Artificial intelligence in cancer imaging: Clinical challenges and applications.

Judgement, as one of the core tenets of medicine, relies upon the integration of multilayered data with nuanced decision making. Cancer offers a unique context for medical decisions given not only its variegated forms with evolution of disease but also the need to take into account the individual condition of patients, their ability to receive treatment, and their responses to treatment. Challenges remain in the accurate detection, characterization, and monitoring of cancers despite improved technologies. Radiographic assessment of disease most commonly relies upon visual evaluations, the interpretations of which may be augmented by advanced computational analyses. In particular, artificial intelligence (AI) promises to make great strides in the qualitative interpretation of cancer imaging by expert clinicians, including volumetric delineation of tumors over time, extrapolation of the tumor genotype and biological course from its radiographic phenotype, prediction of clinical outcome, and assessment of the impact of disease and treatment on adjacent organs. AI may automate processes in the initial interpretation of images and shift the clinical workflow of radiographic detection, management decisions on whether or not to administer an intervention, and subsequent observation to a yet to be envisioned paradigm. Here, the authors review the current state of AI as applied to medical imaging of cancer and describe advances in 4 tumor types (lung, brain, breast, and prostate) to illustrate how common clinical problems are being addressed. Although most studies evaluating AI applications in oncology to date have not been vigorously validated for reproducibility and generalizability, the results do highlight increasingly concerted efforts in pushing AI technology to clinical use and to impact future directions in cancer care.

Real-time active MR-tracking of metallic stylets in MR-guided radiation therapy.

PURPOSE: To develop an active MR-tracking system to guide placement of metallic devices for radiation therapy. METHODS: An actively tracked metallic stylet for brachytherapy was constructed by adding printed-circuit micro-coils to a commercial stylet. The coil design was optimized by electromagnetic simulation, and has a radio-frequency lobe pattern extending ∼5 mm beyond the strong B0 inhomogeneity region near the metal surface. An MR-tracking sequence with phase-field dithering was used to overcome residual effects of B0 and B1 inhomogeneities caused by the metal, as well as from inductive coupling to surrounding metallic stylets. The tracking system was integrated with a graphical workstation for real-time visualization. The 3 Tesla MRI catheter-insertion procedures were tested in phantoms and ex vivo animal tissue, and then performed in three patients during interstitial brachytherapy. RESULTS: The tracking system provided high-resolution (0.6 × 0.6 × 0.6 mm(3) ) and rapid (16 to 40 frames per second, with three to one phase-field dithering directions) catheter localization in phantoms, animals, and three gynecologic cancer patients. CONCLUSION: This is the first demonstration of active tracking of the shaft of metallic stylet in MR-guided brachytherapy. It holds the promise of assisting physicians to achieve better targeting and improving outcomes in interstitial brachytherapy.

Evaluation of mediastinal lymph node segmentation of heterogeneous CT data with full and weak supervision.

Accurate lymph node size estimation is critical for staging cancer patients, initial therapeutic management, and assessing response to therapy. Current standard practice for quantifying lymph node size is based on a variety of criteria that use uni-directional or bi-directional measurements. Segmentation in 3D can provide more accurate evaluations of the lymph node size. Fully convolutional neural networks (FCNs) have achieved state-of-the-art results in segmentation for numerous medical imaging applications, including lymph node segmentation. Adoption of deep learning segmentation models in clinical trials often faces numerous challenges. These include lack of pixel-level ground truth annotations for training, generalizability of the models on unseen test domains due to the heterogeneity of test cases and variation of imaging parameters. In this paper, we studied and evaluated the performance of lymph node segmentation models on a dataset that was completely independent of the one used to create the models. We analyzed the generalizability of the models in the face of a heterogeneous dataset and assessed the potential effects of different disease conditions and imaging parameters. Furthermore, we systematically compared fully-supervised and weakly-supervised methods in this context. We evaluated the proposed methods using an independent dataset comprising 806 mediastinal lymph nodes from 540 unique patients. The results show that performance achieved on the independent test set is comparable to that on the training set. Furthermore, neither the underlying disease nor the heterogeneous imaging parameters impacted the performance of the models. Finally, the results indicate that our weakly-supervised method attains 90%- 91% of the performance achieved by the fully supervised training.

