Overview of approaches to estimate real-world disease progression in lung cancer.

BACKGROUND: Randomized clinical trials of novel treatments for solid tumors normally measure disease progression using the Response Evaluation Criteria in Solid Tumors. However, novel, scalable approaches to estimate disease progression using real-world data are needed to advance cancer outcomes research. The purpose of this narrative review is to summarize examples from the existing literature on approaches to estimate real-world disease progression and their relative strengths and limitations, using lung cancer as a case study. METHODS: A narrative literature review was conducted in PubMed to identify articles that used approaches to estimate real-world disease progression in lung cancer patients. Data abstracted included data source, approach used to estimate real-world progression, and comparison to a selected gold standard (if applicable). RESULTS: A total of 40 articles were identified from 2008 to 2022. Five approaches to estimate real-world disease progression were identified including manual abstraction of medical records, natural language processing of clinical notes and/or radiology reports, treatment-based algorithms, changes in tumor volume, and delta radiomics-based approaches. The accuracy of these progression approaches were assessed using different methods, including correlations between real-world endpoints and overall survival for manual abstraction (Spearman rank ρ = 0.61-0.84) and area under the curve for natural language processing approaches (area under the curve = 0.86-0.96). CONCLUSIONS: Real-world disease progression has been measured in several observational studies of lung cancer. However, comparing the accuracy of methods across studies is challenging, in part, because of the lack of a gold standard and the different methods used to evaluate accuracy. Concerted efforts are needed to define a gold standard and quality metrics for real-world data.

Classifying Malignancy in Prostate Glandular Structures from Biopsy Scans with Deep Learning.

Histopathological classification in prostate cancer remains a challenge with high dependence on the expert practitioner. We develop a deep learning (DL) model to identify the most prominent Gleason pattern in a highly curated data cohort and validate it on an independent dataset. The histology images are partitioned in tiles (14,509) and are curated by an expert to identify individual glandular structures with assigned primary Gleason pattern grades. We use transfer learning and fine-tuning approaches to compare several deep neural network architectures that are trained on a corpus of camera images (ImageNet) and tuned with histology examples to be context appropriate for histopathological discrimination with small samples. In our study, the best DL network is able to discriminate cancer grade (GS3/4) from benign with an accuracy of 91%, F1-score of 0.91 and AUC 0.96 in a baseline test (52 patients), while the cancer grade discrimination of the GS3 from GS4 had an accuracy of 68% and AUC of 0.71 (40 patients).

Repeatability of metabolic tumor burden and lesion glycolysis between clinical readers.

The Metabolic Tumor Volume (MTV) and Tumor Lesion Glycolysis (TLG) has been shown to be independent prognostic predictors for clinical outcome in Diffuse Large B-cell Lymphoma (DLBCL). However, definitions of these measurements have not been standardized, leading to many sources of variation, operator evaluation continues to be one major source. In this study, we propose a reader reproducibility study to evaluate computation of TMV (& TLG) metrics based on differences in lesion delineation. In the first approach, reader manually corrected regional boundaries after automated detection performed across the lesions in a body scan (Reader M using a manual process, or manual). The other reader used a semi-automated method of lesion identification, without any boundary modification (Reader A using a semi- automated process, or auto). Parameters for active lesion were kept the same, derived from standard uptake values (SUVs) over a 41% threshold. We systematically contrasted MTV & TLG differences between expert readers (Reader M & A). We find that MTVs computed by Readers M and A were both concordant between them (concordant correlation coefficient of 0.96) and independently prognostic with a P-value of 0.0001 and 0.0002 respectively for overall survival after treatment. Additionally, we find TLG for these reader approaches showed concordance (CCC of 0.96) and was prognostic for over -all survival (p ≤ 0.0001 for both). In conclusion, the semi-automated approach (Reader A) provides acceptable quantification & prognosis of tumor burden (MTV) and TLG in comparison to expert reader assisted measurement (Reader M) on PET/CT scans.

Volume doubling time and radiomic features predict tumor behavior of screen-detected lung cancers.

