Registration of in vivo prostate MRI and pseudo-whole mount histology using Local Affine Transformations guided by Internal Structures (LATIS)

Multi-scale statistical deformation based co-registration of prostate MRI and post-surgical whole mount histopathology

BACKGROUND

Accurate delineations of regions of interest (ROIs) on multi-parametric magnetic resonance imaging (mpMRI) are crucial for development of automated, machine learning-based prostate cancer (PCa) detection and segmentation models. However, manual ROI delineations are labor-intensive and susceptible to inter-reader variability. Histopathology images from radical prostatectomy (RP) represent the "gold standard" in terms of the delineation of disease extents, for example, PCa, prostatitis, and benign prostatic hyperplasia (BPH). Co-registering digitized histopathology images onto pre-operative mpMRI enables automated mapping of the ground truth disease extents onto mpMRI, thus enabling the development of machine learning tools for PCa detection and risk stratification. Still, MRI-histopathology co-registration is challenging due to various artifacts and large deformation between in vivo MRI and ex vivo whole-mount histopathology images (WMHs). Furthermore, the artifacts on WMHs, such as tissue loss, may introduce unrealistic deformation during co-registration.

PURPOSE

This study presents a new registration pipeline, MSERgSDM, a multi-scale feature-based registration (MSERg) with a statistical deformation (SDM) constraint, which aims to improve accuracy of MRI-histopathology co-registration.

METHODS

In this study, we collected 85 pairs of MRI and WMHs from 48 patients across three cohorts. Cohort 1 (D1), comprised of a unique set of 3D printed mold data from six patients, facilitated the generation of ground truth deformations between ex vivo WMHs and in vivo MRI. The other two clinically acquired cohorts (D2 and D3) included 42 patients. Affine and nonrigid registrations were employed to minimize the deformation between ex vivo WMH and ex vivo T2-weighted MRI (T2WI) in D1. Subsequently, ground truth deformation between in vivo T2WI and ex vivo WMH was approximated as the deformation between in vivo T2WI and ex vivo T2WI. In D2 and D3, the prostate anatomical annotations, for example, tumor and urethra, were made by a pathologist and a radiologist in collaboration. These annotations included ROI boundary contours and landmark points. Before applying the registration, manual corrections were made for flipping and rotation of WMHs. MSERgSDM comprises two main components: (1) multi-scale representation construction, and (2) SDM construction. For the SDM construction, we collected N = 200 reasonable deformation fields generated using MSERg, verified through visual inspection. Three additional methods, including intensity-based registration, ProsRegNet, and MSERg, were also employed for comparison against MSERgSDM.

RESULTS

Our results suggest that MSERgSDM performed comparably to the ground truth (p > 0.05). Additionally, MSERgSDM (ROI Dice ratio = 0.61, landmark distance = 3.26 mm) exhibited significant improvement over MSERg (ROI Dice ratio = 0.59, landmark distance = 3.69 mm) and ProsRegNet (ROI Dice ratio = 0.56, landmark distance = 4.00 mm) in local alignment.

CONCLUSIONS

This study presents a novel registration method, MSERgSDM, for mapping ex vivo WMH onto in vivo prostate MRI. Our preliminary results demonstrate that MSERgSDM can serve as a valuable tool to map ground truth disease annotations from histopathology images onto MRI, thereby assisting in the development of machine learning models for PCa detection on MRI.

Full resolution reconstruction of whole-mount sections from digitized individual tissue fragments

Whole-mount sectioning is a technique in histopathology where a full slice of tissue, such as a transversal cross-section of a prostate specimen, is prepared on a large microscope slide without further sectioning into smaller fragments. Although this technique can offer improved correlation with pre-operative imaging and is paramount for multimodal research, it is not commonly employed due to its technical difficulty, associated cost and cumbersome integration in (digital) pathology workflows. In this work, we present a computational tool named PythoStitcher which reconstructs artificial whole-mount sections from digitized tissue fragments, thereby bringing the benefits of whole-mount sections to pathology labs currently unable to employ this technique. Our proposed algorithm consists of a multi-step approach where it (i) automatically determines how fragments need to be reassembled, (ii) iteratively optimizes the stitch using a genetic algorithm and (iii) efficiently reconstructs the final artificial whole-mount section on full resolution (0.25 µm/pixel). PythoStitcher was validated on a total of 198 cases spanning five datasets with a varying number of tissue fragments originating from different organs from multiple centers. PythoStitcher successfully reconstructed the whole-mount section in 86-100% of cases for a given dataset with a residual registration mismatch of 0.65-2.76 mm on automatically selected landmarks. It is expected that our algorithm can aid pathology labs unable to employ whole-mount sectioning through faster clinical case evaluation and improved radiology-pathology correlation workflows.

Computer-aided detection of prostate cancer in early stages using multi-parameter MRI: A promising approach for early diagnosis

BACKGROUND

Transrectal ultrasound-guided prostate biopsy is the gold standard diagnostic test for prostate cancer, but it is an invasive examination of non-targeted puncture and has a high false-negative rate.

OBJECTIVE

In this study, we aimed to develop a computer-assisted prostate cancer diagnosis method based on multiparametric MRI (mpMRI) images.

METHODS

We retrospectively collected 106 patients who underwent radical prostatectomy after diagnosis with prostate biopsy. mpMRI images, including T2 weighted imaging (T2WI), diffusion weighted imaging (DWI), and dynamic-contrast enhanced (DCE), and were accordingly analyzed. We extracted the region of interest (ROI) about the tumor and benign area on the three sequential MRI axial images at the same level. The ROI data of 433 mpMRI images were obtained, of which 202 were benign and 231 were malignant. Of those, 50 benign and 50 malignant images were used for training, and the 333 images were used for verification. Five main feature groups, including histogram, GLCM, GLGCM, wavelet-based multi-fractional Brownian motion features and Minkowski function features, were extracted from the mpMRI images. The selected characteristic parameters were analyzed by MATLAB software, and three analysis methods with higher accuracy were selected.

RESULTS

Through prostate cancer identification based on mpMRI images, we found that the system uses 58 texture features and 3 classification algorithms, including Support Vector Machine (SVM), K-nearest Neighbor (KNN), and Ensemble Learning (EL), performed well. In the T2WI-based classification results, the SVM achieved the optimal accuracy and AUC values of 64.3% and 0.67. In the DCE-based classification results, the SVM achieved the optimal accuracy and AUC values of 72.2% and 0.77. In the DWI-based classification results, the ensemble learning achieved optimal accuracy as well as AUC values of 75.1% and 0.82. In the classification results based on all data combinations, the SVM achieved the optimal accuracy and AUC values of 66.4% and 0.73.

