Automated graded prognostic assessment for patients with hepatocellular carcinoma using machine learning.

BACKGROUND: Accurate mortality risk quantification is crucial for the management of hepatocellular carcinoma (HCC); however, most scoring systems are subjective. PURPOSE: To develop and independently validate a machine learning mortality risk quantification method for HCC patients using standard-of-care clinical data and liver radiomics on baseline magnetic resonance imaging (MRI). METHODS: This retrospective study included all patients with multiphasic contrast-enhanced MRI at the time of diagnosis treated at our institution. Patients were censored at their last date of follow-up, end-of-observation, or liver transplantation date. The data were randomly sampled into independent cohorts, with 85% for development and 15% for independent validation. An automated liver segmentation framework was adopted for radiomic feature extraction. A random survival forest combined clinical and radiomic variables to predict overall survival (OS), and performance was evaluated using Harrell's C-index. RESULTS: A total of 555 treatment-naïve HCC patients (mean age, 63.8 years ± 8.9 [standard deviation]; 118 females) with MRI at the time of diagnosis were included, of which 287 (51.7%) died after a median time of 14.40 (interquartile range, 22.23) months, and had median followed up of 32.47 (interquartile range, 61.5) months. The developed risk prediction framework required 1.11 min on average and yielded C-indices of 0.8503 and 0.8234 in the development and independent validation cohorts, respectively, outperforming conventional clinical staging systems. Predicted risk scores were significantly associated with OS (p < .00001 in both cohorts). CONCLUSIONS: Machine learning reliably, rapidly, and reproducibly predicts mortality risk in patients with hepatocellular carcinoma from data routinely acquired in clinical practice. CLINICAL RELEVANCE STATEMENT: Precision mortality risk prediction using routinely available standard-of-care clinical data and automated MRI radiomic features could enable personalized follow-up strategies, guide management decisions, and improve clinical workflow efficiency in tumor boards. KEY POINTS: • Machine learning enables hepatocellular carcinoma mortality risk prediction using standard-of-care clinical data and automated radiomic features from multiphasic contrast-enhanced MRI. • Automated mortality risk prediction achieved state-of-the-art performances for mortality risk quantification and outperformed conventional clinical staging systems. • Patients were stratified into low, intermediate, and high-risk groups with significantly different survival times, generalizable to an independent evaluation cohort.

Automated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics.

OBJECTIVES: To develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, and radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI). MATERIALS AND METHODS: This retrospective study included hepatocellular carcinoma patients from an institutional database with portal venous MRI. After manual segmentation, the data was randomly split into independent training, validation, and internal testing sets. From a collaborating institution, de-identified scans were used for external testing. The public LiverHccSeg dataset was used for further external validation. A 3D DCNN was trained to automatically segment the liver. Segmentation accuracy was quantified by the Dice similarity coefficient (DSC) with respect to manual segmentation. A Mann-Whitney U test was used to compare the internal and external test sets. Agreement of volumetry and radiomic features was assessed using the intraclass correlation coefficient (ICC). RESULTS: In total, 470 patients met the inclusion criteria (63.9±8.2 years; 376 males) and 20 patients were used for external validation (41±12 years; 13 males). DSC segmentation accuracy of the DCNN was similarly high between the internal (0.97±0.01) and external (0.96±0.03) test sets (p=0.28) and demonstrated robust segmentation performance on public testing (0.93±0.03). Agreement of liver volumetry was satisfactory in the internal (ICC, 0.99), external (ICC, 0.97), and public (ICC, 0.85) test sets. Radiomic features demonstrated excellent agreement in the internal (mean ICC, 0.98±0.04), external (mean ICC, 0.94±0.10), and public (mean ICC, 0.91±0.09) datasets. CONCLUSION: Automated liver segmentation yields robust and generalizable segmentation performance on MRI data and can be used for volumetry and radiomic feature extraction. CLINICAL RELEVANCE STATEMENT: Liver volumetry, anatomic localization, and extraction of quantitative imaging biomarkers require accurate segmentation, but manual segmentation is time-consuming. A deep convolutional neural network demonstrates fast and accurate segmentation performance on T1-weighted portal venous MRI. KEY POINTS: • This deep convolutional neural network yields robust and generalizable liver segmentation performance on internal, external, and public testing data. • Automated liver volumetry demonstrated excellent agreement with manual volumetry. • Automated liver segmentations can be used for robust and reproducible radiomic feature extraction.

Reliable Prostate Cancer Risk Mapping From MRI Using Targeted and Systematic Core Needle Biopsy Histopathology.

