Accuracy Validation of an Automated Method for Prostate Segmentation in Magnetic Resonance Imaging

Manual prostate MRI segmentation by readers with different experience: a study of the learning progress

OBJECTIVE

To evaluate the learning progress of less experienced readers in prostate MRI segmentation.

MATERIALS AND METHODS

One hundred bi-parametric prostate MRI scans were retrospectively selected from the Göteborg Prostate Cancer Screening 2 Trial (single center). Nine readers with varying degrees of segmentation experience were involved: one expert radiologist, two experienced radiology residents, two inexperienced radiology residents, and four novices. The task was to segment the whole prostate gland. The expert's segmentations were used as reference. For all other readers except three novices, the 100 MRI scans were divided into five rounds (cases 1-10, 11-25, 26-50, 51-76, 76-100). Three novices segmented only 50 cases (three rounds). After each round, a one-on-one feedback session between the expert and the reader was held, with feedback on systematic errors and potential improvements for the next round. Dice similarity coefficient (DSC) > 0.8 was considered accurate.

RESULTS

Using DSC > 0.8 as the threshold, the novices had a total of 194 accurate segmentations out of 250 (77.6%). The residents had a total of 397/400 (99.2%) accurate segmentations. In round 1, the novices had 19/40 (47.5%) accurate segmentations, in round 2 41/60 (68.3%), and in round 3 84/100 (84.0%) indicating learning progress.

CONCLUSIONS

Radiology residents, regardless of prior experience, showed high segmentation accuracy. Novices showed larger interindividual variation and lower segmentation accuracy than radiology residents. To prepare datasets for artificial intelligence (AI) development, employing radiology residents seems safe and provides a good balance between cost-effectiveness and segmentation accuracy. Employing novices should only be considered on an individual basis.

CLINICAL RELEVANCE STATEMENT

Employing radiology residents for prostate MRI segmentation seems safe and can potentially reduce the workload of expert radiologists. Employing novices should only be considered on an individual basis.

KEY POINTS

• Using less experienced readers for prostate MRI segmentation is cost-effective but may reduce quality. • Radiology residents provided high accuracy segmentations while novices showed large inter-reader variability. • To prepare datasets for AI development, employing radiology residents seems safe and might provide a good balance between cost-effectiveness and segmentation accuracy while novices should only be employed on an individual basis.

Reference standard for the evaluation of automatic segmentation algorithms: Quantification of inter observer variability of manual delineation of prostate contour on MRI

PURPOSE

The purpose of this study was to investigate the relationship between inter-reader variability in manual prostate contour segmentation on magnetic resonance imaging (MRI) examinations and determine the optimal number of readers required to establish a reliable reference standard.

MATERIALS AND METHODS

Seven radiologists with various experiences independently performed manual segmentation of the prostate contour (whole-gland [WG] and transition zone [TZ]) on 40 prostate MRI examinations obtained in 40 patients. Inter-reader variability in prostate contour delineations was estimated using standard metrics (Dice similarity coefficient [DSC], Hausdorff distance and volume-based metrics). The impact of the number of readers (from two to seven) on segmentation variability was assessed using pairwise metrics (consistency) and metrics with respect to a reference segmentation (conformity), obtained either with majority voting or simultaneous truth and performance level estimation (STAPLE) algorithm.

RESULTS

The average segmentation DSC for two readers in pairwise comparison was 0.919 for WG and 0.876 for TZ. Variability decreased with the number of readers: the interquartile ranges of the DSC were 0.076 (WG) / 0.021 (TZ) for configurations with two readers, 0.005 (WG) / 0.012 (TZ) for configurations with three readers, and 0.002 (WG) / 0.0037 (TZ) for configurations with six readers. The interquartile range decreased slightly faster between two and three readers than between three and six readers. When using consensus methods, variability often reached its minimum with three readers (with STAPLE, DSC = 0.96 [range: 0.945-0.971] for WG and DSC = 0.94 [range: 0.912-0.957] for TZ, and interquartile range was minimal for configurations with three readers.