CardioVision: A fully automated deep learning package for medical image segmentation and reconstruction generating digital twins for patients with aortic stenosis.

Aortic stenosis (AS) is the most prevalent heart valve disease in western countries that poses a significant public health challenge due to the lack of a medical treatment to prevent valve calcification. Given the aging population demographic, the prevalence of AS is projected to rise, resulting in a progressively significant healthcare and economic burden. While surgical aortic valve replacement (SAVR) has been the gold standard approach, the less invasive transcatheter aortic valve replacement (TAVR) is poised to become the dominant method for high- and medium-risk interventions. Computational simulations using patient-specific models, have opened new research avenues for optimizing emerging devices and predicting clinical outcomes. The traditional techniques of generating digital replicas of patients' aortic root, native valve, and calcification are time-consuming and labor-intensive processes requiring specialized tools and expertise in anatomy. Alternatively, deep learning models, such as the U-Net architecture, have emerged as reliable and fully automated methods for medical image segmentation. Two-dimensional U-Nets have been shown to produce comparable or more accurate results than trained clinicians' manual segmentation while significantly reducing computational costs. In this study, we have developed a fully automatic AI tool capable of reconstructing the digital twin geometry and analyzing the calcification distribution on the aortic valve. The developed automatic segmentation package enables the modeling of patient-specific anatomies, which can then be used to simulate virtual interventional procedures, optimize emerging prosthetic devices, and predict clinical outcomes.

Deep Learning for Detection and Localization of B-Lines in Lung Ultrasound.

Lung ultrasound (LUS) is an important imaging modality used by emergency physicians to assess pulmonary congestion at the patient bedside. B-line artifacts in LUS videos are key findings associated with pulmonary congestion. Not only can the interpretation of LUS be challenging for novice operators, but visual quantification of B-lines remains subject to observer variability. In this work, we investigate the strengths and weaknesses of multiple deep learning approaches for automated B-line detection and localization in LUS videos. We curate and publish, BEDLUS, a new ultrasound dataset comprising 1,419 videos from 113 patients with a total of 15,755 expert-annotated B-lines. Based on this dataset, we present a benchmark of established deep learning methods applied to the task of B-line detection. To pave the way for interpretable quantification of B-lines, we propose a novel "single-point" approach to B-line localization using only the point of origin. Our results show that (a) the area under the receiver operating characteristic curve ranges from 0.864 to 0.955 for the benchmarked detection methods, (b) within this range, the best performance is achieved by models that leverage multiple successive frames as input, and (c) the proposed single-point approach for B-line localization reaches an F 1-score of 0.65, performing on par with the inter-observer agreement. The dataset and developed methods can facilitate further biomedical research on automated interpretation of lung ultrasound with the potential to expand the clinical utility.

PROSTATE CANCER DIAGNOSIS WITH SPARSE BIOPSY DATA AND IN PRESENCE OF LOCATION UNCERTAINTY.

Prostate cancer is the second most prevalent cancer in men worldwide. Deep neural networks have been successfully applied for prostate cancer diagnosis in magnetic resonance images (MRI). Pathology results from biopsy procedures are often used as ground truth to train such systems. There are several sources of noise in creating ground truth from biopsy data including sampling and registration errors. We propose: 1) A fully convolutional neural network (FCN) to produce cancer probability maps across the whole prostate gland in MRI; 2) A Gaussian weighted loss function to train the FCN with sparse biopsy locations; 3) A probabilistic framework to model biopsy location uncertainty and adjust cancer probability given the deep model predictions. We assess the proposed method on 325 biopsy locations from 203 patients. We observe that the proposed loss improves the area under the receiver operating characteristic curve and the biopsy location adjustment improves the sensitivity of the models.

Domain adaptation for segmentation of critical structures for prostate cancer therapy.