CONCLUSION

The proposed computer-aided diagnosis system provides a good assessment of the diagnosis of the prostate cancer, which may reduce the burden of radiologists and improve the early diagnosis of prostate cancer.

Precise localization of microvascular invasion in hepatocellular carcinoma based on three-dimensional histology-MR image fusion: an ex vivo experimental study

Background

Microvascular invasion (MVI) is an independent risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). However, MVI cannot be detected by conventional imaging. To localize MVI precisely on magnetic resonance (MR) images, we evaluated the feasibility and accuracy of 3-dimensional (3D) histology-MR image fusion of the liver.

Methods

Animal models of VX2 liver tumors were established in 10 New Zealand white rabbits under ultrasonographic guidance. The whole liver lobe containing the VX2 tumor was extracted and divided into 4 specimens, for a total of 40 specimens. MR images were obtained with a T2-weighted sequence for each specimen, and then histological images were obtained by intermittent, serial pathological sections. 3D histology-MR image fusion was performed via landmark registration in 3D Slicer software. We calculated the success rate and registration errors of image fusion, and then we located the MVI on MR images. Regarding influencing factors, we evaluated the uniformity of tissue thickness after sampling and the uniformity of tissue shrinkage after dehydration.

Results

The VX2 liver tumor model was successfully established in the 10 rabbits. The incidence of MVI was 80% (8/10). 3D histology-MR image fusion was successfully performed in the 39 specimens, and the success rate was 97.5% (39/40). The average registration error was 0.44±0.15 mm. MVI was detected in 20 of the 39 successfully registered specimens, resulting in a total of 166 MVI lesions. The specific location of all MVI lesions was accurately identified on MR images using 3D histology-MR image fusion. All MVI lesions showed as slightly hyperintense on the high-resolution MR T2-weighted images. The results of the influencing factor assessment showed that the tissue thickness was uniform after sampling (P=0.38), but the rates of the tissue shrinkage was inconsistent after dehydration (P<0.001).

Conclusions

3D histology-MR image fusion of the isolated liver tumor model is feasible and accurate and allows for the successful identification of the specific location of MVI on MR images.

A novel Bayesian functional spatial partitioning method with application to prostate cancer lesion detection using MRI

Spatial partitioning methods correct for nonstationarity in spatially related data by partitioning the space into regions of local stationarity. Existing spatial partitioning methods can only estimate linear partitioning boundaries. This is inadequate for detecting an arbitrarily shaped anomalous spatial region within a larger area. We propose a novel Bayesian functional spatial partitioning (BFSP) algorithm, which estimates closed curves that act as partitioning boundaries around anomalous regions of data with a distinct distribution or spatial process. Our method utilizes transitions between a fixed Cartesian and moving polar coordinate system to model the smooth boundary curves using functional estimation tools. Using adaptive Metropolis-Hastings, the BFSP algorithm simultaneously estimates the partitioning boundary and the parameters of the spatial distributions within each region. Through simulation we show that our method is robust to shape of the target zone and region-specific spatial processes. We illustrate our method through the detection of prostate cancer lesions using magnetic resonance imaging.

Bridging the gap between prostate radiology and pathology through machine learning

Background

Prostate cancer remains the second deadliest cancer for American men despite clinical advancements. Currently, magnetic resonance imaging (MRI) is considered the most sensitive non‐invasive imaging modality that enables visualization, detection, and localization of prostate cancer, and is increasingly used to guide targeted biopsies for prostate cancer diagnosis. However, its utility remains limited due to high rates of false positives and false negatives as well as low inter‐reader agreements.

Purpose

Machine learning methods to detect and localize cancer on prostate MRI can help standardize radiologist interpretations. However, existing machine learning methods vary not only in model architecture, but also in the ground truth labeling strategies used for model training. We compare different labeling strategies and the effects they have on the performance of different machine learning models for prostate cancer detection on MRI.

Methods

Four different deep learning models (SPCNet, U‐Net, branched U‐Net, and DeepLabv3+) were trained to detect prostate cancer on MRI using 75 patients with radical prostatectomy, and evaluated using 40 patients with radical prostatectomy and 275 patients with targeted biopsy. Each deep learning model was trained with four different label types: pathology‐confirmed radiologist labels, pathologist labels on whole‐mount histopathology images, and lesion‐level and pixel‐level digital pathologist labels (previously validated deep learning algorithm on histopathology images to predict pixel‐level Gleason patterns) on whole‐mount histopathology images. The pathologist and digital pathologist labels (collectively referred to as pathology labels) were mapped onto pre‐operative MRI using an automated MRI‐histopathology registration platform.

Results

Radiologist labels missed cancers (ROC‐AUC: 0.75‐0.84), had lower lesion volumes (~68% of pathology lesions), and lower Dice overlaps (0.24‐0.28) when compared with pathology labels. Consequently, machine learning models trained with radiologist labels also showed inferior performance compared to models trained with pathology labels. Digital pathologist labels showed high concordance with pathologist labels of cancer (lesion ROC‐AUC: 0.97‐1, lesion Dice: 0.75‐0.93). Machine learning models trained with digital pathologist labels had the highest lesion detection rates in the radical prostatectomy cohort (aggressive lesion ROC‐AUC: 0.91‐0.94), and had generalizable and comparable performance to pathologist label‐trained‐models in the targeted biopsy cohort (aggressive lesion ROC‐AUC: 0.87‐0.88), irrespective of the deep learning architecture. Moreover, machine learning models trained with pixel‐level digital pathologist labels were able to selectively identify aggressive and indolent cancer components in mixed lesions on MRI, which is not possible with any human‐annotated label type.

Conclusions

Machine learning models for prostate MRI interpretation that are trained with digital pathologist labels showed higher or comparable performance with pathologist label‐trained models in both radical prostatectomy and targeted biopsy cohort. Digital pathologist labels can reduce challenges associated with human annotations, including labor, time, inter‐ and intra‐reader variability, and can help bridge the gap between prostate radiology and pathology by enabling the training of reliable machine learning models to detect and localize prostate cancer on MRI.

Bayesian spatial models for voxel-wise prostate cancer classification using multi-parametric magnetic resonance imaging data

Multi-parametric magnetic resonance imaging (mpMRI) has been playing an increasingly important role in the detection of prostate cancer (PCa). Various computer-aided detection algorithms were proposed for automated PCa detection by combining information in multiple mpMRI parameters. However, there are specific features of mpMRI, including between-voxel correlation within each prostate and heterogeneity across patients, that have not been fully explored but could potentially improve PCa detection if leveraged appropriately. This article proposes novel Bayesian approaches for voxel-wise PCa classification that accounts for spatial correlation and between-patient heterogeneity in the mpMRI data. Modeling the spatial correlation is challenging due to the extreme high dimensionality of the data, and we propose three scalable approaches based on Nearest Neighbor Gaussian Process (NNGP), reduced-rank approximation, and a conditional autoregressive (CAR) model that approximates a Gaussian Process with the Matérn covariance, respectively. Our simulation study shows that properly modeling the spatial correlation and between-patient heterogeneity can substantially improve PCa classification. Application to in vivo data illustrates that classification is improved by all three spatial modeling approaches considered, while modeling the between-patient heterogeneity does not further improve our classifiers. Among the proposed models, the NNGP-based model is recommended given its high classification accuracy and computational efficiency.