CONCLUSION

The number of readers affects the inter-reader variability, in terms of inter-reader consistency and conformity to a reference. Variability is minimal for three readers, or three readers represent a tipping point in the variability evolution, with both pairwise-based metrics or metrics with respect to a reference. Accordingly, three readers may represent an optimal number to determine references for artificial intelligence applications.

DMCA-GAN: Dual Multilevel Constrained Attention GAN for MRI-Based Hippocampus Segmentation

Precise segmentation of the hippocampus is essential for various human brain activity and neurological disorder studies. To overcome the small size of the hippocampus and the low contrast of MR images, a dual multilevel constrained attention GAN for MRI-based hippocampus segmentation is proposed in this paper, which is used to provide a relatively effective balance between suppressing noise interference and enhancing feature learning. First, we design the dual-GAN backbone to effectively compensate for the spatial information damage caused by multiple pooling operations in the feature generation stage. Specifically, dual-GAN performs joint adversarial learning on the multiscale feature maps at the end of the generator, which yields an average Dice coefficient (DSC) gain of 5.95% over the baseline. Next, to suppress MRI high-frequency noise interference, a multilayer information constraint unit is introduced before feature decoding, which improves the sensitivity of the decoder to forecast features by 5.39% and effectively alleviates the network overfitting problem. Then, to refine the boundary segmentation effects, we construct a multiscale feature attention restraint mechanism, which forces the network to concentrate more on effective multiscale details, thus improving the robustness. Furthermore, the dual discriminators D1 and D2 also effectively prevent the negative migration phenomenon. The proposed DMCA-GAN obtained a DSC of 90.53% on the Medical Segmentation Decathlon (MSD) dataset with tenfold cross-validation, which is superior to the backbone by 3.78%.

Learning rate of students detecting and annotating pediatric wrist fractures in supervised artificial intelligence dataset preparations

The use of artificial intelligence (AI) in image analysis is an intensively debated topic in the radiology community these days. AI computer vision algorithms typically rely on large-scale image databases, annotated by specialists. Developing and maintaining them is time-consuming, thus, the involvement of non-experts into the workflow of annotation should be considered. We assessed the learning rate of inexperienced evaluators regarding correct labeling of pediatric wrist fractures on digital radiographs. Students with and without a medical background labeled wrist fractures with bounding boxes in 7,000 radiographs over ten days. Pediatric radiologists regularly discussed their mistakes. We found F1 scores-as a measure for detection rate-to increase substantially under specialist feedback (mean 0.61±0.19 at day 1 to 0.97±0.02 at day 10, p<0.001), but not the Intersection over Union as a parameter for labeling precision (mean 0.27±0.29 at day 1 to 0.53±0.25 at day 10, p<0.001). The times needed to correct the students decreased significantly (mean 22.7±6.3 seconds per image at day 1 to 8.9±1.2 seconds at day 10, p<0.001) and were substantially lower as annotated by the radiologists alone. In conclusion our data showed, that the involvement of undergraduated students into annotation of pediatric wrist radiographs enables a substantial time saving for specialists, therefore, it should be considered.

Integration of Deep Learning and Active Shape Models for More Accurate Prostate Segmentation in 3D MR Images

Magnetic resonance imaging (MRI) has a growing role in the clinical workup of prostate cancer. However, manual three-dimensional (3D) segmentation of the prostate is a laborious and time-consuming task. In this scenario, the use of automated algorithms for prostate segmentation allows us to bypass the huge workload of physicians. In this work, we propose a fully automated hybrid approach for prostate gland segmentation in MR images using an initial segmentation of prostate volumes using a custom-made 3D deep network (VNet-T2), followed by refinement using an Active Shape Model (ASM). While the deep network focuses on three-dimensional spatial coherence of the shape, the ASM relies on local image information and this joint effort allows for improved segmentation of the organ contours. Our method is developed and tested on a dataset composed of T2-weighted (T2w) MRI prostatic volumes of 60 male patients. In the test set, the proposed method shows excellent segmentation performance, achieving a mean dice score and Hausdorff distance of 0.851 and 7.55 mm, respectively. In the future, this algorithm could serve as an enabling technology for the development of computer-aided systems for prostate cancer characterization in MR imaging.