OBJECTIVE: To compute a dense prostate cancer risk map for the individual patient post-biopsy from magnetic resonance imaging (MRI) and to provide a more reliable evaluation of its fitness in prostate regions that were not identified as suspicious for cancer by a human-reader in pre- and intra-biopsy imaging analysis. METHODS: Low-level pre-biopsy MRI biomarkers from targeted and non-targeted biopsy locations were extracted and statistically tested for representativeness against biomarkers from non-biopsied prostate regions. A probabilistic machine learning classifier was optimized to map biomarkers to their core-level pathology, followed by extrapolation of pathology scores to non-biopsied prostate regions. Goodness-of-fit was assessed at targeted and non-targeted biopsy locations for the post-biopsy individual patient. RESULTS: Our experiments showed high predictability of imaging biomarkers in differentiating histopathology scores in thousands of non-targeted core-biopsy locations (ROC-AUCs: 0.85-0.88), but also high variability between patients (Median ROC-AUC [IQR]: 0.81-0.89 [0.29-0.40]). CONCLUSION: The sparseness of prostate biopsy data makes the validation of a whole gland risk mapping a non-trivial task. Previous studies i) focused on targeted-biopsy locations although biopsy-specimens drawn from systematically scattered locations across the prostate constitute a more representative sample to non-biopsied regions, and ii) estimated prediction-power across predicted instances (e.g., biopsy specimens) with no patient distinction, which may lead to unreliable estimation of model fitness to the individual patient due to variation between patients in instance count, imaging characteristics, and pathologies. SIGNIFICANCE: This study proposes a personalized whole-gland prostate cancer risk mapping post-biopsy to allow clinicians to better stage and personalize focal therapy treatment plans.

INTEGRATING PROSTATE SPECIFIC ANTIGEN DENSITY BIOMARKER INTO DEEP LEARNING PROSTATE MRI LESION SEGMENTATION MODELS.

Prostate cancer lesion segmentation in multi-parametric magnetic resonance imaging (mpMRI) is crucial for pre-biopsy diagnosis and targeted biopsy guidance. Deep convolution neural networks have been widely utilized for lesion segmentation. However, these methods fail to achieve a high Dice coefficient because of the large variations in lesion size and location within the gland. To address this problem, we integrate the clinically-meaningful prostate specific antigen density (PSAD) biomarker into the deep learning model using feature-wise transformations to condition the features in latent space, and thus control the size of lesion prediction. We tested our models on a public dataset with 214 annotated mpMRI scans and compared the segmentation performance to a baseline 3D U-Net model. Results demonstrate that integrating the PSAD biomarker significantly improves segmentation performance in both Dice coefficient and centroid distance metric.

Inter-pass motion correction for whole-body dynamic PET and parametric imaging.

Whole-body dynamic FDG-PET imaging through continuous-bed-motion (CBM) mode multi-pass acquisition protocol is a promising metabolism measurement. However, inter-pass misalignment originating from body movement could degrade parametric quantification. We aim to apply a non-rigid registration method for inter-pass motion correction in whole-body dynamic PET. 27 subjects underwent a 90-min whole-body FDG CBM PET scan on a Biograph mCT (Siemens Healthineers), acquiring 9 over-the-heart single-bed passes and subsequently 19 CBM passes (frames). The inter-pass motion correction was executed using non-rigid image registration with multi-resolution, B-spline free-form deformations. The parametric images were then generated by Patlak analysis. The overlaid Patlak slope Ki and y-intercept Vb images were visualized to qualitatively evaluate motion impact and correction effect. The normalized weighted mean squared Patlak fitting errors (NFE) were compared in the whole body, head, and hypermetabolic regions of interest (ROI). In Ki images, ROI statistics were collected and malignancy discrimination capacity was estimated by the area under the receiver operating characteristic curve (AUC). After the inter-pass motion correction was applied, the spatial misalignment appearance between Ki and Vb images was successfully reduced. Voxel-wise normalized fitting error maps showed global error reduction after motion correction. The NFE in the whole body (p = 0.0013), head (p = 0.0021), and ROIs (p = 0.0377) significantly decreased. The visual performance of each hypermetabolic ROI in Ki images was enhanced, while 3.59% and 3.67% average absolute percentage changes were observed in mean and maximum Ki values, respectively, across all evaluated ROIs. The estimated mean Ki values had substantial changes with motion correction (p = 0.0021). The AUC of both mean Ki and maximum Ki after motion correction increased, possibly suggesting the potential of enhancing oncological discrimination capacity through inter-pass motion correction.

