Autosegmentation of Prostate Zones and Cancer Regions from Biparametric Magnetic Resonance Images by Using Deep-Learning-Based Neural Networks

Lai, Cheng-Hsiao; Wang, Hsin Kai; Wang, Fu Nien; Peng, Yu; Lin, Tzu Ping; Peng, Hao‐Kai; Shen, Shu

doi:10.3390/s21082709

Cited by 18 publications

(14 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interestingly, recent studies presenting DL algorithms for automated MRI tumor segmentations of other pelvic malignancies report performance metrics with DSCs in the range of 0.52-0.84 [35][36][37][38][39], i.e., prostate cancer (DSC of 0.52 using k-fold cross-validation [35] [n = 204]), endometrial cancer (DSC of 0.77/0.84 using a test set [36] [n = 139] and DSC of 0.81 using k-fold cross-validation [37] [n = 200]), and rectal cancer (DSC of 0.68/0.70 using a test set [38] [n = 140] and DSC of 0.70 using a test set [39] [n = 300]). Hence, our DSCs for the DL algorithm in CC (DL-R1: median DSC = 0.60, DL-R2: DSC = 0.58) are quite comparable to that of other pelvic malignancies.…”

Section: Discussionmentioning

confidence: 99%

Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer

Hodneland

Kaliyugarasan

Wagner-Larsen

et al. 2022

Cancers

View full text Add to dashboard Cite

Uterine cervical cancer (CC) is the most common gynecologic malignancy worldwide. Whole-volume radiomic profiling from pelvic MRI may yield prognostic markers for tailoring treatment in CC. However, radiomic profiling relies on manual tumor segmentation which is unfeasible in the clinic. We present a fully automatic method for the 3D segmentation of primary CC lesions using state-of-the-art deep learning (DL) techniques. In 131 CC patients, the primary tumor was manually segmented on T2-weighted MRI by two radiologists (R1, R2). Patients were separated into a train/validation (n = 105) and a test- (n = 26) cohort. The segmentation performance of the DL algorithm compared with R1/R2 was assessed with Dice coefficients (DSCs) and Hausdorff distances (HDs) in the test cohort. The trained DL network retrieved whole-volume tumor segmentations yielding median DSCs of 0.60 and 0.58 for DL compared with R1 (DL-R1) and R2 (DL-R2), respectively, whereas DSC for R1-R2 was 0.78. Agreement for primary tumor volumes was excellent between raters (R1-R2: intraclass correlation coefficient (ICC) = 0.93), but lower for the DL algorithm and the raters (DL-R1: ICC = 0.43; DL-R2: ICC = 0.44). The developed DL algorithm enables the automated estimation of tumor size and primary CC tumor segmentation. However, segmentation agreement between raters is better than that between DL algorithm and raters.

show abstract

Section: Discussionmentioning

confidence: 99%

Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer

Hodneland

Kaliyugarasan

Wagner-Larsen

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“…Some researchers proposed the combination of T2WI and DWI to balance the limited spatial resolution of DWI [ 12 , 33 , 34 ]. The combination of T2WI+DWI+ADC exhibited the best performance [ 35 ].Using an ADC map alone, the estimated volume of the HCTV ADC in the present study was less satisfactory. The HCTV ADC underestimated the volume of tumors, which could lead to omission of lesions and thus deteriorate treatment outcome.…”

Section: Discussionmentioning

confidence: 99%

Combining Diffusion-Weighted Imaging and T2-Weighted Imaging to Delineate Tumorous Tissue in Peritoneal Carcinomatosis: A Comparative Study with 18F-Fluoro-Deoxyglucose Positron Emission Tomography with Computed Tomography (FDG PET/CT)