A review of artificial intelligence in prostate cancer detection on imaging

A multitude of studies have explored the role of artificial intelligence (AI) in providing diagnostic support to radiologists, pathologists, and urologists in prostate cancer detection, risk-stratification, and management. This review provides a comprehensive overview of relevant literature regarding the use of AI models in (1) detecting prostate cancer on radiology images (magnetic resonance and ultrasound imaging), (2) detecting prostate cancer on histopathology images of prostate biopsy tissue, and (3) assisting in supporting tasks for prostate cancer detection (prostate gland segmentation, MRI-histopathology registration, MRI-ultrasound registration). We discuss both the potential of these AI models to assist in the clinical workflow of prostate cancer diagnosis, as well as the current limitations including variability in training data sets, algorithms, and evaluation criteria. We also discuss ongoing challenges and what is needed to bridge the gap between academic research on AI for prostate cancer and commercial solutions that improve routine clinical care.

Selective identification and localization of indolent and aggressive prostate cancers via CorrSigNIA: an MRI-pathology correlation and deep learning framework

Automated methods for detecting prostate cancer and distinguishing indolent from aggressive disease on Magnetic Resonance Imaging (MRI) could assist in early diagnosis and treatment planning. Existing automated methods of prostate cancer detection mostly rely on ground truth labels with limited accuracy, ignore disease pathology characteristics observed on resected tissue, and cannot selectively identify aggressive (Gleason Pattern≥4) and indolent (Gleason Pattern=3) cancers when they co-exist in mixed lesions. In this paper, we present a radiology-pathology fusion approach, CorrSigNIA, for the selective identification and localization of indolent and aggressive prostate cancer on MRI. CorrSigNIA uses registered MRI and whole-mount histopathology images from radical prostatectomy patients to derive accurate ground truth labels and learn correlated features between radiology and pathology images. These correlated features are then used in a convolutional neural network architecture to detect and localize normal tissue, indolent cancer, and aggressive cancer on prostate MRI. CorrSigNIA was trained and validated on a dataset of 98 men, including 74 men that underwent radical prostatectomy and 24 men with normal prostate MRI. CorrSigNIA was tested on three independent test sets including 55 men that underwent radical prostatectomy, 275 men that underwent targeted biopsies, and 15 men with normal prostate MRI. CorrSigNIA achieved an accuracy of 80% in distinguishing between men with and without cancer, a lesion-level ROC-AUC of 0.81±0.31 in detecting cancers in both radical prostatectomy and biopsy cohort patients, and lesion-levels ROC-AUCs of 0.82±0.31 and 0.86±0.26 in detecting clinically significant cancers in radical prostatectomy and biopsy cohort patients respectively. CorrSigNIA consistently outperformed other methods across different evaluation metrics and cohorts. In clinical settings, CorrSigNIA may be used in prostate cancer detection as well as in selective identification of indolent and aggressive components of prostate cancer, thereby improving prostate cancer care by helping guide targeted biopsies, reducing unnecessary biopsies, and selecting and planning treatment.

Multi-resolution super learner for voxel-wise classification of prostate cancer using multi-parametric MRI

Multi-parametric MRI (mpMRI) is a critical tool in prostate cancer (PCa) diagnosis and management. To further advance the use of mpMRI in patient care, computer aided diagnostic methods are under continuous development for supporting/supplanting standard radiological interpretation. While voxel-wise PCa classification models are the gold standard, few if any approaches have incorporated the inherent structure of the mpMRI data, such as spatial heterogeneity and between-voxel correlation, into PCa classification. We propose a machine learning-based method to fill in this gap. Our method uses an ensemble learning approach to capture regional heterogeneity in the data, where classifiers are developed at multiple resolutions and combined using the super learner algorithm, and further account for between-voxel correlation through a Gaussian kernel smoother. It allows any type of classifier to be the base learner and can be extended to further classify PCa sub-categories. We introduce the algorithms for binary PCa classification, as well as for classifying the ordinal clinical significance of PCa for which a weighted likelihood approach is implemented to improve the detection of less prevalent cancer categories. The proposed method has shown important advantages over conventional modeling and machine learning approaches in simulations and application to our motivating patient data.

Fully Automatic Registration Methods for Chest X-Ray Images

Purpose

Image registration is important in medical applications accomplished by improving healthcare technology in recent years. Various studies have been proposed in medical applications, including clinical track of events and updating the treatment plan for radiotherapy and surgery. This study presents a fully automatic registration system for chest X-ray images to generate fusion results for difference analysis. Using the accurate alignment of the proposed system, the fusion result indicates the differences in the thoracic area during the treatment process.

Methods

The proposed method consists of a data normalization method, a hybrid L-SVM model to detect lungs, ribs and clavicles for object recognition, a landmark matching algorithm, two-stage transformation approaches and a fusion method for difference analysis to highlight the differences in the thoracic area. In evaluation, a preliminary test was performed to compare three transformation models, with a full evaluation process to compare the proposed method with two existing elastic registration methods.

Results

The results show that the proposed method produces significantly better results than two benchmark methods (P-value \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\le$$\end{document}≤ 0.001). The proposed system achieves the lowest mean registration error distance (MRED) (8.99 mm, 23.55 pixel) and the lowest mean registration error ratio (MRER) w.r.t. the length of image diagonal (1.61%) compared to the two benchmark approaches with MRED (15.64 mm, 40.97 pixel) and (180.5 mm, 472.69 pixel) and MRER (2.81%) and (32.51%), respectively.

Conclusions

The experimental results show that the proposed method is capable of accurately aligning the chest X-ray images acquired at different times, assisting doctors to trace individual health status, evaluate treatment effectiveness and monitor patient recovery progress for thoracic diseases.

Correlation of in-vivo imaging with histopathology: A review

Despite tremendous advancements in in vivo imaging modalities, there remains substantial uncertainty with respect to tumor delineation on in these images. Histopathology remains the gold standard for determining the extent of malignancy, with in vivo imaging to histopathologic correlation enabling spatial comparisons. In this review, the steps necessary for successful imaging to histopathologic correlation are described, including in vivo imaging, resection, fixation, specimen sectioning (sectioning technique, securing technique, orientation matching, slice matching), microtome sectioning and staining, correlation (including image registration) and performance evaluation. The techniques used for each of these steps are also discussed. Hundreds of publications from the past 20 years were surveyed, and 62 selected for detailed analysis. For these 62 publications, each stage of the correlative pathology process (and the sub-steps of specimen sectioning) are listed. A statistical analysis was conducted based on 19 studies that reported target registration error as their performance metric. While some methods promise greater accuracy, they may be expensive. Due to the complexity of the processes involved, correlative pathology studies generally include a small number of subjects, which hinders advanced developments in this field.

