scholarly journals A Deep Learning-Based Automated CT Segmentation of Prostate Cancer Anatomy for Radiation Therapy Planning-A Retrospective Multicenter Study

Diagnostics ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. 959
Author(s):  
Timo Kiljunen ◽  
Saad Akram ◽  
Jarkko Niemelä ◽  
Eliisa Löyttyniemi ◽  
Jan Seppälä ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Deep Learning ◽  
Lymph Node ◽  
Seminal Vesicles ◽  
Dice Similarity Coefficient ◽  
Efficiency Gain ◽  
Data Set ◽  
Femoral Heads ◽  
The Mean ◽  
Penile Bulb

A commercial deep learning (DL)-based automated segmentation tool (AST) for computed tomography (CT) is evaluated for accuracy and efficiency gain within prostate cancer patients. Thirty patients from six clinics were reviewed with manual- (MC), automated- (AC) and automated and edited (AEC) contouring methods. In the AEC group, created contours (prostate, seminal vesicles, bladder, rectum, femoral heads and penile bulb) were edited, whereas the MC group included empty datasets for MC. In one clinic, lymph node CTV delineations were evaluated for interobserver variability. Compared to MC, the mean time saved using the AST was 12 min for the whole data set (46%) and 12 min for the lymph node CTV (60%), respectively. The delineation consistency between MC and AEC groups according to the Dice similarity coefficient (DSC) improved from 0.78 to 0.94 for the whole data set and from 0.76 to 0.91 for the lymph nodes. The mean DSCs between MC and AC for all six clinics were 0.82 for prostate, 0.72 for seminal vesicles, 0.93 for bladder, 0.84 for rectum, 0.69 for femoral heads and 0.51 for penile bulb. This study proves that using a general DL-based AST for CT images saves time and improves consistency.

What is the optimum number of beams and energy for IMRT boost in prostate cancer? A plan comparison study

2009 ◽  
Vol 27 (15_suppl) ◽  
pp. e16158-e16158
Author(s):  
H. Kunhiparambath ◽  
R. Prabhakar ◽  
G. K. Rath ◽  
D. N. Sharma ◽  
P. Heera ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Maximum Dose ◽  
Target Volume ◽  
Seminal Vesicles ◽  
Integral Dose ◽  
Dose Volume ◽  
Carcinoma Prostate ◽  
Femoral Heads ◽  
Dose Homogeneity ◽  
The Mean

e16158 Background: Intensity Modulated Radiotherapy (IMRT) is used in carcinoma prostate to achieve better target coverage with less dose to critical organs thereby permitting dose escalation and eventually better therapeutic ratio. There is scarcity of literature evaluating beam number and energy in prostate cancer treated by IMRT. Aim of our study is to identify the optimal number of beams and energy in the boost treatment of prostate cancer by IMRT. Methods: Ten patients were included in this study. Initially a dose of 45 Gy in 25 fractions was delivered to the prostate, seminal vesicles and the nodes by 3DCRT. A boost dose of 27 Gy in 15 fractions was planned to the prostate and the seminal vesicles by sliding window IMRT. Four different sets of IMRT plans: 5, 7 and 9 field with 6 MV; 7 field with 15 MV were generated. The dose constraints to the critical structures and the target volume were based on standard guidelines. The mean dose, maximum dose, volume receiving the prescribed dose (V100), volume receiving > 107% and <95% of the prescribed dose were analyzed for CTV and planning target volume (PTV). The mean dose, volume receiving 100%, 50% and 30% of the prescribed dose were analyzed for the bladder and the rectum. Similarly, the mean dose and the maximum dose to the right and left femoral heads, monitor units (MU) and the integral dose were analyzed. SPSS V10.0 software was used for statistical analysis. Results: The seven beam plan provide better dose homogeneity to PTV and lesser doses to critical structures like bladder, rectum and femoral heads when 6 MV photon is used. 15 MV photons further improve the dose homogeneity and decrease the dose to critical structures. The Monitoring Units required to deliver the treatment and the Integral dose is significantly reduced by using 15 MV compared to 6 MV. Conclusions: The optimal IMRT plan for boost planning in carcinoma prostate is that uses 7 beams and higher energy. This yields lesser dose to surrounding critical structures with better target conformity. [Table: see text] No significant financial relationships to disclose.

scholarly journals Lesion-Based Bone Metastasis Detection in Chest Bone Scintigraphy Images of Prostate Cancer Patients Using Pre-Train, Negative Mining, and Deep Learning

Diagnostics ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 518
Author(s):  
Da-Chuan Cheng ◽  
Te-Chun Hsieh ◽  
Kuo-Yang Yen ◽  
Chia-Hung Kao
Keyword(s):  
Breast Cancer ◽  
Prostate Cancer ◽  
Deep Learning ◽  
Bone Metastasis ◽  
Cancer Patients ◽  
Bone Scintigraphy ◽  
Breast Cancer Patients ◽  
Location Detection ◽  
The Mean ◽  
Mean Sensitivity

