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

2021 ◽  
Vol 11 ◽  
Author(s):  
Xiang Liu ◽  
Chao Han ◽  
Yingpu Cui ◽  
Tingting Xie ◽  
Xiaodong Zhang ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Deep Learning ◽  
Bone Metastases ◽  
Model Development ◽  
Whole Body ◽  
Pelvic Bone ◽  
Skeletal Metastases ◽  
Dice Similarity Coefficient ◽  
Patient Level ◽  
Lesion Level

ObjectiveTo 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.MethodsThe 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.ResultsThe 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.ConclusionThe 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.

scholarly journals Kezdeti tapasztalatok a 99mTc-PSMA-SPECT/CT-vel prosztatarákos betegekben

2018 ◽  
Vol 159 (35) ◽  
pp. 1433-1440
Author(s):  
István Farkas ◽  
Zsuzsanna Besenyi ◽  
Anikó Maráz ◽  
Zoltán Bajory ◽  
András Palkó ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Bone Metastases ◽  
Bone Scintigraphy ◽  
Transmembrane Protein ◽  
Tracer Uptake ◽  
Whole Body ◽  
Primary Prostate Cancer ◽  
Cancer Tumor ◽  
Visceral Metastases ◽  
Male Patients

Abstract: Introduction: The prostate-specific membrane antigen (PSMA) is a transmembrane protein, that is highly expressed on the surface of prostate cancer cells. In the last few years, several PSMA-specific ligands have been developed, that can be successfully used to detect primary prostate cancer, tumor recurrences and metastases as well. Aim: The goal of our work was to examine the clinical application of a 99mtechnetium-labeled PSMA-radiopharmaceutical as part of the routine diagnostics of prostate cancer. Method: We examined 15 male patients with verified prostate adenocarcinoma with suspicion of progression or recurrence of the disease. We performed whole-body PSMA-SPECT/CTs and multiparametric MRIs of the prostate and the pelvic regions within a week. We used 99mTc-mas3-y-nal-k(Sub-KuE) for the PSMA-SPECT scans. The images were visually evaluated by independent observers. The results were compared with the follow-up bone scintigraphies as well. Results: Twenty-two PSMA-positive lesions were found. Nine of them were localized outside, 13 were within the MRI’s field of view. From these 13 lesions, 7 matched with the SPECT/CT results and in 5 cases the MRI images showed no abnormalities. In one case, bone metastasis was suspected on the MRI scan but there was no corresponding pathological tracer uptake on the SPECT images. In two patients, none of the examinations showed signs of prostate malignancy. Four patients had PSMA-positive bone metastases. One of them had a matching PSMA/SPECT and bone scintigraphy result and in one case the PSMA examination showed metastasis in contrast to the negative bone scintigraphy. Conclusion: PSMA-SPECT/CT with 99mTc-mas3-y-nal-k(Sub-KuE) is a promising diagnostic tool. This technique is capable of visualizing bone metastases and it can detect local recurrences and visceral metastases as well. Orv Hetil. 2018; 159(35): 1433–1440.

scholarly journals Classification of Clinically Significant Prostate Cancer on Multi-Parametric MRI: A Validation Study Comparing Deep Learning and Radiomics

Cancers ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 12
Author(s):  
Jose M. Castillo T. ◽  
Muhammad Arif ◽  
Martijn P. A. Starmans ◽  
Wiro J. Niessen ◽  
Chris H. Bangma ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Deep Learning ◽  
Characteristic Curve ◽  
Model Development ◽  
Learning Model ◽  
Multiparametric Mri ◽  
Data Sets ◽  
Data Set ◽  
Test Sets ◽  
Deep Learning Model