Preoperative assessment of the proximity of critical structures to the tumors is crucial in avoiding unnecessary damage during prostate cancer treatment. A patient-specific 3D anatomical model of those structures, namely the neurovascular bundles (NVB) and the external urethral sphincters (EUS), can enable physicians to perform such assessments intuitively. As a crucial step to generate a patient-specific anatomical model from preoperative MRI in a clinical routine, we propose a multi-class automatic segmentation based on an anisotropic convolutional network. Our specific challenge is to train the network model on a unique source dataset only available at a single clinical site and deploy it to another target site without sharing the original images or labels. As network models trained on data from a single source suffer from quality loss due to the domain shift, we propose a semi-supervised domain adaptation (DA) method to refine the model's performance in the target domain. Our DA method combines transfer learning and uncertainty guided self-learning based on deep ensembles. Experiments on the segmentation of the prostate, NVB, and EUS, show significant performance gain with the combination of those techniques compared to pure TL and the combination of TL with simple self-learning ([Formula: see text] for all structures using a Wilcoxon's signed-rank test). Results on a different task and data (Pancreas CT segmentation) demonstrate our method's generic application capabilities. Our method has the advantage that it does not require any further data from the source domain, unlike the majority of recent domain adaptation strategies. This makes our method suitable for clinical applications, where the sharing of patient data is restricted.

Lung Nodule Malignancy Prediction in Sequential CT Scans: Summary of ISBI 2018 Challenge.

Lung cancer is by far the leading cause of cancer death in the US. Recent studies have demonstrated the effectiveness of screening using low dose CT (LDCT) in reducing lung cancer related mortality. While lung nodules are detected with a high rate of sensitivity, this exam has a low specificity rate and it is still difficult to separate benign and malignant lesions. The ISBI 2018 Lung Nodule Malignancy Prediction Challenge, developed by a team from the Quantitative Imaging Network of the National Cancer Institute, was focused on the prediction of lung nodule malignancy from two sequential LDCT screening exams using automated (non-manual) algorithms. We curated a cohort of 100 subjects who participated in the National Lung Screening Trial and had established pathological diagnoses. Data from 30 subjects were randomly selected for training and the remaining was used for testing. Participants were evaluated based on the area under the receiver operating characteristic curve (AUC) of nodule-wise malignancy scores generated by their algorithms on the test set. The challenge had 17 participants, with 11 teams submitting reports with method description, mandated by the challenge rules. Participants used quantitative methods, resulting in a reporting test AUC ranging from 0.698 to 0.913. The top five contestants used deep learning approaches, reporting an AUC between 0.87 - 0.91. The team's predictor did not achieve significant differences from each other nor from a volume change estimate (p =.05 with Bonferroni-Holm's correction).

PEP: Parameter Ensembling by Perturbation.

Ensembling is now recognized as an effective approach for increasing the predictive performance and calibration of deep networks. We introduce a new approach, Parameter Ensembling by Perturbation (PEP), that constructs an ensemble of parameter values as random perturbations of the optimal parameter set from training by a Gaussian with a single variance parameter. The variance is chosen to maximize the log-likelihood of the ensemble average ( L ) on the validation data set. Empirically, and perhaps surprisingly, L has a well-defined maximum as the variance grows from zero (which corresponds to the baseline model). Conveniently, calibration level of predictions also tends to grow favorably until the peak of L is reached. In most experiments, PEP provides a small improvement in performance, and, in some cases, a substantial improvement in empirical calibration. We show that this "PEP effect" (the gain in log-likelihood) is related to the mean curvature of the likelihood function and the empirical Fisher information. Experiments on ImageNet pre-trained networks including ResNet, DenseNet, and Inception showed improved calibration and likelihood. We further observed a mild improvement in classification accuracy on these networks. Experiments on classification benchmarks such as MNIST and CIFAR-10 showed improved calibration and likelihood, as well as the relationship between the PEP effect and overfitting; this demonstrates that PEP can be used to probe the level of overfitting that occurred during training. In general, no special training procedure or network architecture is needed, and in the case of pre-trained networks, no additional training is needed.

Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation.

Fully convolutional neural networks (FCNs), and in particular U-Nets, have achieved state-of-the-art results in semantic segmentation for numerous medical imaging applications. Moreover, batch normalization and Dice loss have been used successfully to stabilize and accelerate training. However, these networks are poorly calibrated i.e. they tend to produce overconfident predictions for both correct and erroneous classifications, making them unreliable and hard to interpret. In this paper, we study predictive uncertainty estimation in FCNs for medical image segmentation. We make the following contributions: 1) We systematically compare cross-entropy loss with Dice loss in terms of segmentation quality and uncertainty estimation of FCNs; 2) We propose model ensembling for confidence calibration of the FCNs trained with batch normalization and Dice loss; 3) We assess the ability of calibrated FCNs to predict segmentation quality of structures and detect out-of-distribution test examples. We conduct extensive experiments across three medical image segmentation applications of the brain, the heart, and the prostate to evaluate our contributions. The results of this study offer considerable insight into the predictive uncertainty estimation and out-of-distribution detection in medical image segmentation and provide practical recipes for confidence calibration. Moreover, we consistently demonstrate that model ensembling improves confidence calibration.

Improving detection of prostate cancer foci via information fusion of MRI and temporal enhanced ultrasound.

PURPOSE: The detection of clinically significant prostate cancer (PCa) is shown to greatly benefit from MRI-ultrasound fusion biopsy, which involves overlaying pre-biopsy MRI volumes (or targets) with real-time ultrasound images. In previous literature, machine learning models trained on either MRI or ultrasound data have been proposed to improve biopsy guidance and PCa detection. However, quantitative fusion of information from MRI and ultrasound has not been explored in depth in a large study. This paper investigates information fusion approaches between MRI and ultrasound to improve targeting of PCa foci in biopsies. METHODS: We build models of fully convolutional networks (FCN) using data from a newly proposed ultrasound modality, temporal enhanced ultrasound (TeUS), and apparent diffusion coefficient (ADC) from 107 patients with 145 biopsy cores. The architecture of our models is based on U-Net and U-Net with attention gates. Models are built using joint training through intermediate and late fusion of the data. We also build models with data from each modality, separately, to use as baseline. The performance is evaluated based on the area under the curve (AUC) for predicting clinically significant PCa. RESULTS: Using our proposed deep learning framework and intermediate fusion, integration of TeUS and ADC outperforms the individual modalities for cancer detection. We achieve an AUC of 0.76 for detection of all PCa foci, and 0.89 for PCa with larger foci. Results indicate a shared representation between multiple modalities outperforms the average unimodal predictions. CONCLUSION: We demonstrate the significant potential of multimodality integration of information from MRI and TeUS to improve PCa detection, which is essential for accurate targeting of cancer foci during biopsy. By using FCNs as the architecture of choice, we are able to predict the presence of clinically significant PCa in entire imaging planes immediately, without the need for region-based analysis. This reduces the overall computational time and enables future intra-operative deployment of this technology.

Open Source Platform for Transperineal In-Bore MRI-Guided Targeted Prostate Biopsy.

OBJECTIVE: Accurate biopsy sampling of the suspected lesions is critical for the diagnosis and clinical management of prostate cancer. Transperineal in-bore MRI-guided prostate biopsy (tpMRgBx) is a targeted biopsy technique that was shown to be safe, efficient, and accurate. Our goal was to develop an open source software platform to support evaluation, refinement, and translation of this biopsy approach. METHODS: We developed SliceTracker, a 3D Slicer extension to support tpMRgBx. We followed modular design of the implementation to enable customization of the interface and interchange of image segmentation and registration components to assess their effect on the processing time, precision, and accuracy of the biopsy needle placement. The platform and supporting documentation were developed to enable the use of software by an operator with minimal technical training to facilitate translation. Retrospective evaluation studied registration accuracy, effect of the prostate segmentation approach, and re-identification time of biopsy targets. Prospective evaluation focused on the total procedure time and biopsy targeting error (BTE). RESULTS: Evaluation utilized data from 73 retrospective and ten prospective tpMRgBx cases. Mean landmark registration error for retrospective evaluation was 1.88 ± 2.63 mm, and was not sensitive to the approach used for prostate gland segmentation. Prospectively, we observed target re-identification time of 4.60 ± 2.40 min and BTE of 2.40 ± 0.98 mm. CONCLUSION: SliceTracker is modular and extensible open source platform for supporting image processing aspects of the tpMRgBx procedure. It has been successfully utilized to support clinical research procedures at our site.