Automatic zonal segmentation of the prostate from 2D and 3D T2-weighted MRI and evaluation for clinical use

Purpose: An accurate zonal segmentation of the prostate is required for prostate cancer (PCa) management with MRI. Approach: The aim of this work is to present UFNet, a deep learning-based method for automatic zonal segmentation of the prostate from T2-weighted (T2w) MRI. It takes into account the image anisotropy, includes both spatial and channelwise attention mechanisms and uses loss functions to enforce prostate partition. The method was applied on a private multicentric three-dimensional T2w MRI dataset and on the public two-dimensional T2w MRI dataset ProstateX. To assess the model performance, the structures segmented by the algorithm on the private dataset were compared with those obtained by seven radiologists of various experience levels. Results: On the private dataset, we obtained a Dice score (DSC) of 93.90 ± 2.85 for the whole gland (WG), 91.00 ± 4.34 for the transition zone (TZ), and 79.08 ± 7.08 for the peripheral zone (PZ). Results were significantly better than other compared networks' ( p - value < 0.05 ). On ProstateX, we obtained a DSC of 90.90 ± 2.94 for WG, 86.84 ± 4.33 for TZ, and 78.40 ± 7.31 for PZ. These results are similar to state-of-the art results and, on the private dataset, are coherent with those obtained by radiologists. Zonal locations and sectorial positions of lesions annotated by radiologists were also preserved. Conclusions: Deep learning-based methods can provide an accurate zonal segmentation of the prostate leading to a consistent zonal location and sectorial position of lesions, and therefore can be used as a helping tool for PCa diagnosis.

Combined model-based and deep learning-based automated 3D zonal segmentation of the prostate on T2-weighted MR images: clinical evaluation

OBJECTIVE

To train and to test for prostate zonal segmentation an existing algorithm already trained for whole-gland segmentation.

METHODS

The algorithm, combining model-based and deep learning-based approaches, was trained for zonal segmentation using the NCI-ISBI-2013 dataset and 70 T2-weighted datasets acquired at an academic centre. Test datasets were randomly selected among examinations performed at this centre on one of two scanners (General Electric, 1.5 T; Philips, 3 T) not used for training. Automated segmentations were corrected by two independent radiologists. When segmentation was initiated outside the prostate, images were cropped and segmentation repeated. Factors influencing the algorithm's mean Dice similarity coefficient (DSC) and its precision were assessed using beta regression.

RESULTS

Eighty-two test datasets were selected; one was excluded. In 13/81 datasets, segmentation started outside the prostate, but zonal segmentation was possible after image cropping. Depending on the radiologist chosen as reference, algorithm's median DSCs were 96.4/97.4%, 91.8/93.0% and 79.9/89.6% for whole-gland, central gland and anterior fibromuscular stroma (AFMS) segmentations, respectively. DSCs comparing radiologists' delineations were 95.8%, 93.6% and 81.7%, respectively. For all segmentation tasks, the scanner used for imaging significantly influenced the mean DSC and its precision, and the mean DSC was significantly lower in cases with initial segmentation outside the prostate. For central gland segmentation, the mean DSC was also significantly lower in larger prostates. The radiologist chosen as reference had no significant impact, except for AFMS segmentation.

CONCLUSIONS

The algorithm performance fell within the range of inter-reader variability but remained significantly impacted by the scanner used for imaging.

KEY POINTS

• Median Dice similarity coefficients obtained by the algorithm fell within human inter-reader variability for the three segmentation tasks (whole gland, central gland, anterior fibromuscular stroma). • The scanner used for imaging significantly impacted the performance of the automated segmentation for the three segmentation tasks. • The performance of the automated segmentation of the anterior fibromuscular stroma was highly variable across patients and showed also high variability across the two radiologists.