BACKGROUND: Image-based biomarkers could have translational implications by characterizing tumor behavior of lung cancers diagnosed during lung cancer screening. In this study, peritumoral and intratumoral radiomics and volume doubling time (VDT) were used to identify high-risk subsets of lung patients diagnosed in lung cancer screening that are associated with poor survival outcomes. METHODS: Data and images were acquired from the National Lung Screening Trial. VDT was calculated between two consequent screening intervals approximately 1 year apart; peritumoral and intratumoral radiomics were extracted from the baseline screen. Overall survival (OS) was the main endpoint. Classification and Regression Tree analyses identified the most predictive covariates to classify patient outcomes. RESULTS: Decision tree analysis stratified patients into three risk-groups (low, intermediate, and high) based on VDT and one radiomic feature (compactness). High-risk patients had extremely poor survival outcomes (hazard ratio [HR] = 8.15; 25% 5-year OS) versus low-risk patients (HR = 1.00; 83.3% 5-year OS). Among early-stage lung cancers, high-risk patients had poor survival outcomes (HR = 9.07; 44.4% 5-year OS) versus the low-risk group (HR = 1.00; 90.9% 5-year OS). For VDT, the decision tree analysis identified a novel cut-point of 279 days and using this cut-point VDT alone discriminated between aggressive (HR = 4.18; 45% 5-year OS) versus indolent/low-risk cancers (HR = 1.00; 82.8% 5-year OS). CONCLUSION: We utilized peritumoral and intratumoral radiomic features and VDT to generate a model that identify a high-risk group of screen-detected lung cancers associated with poor survival outcomes. These vulnerable subset of screen-detected lung cancers may be candidates for more aggressive surveillance/follow-up and treatment, such as adjuvant therapy.

Noise-Based Image Harmonization Significantly Increases Repeatability and Reproducibility of Radiomics Features in PET Images: A Phantom Study.

For multicenter clinical studies, characterizing the robustness of image-derived radiomics features is essential. Features calculated on PET images have been shown to be very sensitive to image noise. The purpose of this work was to investigate the efficacy of a relatively simple harmonization strategy on feature robustness and agreement. A purpose-built texture pattern phantom was scanned on 10 different PET scanners in 7 institutions with various different image acquisition and reconstruction protocols. An image harmonization technique based on equalizing a contrast-to-noise ratio was employed to generate a "harmonized" alongside a "standard" dataset for a reproducibility study. In addition, a repeatability study was performed with images from a single PET scanner of variable image noise, varying the binning time of the reconstruction. Feature agreement was measured using the intraclass correlation coefficient (ICC). In the repeatability study, 81/93 features had a lower ICC on the images with the highest image noise as compared to the images with the lowest image noise. Using the harmonized dataset significantly improved the feature agreement for five of the six investigated feature classes over the standard dataset. For three feature classes, high feature agreement corresponded with higher sensitivity to the different patterns, suggesting a way to select suitable features for predictive models.

In Vivo Imaging of Rat Vascularity with FDG-Labeled Erythrocytes.

Microvascular disease is frequently found in major pathologies affecting vital organs, such as the brain, heart, and kidneys. While imaging modalities, such as ultrasound, computed tomography, single photon emission computed tomography, and magnetic resonance imaging, are widely used to visualize vascular abnormalities, the ability to non-invasively assess an organ's total vasculature, including microvasculature, is often limited or cumbersome. Previously, we have demonstrated proof of concept that non-invasive imaging of the total mouse vasculature can be achieved with 18F-fluorodeoxyglucose (18F-FDG)-labeled human erythrocytes and positron emission tomography/computerized tomography (PET/CT). In this work, we demonstrate that changes in the total vascular volume of the brain and left ventricular myocardium of normal rats can be seen after pharmacological vasodilation using 18F-FDG-labeled rat red blood cells (FDG RBCs) and microPET/CT imaging. FDG RBC PET imaging was also used to approximate the location of myocardial injury in a surgical myocardial infarction rat model. Finally, we show that FDG RBC PET imaging can detect relative differences in the degree of drug-induced intra-myocardial vasodilation between diabetic rats and normal controls. This FDG-labeled RBC PET imaging technique may thus be useful for assessing microvascular disease pathologies and characterizing pharmacological responses in the vascular bed of interest.