Automated detection of aggressive and indolent prostate cancer on magnetic resonance imaging

PURPOSE

While multi-parametric magnetic resonance imaging (MRI) shows great promise in assisting with prostate cancer diagnosis and localization, subtle differences in appearance between cancer and normal tissue lead to many false positive and false negative interpretations by radiologists. We sought to automatically detect aggressive cancer (Gleason pattern ≥ 4) and indolent cancer (Gleason pattern 3) on a per-pixel basis on MRI to facilitate the targeting of aggressive cancer during biopsy.

METHODS

We created the Stanford Prostate Cancer Network (SPCNet), a convolutional neural network model, trained to distinguish between aggressive cancer, indolent cancer, and normal tissue on MRI. Ground truth cancer labels were obtained by registering MRI with whole-mount digital histopathology images from patients who underwent radical prostatectomy. Before registration, these histopathology images were automatically annotated to show Gleason patterns on a per-pixel basis. The model was trained on data from 78 patients who underwent radical prostatectomy and 24 patients without prostate cancer. The model was evaluated on a pixel and lesion level in 322 patients, including six patients with normal MRI and no cancer, 23 patients who underwent radical prostatectomy, and 293 patients who underwent biopsy. Moreover, we assessed the ability of our model to detect clinically significant cancer (lesions with an aggressive component) and compared it to the performance of radiologists.

RESULTS

Our model detected clinically significant lesions with an area under the receiver operator characteristics curve of 0.75 for radical prostatectomy patients and 0.80 for biopsy patients. Moreover, the model detected up to 18% of lesions missed by radiologists, and overall had a sensitivity and specificity that approached that of radiologists in detecting clinically significant cancer.

CONCLUSIONS

Our SPCNet model accurately detected aggressive prostate cancer. Its performance approached that of radiologists, and it helped identify lesions otherwise missed by radiologists. Our model has the potential to assist physicians in specifically targeting the aggressive component of prostate cancers during biopsy or focal treatment.

Registration of histopathology to magnetic resonance imaging of prostate cancer

BACKGROUND AND PURPOSE

The diagnostic accuracy of new imaging techniques requires validation, preferably by histopathological verification. The aim of this study was to develop and present a registration procedure between histopathology and in-vivo magnetic resonance imaging (MRI) of the prostate, to estimate its uncertainty and to evaluate the benefit of adding a contour-correcting registration.

MATERIALS AND METHODS

For twenty-five prostate cancer patients, planned for radical prostatectomy, a 3D-printed prostate mold based on in-vivo MRI was created and an ex-vivo MRI of the specimen, placed inside the mold, was performed. Each histopathology slice was registered to its corresponding ex-vivo MRI slice using a 2D-affine registration. The ex-vivo MRI was rigidly registered to the in-vivo MRI and the resulting transform was applied to the histopathology stack. A 2D deformable registration was used to correct for specimen distortion concerning the specimen's fit inside the mold. We estimated the spatial uncertainty by comparing positions of landmarks in the in-vivo MRI and the corresponding registered histopathology stack.

RESULTS

Eighty-four landmarks were identified, located in the urethra (62%), prostatic cysts (33%), and the ejaculatory ducts (5%). The median number of landmarks was 3 per patient. We showed a median in-plane error of 1.8 mm before and 1.7 mm after the contour-correcting deformable registration. In patients with extraprostatic margins, the median in-plane error improved from 2.1 mm to 1.8 mm after the contour-correcting deformable registration.

CONCLUSIONS

Our registration procedure accurately registers histopathology to in-vivo MRI, with low uncertainty. The contour-correcting registration was beneficial in patients with extraprostatic surgical margins.

The impact of the co-registration technique and analysis methodology in comparison studies between advanced imaging modalities and whole-mount-histology reference in primary prostate cancer

Comparison studies using histopathology as standard of reference enable a validation of the diagnostic performance of imaging methods. This study analysed (1) the impact of different image-histopathology co-registration pathways, (2) the impact of the applied data analysis method and (3) intraindividually compared multiparametric magnet resonance tomography (mpMRI) and prostate specific membrane antigen positron emission tomography (PSMA-PET) by using the different approaches. Ten patients with primary PCa who underwent mpMRI and [¹⁸F]PSMA-1007 PET/CT followed by prostatectomy were prospectively enrolled. We demonstrate that the choice of the intermediate registration step [(1) via ex-vivo CT or (2) mpMRI] does not significantly affect the performance of the registration framework. Comparison of analysis methods revealed that methods using high spatial resolutions e.g. quadrant-based slice-by-slice analysis are beneficial for a differentiated analysis of performance, compared to methods with a lower resolution (segment-based analysis with 6 or 18 segments and lesions-based analysis). Furthermore, PSMA-PET outperformed mpMRI for intraprostatic PCa detection in terms of sensitivity (median %: 83-85 vs. 60-69, p < 0.04) with similar specificity (median %: 74-93.8 vs. 100) using both registration pathways. To conclude, the choice of an intermediate registration pathway does not significantly affect registration performance, analysis methods with high spatial resolution are preferable and PSMA-PET outperformed mpMRI in terms of sensitivity in our cohort.

ProsRegNet: A deep learning framework for registration of MRI and histopathology images of the prostate

Magnetic resonance imaging (MRI) is an increasingly important tool for the diagnosis and treatment of prostate cancer. However, interpretation of MRI suffers from high inter-observer variability across radiologists, thereby contributing to missed clinically significant cancers, overdiagnosed low-risk cancers, and frequent false positives. Interpretation of MRI could be greatly improved by providing radiologists with an answer key that clearly shows cancer locations on MRI. Registration of histopathology images from patients who had radical prostatectomy to pre-operative MRI allows such mapping of ground truth cancer labels onto MRI. However, traditional MRI-histopathology registration approaches are computationally expensive and require careful choices of the cost function and registration hyperparameters. This paper presents ProsRegNet, a deep learning-based pipeline to accelerate and simplify MRI-histopathology image registration in prostate cancer. Our pipeline consists of image preprocessing, estimation of affine and deformable transformations by deep neural networks, and mapping cancer labels from histopathology images onto MRI using estimated transformations. We trained our neural network using MR and histopathology images of 99 patients from our internal cohort (Cohort 1) and evaluated its performance using 53 patients from three different cohorts (an additional 12 from Cohort 1 and 41 from two public cohorts). Results show that our deep learning pipeline has achieved more accurate registration results and is at least 20 times faster than a state-of-the-art registration algorithm. This important advance will provide radiologists with highly accurate prostate MRI answer keys, thereby facilitating improvements in the detection of prostate cancer on MRI. Our code is freely available at https://github.com/pimed//ProsRegNet.