An Online Calculator for the Prediction of Survival in Glioblastoma Patients Using Classical Statistics and Machine Learning.

BACKGROUND: Although survival statistics in patients with glioblastoma multiforme (GBM) are well-defined at the group level, predicting individual patient survival remains challenging because of significant variation within strata. OBJECTIVE: To compare statistical and machine learning algorithms in their ability to predict survival in GBM patients and deploy the best performing model as an online survival calculator. METHODS: Patients undergoing an operation for a histopathologically confirmed GBM were extracted from the Surveillance Epidemiology and End Results (SEER) database (2005-2015) and split into a training and hold-out test set in an 80/20 ratio. Fifteen statistical and machine learning algorithms were trained based on 13 demographic, socioeconomic, clinical, and radiographic features to predict overall survival, 1-yr survival status, and compute personalized survival curves. RESULTS: In total, 20 821 patients met our inclusion criteria. The accelerated failure time model demonstrated superior performance in terms of discrimination (concordance index = 0.70), calibration, interpretability, predictive applicability, and computational efficiency compared to Cox proportional hazards regression and other machine learning algorithms. This model was deployed through a free, publicly available software interface (https://cnoc-bwh.shinyapps.io/gbmsurvivalpredictor/). CONCLUSION: The development and deployment of survival prediction tools require a multimodal assessment rather than a single metric comparison. This study provides a framework for the development of prediction tools in cancer patients, as well as an online survival calculator for patients with GBM. Future efforts should improve the interpretability, predictive applicability, and computational efficiency of existing machine learning algorithms, increase the granularity of population-based registries, and externally validate the proposed prediction tool.

Automating Clinical Chart Review: An Open-Source Natural Language Processing Pipeline Developed on Free-Text Radiology Reports From Patients With Glioblastoma.

PURPOSE: The aim of this study was to develop an open-source natural language processing (NLP) pipeline for text mining of medical information from clinical reports. We also aimed to provide insight into why certain variables or reports are more suitable for clinical text mining than others. MATERIALS AND METHODS: Various NLP models were developed to extract 15 radiologic characteristics from free-text radiology reports for patients with glioblastoma. Ten-fold cross-validation was used to optimize the hyperparameter settings and estimate model performance. We examined how model performance was associated with quantitative attributes of the radiologic characteristics and reports. RESULTS: In total, 562 unique brain magnetic resonance imaging reports were retrieved. NLP extracted 15 radiologic characteristics with high to excellent discrimination (area under the curve, 0.82 to 0.98) and accuracy (78.6% to 96.6%). Model performance was correlated with the inter-rater agreement of the manually provided labels (ρ = 0.904; P < .001) but not with the frequency distribution of the variables of interest (ρ = 0.179; P = .52). All variables labeled with a near perfect inter-rater agreement were classified with excellent performance (area under the curve > 0.95). Excellent performance could be achieved for variables with only 50 to 100 observations in the minority group and class imbalances up to a 9:1 ratio. Report-level classification accuracy was not associated with the number of words or the vocabulary size in the distinct text documents. CONCLUSION: This study provides an open-source NLP pipeline that allows for text mining of narratively written clinical reports. Small sample sizes and class imbalance should not be considered as absolute contraindications for text mining in clinical research. However, future studies should report measures of inter-rater agreement whenever ground truth is based on a consensus label and use this measure to identify clinical variables eligible for text mining.