The computer-aided analysis of prostate multiparametric MRI (mpMRI) could improve significant-prostate-cancer (PCa) detection. Various deep-learning- and radiomics-based methods for significant-PCa segmentation or classification have been reported in the literature. To be able to assess the generalizability of the performance of these methods, using various external data sets is crucial. While both deep-learning and radiomics approaches have been compared based on the same data set of one center, the comparison of the performances of both approaches on various data sets from different centers and different scanners is lacking. The goal of this study was to compare the performance of a deep-learning model with the performance of a radiomics model for the significant-PCa diagnosis of the cohorts of various patients. We included the data from two consecutive patient cohorts from our own center (n = 371 patients), and two external sets of which one was a publicly available patient cohort (n = 195 patients) and the other contained data from patients from two hospitals (n = 79 patients). Using multiparametric MRI (mpMRI), the radiologist tumor delineations and pathology reports were collected for all patients. During training, one of our patient cohorts (n = 271 patients) was used for both the deep-learning- and radiomics-model development, and the three remaining cohorts (n = 374 patients) were kept as unseen test sets. The performances of the models were assessed in terms of their area under the receiver-operating-characteristic curve (AUC). Whereas the internal cross-validation showed a higher AUC for the deep-learning approach, the radiomics model obtained AUCs of 0.88, 0.91 and 0.65 on the independent test sets compared to AUCs of 0.70, 0.73 and 0.44 for the deep-learning model. Our radiomics model that was based on delineated regions resulted in a more accurate tool for significant-PCa classification in the three unseen test sets when compared to a fully automated deep-learning model.

68Ga-PSMA-PET/CT in comparison with 18F-fluoride-PET/CT and whole-body MRI for the detection of bone metastases in patients with prostate cancer: a prospective diagnostic accuracy study

2018 ◽  
Vol 29 (3) ◽  
pp. 1221-1230 ◽  
Author(s):  
Eva Dyrberg ◽  
Helle W. Hendel ◽  
Tri Hien Viet Huynh ◽  
Tobias Wirenfeldt Klausen ◽  
Vibeke B. Løgager ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Diagnostic Accuracy ◽  
Bone Metastases ◽  
Whole Body ◽  
Diagnostic Accuracy Study ◽  
Whole Body Mri ◽  
Psma Pet ◽  
Pet Ct ◽  
Accuracy Study ◽  
18F Fluoride

Whole-body MRI (WB-MRI) versus axial skeleton MRI (AS-MRI) to detect and measure bone metastases in prostate cancer (PCa)

2010 ◽  
Vol 20 (12) ◽  
pp. 2973-2982 ◽  
Author(s):  
F. E. Lecouvet ◽  
M. Simon ◽  
B. Tombal ◽  
J. Jamart ◽  
B. C. Vande Berg ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Bone Metastases ◽  
Axial Skeleton ◽  
Whole Body ◽  
Whole Body Mri

scholarly journals SURVIVAL IMPACT OF SKELETAL METASTASIS ON BONE SCINTIGRAPHY IN PATIENTS WITH GERM CELL TUMOURS

2016 ◽  
Vol 2 (4) ◽  
Author(s):  
Maimoona Siddique ◽  
Aamna Hassan ◽  
Saadiya J Khan
Keyword(s):  
Germ Cell ◽  
Bone Metastases ◽  
Bone Scintigraphy ◽  
Bone Scan ◽  
Disease Free Survival ◽  
Skeletal Metastasis ◽  
Whole Body ◽  
Skeletal Metastases ◽  
Germ Cell Tumours ◽  
Visceral Metastases

Objective: Our aim was to determine the frequency of skeletal metastasis in germ cell tumours (GCT) at baseline and relapse on conventional technetium-99m methylene diphosphonate (Tc-99m MDP) whole body bone scan (bone scan) and to evaluate the effect of bone metastases on survival. Materials and Methods: Electronic medical records of histologically proven GCT over 64 months were retrospectively analysed. Basic demographic and histologic information were correlated with the presence of osseous and visceral metastases. 5-year disease-free survival (DFS) and overall survival (OS) were calculated in presence, the absence of bone metastases at baseline and at relapse. Results: A total of 130 gonadal and extragonadal GCT patients underwent Tc-99m MDP bone scans; four with insuf cient data were excluded from the study. 47% were females and 53% were males with the age range of 1 month – 72 years. 105 (83%) were under 18 years of age. Osseous metastasis was detected in 12 (9.5%). Two (17%) had solitary and 10 (83%) had multifocal skeletal metastases. Clinically, 83% had localised bone pain. Osseous metastases were more frequently associated with mixed GCT and yolk sac tumour. 50% of mediastinal GCT developed bone metastases. 42% died within 4–18 months. There was a statistically signi cant impact of visceral metastases on DFS and OS. OS at 5 years in patients without bone metastases, with bone metastases at baseline and bone metastases at relapse, was 77%, 38% and 75%, respectively. 5-year DFS for the same cohort groups was 63%, 38% and 20%, respectively. Conclusion: Osseous involvement was found in 9.5% of GCT patients undergoing diagnostic Tc-99m MDP bone scan. Baseline skeletal evaluation for metastases should be done, particularly in the case of bone pains or known systemic metastases. Although skeletal relapses are rare, they have a grim outcome. Key words: Bone scintigraphy, germ cell tumours, skeletal metastases 

scholarly journals Correcting B0 inhomogeneity-induced distortions in whole-body diffusion MRI of bone metastases