LiverHccSeg: A publicly available multiphasic MRI dataset with liver and HCC tumor segmentations and inter-rater agreement analysis.

Accurate segmentation of liver and tumor regions in medical imaging is crucial for the diagnosis, treatment, and monitoring of hepatocellular carcinoma (HCC) patients. However, manual segmentation is time-consuming and subject to inter- and intra-rater variability. Therefore, automated methods are necessary but require rigorous validation of high-quality segmentations based on a consensus of raters. To address the need for reliable and comprehensive data in this domain, we present LiverHccSeg, a dataset that provides liver and tumor segmentations on multiphasic contrast-enhanced magnetic resonance imaging from two board-approved abdominal radiologists, along with an analysis of inter-rater agreement. LiverHccSeg provides a curated resource for liver and HCC tumor segmentation tasks. The dataset includes a scientific reading and co-registered contrast-enhanced multiphasic magnetic resonance imaging (MRI) scans with corresponding manual segmentations by two board-approved abdominal radiologists and relevant metadata and offers researchers a comprehensive foundation for external validation, and benchmarking of liver and tumor segmentation algorithms. The dataset also provides an analysis of the agreement between the two sets of liver and tumor segmentations. Through the calculation of appropriate segmentation metrics, we provide insights into the consistency and variability in liver and tumor segmentations among the radiologists. A total of 17 cases were included for liver segmentation and 14 cases for HCC tumor segmentation. Liver segmentations demonstrates high segmentation agreement (mean Dice, 0.95 ± 0.01 [standard deviation]) and HCC tumor segmentations showed higher variation (mean Dice, 0.85 ± 0.16 [standard deviation]). The applications of LiverHccSeg can be manifold, ranging from testing machine learning algorithms on public external data to radiomic feature analyses. Leveraging the inter-rater agreement analysis within the dataset, researchers can investigate the impact of variability on segmentation performance and explore methods to enhance the accuracy and robustness of liver and tumor segmentation algorithms in HCC patients. By making this dataset publicly available, LiverHccSeg aims to foster collaborations, facilitate innovative solutions, and ultimately improve patient outcomes in the diagnosis and treatment of HCC.

Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning.

Tumor recurrence affects up to 70% of early-stage hepatocellular carcinoma (HCC) patients, depending on treatment option. Deep learning algorithms allow in-depth exploration of imaging data to discover imaging features that may be predictive of recurrence. This study explored the use of convolutional neural networks (CNN) to predict HCC recurrence in patients with early-stage HCC from pre-treatment magnetic resonance (MR) images. This retrospective study included 120 patients with early-stage HCC. Pre-treatment MR images were fed into a machine learning pipeline (VGG16 and XGBoost) to predict recurrence within six different time frames (range 1-6 years). Model performance was evaluated with the area under the receiver operating characteristic curves (AUC-ROC). After prediction, the model's clinical relevance was evaluated using Kaplan-Meier analysis with recurrence-free survival (RFS) as the endpoint. Of 120 patients, 44 had disease recurrence after therapy. Six different models performed with AUC values between 0.71 to 0.85. In Kaplan-Meier analysis, five of six models obtained statistical significance when predicting RFS (log-rank p < 0.05). Our proof-of-concept study indicates that deep learning algorithms can be utilized to predict early-stage HCC recurrence. Successful identification of high-risk recurrence candidates may help optimize follow-up imaging and improve long-term outcomes post-treatment.

Deep learning of image-derived measures of body composition in pediatric, adolescent, and young adult lymphoma: association with late treatment effects.