2022

Med Sci Monit

View full text Add to dashboard Cite

Background The high rate of malignancy of peritoneal carcinomatosis makes its accurate detection vital in treatment planning. The combination of anatomical and functional information, provided by T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI), respectively, could potentially aid in the segmentation of tumors. The aim of this study was to compare the functional tumor volume estimated by a T2WI- and DWI-derived apparent diffusion coefficient (ADC) map, with metabolic tumor volume measured by 18F-fluoro-deoxyglucose positron emission tomography with computed tomography (FDG PET/CT). Material/Methods In 108 lesions from 108 patients with peritoneal carcinomatosis, gross tumor volume (GTV) was manually delineated on DWI. Within each region of interest, k-means clustering was used to exclude non-tumorous tissue from tumorous tissue. The high-cellularity tumor volume estimated from ADC (HCTV ADC ) and combined high-cellularity tumor volume (HCTV C ), which was estimated by combining anatomical information from T2WI and functional information from ADC, were generated. Taking metabolic tumor volume (MTV) in PET/CT as a reference, GTV, HCTV ADC , and HCTV C were compared with MTV. Results GTV ( P =0.017) and HCTV ADC ( P =0.048) differed significantly from MTV. However, the HCTV C measured by combining DWI and T2WI showed high concordance (ICC=0.99) with the MTV measured by FDG PET/CT in differentiating tumorous tissues with high cellularity from non-tumorous tissues. Conclusions In conclusion, our results suggested the potential value of this semiautomatic method serving as an alternative to PET/CT in radiotherapy tumor contouring.

show abstract

“…The absence of an external testing dataset is a critical limitation to the clinical applicability of the developed models. Data augmentation and transfer learning were also used to help addressing this issue [ 6 , 14 – 16 , 29 , 31 , 33 , 35 – 41 , 43 , 51 ]. It is important to note that some bias cannot be balanced-out by increasing the sample size by data augmentation or repetition of training.…”

Section: Discussionmentioning

confidence: 99%

Automatic segmentation of prostate zonal anatomy on MRI: a systematic review of the literature

Montagne

Hamzaoui

et al. 2022

Insights Imaging

View full text Add to dashboard Cite

Objectives Accurate zonal segmentation of prostate boundaries on MRI is a critical prerequisite for automated prostate cancer detection based on PI-RADS. Many articles have been published describing deep learning methods offering great promise for fast and accurate segmentation of prostate zonal anatomy. The objective of this review was to provide a detailed analysis and comparison of applicability and efficiency of the published methods for automatic segmentation of prostate zonal anatomy by systematically reviewing the current literature. Methods A Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) was conducted until June 30, 2021, using PubMed, ScienceDirect, Web of Science and EMBase databases. Risk of bias and applicability based on Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) criteria adjusted with Checklist for Artificial Intelligence in Medical Imaging (CLAIM) were assessed. Results A total of 458 articles were identified, and 33 were included and reviewed. Only 2 articles had a low risk of bias for all four QUADAS-2 domains. In the remaining, insufficient details about database constitution and segmentation protocol provided sources of bias (inclusion criteria, MRI acquisition, ground truth). Eighteen different types of terminology for prostate zone segmentation were found, while 4 anatomic zones are described on MRI. Only 2 authors used a blinded reading, and 4 assessed inter-observer variability. Conclusions Our review identified numerous methodological flaws and underlined biases precluding us from performing quantitative analysis for this review. This implies low robustness and low applicability in clinical practice of the evaluated methods. Actually, there is not yet consensus on quality criteria for database constitution and zonal segmentation methodology.

show abstract

Autosegmentation of Prostate Zones and Cancer Regions from Biparametric Magnetic Resonance Images by Using Deep-Learning-Based Neural Networks

Cited by 18 publications

References 33 publications

Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer

Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer

Combining Diffusion-Weighted Imaging and T2-Weighted Imaging to Delineate Tumorous Tissue in Peritoneal Carcinomatosis: A Comparative Study with 18F-Fluoro-Deoxyglucose Positron Emission Tomography with Computed Tomography (FDG PET/CT)

Automatic segmentation of prostate zonal anatomy on MRI: a systematic review of the literature

Contact Info

Product

Resources

About