This study aimed to explore efficient ways to diagnose bone metastasis early using bone scintigraphy images through negative mining, pre-training, the convolutional neural network, and deep learning. We studied 205 prostate cancer patients and 371 breast cancer patients and used bone scintigraphy data from breast cancer patients to pre-train a YOLO v4 with a false-positive reduction strategy. With the pre-trained model, transferred learning was applied to prostate cancer patients to build a model to detect and identify metastasis locations using bone scintigraphy. Ten-fold cross validation was conducted. The mean sensitivity and precision rates for bone metastasis location detection and classification (lesion-based) in the chests of prostate patients were 0.72 ± 0.04 and 0.90 ± 0.04, respectively. The mean sensitivity and specificity rates for bone metastasis classification (patient-based) in the chests of prostate patients were 0.94 ± 0.09 and 0.92 ± 0.09, respectively. The developed system has the potential to provide pre-diagnostic reports to aid in physicians’ final decisions.

Parsing of Urban Facades from 3D Point Clouds Based on a Novel Multi-View Domain

2021 ◽  
Vol 87 (4) ◽  
pp. 283-293
Author(s):  
Wei Wang ◽  
Yuan Xu ◽  
Yingchao Ren ◽  
Gang Wang
Keyword(s):  
Deep Learning ◽  
Prior Knowledge ◽  
Performance Improvement ◽  
Data Distribution ◽  
Point Clouds ◽  
Learning Models ◽  
Data Set ◽  
3D Point Clouds ◽  
Segmentation Accuracy ◽  
The Mean

Recently, performance improvement in facade parsing from 3D point clouds has been brought about by designing more complex network structures, which cost huge computing resources and do not take full advantage of prior knowledge of facade structure. Instead, from the perspective of data distribution, we construct a new hierarchical mesh multi-view data domain based on the characteristics of facade objects to achieve fusion of deep-learning models and prior knowledge, thereby significantly improving segmentation accuracy. We comprehensively evaluate the current mainstream method on the RueMonge 2014 data set and demonstrate the superiority of our method. The mean intersection-over-union index on the facade-parsing task reached 76.41%, which is 2.75% higher than the current best result. In addition, through comparative experiments, the reasons for the performance improvement of the proposed method are further analyzed.

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 &lt;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 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.

Dosimetric evaluation of whole-pelvis radiation therapy of prostate cancers: clinical experience

2020 ◽  
pp. 1-15
Author(s):  
Ernest Osei ◽  
Hafsa Mansoor ◽  
Johnson Darko ◽  
Beverley Osei ◽  
Katrina Fleming ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Radiation Therapy ◽  
High Risk ◽  
Cancer Patients ◽  
Seminal Vesicles ◽  
Conformity Index ◽  
Prostate Bed ◽  
Risk Patients ◽  
Treatment Plans ◽  
The Mean

Abstract Background: The standard treatment modalities for prostate cancer include surgery, chemotherapy, hormonal therapy and radiation therapy or any combination depending on the stage of the tumour. Radiation therapy is a common and effective treatment modality for low-intermediate-risk patients with localised prostate cancer, to treat the intact prostate and seminal vesicles or prostate bed post prostatectomy. However, for high-risk patients with lymph node involvement, treatment with radiation will usually include treatment of the whole pelvis to cover the prostate and seminal vesicles or prostate bed and the pelvic lymph nodes followed by a boost delivery dose to the prostate and seminal vesicles or prostate bed. Materials and Methods: We retrospectively analysed the treatment plans for 179 prostate cancer patients treated at the cancer centre with the volumetric-modulated arc therapy (VMAT) technique via RapidArc using 6 MV photon beam. Patients were either treated with a total prescription dose of 78 Gy in 39 fractions for patients with intact prostate or 66 Gy in 33 fractions for post prostatectomy patients. Results: There were 114 (64%) patients treated with 78 Gy/39 and 65 (36%) treated with 66 Gy/34. The mean homogeneity index (HI), conformity index (CI) and uniformity index (UI) for the PTV-primary of patients treated with 78 Gy are 0.06 ± 0.01, 1.04 ± 0.01 and 0.99 ± 0.01, respectively, and the corresponding mean values for patients treated with 66 Gy are 0.06 ± 0.02, 1.05 ± 0.01 and 0.99 ± 0.01, respectively. The mean PTV-primary V95%, V100% and V105% are 99.5 ± 0.5%, 78.8 ± 12.2% and 0.1 ± 0.5%, respectively, for patients treated with 78 Gy and 99.3 ± 0.9%, 78.1 ± 10.6% and 0.1 ± 0.4%, respectively, for patients treated with 66 Gy. The rectal V50Gy, V65Gy, V66.6Gy, V70Gy, V75Gy and V80Gy are 26.8 ± 9.1%, 14.2 ± 5.3%, 13.1 ± 5.0%, 10.8 ± 4.3%, 6.9 ± 3.1% and 0.1 ± 0.1%, respectively, for patients treated with 78 Gy and 33.7 ± 8.4%, 14.1 ± 4.5%, 6.7 ± 4.5%, 0.0 ± 0.2%, 0.0% and 0.0%, respectively, for patients treated with 66 Gy. Conclusion: The use of VMAT technique for radiation therapy of high-risk prostate cancer patients is an efficient and reliable method for achieving superior dose conformity, uniformity and homogeneity to the PTV and minimal doses to the organs at risk. Results from this study provide the basis for the development and implementation of consistent treatment criteria in radiotherapy programs, have the potential to establish an evaluation process to define a consistent, standardised and transparent treatment path for all patients that reduces significant variations in the acceptability of treatment plans and potentially improve patient standard of care.