Challenge of prostate MRI segmentation on T2-weighted images: inter-observer variability and impact of prostate morphology

Background

Accurate prostate zonal segmentation on magnetic resonance images (MRI) is a critical prerequisite for automated prostate cancer detection. We aimed to assess the variability of manual prostate zonal segmentation by radiologists on T2-weighted (T2W) images, and to study factors that may influence it.

Methods

Seven radiologists of varying levels of experience segmented the whole prostate gland (WG) and the transition zone (TZ) on 40 axial T2W prostate MRI images (3D T2W images for all patients, and both 3D and 2D images for a subgroup of 12 patients). Segmentation variabilities were evaluated based on: anatomical and morphological variation of the prostate (volume, retro-urethral lobe, intensity contrast between zones, presence of a PI-RADS ≥ 3 lesion), variation in image acquisition (3D vs 2D T2W images), and reader’s experience. Several metrics including Dice Score (DSC) and Hausdorff Distance were used to evaluate differences, with both a pairwise and a consensus (STAPLE reference) comparison.

Results

DSC was 0.92 (± 0.02) and 0.94 (± 0.03) for WG, 0.88 (± 0.05) and 0.91 (± 0.05) for TZ respectively with pairwise comparison and consensus reference. Variability was significantly (p < 0.05) lower for the mid-gland (DSC 0.95 (± 0.02)), higher for the apex (0.90 (± 0.06)) and the base (0.87 (± 0.06)), and higher for smaller prostates (p < 0.001) and when contrast between zones was low (p < 0.05). Impact of the other studied factors was non-significant.

Conclusions

Variability is higher in the extreme parts of the gland, is influenced by changes in prostate morphology (volume, zone intensity ratio), and is relatively unaffected by the radiologist’s level of expertise.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-021-01010-9.

Methodological approach to create an atlas using a commercial auto-contouring software

PURPOSE

The aim of this work was to establish a methodological approach for creation and optimization of an atlas for auto-contouring, using the commercial software MIM MAESTRO (MIM Software Inc. Cleveland OH).

METHODS

A computed tomography (CT) male pelvis atlas was created and optimized to evaluate how different tools and options impact on the accuracy of automatic segmentation. Pelvic lymph nodes (PLN), rectum, bladder, and femurs of 55 subjects were reviewed for consistency by a senior consultant radiation oncologist with 15 yr of experience. Several atlas and workflow options were tuned to optimize the accuracy of auto-contours. The deformable image registration (DIR), the finalization method, the k number of atlas best matching subjects, and several post-processing options were studied. To test our atlas performances, automatic and reference manual contours of 20 test subjects were statistically compared based on dice similarity coefficient (DSC) and mean distance to agreement (MDA) indices. The effect of field of view (FOV) reduction on auto-contouring time was also investigated.

RESULTS

With the optimized atlas and workflow, DSC and MDA median values of bladder, rectum, PLN, and femurs were 0.91 and 1.6 mm, 0.85 and 1.6 mm, 0.85 and 1.8 mm, and 0.96 and 0.5 mm, respectively. Auto-contouring time was more than halved by strictly cropping the FOV of the subject to be contoured to the pelvic region.

CONCLUSION

A statistically significant improvement of auto-contours accuracy was obtained using our atlas and optimized workflow instead of the MIM Software pelvic atlas.

Evaluation of Multimodal Algorithms for the Segmentation of Multiparametric MRI Prostate Images

Prostate segmentation in multiparametric magnetic resonance imaging (mpMRI) can help to support prostate cancer diagnosis and therapy treatment. However, manual segmentation of the prostate is subjective and time-consuming. Many deep learning monomodal networks have been developed for automatic whole prostate segmentation from T2-weighted MR images. We aimed to investigate the added value of multimodal networks in segmenting the prostate into the peripheral zone (PZ) and central gland (CG). We optimized and evaluated monomodal DenseVNet, multimodal ScaleNet, and monomodal and multimodal HighRes3DNet, which yielded dice score coefficients (DSC) of 0.875, 0.848, 0.858, and 0.890 in WG, respectively. Multimodal HighRes3DNet and ScaleNet yielded higher DSC with statistical differences in PZ and CG only compared to monomodal DenseVNet, indicating that multimodal networks added value by generating better segmentation between PZ and CG regions but did not improve the WG segmentation. No significant difference was observed in the apex and base of WG segmentation between monomodal and multimodal networks, indicating that the segmentations at the apex and base were more affected by the general network architecture. The number of training data was also varied for DenseVNet and HighRes3DNet, from 20 to 120 in steps of 20. DenseVNet was able to yield DSC of higher than 0.65 even for special cases, such as TURP or abnormal prostate, whereas HighRes3DNet's performance fluctuated with no trend despite being the best network overall. Multimodal networks did not add value in segmenting special cases but generally reduced variations in segmentation compared to the same matched monomodal network.