2020 ◽  
Author(s):  
Leonardino A. Digma ◽  
Christine H. Feng ◽  
Christopher C. Conlin ◽  
Ana E. Rodríguez-Soto ◽  
Kanha Batra ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Bone Metastases ◽  
Bone Lesion ◽  
Distortion Correction ◽  
Whole Body ◽  
Bone Lesions ◽  
Thoracic Vertebrae ◽  
Signed Rank ◽  
Spatial Displacements ◽  
T2 Weighted Images

AbstractBackgroundAccurate imaging of bone metastases is necessary for treatment planning and assessing treatment response. Diffusion-weighted magnetic resonance imaging (DWI) can detect bone metastases, but DWI acquired with echo-planar imaging is susceptible to distortions due to static magnetic field inhomogeneities.PurposeEstimate spatial displacements of bone lesions on DWI. Examine whether distortion-corrected DWI more accurately reflects underlying anatomy.Study TypeRetrospective.Subjects18 patients with prostate cancer bone metastases.Field Strength/Sequence3.0 T; DWI and T2-weighted imaging.AssessmentWe first applied the reverse polarity gradient (RPG) technique to estimate spatial displacements of bone metastasis on DWI. Next, we calculated changes in mutual information (MI) between DWI and T2-weighted images after RPG distortion correction. Further, we annotated skeletal landmarks on DWI and T2-weighted images. RPG was again used to estimate displacements of these landmarks. Lastly, we calculated changes in distance between DWI- and T2-defined landmarks (i.e., changes in error) after RPG distortion correction.Statistical TestsMean and bootstrap-derived confidence intervals were used to summarize variables that estimate bone lesion distortions. Wilcoxon signed-rank tests were used to assess change in MI between DWI and T2-weighted images after RPG.ResultsMean (95% CI) displacement of bone lesions was 5.6 mm (95% CI: 4.8-6.5); maximum displacement was 17.1 mm. Corrected diffusion images were more similar to structural MRI, as evidenced by consistent increases in MI after applying RPG (Wilcoxon signed-rank p<10−13). Like bone metastases, our annotated skeletal landmarks also underwent substantial displacement (average, 6.3 mm). Lastly, RPG led to consistent error reductions between DWI and T2 for each skeletal landmark (mean, [95% CI]): thoracic vertebrae (−3.8 mm, [-4.3,-3.3]), abdominal vertebrae (−1.0 mm, [-1.2,-0.71]), pelvic vertebrae (−0.6 mm, [-1.0,-0.17]), and femoral head (−1.2 mm, [-2.1,-0.4]).Data ConclusionsThese findings support the use of distortion correction techniques to improve localization of bone metastases on DWI.Grant SupportThis work was supported by NIH/NIBIB #K08EB026503, American Society for Radiation Oncology, and the Prostate Cancer Foundation. This work was further supported by the National Institute on Aging T35 grant AG26757 (PI: Dilip V. Jeste, MD, and Alison Moore, MD, MPH), and the Stein Institute for Research on Aging and the Center for Healthy Aging at the University of California, San Diego.

Comparison of 11C-choline-PET/CT and whole body-MRI for staging of prostate cancer

2007 ◽  
Vol 46 (05) ◽  
pp. 161-168 ◽  
Author(s):  
A. C. Pfannenberg ◽  
A. Rieger ◽  
P. Aschoff ◽  
M. Müller ◽  
F. Paulsen ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Lymph Node ◽  
Bone Metastases ◽  
Lymph Node Metastases ◽  
Specific Antigen ◽  
Whole Body ◽  
Curative Therapy ◽  
Pet Ct ◽  
Node Metastases ◽  
Consensus Reading