OBJECTIVES: The objective of this study was to translate a deep learning (DL) approach for semiautomated analysis of body composition (BC) measures from standard of care CT images to investigate the prognostic value of BC in pediatric, adolescent, and young adult (AYA) patients with lymphoma. METHODS: This 10-year retrospective, single-site study of 110 pediatric and AYA patients with lymphoma involved manual segmentation of fat and muscle tissue from 260 CT imaging datasets obtained as part of routine imaging at initial staging and first therapeutic follow-up. A DL model was trained to perform semiautomated image segmentation of adipose and muscle tissue. The association between BC measures and the occurrence of 3-year late effects was evaluated using Cox proportional hazards regression analyses. RESULTS: DL-guided measures of BC were in close agreement with those obtained by a human rater, as demonstrated by high Dice scores (≥ 0.95) and correlations (r > 0.99) for each tissue of interest. Cox proportional hazards regression analyses revealed that patients with elevated subcutaneous adipose tissue at baseline and first follow-up, along with patients who possessed lower volumes of skeletal muscle at first follow-up, have increased risk of late effects compared to their peers. CONCLUSIONS: DL provides rapid and accurate quantification of image-derived measures of BC that are associated with risk for treatment-related late effects in pediatric and AYA patients with lymphoma. Image-based monitoring of BC measures may enhance future opportunities for personalized medicine for children with lymphoma by identifying patients at the highest risk for late effects of treatment. KEY POINTS: • Deep learning-guided CT image analysis of body composition measures achieved high agreement level with manual image analysis. • Pediatric patients with more fat and less muscle during the course of cancer treatment were more likely to experience a serious adverse event compared to their clinical counterparts. • Deep learning of body composition may add value to routine CT imaging by offering real-time monitoring of pediatric, adolescent, and young adults at high risk for late effects of cancer treatment.

Deep learning-based attenuation map generation with simultaneously reconstructed PET activity and attenuation and low-dose application.

Objective. In PET/CT imaging, CT is used for positron emission tomography (PET) attenuation correction (AC). CT artifacts or misalignment between PET and CT can cause AC artifacts and quantification errors in PET. Simultaneous reconstruction (MLAA) of PET activity (λ-MLAA) and attenuation (µ-MLAA) maps was proposed to solve those issues using the time-of-flight PET raw data only. However,λ-MLAA still suffers from quantification error as compared to reconstruction using the gold-standard CT-based attenuation map (µ-CT). Recently, a deep learning (DL)-based framework was proposed to improve MLAA by predictingµ-DL fromλ-MLAA andµ-MLAA using an image domain loss function (IM-loss). However, IM-loss does not directly measure the AC errors according to the PET attenuation physics. Our preliminary studies showed that an additional physics-based loss function can lead to more accurate PET AC. The main objective of this study is to optimize the attenuation map generation framework for clinical full-dose18F-FDG studies. We also investigate the effectiveness of the optimized network on predicting attenuation maps for synthetic low-dose oncological PET studies.Approach. We optimized the proposed DL framework by applying different preprocessing steps and hyperparameter optimization, including patch size, weights of the loss terms and number of angles in the projection-domain loss term. The optimization was performed based on 100 skull-to-toe18F-FDG PET/CT scans with minimal misalignment. The optimized framework was further evaluated on 85 clinical full-dose neck-to-thigh18F-FDG cancer datasets as well as synthetic low-dose studies with only 10% of the full-dose raw data.Main results. Clinical evaluation of tumor quantification as well as physics-based figure-of-merit metric evaluation validated the promising performance of our proposed method. For both full-dose and low-dose studies, the proposed framework achieved <1% error in tumor standardized uptake value measures.Significance. It is of great clinical interest to achieve CT-less PET reconstruction, especially for low-dose PET studies.

Prediction of Adverse Pathology at Radical Prostatectomy in Grade Group 2 and 3 Prostate Biopsies Using Machine Learning.

PURPOSE: There is ongoing clinical need to improve estimates of disease outcome in prostate cancer. Machine learning (ML) approaches to pathologic diagnosis and prognosis are a promising and increasingly used strategy. In this study, we use an ML algorithm for prediction of adverse outcomes at radical prostatectomy (RP) using whole-slide images (WSIs) of prostate biopsies with Grade Group (GG) 2 or 3 disease. METHODS: We performed a retrospective review of prostate biopsies collected at our institution which had corresponding RP, GG 2 or 3 disease one or more cores, and no biopsies with higher than GG 3 disease. A hematoxylin and eosin-stained core needle biopsy from each site with GG 2 or 3 disease was scanned and used as the sole input for the algorithm. The ML pipeline had three phases: image preprocessing, feature extraction, and adverse outcome prediction. First, patches were extracted from each biopsy scan. Subsequently, the pre-trained Visual Geometry Group-16 convolutional neural network was used for feature extraction. A representative feature vector was then used as input to an Extreme Gradient Boosting classifier for predicting the binary adverse outcome. We subsequently assessed patient clinical risk using CAPRA score for comparison with the ML pipeline results. RESULTS: The data set included 361 WSIs from 107 patients (56 with adverse pathology at RP). The area under the receiver operating characteristic curves for the ML classification were 0.72 (95% CI, 0.62 to 0.81), 0.65 (95% CI, 0.53 to 0.79) and 0.89 (95% CI, 0.79 to 1.00) for the entire cohort, and GG 2 and GG 3 patients, respectively, similar to the performance of the CAPRA clinical risk assessment. CONCLUSION: We provide evidence for the potential of ML algorithms to use WSIs of needle core prostate biopsies to estimate clinically relevant prostate cancer outcomes.