3D Registration of pre-surgical prostate MRI and histopathology images via super-resolution volume reconstruction

The use of MRI for prostate cancer diagnosis and treatment is increasing rapidly. However, identifying the presence and extent of cancer on MRI remains challenging, leading to high variability in detection even among expert radiologists. Improvement in cancer detection on MRI is essential to reducing this variability and maximizing the clinical utility of MRI. To date, such improvement has been limited by the lack of accurately labeled MRI datasets. Data from patients who underwent radical prostatectomy enables the spatial alignment of digitized histopathology images of the resected prostate with corresponding pre-surgical MRI. This alignment facilitates the delineation of detailed cancer labels on MRI via the projection of cancer from histopathology images onto MRI. We introduce a framework that performs 3D registration of whole-mount histopathology images to pre-surgical MRI in three steps. First, we developed a novel multi-image super-resolution generative adversarial network (miSRGAN), which learns information useful for 3D registration by producing a reconstructed 3D MRI. Second, we trained the network to learn information between histopathology slices to facilitate the application of 3D registration methods. Third, we registered the reconstructed 3D histopathology volumes to the reconstructed 3D MRI, mapping the extent of cancer from histopathology images onto MRI without the need for slice-to-slice correspondence. When compared to interpolation methods, our super-resolution reconstruction resulted in the highest PSNR relative to clinical 3D MRI (32.15 dB vs 30.16 dB for BSpline interpolation). Moreover, the registration of 3D volumes reconstructed via super-resolution for both MRI and histopathology images showed the best alignment of cancer regions when compared to (1) the state-of-the-art RAPSODI approach, (2) volumes that were not reconstructed, or (3) volumes that were reconstructed using nearest neighbor, linear, or BSpline interpolations. The improved 3D alignment of histopathology images and MRI facilitates the projection of accurate cancer labels on MRI, allowing for the development of improved MRI interpretation schemes and machine learning models to automatically detect cancer on MRI.

Histological Validation of MRI: A Review of Challenges in Registration of Imaging and Whole-Mount Histopathology

Rigorous validation with ground truth information such as histology is needed to reliably assess the current and potential value of MRI techniques to characterize tissue and identify disease-related tissue alterations. Commonly used methods that aim to directly correlate histology and MRI data generally fall short of this goal due to spatial errors that preclude direct matching. Errors result from tissue deformation, differences in spatial resolution and slice thickness, non-coplanar and/or nonintersecting plane orientations, and different image contrast mechanisms. Some of these problems arise from limitations in standard protocols for clinical tissue processing and histology-based pathology reporting, and to some extent can be addressed by modifications to standard protocols without compromising the clinical process. Typical modifications include ex vivo specimen MRI, block-face photography, addition of fiducial markers, and 3D printed molds to constrain tissue deformation and guide sectioning. This review summarizes the advantages and limitations of MRI validation techniques based on coregistration of MRI with whole-mount histology of tissue specimens. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY STAGE: 1.

Registration of presurgical MRI and histopathology images from radical prostatectomy via RAPSODI

PURPOSE

Magnetic resonance imaging (MRI) has great potential to improve prostate cancer diagnosis; however, subtle differences between cancer and confounding conditions render prostate MRI interpretation challenging. The tissue collected from patients who undergo radical prostatectomy provides a unique opportunity to correlate histopathology images of the prostate with preoperative MRI to accurately map the extent of cancer from histopathology images onto MRI. We seek to develop an open-source, easy-to-use platform to align presurgical MRI and histopathology images of resected prostates in patients who underwent radical prostatectomy to create accurate cancer labels on MRI.

METHODS

Here, we introduce RAdiology Pathology Spatial Open-Source multi-Dimensional Integration (RAPSODI), the first open-source framework for the registration of radiology and pathology images. RAPSODI relies on three steps. First, it creates a three-dimensional (3D) reconstruction of the histopathology specimen as a digital representation of the tissue before gross sectioning. Second, RAPSODI registers corresponding histopathology and MRI slices. Third, the optimized transforms are applied to the cancer regions outlined on the histopathology images to project those labels onto the preoperative MRI.

RESULTS

We tested RAPSODI in a phantom study where we simulated various conditions, for example, tissue shrinkage during fixation. Our experiments showed that RAPSODI can reliably correct multiple artifacts. We also evaluated RAPSODI in 157 patients from three institutions that underwent radical prostatectomy and have very different pathology processing and scanning. RAPSODI was evaluated in 907 corresponding histpathology-MRI slices and achieved a Dice coefficient of 0.97 ± 0.01 for the prostate, a Hausdorff distance of 1.99 ± 0.70 mm for the prostate boundary, a urethra deviation of 3.09 ± 1.45 mm, and a landmark deviation of 2.80 ± 0.59 mm between registered histopathology images and MRI.

CONCLUSION

Our robust framework successfully mapped the extent of cancer from histopathology slices onto MRI providing labels from training machine learning methods to detect cancer on MRI.

Accurate validation of ultrasound imaging of prostate cancer: a review of challenges in registration of imaging and histopathology

As the development of modalities for prostate cancer (PCa) imaging advances, the challenge of accurate registration between images and histopathologic ground truth becomes more pressing. Localization of PCa, rather than detection, requires a pixel-to-pixel validation of imaging based on histopathology after radical prostatectomy. Such a registration procedure is challenging for ultrasound modalities; not only the deformations of the prostate after resection have to be taken into account, but also the deformation due to the employed transrectal probe and the mismatch in orientation between imaging planes and pathology slices. In this work, we review the latest techniques to facilitate accurate validation of PCa localization in ultrasound imaging studies and extrapolate a general strategy for implementation of a registration procedure.

Detection of prostate cancer with multiparametric MRI utilizing the anatomic structure of the prostate

Multiparametric magnetic resonance imaging (mpMRI), which combines traditional anatomic and newer quantitative MRI methods, has been shown to result in improved voxel-wise classification of prostate cancer as compared with any single MRI parameter. While these results are promising, substantial heterogeneity in the mpMRI parameter values and voxel-wise prostate cancer risk has been observed both between and within regions of the prostate. This suggests that classification of prostate cancer can potentially be improved by incorporating structural information into the classifier. In this paper, we propose a novel voxel-wise classifier of prostate cancer that accounts for the anatomic structure of the prostate by Bayesian hierarchical modeling, which can be combined with post hoc spatial Gaussian kernel smoothing to account for residual spatial correlation. Our proposed classifier results in significantly improved area under the ROC curve (0.822 vs 0.729, P < .001) and sensitivity corresponding to 90% specificity (0.599 vs 0.429, P < .001), compared with a baseline model that does not account for the anatomic structure of the prostate. Furthermore, the classifier can also be applied on voxels with missing mpMRI parameters, resulting in similar performance, which is an important practical consideration that cannot be easily accommodated using regression-based classifiers. In addition, our classifier achieved high computational efficiency with a closed-form solution for the posterior predictive cancer probability.