Fully automatic catheter segmentation in MRI with 3D convolutional neural networks: application to MRI-guided gynecologic brachytherapy.

External-beam radiotherapy followed by high dose rate (HDR) brachytherapy is the standard-of-care for treating gynecologic cancers. The enhanced soft-tissue contrast provided by magnetic resonance imaging (MRI) makes it a valuable imaging modality for diagnosing and treating these cancers. However, in contrast to computed tomography (CT) imaging, the appearance of the brachytherapy catheters, through which radiation sources are inserted to reach the cancerous tissue later on, is often variable across images. This paper reports, for the first time, a new deep-learning-based method for fully automatic segmentation of multiple closely spaced brachytherapy catheters in intraoperative MRI. Represented in the data are 50 gynecologic cancer patients treated by MRI-guided HDR brachytherapy. For each patient, a single intraoperative MRI was used. 826 catheters in the images were manually segmented by an expert radiation physicist who is also a trained radiation oncologist. The number of catheters in a patient ranged between 10 and 35. A deep 3D convolutional neural network (CNN) model was developed and trained. In order to make the learning process more robust, the network was trained 5 times, each time using a different combination of shown patients. Finally, each test case was processed by the five networks and the final segmentation was generated by voting on the obtained five candidate segmentations. 4-fold validation was executed and all the patients were segmented. An average distance error of 2.0 ± 3.4 mm was achieved. False positive and false negative catheters were 6.7% and 1.5% respectively. Average Dice score was equal to 0.60 ± 0.17. The algorithm is available for use in the open source software platform 3D Slicer allowing for wide scale testing and research discussion. In conclusion, to the best of our knowledge, fully automatic segmentation of multiple closely spaced catheters from intraoperative MR images was achieved for the first time in gynecological brachytherapy.

Natural Language Processing for Automated Quantification of Brain Metastases Reported in Free-Text Radiology Reports.

PURPOSE: Although the bulk of patient-generated health data are increasing exponentially, their use is impeded because most data come in unstructured format, namely as free-text clinical reports. A variety of natural language processing (NLP) methods have emerged to automate the processing of free text ranging from statistical to deep learning-based models; however, the optimal approach for medical text analysis remains to be determined. The aim of this study was to provide a head-to-head comparison of novel NLP techniques and inform future studies about their utility for automated medical text analysis. PATIENTS AND METHODS: Magnetic resonance imaging reports of patients with brain metastases treated in two tertiary centers were retrieved and manually annotated using a binary classification (single metastasis v two or more metastases). Multiple bag-of-words and sequence-based NLP models were developed and compared after randomly splitting the annotated reports into training and test sets in an 80:20 ratio. RESULTS: A total of 1,479 radiology reports of patients diagnosed with brain metastases were retrieved. The least absolute shrinkage and selection operator (LASSO) regression model demonstrated the best overall performance on the hold-out test set with an area under the receiver operating characteristic curve of 0.92 (95% CI, 0.89 to 0.94), accuracy of 83% (95% CI, 80% to 87%), calibration intercept of -0.06 (95% CI, -0.14 to 0.01), and calibration slope of 1.06 (95% CI, 0.95 to 1.17). CONCLUSION: Among various NLP techniques, the bag-of-words approach combined with a LASSO regression model demonstrated the best overall performance in extracting binary outcomes from free-text clinical reports. This study provides a framework for the development of machine learning-based NLP models as well as a clinical vignette of patients diagnosed with brain metastases.

Automatic Needle Segmentation and Localization in MRI With 3-D Convolutional Neural Networks: Application to MRI-Targeted Prostate Biopsy.

