBS interpretation. By training DL models with larger and more diverse cohorts, AI could potentially be used to assist physicians in the assessment of WBS images.

Unassisted Clinicians Versus Deep Learning-Assisted Clinicians in Image-Based Cancer Diagnostics: Systematic Review With Meta-analysis

BACKGROUND

A number of publications have demonstrated that deep learning (DL) algorithms matched or outperformed clinicians in image-based cancer diagnostics, but these algorithms are frequently considered as opponents rather than partners. Despite the clinicians-in-the-loop DL approach having great potential, no study has systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification.

OBJECTIVE

We systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification.

METHODS

PubMed, Embase, IEEEXplore, and the Cochrane Library were searched for studies published between January 1, 2012, and December 7, 2021. Any type of study design was permitted that focused on comparing unassisted clinicians and DL-assisted clinicians in cancer identification using medical imaging. Studies using medical waveform-data graphics material and those investigating image segmentation rather than classification were excluded. Studies providing binary diagnostic accuracy data and contingency tables were included for further meta-analysis. Two subgroups were defined and analyzed, including cancer type and imaging modality.

RESULTS

In total, 9796 studies were identified, of which 48 were deemed eligible for systematic review. Twenty-five of these studies made comparisons between unassisted clinicians and DL-assisted clinicians and provided sufficient data for statistical synthesis. We found a pooled sensitivity of 83% (95% CI 80%-86%) for unassisted clinicians and 88% (95% CI 86%-90%) for DL-assisted clinicians. Pooled specificity was 86% (95% CI 83%-88%) for unassisted clinicians and 88% (95% CI 85%-90%) for DL-assisted clinicians. The pooled sensitivity and specificity values for DL-assisted clinicians were higher than for unassisted clinicians, at ratios of 1.07 (95% CI 1.05-1.09) and 1.03 (95% CI 1.02-1.05), respectively. Similar diagnostic performance by DL-assisted clinicians was also observed across the predefined subgroups.

CONCLUSIONS

The diagnostic performance of DL-assisted clinicians appears better than unassisted clinicians in image-based cancer identification. However, caution should be exercised, because the evidence provided in the reviewed studies does not cover all the minutiae involved in real-world clinical practice. Combining qualitative insights from clinical practice with data-science approaches may improve DL-assisted practice, although further research is required.

TRIAL REGISTRATION

PROSPERO CRD42021281372; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=281372.

Deep learning based identification of bone scintigraphies containing metastatic bone disease foci

PURPOSE

Metastatic bone disease (MBD) is the most common form of metastases, most frequently deriving from prostate cancer. MBD is screened with bone scintigraphy (BS), which have high sensitivity but low specificity for the diagnosis of MBD, often requiring further investigations. Deep learning (DL) - a machine learning technique designed to mimic human neuronal interactions- has shown promise in the field of medical imaging analysis for different purposes, including segmentation and classification of lesions. In this study, we aim to develop a DL algorithm that can classify areas of increased uptake on bone scintigraphy scans.

METHODS

We collected 2365 BS from three European medical centres. The model was trained and validated on 1203 and 164 BS scans respectively. Furthermore we evaluated its performance on an external testing set composed of 998 BS scans. We further aimed to enhance the explainability of our developed algorithm, using activation maps. We compared the performance of our algorithm to that of 6 nuclear medicine physicians.

RESULTS

The developed DL based algorithm is able to detect MBD on BSs, with high specificity and sensitivity (0.80 and 0.82 respectively on the external test set), in a shorter time compared to the nuclear medicine physicians (2.5 min for AI and 30 min for nuclear medicine physicians to classify 134 BSs). Further prospective validation is required before the algorithm can be used in the clinic.

Clinical Significance of the Highest Regional Bone Scan Index in Patients with Metastatic Castration-Resistant Prostate Cancer

Purpose

This study evaluated the clinical utility of the highest bone scan index (BSI), among other BSIs, for each bone metastatic site in patients with bone metastatic castration-resistant prostate cancer (bmCRPC).

Methods

Thirty patients, diagnosed with bmCRPC by bone scintigraphy, were included. Total BSI, the number of hot spots, and regional BSI on each hot spot from bone scintigraphy at diagnosis with bmCRPC were evaluated by VSBONE BSI®. Highest regional BSI was defined as the highest value among regional BSIs on each hot spot in each patient. Related factors to overall survival and skeletal-related events (SREs) were evaluated using the Cox proportional-hazards model.

Results

The median follow-up time from diagnosis with bmCRPC was 29.0 months. During this time, 24 patients died, of which 22 patients died from prostate cancer. On univariate analysis, alkaline phosphatase (ALP) [Hazard ratio (HR): 5.96, 95% confidence interval (CI): 2.05-17.3] and highest regional BSI (HR: 2.01, 95% CI: 1.17-7.05) had significant correlation with overall survival. On multivariate analysis, ALP (HR: 4.79, 95% CI: 1.61-14.2) had significant correlation with overall survival. SREs were found in eight patients. Only the highest regional BSI (HR: 9.99, 95% CI: 2.46-40.6) significantly correlated with SREs on univariate analysis.