Registration Accuracy of Patient-Specific, Three-Dimensional-Printed Prostate Molds for Correlating Pathology With Magnetic Resonance Imaging

OBJECTIVE

This investigation was performed to evaluate the registration accuracy between magnetic resonance imaging (MRI) and pathology using three-dimensional (3-D) printed molds.

METHODS

Tissue-mimicking prostate phantoms were manufactured with embedded fiducials. The fiducials were used to measure and compare target registration error (TRE) between phantoms that were sliced by hand versus phantoms that were sliced within 3-D-printed molds. Subsequently, ten radical prostatectomy specimens were placed inside molds, scanned with MRI, and then sliced. The ex vivo scan was used to assess the true location of whole mount (WM) slides relative to in vivo MRI. The TRE between WM and in vivo MRI was measured using anatomic landmarks.

RESULTS

Manually sliced phantoms had a 4.1-mm mean TRE, whereas mold-sliced phantoms had a 1.9-mm mean TRE. Similarly, mold-assisted slicing reduced mean angular misalignment around the left-right (LR) anatomic axis from 10.7° to 4.5°. However, ex vivo MRI revealed that excised prostates were misaligned within molds, including a mean 14° rotation about the LR axis. The mean in-plane TRE was 3.3 mm using molds alone and 2.2 mm after registration was corrected with ex vivo MRI.

CONCLUSION

Patient-specific molds improved accuracy relative to manual slicing techniques in a phantom model. However, the registration accuracy of surgically resected specimens was limited by their imperfect fit within molds. This limitation can be overcome with the addition of ex vivo imaging.

SIGNIFICANCE

The accuracy of 3-D-printed molds was characterized, quantifying their utility for facilitating MRI-pathology registration.

Development of a measure for evaluating lesion-wise performance of CAD algorithms in the context of mpMRI detection of prostate cancer

PURPOSE

Computer-aided detection/diagnosis (CAD) of prostate cancer (PCa) on multiparametric MRI (mpMRI) is an active area of research. In the literature, the performance of predictive models trained to detect PCa on mpMRI has typically been reported in terms of voxel-wise measures such as sensitivity and specificity and/or area under the receiver operating curve (AUC). However, it is unclear whether models that score higher by these measures are actually superior. Here, we propose a novel method for lesion identification as well as novel measures that assess the quality of the detected lesions.

METHODS

A total of 46 axial MRI slices of interest from 34 patients and the associated histopathologic ground truths were used to develop and to characterize the proposed measures. The proposed lesion-wise score s_ℓ is based on the Jaccard similarity index with modifications that emphasize the overlap and colocalization of predicted lesions with ground truth lesions. Thresholding of s_ℓ allowed for the sensitivity and specificity of lesion detection to be assessed, while the proposed lesion-summary score s_σ is a weighted average of s_ℓ s that provides a single summary statistic of lesion detection performance. The proposed measures were used to compare the lesion detection performance of a predictive model vs that of a radiologist on the same data set. The measures were also used to evaluate the degree to which viewing the cancer prediction improved diagnostic accuracy.

RESULTS

The lesion-wise score qualitatively reflected the goodness of predicted lesions over a wide range of values (s_ℓ = 0.1 to s_ℓ = 0.8) and was found to encompass a larger range of values than the Dice coefficient did over the same range of prediction qualities (0-0.9 vs 0-0.75). The lesion-summary score was shown to vary linearly with voxel-wise sensitivity and quadratically with voxel-wise specificity and correlated well with voxel-wise AUC (ρ = 0.68) and the Dice coefficient (ρ = 0.88). Radiologist performance was found to be significantly improved after viewing the model-generated cancer prediction maps as quantified by both s_σ (P = 0.01) and DSC (P = 0.04), with improvements in both lesion detection sensitivity and specificity.

CONCLUSION

The proposed measures allow for the assessment of lesion detection performance, which is most relevant in a clinical setting and would not be possible to do with voxel-wise measures alone.

Improved Magnetic Resonance Imaging-Pathology Correlation With Imaging-Derived, 3D-Printed, Patient-Specific Whole-Mount Molds of the Prostate

OBJECTIVES

The aim of this study was to compare the anatomical registration of preoperative magnetic resonance imaging (MRI) and prostate whole-mount obtained with 3D-printed, patient-specific, MRI-derived molds (PSM) versus conventional whole-mount sectioning (WMS).

MATERIALS AND METHODS

Based on an a priori power analysis, this institutional review board-approved study prospectively included 50 consecutive men who underwent 3 T multiparametric prostate MRI followed by radical prostatectomy. Two blinded and independent readers (R1 and R2) outlined the contours of the prostate, tumor, peripheral, and transition zones in the MRI scans using regions of interest. These were compared with the corresponding regions of interest from the whole-mounted histopathology, the reference standard, using PSM whole-mount results obtained in the study group (n = 25) or conventional WMS in the control group (n = 25). The spatial overlap across the MRI and histology data sets was calculated using the Dice similarity coefficient (DSC) for the prostate overall (DSCprostate), tumor (DSCtumor), peripheral (DSCPZ), and transition (DSCTZ) zone. Results in the study and control groups were compared using Wilcoxon rank sum test.

RESULTS

The MRI histopathology anatomical registration for the prostate gland overall, tumor, peripheral, and transition zones were significantly superior with the use of PSMs (DSCs for R1: 0.95, 0.86, 0.84, and 0.89; for R2: 0.93, 0.75, 0.78, and 0.85, respectively) than with the use of standard WMS (R1: 0.85, 0.46, 0.66, and 0.69; R2: 0.85, 0.46, 0.66, and 0.69) (P < 0.0001).

CONCLUSIONS

The use of PSMs for prostate specimen whole-mount sectioning provides significantly superior anatomical registration of in vivo multiparametric MRI and ex vivo prostate whole-mounts than conventional WMS.

Intensity-based volumetric registration of magnetic resonance images and whole-mount sections of the prostate

OBJECTIVE

Magnetic Resonance Imaging (MRI) of the prostate provides useful in vivo diagnostic tissue information such as tumor location and aggressiveness, but ex vivo histopathology remains the ground truth. There are several challenges related to the registration of MRI to histopathology. We present a method for registration of standard clinical T2-weighted MRI (T2W-MRI) and transverse histopathology whole-mount (WM) sections of the prostate.