MR Imaging Biomarkers for the Prediction of Outcome after Radiofrequency Ablation of Hepatocellular Carcinoma: Qualitative and Quantitative Assessments of the Liver Imaging Reporting and Data System and Radiomic Features.

PURPOSE: To assess the Liver Imaging Reporting and Data System (LI-RADS) and radiomic features in pretreatment magnetic resonance (MR) imaging for predicting progression-free survival (PFS) in patients with nodular hepatocellular carcinoma (HCC) treated with radiofrequency (RF) ablation. MATERIAL AND METHODS: Sixty-five therapy-naïve patients with 85 nodular HCC tumors <5 cm in size were included in this Health Insurance Portability and Accountability Act-compliant, institutional review board-approved, retrospective study. All patients underwent RF ablation as first-line treatment and demonstrated complete response on the first follow-up imaging. Gadolinium-enhanced MR imaging biomarkers were analyzed for LI-RADS features by 2 board-certified radiologists or by analysis of nodular and perinodular radiomic features from 3-dimensional segmentations. A radiomic signature was calculated with the most informative features of a least absolute shrinkage and selection operator Cox regression model using leave-one-out cross-validation. The association between both LI-RADS features and radiomic signatures with PFS was assessed via the Kaplan-Meier analysis and a weighted log-rank test. RESULTS: The median PFS was 19 months (95% confidence interval, 16.1-19.4) for a follow-up period of 24 months. Multifocality (P = .033); the appearance of capsular continuity, compared with an absent or discontinuous capsule (P = .012); and a higher radiomic signature based on nodular and perinodular features (P = .030) were associated with poorer PFS in early-stage HCC. The observation size, presence of arterial hyperenhancement, nonperipheral washout, and appearance of an enhancing "capsule" were not associated with PFS (P > .05). CONCLUSIONS: Although multifocal HCC clearly indicates a more aggressive phenotype even in early-stage disease, the continuity of an enhancing capsule and a higher radiomic signature may add value as MR imaging biomarkers for poor PFS in HCC treated with RF ablation.

Deep learning-based attenuation correction for whole-body PET - a multi-tracer study with 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine.

A novel deep learning (DL)-based attenuation correction (AC) framework was applied to clinical whole-body oncology studies using 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. The framework used activity (λ-MLAA) and attenuation (µ-MLAA) maps estimated by the maximum likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a modified U-net neural network with a novel imaging physics-based loss function to learn a CT-derived attenuation map (µ-CT). METHODS: Clinical whole-body PET/CT datasets of 18F-FDG (N = 113), 68 Ga-DOTATATE (N = 76), and 18F-Fluciclovine (N = 90) were used to train and test tracer-specific neural networks. For each tracer, forty subjects were used to train the neural network to predict attenuation maps (µ-DL). µ-DL and µ-MLAA were compared to the gold-standard µ-CT. PET images reconstructed using the OSEM algorithm with µ-DL (OSEMDL) and µ-MLAA (OSEMMLAA) were compared to the CT-based reconstruction (OSEMCT). Tumor regions of interest were segmented by two radiologists and tumor SUV and volume measures were reported, as well as evaluation using conventional image analysis metrics. RESULTS: µ-DL yielded high resolution and fine detail recovery of the attenuation map, which was superior in quality as compared to µ-MLAA in all metrics for all tracers. Using OSEMCT as the gold-standard, OSEMDL provided more accurate tumor quantification than OSEMMLAA for all three tracers, e.g., error in SUVmax for OSEMMLAA vs. OSEMDL: - 3.6 ± 4.4% vs. - 1.7 ± 4.5% for 18F-FDG (N = 152), - 4.3 ± 5.1% vs. 0.4 ± 2.8% for 68 Ga-DOTATATE (N = 70), and - 7.3 ± 2.9% vs. - 2.8 ± 2.3% for 18F-Fluciclovine (N = 44). OSEMDL also yielded more accurate tumor volume measures than OSEMMLAA, i.e., - 8.4 ± 14.5% (OSEMMLAA) vs. - 3.0 ± 15.0% for 18F-FDG, - 14.1 ± 19.7% vs. 1.8 ± 11.6% for 68 Ga-DOTATATE, and - 15.9 ± 9.1% vs. - 6.4 ± 6.4% for 18F-Fluciclovine. CONCLUSIONS: The proposed framework provides accurate and robust attenuation correction for whole-body 18F-FDG, 68 Ga-DOTATATE and 18F-Fluciclovine in tumor SUV measures as well as tumor volume estimation. The proposed method provides clinically equivalent quality as compared to CT in attenuation correction for the three tracers.