Image guidance improves tissue sampling during biopsy by allowing the physician to visualize the tip and trajectory of the biopsy needle relative to the target in MRI, CT, ultrasound, or other relevant imagery. This paper reports a system for fast automatic needle tip and trajectory localization and visualization in MRI that has been developed and tested in the context of an active clinical research program in prostate biopsy. To the best of our knowledge, this is the first reported system for this clinical application and also the first reported system that leverages deep neural networks for segmentation and localization of needles in MRI across biomedical applications. Needle tip and trajectory were annotated on 583 T2-weighted intra-procedural MRI scans acquired after needle insertion for 71 patients who underwent transperineal MRI-targeted biopsy procedure at our institution. The images were divided into two independent training-validation and test sets at the patient level. A deep 3-D fully convolutional neural network model was developed, trained, and deployed on these samples. The accuracy of the proposed method, as tested on previously unseen data, was 2.80-mm average in needle tip detection and 0.98° in needle trajectory angle. An observer study was designed in which independent annotations by a second observer, blinded to the original observer, were compared with the output of the proposed method. The resultant error was comparable to the measured inter-observer concordance, reinforcing the clinical acceptability of the proposed method. The proposed system has the potential for deployment in clinical routine.

Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge.

Quantification of cerebral white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Currently, measurements are often still obtained from manual segmentations on brain MR images, which is a laborious procedure. The automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their methods on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge. Sixty T1 + FLAIR images from three MR scanners were released with the manual WMH segmentations for training. A test set of 110 images from five MR scanners was used for evaluation. The segmentation methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: 1) Dice similarity coefficient; 2) modified Hausdorff distance (95th percentile); 3) absolute log-transformed volume difference; 4) sensitivity for detecting individual lesions; and 5) F1-score for individual lesions. In addition, the methods were ranked on their inter-scanner robustness; 20 participants submitted their methods for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods, with one clear winner. The inter-scanner robustness ranking shows that not all the methods generalize to unseen scanners. The challenge remains open for future submissions and provides a public platform for method evaluation.

Using the variogram for vector outlier screening: application to feature-based image registration.

PURPOSE: Matching points that are derived from features or landmarks in image data is a key step in some medical imaging applications. Since most robust point matching algorithms claim to be able to deal with outliers, users may place high confidence in the matching result and use it without further examination. However, for tasks such as feature-based registration in image-guided neurosurgery, even a few mismatches, in the form of invalid displacement vectors, could cause serious consequences. As a result, having an effective tool by which operators can manually screen all matches for outliers could substantially benefit the outcome of those applications. METHODS: We introduce a novel variogram-based outlier screening method for vectors. The variogram is a powerful geostatistical tool for characterizing the spatial dependence of stochastic processes. Since the spatial correlation of invalid displacement vectors, which are considered as vector outliers, tends to behave differently than normal displacement vectors, they can be efficiently identified on the variogram. RESULTS: We validate the proposed method on 9 sets of clinically acquired ultrasound data. In the experiment, potential outliers are flagged on the variogram by one operator and further evaluated by 8 experienced medical imaging researchers. The matching quality of those potential outliers is approximately 1.5 lower, on a scale from 1 (bad) to 5 (good), than valid displacement vectors. CONCLUSION: The variogram is a simple yet informative tool. While being used extensively in geostatistical analysis, it has not received enough attention in the medical imaging field. We believe there is a good deal of potential for clinically applying the proposed outlier screening method. By way of this paper, we also expect researchers to find variogram useful in other medical applications that involve motion vectors analyses.

Classification of Clinical Significance of MRI Prostate Findings Using 3D Convolutional Neural Networks.

Prostate cancer (PCa) remains a leading cause of cancer mortality among American men. Multi-parametric magnetic resonance imaging (mpMRI) is widely used to assist with detection of PCa and characterization of its aggressiveness. Computer-aided diagnosis (CADx) of PCa in MRI can be used as clinical decision support system to aid radiologists in interpretation and reporting of mpMRI. We report on the development of a convolution neural network (CNN) model to support CADx in PCa based on the appearance of prostate tissue in mpMRI, conducted as part of the SPIE-AAPM-NCI PROSTATEx challenge. The performance of different combinations of mpMRI inputs to CNN was assessed and the best result was achieved using DWI and DCE-MRI modalities together with the zonal information of the finding. On the test set, the model achieved an area under the receiver operating characteristic curve of 0.80.