METHODS

An isotropic volume stack was created from the WM sections using 2D rigid and deformable registration combined with linear interpolation. The prostate was segmented manually from the T2W-MRI volume and registered to the WM section volume using a combination of affine and deformable registration. The method was evaluated on a set of 12 patients who had undergone radical prostatectomy. Registration accuracy was assessed using volume overlap (Dice Coefficient, DC) and landmark distances.

RESULTS

The DC was 0.94 for the whole prostate, 0.63 for the peripheral zone and 0.77 for the remaining gland. The landmark distances were on average 5.4 mm.

CONCLUSION

The volume overlap for the whole prostate and remaining gland, as well as the landmark distances indicate good registration accuracy for the proposed method, and shows that it can be highly useful for registering clinical available MRI and WM sections of the prostate.

Prostate Cancer: A Correlative Study of Multiparametric MR Imaging and Digital Histopathology

Purpose To correlate multiparametric magnetic resonance (MR) imaging and quantitative digital histopathologic analysis (DHA) of the prostate. Materials and Methods This retrospective study was approved by the local institutional review board and was HIPAA compliant. Forty patients (median age, 60 years; age range, 44-71 years) who underwent prostate MR imaging consisting of T2-weighted and diffusion-weighted (DW) MR imaging along with subsequent robot-assisted radical prostatectomy gave informed consent to be included. Whole-mount tissue specimens were obtained with a patient-specific mold, and DHA was performed to assess the lumen, epithelium, stroma, and epithelial nucleus. These DHA images were registered with MR images and were correlated on a per-voxel basis. The relationship between MR imaging and DHA was assessed by using a linear mixed-effects model and the Pearson correlation coefficient. Results T2-weighted MR imaging, apparent diffusion coefficient (ADC) of DW imaging, and high-b-value DW imaging were significantly related to specific DHA parameters (P < .01). For instance, lumen density (ie, the percentage area of tissue components) was associated with T2-weighted MR imaging (slope = 0.36 ± 0.05 [standard error], γ = 0.35), ADC (slope = 0.47 ± 0.05, γ = 0.50), and high-b-value DW imaging (slope = -0.44 ± 0.05, γ = -0.44). Differences between regions harboring benign tissue and those harboring malignant tissue were observed at MR imaging and DHA (P < .01). Gleason score was significantly associated with MR imaging and DHA parameters (P < .05). For example, it was positively related to high-b-value DW imaging (slope = 0.21 ± 0.16, γ = 0.18) and negatively related to lumen density (slope = -0.19 ± 0.18, γ = -0.35). Conclusion Overall, significant associations were observed between MR imaging and DHA, regardless of prostate anatomy. ^© RSNA, 2017 Online supplemental material is available for this article.

Multiregional Radiogenomic Assessment of Prostate Microenvironments with Multiparametric MR Imaging and DNA Whole-Exome Sequencing of Prostate Glands with Adenocarcinoma

Purpose To assess the underlying genomic variation of prostate gland microenvironments of patients with prostate adenocarcinoma in the context of colocalized multiparametric magnetic resonance (MR) imaging and histopathologic assessment of normal and abnormal regions by using whole-exome sequencing. Materials and Methods Six patients with prostate adenocarcinoma who underwent robotic prostatectomy with whole-mount preservation of the prostate were identified, which enabled spatial mapping between preoperative multiparametric MR imaging and the gland. Four regions of interest were identified within each gland, including regions found to be normal and abnormal via histopathologic analysis. Whole-exome DNA sequencing (>50 times coverage) was performed on each of these spatially targeted regions. Radiogenomic analysis of imaging and mutation data were performed with hierarchical clustering, phylogenetic analysis, and principal component analysis. Results Radiogenomic multiparametric MR imaging and whole-exome spatial characterization in six patients with prostate adenocarcinoma (three patients, Gleason score of 3 + 4; and three patients, Gleason score of 4 + 5) was performed across 23 spatially distinct regions. Hierarchical clustering separated histopathologic analysis-proven high-grade lesions from the normal regions, and this reflected concordance between multiparametric MR imaging and resultant histopathologic analysis in all patients. Seventy-seven mutations involving 29 cancer-associated genes across the 23 spatially distinct prostate samples were identified. There was no significant difference in mutation load in cancer-associated genes between regions that were proven to be normal via histopathologic analysis (34 mutations per sample ± 19), mildly suspicious via multiparametric MR imaging (37 mutations per sample ± 21), intermediately suspicious via multiparametric MR imaging (31 mutations per sample ± 15), and high-grade cancer (33 mutations per sample ± 18) (P = .30). Principal component analysis resolved samples from different patients and further classified samples (regardless of histopathologic status) from prostate glands with Gleason score 3 + 4 versus 4 + 5 samples. Conclusion Multiregion spatial multiparametric MR imaging and whole-exome radiogenomic analysis of prostate glands with adenocarcinoma shows a continuum of mutations across regions that were found via histologic analysis to be high grade and normal. ^© RSNA, 2017 Online supplemental material is available for this article.

Apparatus for Histological Validation of In Vivo and Ex Vivo Magnetic Resonance Imaging of the Human Prostate

This article describes apparatus to aid histological validation of magnetic resonance imaging studies of the human prostate. The apparatus includes a 3D-printed patient-specific mold that facilitates aligned in vivo and ex vivo imaging, in situ tissue fixation, and tissue sectioning with minimal organ deformation. The mold and a dedicated container include MRI-visible landmarks to enable consistent tissue positioning and minimize image registration complexity. The inclusion of high spatial resolution ex vivo imaging aids in registration of in vivo MRI and histopathology data.

Evaluation of tongue squamous cell carcinoma resection margins using ex-vivo MR

Purpose

Purpose of this feasibility study was (1) to evaluate whether application of ex-vivo 7T MR of the resected tongue specimen containing squamous cell carcinoma may provide information on the resection margin status and (2) to evaluate the research and developmental issues that have to be solved for this technique to have the beneficial impact on clinical outcome that we expect: better oncologic and functional outcomes, better quality of life, and lower costs.

Methods

We performed a non-blinded validation of ex-vivo 7T MR to detect the tongue squamous cell carcinoma and resection margin in 10 fresh tongue specimens using histopathology as gold standard.

Results

In six of seven specimens with a histopathologically determined invasion depth of the tumor of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\ge }3$$\end{document}≥3 mm, the tumor could be recognized on MR, with a resection margin within a 2 mm range as compared to histopathology. In three specimens with an invasion depth of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${<}1$$\end{document}<1 mm, the tumor was not visible on MR. Technical limitations mainly included scan time, image resolution, and the fact that we used a less available small-bore 7T MR machine.