SummaryAim of this study was to compare the diagnostic accuracy of positron emission tomography and computed tomography with 11C-Choline (Cho-PET/CT) and whole body magnetic resonance imaging (WB-MRI) for diagnostic work-up of prostate cancer. Patients, methods: We evaluated retrospectively 42 patients with untreated prostate cancer (n = 17), or increasing levels of prostate-specific antigen (PSA) after curative therapy (n = 25) who had been investigated by both Cho-PET/CT and WB-MRI. MRI, CT, and PET images were separately analyzed by experienced radiologists or nuclear medicine experts, followed by consensus reading. Validation was established by histology, follow-up, or consensus reading. Results: 88/103 detected lesions were considered as malignant: 44 bone metastases, 22 local tumor, 15 lymph node metastases, 3 lung, and 3 brain metastases. One further lesion was located in the adrenal gland, which was a second tumor. Overall sensitivity, specificity and accuracy for Cho-PET/CT were 96.6%, 76.5%, and 93.3%, resp., and for WB-MRI 78.4%, 94.1%, and 81.0%, resp. 3 vertebral metastases had initially been missed by Cho-PET/CT and were found retrospectively. MRI identified 2 bone metastases and 1 lymph node metastasis after being informed about the results of Cho-PET/CT. Conclusions: Cho-PET/CT and WB-MRI both presented high accuracy in the detection of bone and lymph node metastases. The strength of MRI is excellent image quality providing detailed anatomical information whereas the advantage of Cho-PET/CT is high image contrast of pathological foci.

Study of the Usefulness of Bone Scan Index Calculated From 99m-Technetium-Hydroxymethylene Diphosphonate (99mtc-HMDP) Bone Scintigraphy for Bone Metastases from Prostate Cancer Using Deep Learning Algorithms

2020 ◽  
Vol 16 ◽  
Author(s):  
Shigeaki Higashiyama ◽  
Atsushi Yoshida ◽  
Joji Kawabe
Keyword(s):  
Prostate Cancer ◽  
Deep Learning ◽  
Bone Metastasis ◽  
Bone Metastases ◽  
Bone Scintigraphy ◽  
Bone Scan ◽  
Learning Algorithms ◽  
Bone Imaging ◽  
Bone Scan Index ◽  
Metabolic Biomarkers

Background: BSI calculated from bone scintigraphy using 99mtechnetium-methylene diphosphonate (99mTc-MDP) is used as a quantitative indicator of metastatic bone involvement in bone metastasis diagnosis, therapeutic effect assessment, and prognosis prediction. However, the BONE NAVI, which calculates BSI, only supports bone scintigraphy using 99mTc-MDP. Aims: We developed a method in collaboration with the Tokyo University of Agriculture and Technology to calculate bone scan index (BSI) employing deep learning algorithms with bone scintigraphy images using 99mtechnetiumhydroxymethylene diphosphonate (99mTc-HMDP). We used a convolutional neural network (CNN) enabling the simultaneous processing of anterior and posterior bone scintigraphy images named CNNapis. Objectives: The purpose of this study is to investigate the usefulness of the BSI calculated by CNNapis as bone imaging and bone metabolic biomarkers in patients with bone metastases from prostate cancer. Methods: At our hospital, 121 bone scintigraphy scans using 99mTc-HMDP were performed and analyzed to examine bone metastases from prostate cancer, revealing the abnormal accumulation of radioisotope (RI) at bone metastasis sites. Blood tests for serum prostate-specific antigen (PSA) and alkaline phosphatase (ALP) were performed concurrently. BSI values calculated by CNNapis were used to quantify the metastatic bone tumor involvement. Correlations between BSI and PSA and between BSI and ALP were calculated. Subjects were divided into four groups by BSI values (Group 1, 0 to <1; Group 2, 1 to <3; Group 3, 3 to <10; Group 4, >10), and the PSA and ALP values in each group were statistically compared. Results: Patients diagnosed with bone metastases after bone scintigraphy were also diagnosed with bone metastases using CNNapis. BSI corresponding to the range of abnormal RI accumulation was calculated. PSA and BSI (r = 0.2791) and ALP and BSI (r = 0.6814) correlated positively. Significant intergroup differences in PSA between Groups 1 and 2, Groups 1 and 4, Groups 2 and 3, and Groups 3 and 4 and in ALP between Groups 1 and 4, Groups 2 and 4, and Groups 3 and 4 were found. Conclusion : BSI calculated using CNNapis correlated with ALP and PSA values and is useful as bone imaging and bone metabolic biomarkers, indicative of the activity and spread of bone metastases from prostate cancer.

Sign in / Sign up

Export Citation Format

Share Document