Artificial intelligence and radiomics in pediatric molecular imaging

In the past decade, a new approach for quantitative analysis of medical images and prognostic modelling has emerged. Defined as the extraction and analysis of a large number of quantitative parameters from medical images, radiomics is an evolving field in precision medicine with the ultimate goal of the discovery of new imaging biomarkers for disease. Radiomics has already shown promising results in extracting diagnostic, prognostic, and molecular information latent in medical images. After acquisition of the medical images as part of the standard of care, a region of interest is defined often via a manual or semi-automatic approach. An algorithm then extracts and computes quantitative radiomics parameters from the region of interest. Whereas radiomics captures quantitative values of shape and texture based on predefined mathematical terms, neural networks have recently been used to directly learn and identify predictive features from medical images. Thereby, neural networks largely forego the need for so called "hand-engineered" features, which appears to result in significantly improved performance and reliability. Opportunities for radiomics and neural networks in pediatric nuclear medicine/radiology/molecular imaging are broad and can be thought of in three categories: automating well-defined administrative or clinical tasks, augmenting broader administrative or clinical tasks, and unlocking new methods of generating value. Specific applications include intelligent order sets, automated protocoling, improved image acquisition, computer aided triage and detection of abnormalities, next generation voice dictation systems, biomarker development, and therapy planning.

Prostate zonal segmentation in 1.5T and 3T T2W MRI using a convolutional neural network

Zonal segmentation of the prostate gland using magnetic resonance imaging (MRI) is clinically important for prostate cancer (PCa) diagnosis and image-guided treatments. A two-dimensional convolutional neural network (CNN) based on the U-net architecture was evaluated for segmentation of the central gland (CG) and peripheral zone (PZ) using a dataset of 40 patients (34 PCa positive and 6 PCa negative) scanned on two different MRI scanners (1.5T GE and 3T Siemens). Images were cropped around the prostate gland to exclude surrounding tissues, resampled to 0.5 × 0.5 × 0.5    mm   voxels and z -score normalized before being propagated through the CNN. Performance was evaluated using the Dice similarity coefficient (DSC) and mean absolute distance (MAD) in a fivefold cross-validation setup. Overall performance showed DSC of 0.794 and 0.692, and MADs of 3.349 and 2.993 for CG and PZ, respectively. Dividing the gland into apex, mid, and base showed higher DSC for the midgland compared to apex and base for both CG and PZ. We found no significant difference in DSC between the two scanners. A larger dataset, preferably with multivendor scanners, is necessary for validation of the proposed algorithm; however, our results are promising and have clinical potential.

A semiautomatic approach for prostate segmentation in MR images using local texture classification and statistical shape modeling