Conclusion

Ex-vivo 7T probably will have a low negative predictive value but a high positive predictive value, meaning that in tumors thicker than a few millimeters we expect to be able to predict whether the resection margin is too small. A randomized controlled trial needs to be performed to show our hypothesis: better oncologic and functional outcomes, better quality of life, and lower costs.

Computer-aided Detection of Prostate Cancer with MRI: Technology and Applications

One in six men will develop prostate cancer in his lifetime. Early detection and accurate diagnosis of the disease can improve cancer survival and reduce treatment costs. Recently, imaging of prostate cancer has greatly advanced since the introduction of multiparametric magnetic resonance imaging (mp-MRI). Mp-MRI consists of T2-weighted sequences combined with functional sequences including dynamic contrast-enhanced MRI, diffusion-weighted MRI, and magnetic resonance spectroscopy imaging. Because of the big data and variations in imaging sequences, detection can be affected by multiple factors such as observer variability and visibility and complexity of the lesions. To improve quantitative assessment of the disease, various computer-aided detection systems have been designed to help radiologists in their clinical practice. This review paper presents an overview of literatures on computer-aided detection of prostate cancer with mp-MRI, which include the technology and its applications. The aim of the survey is threefold: an introduction for those new to the field, an overview for those working in the field, and a reference for those searching for literature on a specific application.

Detection of Prostate Cancer: Quantitative Multiparametric MR Imaging Models Developed Using Registered Correlative Histopathology

Purpose To develop multiparametric magnetic resonance (MR) imaging models to generate a quantitative, user-independent, voxel-wise composite biomarker score (CBS) for detection of prostate cancer by using coregistered correlative histopathologic results, and to compare performance of CBS-based detection with that of single quantitative MR imaging parameters. Materials and Methods Institutional review board approval and informed consent were obtained. Patients with a diagnosis of prostate cancer underwent multiparametric MR imaging before surgery for treatment. All MR imaging voxels in the prostate were classified as cancer or noncancer on the basis of coregistered histopathologic data. Predictive models were developed by using more than one quantitative MR imaging parameter to generate CBS maps. Model development and evaluation of quantitative MR imaging parameters and CBS were performed separately for the peripheral zone and the whole gland. Model accuracy was evaluated by using the area under the receiver operating characteristic curve (AUC), and confidence intervals were calculated with the bootstrap procedure. The improvement in classification accuracy was evaluated by comparing the AUC for the multiparametric model and the single best-performing quantitative MR imaging parameter at the individual level and in aggregate. Results Quantitative T2, apparent diffusion coefficient (ADC), volume transfer constant (K(trans)), reflux rate constant (kep), and area under the gadolinium concentration curve at 90 seconds (AUGC90) were significantly different between cancer and noncancer voxels (P < .001), with ADC showing the best accuracy (peripheral zone AUC, 0.82; whole gland AUC, 0.74). Four-parameter models demonstrated the best performance in both the peripheral zone (AUC, 0.85; P = .010 vs ADC alone) and whole gland (AUC, 0.77; P = .043 vs ADC alone). Individual-level analysis showed statistically significant improvement in AUC in 82% (23 of 28) and 71% (24 of 34) of patients with peripheral-zone and whole-gland models, respectively, compared with ADC alone. Model-based CBS maps for cancer detection showed improved visualization of cancer location and extent. Conclusion Quantitative multiparametric MR imaging models developed by using coregistered correlative histopathologic data yielded a voxel-wise CBS that outperformed single quantitative MR imaging parameters for detection of prostate cancer, especially when the models were assessed at the individual level. (©) RSNA, 2016 Online supplemental material is available for this article.

Correlation of magnetic resonance imaging with digital histopathology in prostate

PURPOSE

We propose a systematic approach to correlate MRI and digital histopathology in prostate.

METHODS

T2-weighted (T2W) MRI and diffusion-weighted imaging (DWI) are acquired, and a patient-specific mold (PSM) is designed from the MRI. Following prostatectomy, a whole mount tissue specimen is placed in the PSM and sectioned, ensuring that tissue blocks roughly correspond to MRI slices. Rigid body and thin plate spline deformable registration attempt to correct deformation during image acquisition and tissue preparation and achieve a more complete one-to-one correspondence between MRIs and tissue sections. Each tissue section is stained with hematoxylin and eosin and segmented by adopting a machine learning approach. Utilizing this tissue segmentation and image registration, the density of cellular and tissue components (lumen, nucleus, epithelium, and stroma) is estimated per MR voxel, generating density maps for the whole prostate.

RESULTS

This study was approved by the local IRB, and informed consent was obtained from all patients. Registration of tissue specimens and MRIs was aided by the PSM and subsequent image registration. Tissue segmentation was performed using a machine learning approach, achieving ≥0.98 AUCs for lumen, nucleus, epithelium, and stroma. Examining the density map of tissue components, significant differences were observed between cancer, benign peripheral zone, and benign prostatic hyperplasia (p value <5e−2). Similarly, the signal intensity of the corresponding areas in both T2W MRI and DWI was significantly different (p value <1e−10).

CONCLUSIONS

The proposed approach is able to correlate MRI and digital histopathology of the prostate and is promising as a potential tool to facilitate a more cellular and zonal tissue-based analysis of prostate MRI, based upon a correlative histopathology perspective.

A system for evaluating magnetic resonance imaging of prostate cancer using patient-specific 3D printed molds

We have developed a system for evaluating magnetic resonance imaging of prostate cancer, using patient-specific 3D printed molds to facilitate MR-histology correlation. Prior to radical prostatectomy a patient receives a multiparametric MRI, which an expert genitourinary radiologist uses to identify and contour regions suspicious for disease. The same MR series is used to generate a prostate contour, which is the basis for design of a patient-specific mold. The 3D printed mold contains a series of evenly spaced parallel slits, each of which corresponds to a known MRI slice. After surgery, the patient's specimen is enclosed within the mold, and all whole-mount levels are obtained simultaneously through use of a multi-bladed slicing device. The levels are then formalin fixed, processed, and delivered to an expert pathologist, who identifies and grades all lesions within the slides. Finally, the lesion contours are loaded into custom software, which elastically warps them to fit the MR prostate contour. The suspicious regions on MR can then be directly compared to lesions on histology. Furthermore, the false-negative and false-positive regions on MR can be retrospectively examined, with the ultimate goal of developing methods for improving the predictive accuracy of MRI. This work presents the details of our analysis method, following a patient from diagnosis through the MR-histology correlation process. For this patient MRI successfully predicted the presence of cancer, but true lesion volume and extent were underestimated. Most cancer-positive regions missed on MR were observed to have patterns of low T2 signal, suggesting that there is potential to improve sensitivity.