scholarly journals Helical Tomotherapy with Simultaneous Integrated Boost for High-Risk and Lymph Node-Positive Prostate Cancer: Early Report on Acute and Late Toxicity

2009 ◽  
Vol 8 (5) ◽  
pp. 353-359 ◽  
Author(s):  
Benedikt Engels ◽  
Guy Soete ◽  
Koen Tournel ◽  
Samuel Bral ◽  
Peter De Coninck ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Lymph Node ◽  
Side Effects ◽  
High Risk ◽  
Dose Escalation ◽  
Helical Tomotherapy ◽  
Seminal Vesicles ◽  
Node Positive ◽  
Integrated Boost ◽  
Lymph Node Positive

The use of whole pelvic radiotherapy (WPRT) for high-risk and lymph node-positive prostate cancer (PC) remains controversial. The purpose of this study was to evaluate the acute toxicity associated with helical tomotherapy in the treatment of high-risk and lymph node-positive prostate cancer. To do so, twenty-eight patients were treated to a dose of 54 Gy in daily fractions of 1.8 Gy to the pelvic lymph node area, while the prostate and the seminal vesicles received a simultaneous integrated boost (SIB) to a dose of 70.5 Gy. A SIB to a dose of 60 Gy was delivered to the involved lymph node region(s) in 8 patients with pelvic lymph node metastases. All patients received concurrent hormonal treatment. The incidence of grade 2 and 3 acute gastrointestinal (GI) toxicity was 7% and 0% respectively. Grade 2 and 3 acute genito-urinary (GU) side effects were observed in 14% and 4% of the patients respectively. No grade 4 side effects occurred. No increased toxicity was observed in the 8 lymph node-positive patients receiving a simultaneous pelvic nodal dose escalation. In conclusion, WPRT with a SIB to the prostate and seminal vesicles by helical tomotherapy resulted in a favourable toxicity profile. Pelvic nodal dose escalation in node-positive patients is feasible without increasing toxicity.

scholarly journals Clinical Outcome of Patients with Lymph Node-Positive Prostate Cancer following Radical Prostatectomy and Extended Sentinel Lymph Node Dissection

2014 ◽  
Vol 94 (3) ◽  
pp. 296-306 ◽  
Author(s):  
Alexander Muck ◽  
Christian Langesberg ◽  
Michael Mugler ◽  
Jörg Rahnenführer ◽  
Bernd Wullich ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Lymph Node ◽  
Sentinel Lymph Node ◽  
Clinical Outcome ◽  
Lymph Node Dissection ◽  
Radical Retropubic Prostatectomy ◽  
Sentinel Lymph Node Dissection ◽  
Node Dissection ◽  
Cancer Specific Survival ◽  
The Mean

Objective: This study sought to evaluate the clinical outcome after extended sentinel lymph node dissection (eSLND) and radical retropubic prostatectomy (RRP) in patients with clinically localized prostate cancer (PCa). Subjects and Methods: From August 2002 until February 2011, a total of 819 patients with clinically localized PCa, confirmed by biopsy, were treated with RRP plus eSLND. Biochemical recurrence-free survival (RFS), cancer-specific survival (CSS), and overall survival (OS) were assessed with Kaplan-Meier curves. Various histopathological parameters were analyzed by univariate and multivariate analysis. Results: The mean follow-up was 5.3 years. Lymph node (LN) metastases occurred in 140 patients. We removed an average of 10.9 LNs via eSLND from patients with pN1 PCa. Postoperatively, 121 pN1 patients temporarily received adjuvant androgen deprivation therapy. The mean survival periods for RFS, RFS after secondary treatment, CSS, and OS were 4.7, 7.0, 8.8, and 8.1 years, respectively. The cancer-specific death rate of the 140 pN1 patients was 13.6%. RFS, CSS, and OS were significantly correlated with pathological margin status, LN density, the total diameter of evident metastases, and membership in the subgroup ‘micrometastases only'. Conclusion: Despite the presence of LN metastases, patients with a low nodal tumor burden demonstrate a remarkable clinical outcome after undergoing eSLND and RRP, thus suggesting a potential curative therapeutic approach.

Sign in / Sign up

Export Citation Format

Share Document