Segmentation of the prostate in magnetic resonance (MR) images has many applications in image-guided treatment planning and procedures such as biopsy and focal therapy. However, manual delineation of the prostate boundary is a time-consuming task with high inter-observer variation. In this study, we proposed a semiautomated, three-dimensional (3D) prostate segmentation technique for T2-weighted MR images based on shape and texture analysis. The prostate gland shape is usually globular with a smoothly curved surface that could be accurately modeled and reconstructed if the locations of a limited number of well-distributed surface points are known. For a training image set, we used an inter-subject correspondence between the prostate surface points to model the prostate shape variation based on a statistical point distribution modeling. We also studied the local texture difference between prostate and non-prostate tissues close to the prostate surface. To segment a new image, we used the learned prostate shape and texture characteristics to search for the prostate border close to an initially estimated prostate surface. We used 23 MR images for training, and 14 images for testing the algorithm performance. We compared the results to two sets of experts' manual reference segmentations. The measured mean ± standard deviation of error values for the whole gland were 1.4 ± 0.4 mm, 8.5 ± 2.0 mm, and 86 ± 3% in terms of mean absolute distance (MAD), Hausdorff distance (HDist), and Dice similarity coefficient (DSC). The average measured differences between the two experts on the same datasets were 1.5 mm (MAD), 9.0 mm (HDist), and 83% (DSC). The proposed algorithm illustrated a fast, accurate, and robust performance for 3D prostate segmentation. The accuracy of the algorithm is within the inter-expert variability observed in manual segmentation and comparable to the best performance results reported in the literature.

Survey on deep learning for radiotherapy

More than 50% of cancer patients are treated with radiotherapy, either exclusively or in combination with other methods. The planning and delivery of radiotherapy treatment is a complex process, but can now be greatly facilitated by artificial intelligence technology. Deep learning is the fastest-growing field in artificial intelligence and has been successfully used in recent years in many domains, including medicine. In this article, we first explain the concept of deep learning, addressing it in the broader context of machine learning. The most common network architectures are presented, with a more specific focus on convolutional neural networks. We then present a review of the published works on deep learning methods that can be applied to radiotherapy, which are classified into seven categories related to the patient workflow, and can provide some insights of potential future applications. We have attempted to make this paper accessible to both radiotherapy and deep learning communities, and hope that it will inspire new collaborations between these two communities to develop dedicated radiotherapy applications.

Accuracy of tumor segmentation from multi-parametric prostate MRI and 18F-choline PET/CT for focal prostate cancer therapy applications

BACKGROUND

The study aims to assess the accuracy of multi-parametric prostate MRI (mpMRI) and 18F-choline PET/CT in tumor segmentation for clinically significant prostate cancer. 18F-choline PET/CT and 3 T mpMRI were performed in 10 prospective subjects prior to prostatectomy. All subjects had a single biopsy-confirmed focus of Gleason ≥ 3+4 cancer. Two radiologists (readers 1 and 2) determined tumor boundaries based on in vivo mpMRI sequences, with clinical and pathologic data available. 18F-choline PET data were co-registered to T2-weighted 3D sequences and a semi-automatic segmentation routine was used to define tumor volumes. Registration of whole-mount surgical pathology to in vivo imaging was conducted utilizing two ex vivo prostate specimen MRIs, followed by gross sectioning of the specimens within a custom-made 3D-printed plastic mold. Overlap and similarity coefficients of manual segmentations (seg1, seg2) and 18F-choline-based segmented lesions (seg3) were compared to the pathologic reference standard.

RESULTS

All segmentation methods greatly underestimated the true tumor volumes. Human readers (seg1, seg2) and the PET-based segmentation (seg3) underestimated an average of 79, 80, and 58% of the tumor volumes, respectively. Combining segmentation volumes (union of seg1, seg2, seg3 = seg4) decreased the mean underestimated tumor volume to 42% of the true tumor volume. When using the combined segmentation with 5 mm contour expansion, the mean underestimated tumor volume was significantly reduced to 0.03 ± 0.05 mL (2.04 ± 2.84%). Substantial safety margins up to 11-15 mm were needed to include all tumors when the initial segmentation boundaries were drawn by human readers or the semi-automated 18F-choline segmentation tool. Combining MR-based human segmentations with the metabolic information based on 18F-choline PET reduced the necessary safety margin to a maximum of 9 mm to cover all tumors entirely.

CONCLUSIONS

To improve the outcome of focal therapies for significant prostate cancer, it is imperative to recognize the full extent of the underestimation of tumor volumes by mpMRI. Combining metabolic information from 18F-choline with MRI-based segmentation can improve tumor coverage. However, this approach requires confirmation in further clinical studies.