Extent of High-Grade Prostatic Adenocarcinoma in Multiparametric Magnetic Resonance Imaging-Targeted Biopsy Enhances Prediction of Pathologic Stage.

CONTEXT.­: Multiparametric magnetic resonance imaging (mpMRI) of prostate with targeted biopsy has enhanced detection of high-grade prostatic adenocarcinoma (HG PCa). However, utility of amount of HG PCa (Gleason pattern 4/5) in mpMRI-targeted biopsies versus standard 12-core biopsies in predicting adverse outcomes on radical prostatectomy (RP) is unknown. OBJECTIVE.­: To examine the utility of amount of HG PCa in mpMRI-targeted biopsies versus standard 12-core biopsies in predicting adverse RP outcomes. DESIGN.­: We performed a retrospective review of prostate biopsies that had corresponding RP, 1 or more mpMRI-targeted biopsy, and Grade Group 2 disease or higher. For the 169 cases identified, total millimeters of carcinoma and HG PCa and longest length HG PCa in a single core were recorded for 12-core biopsies and each set of mpMRI-targeted biopsies. For RP specimens, Gleason grade, extraprostatic extension, seminal vesicle involvement, and lymph node metastasis were recorded. The main outcome studied was prostate-confined disease at RP. A logistic regression model was used to test which pre-RP variables related to this outcome. RESULTS.­: Univariate analysis showed significant associations with adverse RP outcomes in 5 of 8 quantifiable variables; longest millimeter HG PCa in a single 12-core biopsy, highest Grade Group in any core, and total millimeter HG in mpMRI-targeted biopsies showed no statistical association (P = .54, P = .13, and P = .55, respectively). In multivariate analysis, total millimeter carcinoma in all cores, highest Grade Group in any core, and longest millimeter HG PCa in a single mpMRI-targeted core provided additional predictive value (P < .001, P = .004, and P = .03, respectively). CONCLUSIONS.­: Quantitation of HG PCa in mpMRI-targeted biopsies provides additional value over 12-core biopsies alone in predicting nonorgan confined prostate cancer at RP. Linear millimeters of HG PCa in mpMRI-targeted biopsies is a significant parameter associated with higher pathologic stage and could be of value in risk models.

Atlas-based Semantic Segmentation of Prostate Zones.

Segmentation of the prostate into specific anatomical zones is important for radiological assessment of prostate cancer in magnetic resonance imaging (MRI). Of particular interest is segmenting the prostate into two regions of interest: the central gland (CG) and peripheral zone (PZ). In this paper, we propose to integrate an anatomical atlas of prostate zone shape into a deep learning semantic segmentation framework to segment the CG and PZ in T2-weighted MRI. Our approach incorporates anatomical information in the form of a probabilistic prostate zone atlas and utilizes a dynamically controlled hyperparameter to combine the atlas with the semantic segmentation result. In addition to providing significantly improved segmentation performance, this hyperparameter is capable of being dynamically adjusted during the inference stage to provide users with a mechanism to refine the segmentation. We validate our approach using an external test dataset and demonstrate Dice similarity coefficient values (mean±SD) of 0.91±0.05 for the CG and 0.77±0.16 for the PZ that significantly improves upon the baseline segmentation results without the atlas. All code is publicly available on GitHub: https://github.com/OnofreyLab/prostate_atlas_segm_miccai2022.

Improved performance and consistency of deep learning 3D liver segmentation with heterogeneous cancer stages in magnetic resonance imaging.