Conclusion

Highest regional BSI may provide important information regarding prognosis and SREs in patients with bmCRPC.

Comparison of skeletal segmentation by deep learning-based and atlas-based segmentation in prostate cancer patients

OBJECTIVE

We aimed to compare the deep learning-based (VSBONE BSI) and atlas-based (BONENAVI) segmentation accuracy that have been developed to measure the bone scan index based on skeletal segmentation.

METHODS

We retrospectively conducted bone scans for 383 patients with prostate cancer. These patients were divided into two groups: 208 patients were injected with ^99mTc-hydroxymethylene diphosphonate processed by VSBONE BSI, and 175 patients were injected with ^99mTc-methylene diphosphonate processed by BONENAVI. Three observers classified the skeletal segmentations as either a "Match" or "Mismatch" in the following regions: the skull, cervical vertebrae, thoracic vertebrae, lumbar vertebrae, pelvis, sacrum, humerus, rib, sternum, clavicle, scapula, and femur. Segmentation error was defined if two or more observers selected "Mismatch" in the same region. We calculated the segmentation error rate according to each administration group and evaluated the presence of hot spots suspected bone metastases in "Mismatch" regions. Multivariate logistic regression analysis was used to determine the association between segmentation error and variables like age, uptake time, total counts, extent of disease, and gamma cameras.

RESULTS

The regions of "Mismatch" were more common in the long tube bones for VSBONE BSI and in the pelvis and axial skeletons for BONENAVI. Segmentation error was observed in 49 cases (23.6%) with VSBONE BSI and 58 cases (33.1%) with BONENAVI. VSBONE BSI tended that "Mismatch" regions contained hot spots suspected of bone metastases in patients with multiple bone metastases and showed that patients with higher extent of disease (odds ratio = 8.34) were associated with segmentation error in multivariate logistic regression analysis.

CONCLUSIONS

VSBONE BSI has a potential to be higher segmentation accuracy compared with BONENAVI. However, the segmentation error in VSBONE BSI occurred dependent on bone metastases burden. We need to be careful when evaluating multiple bone metastases using VSBONE BSI.

Convolutional neural networks for detection of transthyretin amyloidosis in 2D scintigraphy images

BACKGROUND

Transthyretin amyloidosis (ATTR) is a progressive disease which can be diagnosed non-invasively using bone avid [^99mTc]-labeled radiotracers. Thus, ATTR is also an occasional incidental finding on bone scintigraphy. In this study, we trained convolutional neural networks (CNN) to automatically detect and classify ATTR from scintigraphy images. The study population consisted of 1334 patients who underwent [^99mTc]-labeled hydroxymethylene diphosphonate (HMDP) scintigraphy and were visually graded using Perugini grades (grades 0-3). A total of 47 patients had visual grade ≥ 2 which was considered positive for ATTR. Two custom-made CNN architectures were trained to discriminate between the four Perugini grades of cardiac uptake. The classification performance was compared to four state-of-the-art CNN models.

RESULTS

Our CNN models performed better than, or equally well as, the state-of-the-art models in detection and classification of cardiac uptake. Both models achieved area under the curve (AUC) ≥ 0.85 in the four-class Perugini grade classification. Accuracy was good in detection of negative vs. positive ATTR patients (grade < 2 vs grade ≥ 2, AUC > 0.88) and high-grade cardiac uptake vs. other patients (grade < 3 vs. grade 3, AUC = 0.94). Maximum activation maps demonstrated that the automated deep learning models were focused on detecting the myocardium and not extracardiac features.

CONCLUSION

Automated convolutional neural networks can accurately detect and classify different grades of cardiac uptake on bone scintigraphy. The CNN models are focused on clinically relevant image features. Automated screening of bone scintigraphy images using CNN could improve the early diagnosis of ATTR.

Deep learning-based detection of parathyroid adenoma by 99mTc-MIBI scintigraphy in patients with primary hyperparathyroidism

OBJECTIVE

It is important to detect parathyroid adenomas by parathyroid scintigraphy with 99m-technetium sestamibi (^99mTc-MIBI) before surgery. This study aimed to develop and validate deep learning (DL)-based models to detect parathyroid adenoma in patients with primary hyperparathyroidism, from parathyroid scintigrams with ^99mTc-MIBI.

METHODS

DL-based models for detecting parathyroid adenoma in early- and late-phase parathyroid scintigrams were, respectively, developed and evaluated. The training dataset used to train the models was collected from 192 patients (165 adenoma cases, mean age: 64 years ± 13, 145 women) and the validation dataset used to tune the models was collected from 45 patients (30 adenoma cases, mean age: 67 years ± 12, 37 women). The images were collected from patients who were pathologically diagnosed with parathyroid adenomas or in whom no lesions could be detected by either parathyroid scintigraphy or ultrasonography at our institution from June 2010 to March 2019. The models were tested on a dataset collected from 44 patients (30 adenoma cases, mean age: 67 years ± 12, 38 women) who took scintigraphy from April 2019 to March 2020. The models' lesion-based sensitivity and mean false positive indications per image (mFPI) were assessed with the test dataset.