PURPOSE: Accurate liver segmentation is key for volumetry assessment to guide treatment decisions. Moreover, it is an important pre-processing step for cancer detection algorithms. Liver segmentation can be especially challenging in patients with cancer-related tissue changes and shape deformation. The aim of this study was to assess the ability of state-of-the-art deep learning 3D liver segmentation algorithms to generalize across all different Barcelona Clinic Liver Cancer (BCLC) liver cancer stages. METHODS: This retrospective study, included patients from an institutional database that had arterial-phase T1-weighted magnetic resonance images with corresponding manual liver segmentations. The data was split into 70/15/15% for training/validation/testing each proportionally equal across BCLC stages. Two 3D convolutional neural networks were trained using identical U-net-derived architectures with equal sized training datasets: one spanning all BCLC stages ("All-Stage-Net": AS-Net), and one limited to early and intermediate BCLC stages ("Early-Intermediate-Stage-Net": EIS-Net). Segmentation accuracy was evaluated by the Dice Similarity Coefficient (DSC) on a dataset spanning all BCLC stages and a Wilcoxon signed-rank test was used for pairwise comparisons. RESULTS: 219 subjects met the inclusion criteria (170 males, 49 females, 62.8±9.1 years) from all BCLC stages. Both networks were trained using 129 subjects: AS-Net training comprised 19, 74, 18, 8, and 10 BCLC 0, A, B, C, and D patients, respectively; EIS-Net training comprised 21, 86, and 22 BCLC 0, A, and B patients, respectively. DSCs (mean±SD) were 0.954±0.018 and 0.946±0.032 for AS-Net and EIS-Net (p<0.001), respectively. The AS-Net 0.956±0.014 significantly outperformed the EIS-Net 0.941±0.038 on advanced BCLC stages (p<0.001) and yielded similarly good segmentation performance on early and intermediate stages (AS-Net: 0.952±0.021; EIS-Net: 0.949±0.027; p = 0.107). CONCLUSION: To ensure robust segmentation performance across cancer stages that is independent of liver shape deformation and tumor burden, it is critical to train deep learning models on heterogeneous imaging data spanning all BCLC stages.

Doubling of Decipher Biopsy Genomic Score Is Related to Disease Reclassification on Subsequent Surveillance Biopsy but Not Adverse Features on Radical Prostatectomy.

The utility of serial Decipher biopsy scores in a true active surveillance population is still unknown. In a man on active surveillance for low-risk prostate cancer, a doubling of the Decipher biopsy score within genomic low-risk category from first to the second biopsy related to biopsy reclassification to Gleason grade group 4 on the third biopsy. However, the final pathology at radical prostatectomy showed Gleason grade group 2 with an organ-confined disease. This case suggests that the genomic risk category of Decipher biopsy scores during active surveillance may be more informative than either the interval genomic score change or the biopsy Gleason grade group.

Supervised Machine Learning in Oncology: A Clinician's Guide.

The widespread adoption of electronic health records has resulted in an abundance of imaging and clinical information. New data-processing technologies have the potential to revolutionize the practice of medicine by deriving clinically meaningful insights from large-volume data. Among those techniques is supervised machine learning, the study of computer algorithms that use self-improving models that learn from labeled data to solve problems. One clinical area of application for supervised machine learning is within oncology, where machine learning has been used for cancer diagnosis, staging, and prognostication. This review describes a framework to aid clinicians in understanding and critically evaluating studies applying supervised machine learning methods. Additionally, we describe current studies applying supervised machine learning techniques to the diagnosis, prognostication, and treatment of cancer, with a focus on gastroenterological cancers and other related pathologies.

An investigation of quantitative accuracy for deep learning based denoising in oncological PET.

Reducing radiation dose is important for PET imaging. However, reducing injection doses causes increased image noise and low signal-to-noise ratio (SNR), subsequently affecting diagnostic and quantitative accuracies. Deep learning methods have shown a great potential to reduce the noise and improve the SNR in low dose PET data. In this work, we comprehensively investigated the quantitative accuracy of small lung nodules, in addition to visual image quality, using deep learning based denoising methods for oncological PET imaging. We applied and optimized an advanced deep learning method based on the U-net architecture to predict the standard dose PET image from 10% low-dose PET data. We also investigated the effect of different network architectures, image dimensions, labels and inputs for deep learning methods with respect to both noise reduction performance and quantitative accuracy. Normalized mean square error (NMSE), SNR, and standard uptake value (SUV) bias of different nodule regions of interest (ROIs) were used for evaluation. Our results showed that U-net and GAN are superior to CAE with smaller SUVmean and SUVmax bias at the expense of inferior SNR. A fully 3D U-net has optimal quantitative performance compared to 2D and 2.5D U-net with less than 15% SUVmean bias for all the ten patients. U-net outperforms Residual U-net (r-U-net) in general with smaller NMSE, higher SNR and lower SUVmax bias. Fully 3D U-net is superior to several existing denoising methods, including Gaussian filter, anatomical-guided non-local mean (NLM) filter, and MAP reconstruction with Quadratic prior and relative difference prior, in terms of superior image quality and trade-off between noise and bias. Furthermore, incorporating aligned CT images has the potential to further improve the quantitative accuracy in multi-channel U-net. We found the optimal architectures and parameters of deep learning based methods are different for absolute quantitative accuracy and visual image quality. Our quantitative results demonstrated that fully 3D U-net can both effectively reduce image noise and control bias even for sub-centimeter small lung nodules when generating standard dose PET using 10% low count down-sampled data.