RESULTS

The sensitivity was 82% [95% confidence interval 72-92%] with mFPI of 0.44 for the scintigrams of the early-phase model and 83% [73-92%] with mFPI of 0.31 for the scintigrams of the delayed-phase model in the test dataset, respectively.

CONCLUSIONS

The DL-based models were able to detect parathyroid adenomas with a high sensitivity using parathyroid scintigraphy with 99m-technetium sestamibi.

Artificial intelligence for nuclear medicine in oncology

As in all other medical fields, artificial intelligence (AI) is increasingly being used in nuclear medicine for oncology. There are many articles that discuss AI from the viewpoint of nuclear medicine, but few focus on nuclear medicine from the viewpoint of AI. Nuclear medicine images are characterized by their low spatial resolution and high quantitativeness. It is noted that AI has been used since before the emergence of deep learning. AI can be divided into three categories by its purpose: (1) assisted interpretation, i.e., computer-aided detection (CADe) or computer-aided diagnosis (CADx). (2) Additional insight, i.e., AI provides information beyond the radiologist's eye, such as predicting genes and prognosis from images. It is also related to the field called radiomics/radiogenomics. (3) Augmented image, i.e., image generation tasks. To apply AI to practical use, harmonization between facilities and the possibility of black box explanations need to be resolved.

Detection and Segmentation of Pelvic Bones Metastases in MRI Images for Patients With Prostate Cancer Based on Deep Learning

Objective

To establish and evaluate the 3D U-Net model for automated segmentation and detection of pelvic bone metastases in patients with prostate cancer (PCa) using diffusion-weighted imaging (DWI) and T1 weighted imaging (T1WI) images.

Methods

The model consisted of two 3D U-Net algorithms. A total of 859 patients with clinically suspected or confirmed PCa between January 2017 and December 2020 were enrolled for the first 3D U-Net development of pelvic bony structure segmentation. Then, 334 PCa patients were selected for the model development of bone metastases segmentation. Additionally, 63 patients from January to May 2021 were recruited for the external evaluation of the network. The network was developed using DWI and T1WI images as input. Dice similarity coefficient (DSC), volumetric similarity (VS), and Hausdorff distance (HD) were used to evaluate the segmentation performance. Sensitivity, specificity, and area under the curve (AUC) were used to evaluate the detection performance at the patient level; recall, precision, and F1-score were assessed at the lesion level.

Results

The pelvic bony structures segmentation on DWI and T1WI images had mean DSC and VS values above 0.85, and the HD values were <15 mm. In the testing set, the AUC of the metastases detection at the patient level were 0.85 and 0.80 on DWI and T1WI images. At the lesion level, the F1-score achieved 87.6% and 87.8% concerning metastases detection on DWI and T1WI images, respectively. In the external dataset, the AUC of the model for M-staging was 0.94 and 0.89 on DWI and T1WI images.

Conclusion

The deep learning-based 3D U-Net network yields accurate detection and segmentation of pelvic bone metastases for PCa patients on DWI and T1WI images, which lays a foundation for the whole-body skeletal metastases assessment.

Radiomics for Identification and Prediction in Metastatic Prostate Cancer: A Review of Studies

Metastatic Prostate Cancer (mPCa) is associated with a poor patient prognosis. mPCa spreads throughout the body, often to bones, with spatial and temporal variations that make the clinical management of the disease difficult. The evolution of the disease leads to spatial heterogeneity that is extremely difficult to characterise with solid biopsies. Imaging provides the opportunity to quantify disease spread. Advanced image analytics methods, including radiomics, offer the opportunity to characterise heterogeneity beyond what can be achieved with simple assessment. Radiomics analysis has the potential to yield useful quantitative imaging biomarkers that can improve the early detection of mPCa, predict disease progression, assess response, and potentially inform the choice of treatment procedures. Traditional radiomics analysis involves modelling with hand-crafted features designed using significant domain knowledge. On the other hand, artificial intelligence techniques such as deep learning can facilitate end-to-end automated feature extraction and model generation with minimal human intervention. Radiomics models have the potential to become vital pieces in the oncology workflow, however, the current limitations of the field, such as limited reproducibility, are impeding their translation into clinical practice. This review provides an overview of the radiomics methodology, detailing critical aspects affecting the reproducibility of features, and providing examples of how artificial intelligence techniques can be incorporated into the workflow. The current landscape of publications utilising radiomics methods in the assessment and treatment of mPCa are surveyed and reviewed. Associated studies have incorporated information from multiple imaging modalities, including bone scintigraphy, CT, PET with varying tracers, multiparametric MRI together with clinical covariates, spanning the prediction of progression through to overall survival in varying cohorts. The methodological quality of each study is quantified using the radiomics quality score. Multiple deficits were identified, with the lack of prospective design and external validation highlighted as major impediments to clinical translation. These results inform some recommendations for future directions of the field.