Noninvasive In Vivo Quantification of Adeno-Associated Virus Serotype 9-Mediated Expression of the Sodium/Iodide Symporter Under Hindlimb Ischemia and Neuraminidase Desialylation in Skeletal Muscle Using Single-Photon Emission Computed Tomography/Computed Tomography.

BACKGROUND: We propose micro single-photon emission computed tomography/computed tomography imaging of the hNIS (human sodium/iodide symporter) to noninvasively quantify adeno-associated virus 9 (AAV9)-mediated gene expression in a murine model of peripheral artery disease. METHODS: AAV9-hNIS (2×1011 viral genome particles) was injected into nonischemic or ischemic gastrocnemius muscles of C57Bl/6J mice following unilateral hindlimb ischemia ± the α-sialidase NA (neuraminidase). Control nonischemic limbs were injected with phosphate buffered saline or remained noninjected. Twelve mice underwent micro single-photon emission computed tomography/computed tomography imaging after serial injection of pertechnetate (99mTcO4-), a NIS substrate, up to 28 days after AAV9-hNIS injection. Twenty four animals were euthanized at selected times over 1 month for ex vivo validation. Forty-two animals were imaged with 99mTcO4- ± the selective NIS inhibitor perchlorate on day 10, to ascertain specificity of radiotracer uptake. Tissue was harvested for ex vivo validation. A modified version of the U-Net deep learning algorithm was used for image quantification. RESULTS: As quantitated by standardized uptake value, there was a gradual temporal increase in 99mTcO4- uptake in muscles treated with AAV9-hNIS. Hindlimb ischemia, NA, and hindlimb ischemia plus NA increased the magnitude of 99mTcO4- uptake by 4- to 5-fold compared with nonischemic muscle treated with only AAV9-hNIS. Perchlorate treatment significantly reduced 99mTcO4- uptake in AAV9-hNIS-treated muscles, demonstrating uptake specificity. The imaging results correlated well with ex vivo well counting (r2=0.9375; P<0.0001) and immunoblot analysis of NIS protein (r2=0.65; P<0.0001). CONCLUSIONS: Micro single-photon emission computed tomography/computed tomography imaging of hNIS-mediated 99mTcO4- uptake allows for accurate in vivo quantification of AAV9-driven gene expression, which increases under ischemic conditions or neuraminidase desialylation in skeletal muscle.

Deep-learned placental vessel segmentation for intraoperative video enhancement in fetoscopic surgery.

INTRODUCTION: Twin-to-twin transfusion syndrome (TTTS) is a potentially lethal condition that affects pregnancies in which twins share a single placenta. The definitive treatment for TTTS is fetoscopic laser photocoagulation, a procedure in which placental blood vessels are selectively cauterized. Challenges in this procedure include difficulty in quickly identifying placental blood vessels due to the many artifacts in the endoscopic video that the surgeon uses for navigation. We propose using deep-learned segmentations of blood vessels to create masks that can be recombined with the original fetoscopic video frame in such a way that the location of placental blood vessels is discernable at a glance. METHODS: In a process approved by an institutional review board, intraoperative videos were acquired from ten fetoscopic laser photocoagulation surgeries performed at Yale New Haven Hospital. A total of 345 video frames were selected from these videos at regularly spaced time intervals. The video frames were segmented once by an expert human rater (a clinician) and once by a novice, but trained human rater (an undergraduate student). The segmentations were used to train a fully convolutional neural network of 25 layers. RESULTS: The neural network was able to produce segmentations with a high similarity to ground truth segmentations produced by an expert human rater (sensitivity = 92.15% ± 10.69%) and produced segmentations that were significantly more accurate than those produced by a novice human rater (sensitivity = 56.87% ± 21.64%; p < 0.01). CONCLUSION: A convolutional neural network can be trained to segment placental blood vessels with near-human accuracy and can exceed the accuracy of novice human raters. Recombining these segmentations with the original fetoscopic video frames can produced enhanced frames in which blood vessels are easily detectable. This has significant implications for aiding fetoscopic surgeons-especially trainees who are not yet at an expert level.