Integrated Biomarkers for the Management of Indeterminate Pulmonary Nodules.

Rationale: Patients with indeterminate pulmonary nodules (IPNs) at risk of cancer undergo high rates of invasive, costly, and morbid procedures. Objectives: To train and externally validate a risk prediction model that combined clinical, blood, and imaging biomarkers to improve the noninvasive management of IPNs. Methods: In this prospectively collected, retrospective blinded evaluation study, probability of cancer was calculated for 456 patient nodules using the Mayo Clinic model, and patients were categorized into low-, intermediate-, and high-risk groups. A combined biomarker model (CBM) including clinical variables, serum high sensitivity CYFRA 21-1 level, and a radiomic signature was trained in cohort 1 (n = 170) and validated in cohorts 2-4 (total n = 286). All patients were pooled to recalibrate the model for clinical implementation. The clinical utility of the CBM compared with current clinical care was evaluated in 2 cohorts. Measurements and Main Results: The CBM provided improved diagnostic accuracy over the Mayo Clinic model with an improvement in area under the curve of 0.124 (95% bootstrap confidence interval, 0.091-0.156; P < 2 × 10-16). Applying 10% and 70% risk thresholds resulted in a bias-corrected clinical reclassification index for cases and control subjects of 0.15 and 0.12, respectively. A clinical utility analysis of patient medical records estimated that a CBM-guided strategy would have reduced invasive procedures from 62.9% to 50.6% in the intermediate-risk benign population and shortened the median time to diagnosis of cancer from 60 to 21 days in intermediate-risk cancers. Conclusions: Integration of clinical, blood, and image biomarkers improves noninvasive diagnosis of patients with IPNs, potentially reducing the rate of unnecessary invasive procedures while shortening the time to diagnosis.

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).

Correction: Quantitative Computed Tomographic Descriptors Associate Tumor Shape Complexity and Intratumor Heterogeneity with Prognosis in Lung Adenocarcinoma.

[This corrects the article DOI: 10.1371/journal.pone.0118261.].

Requirements and reliability of AI in the medical context.

The digital information age has been a catalyst in creating a renewed interest in Artificial Intelligence (AI) approaches, especially the subclass of computer algorithms that are popularly grouped into Machine Learning (ML). These methods have allowed one to go beyond limited human cognitive ability into understanding the complexity in the high dimensional data. Medical sciences have seen a steady use of these methods but have been slow in adoption to improve patient care. There are some significant impediments that have diluted this effort, which include availability of curated diverse data sets for model building, reliable human-level interpretation of these models, and reliable reproducibility of these methods for routine clinical use. Each of these aspects has several limiting conditions that need to be balanced out, considering the data/model building efforts, clinical implementation, integration cost to translational effort with minimal patient level harm, which may directly impact future clinical adoption. In this review paper, we will assess each aspect of the problem in the context of reliable use of the ML methods in oncology, as a representative study case, with the goal to safeguard utility and improve patient care in medicine in general.

Quantitative Measures of Background Parenchymal Enhancement Predict Breast Cancer Risk.

BACKGROUND. Higher categories of background parenchymal enhancement (BPE) increase breast cancer risk. However, current clinical BPE categorization is subjective. OBJECTIVE. Using a semiautomated segmentation algorithm, we calculated quantitative BPE measures and investigated the utility of individual features and feature pairs in significantly predicting subsequent breast cancer risk compared with radiologist-assigned BPE category. METHODS. In this retrospective case-control study, we identified 95 women at high risk of breast cancer but without a personal history of breast cancer who underwent breast MRI. Of these women, 19 subsequently developed breast cancer and were included as cases. Each case was age matched to four control patients (76 control patients total). Sociodemographic characteristics were compared between the cases and matched control patients using the Mann-Whitney U test. From each dynamic contrast-enhanced MRI examination, quantitative fibroglandular tissue and BPE measures were computed by averaging enhancing voxels above enhancement ratio thresholds (0-100%), totaling the enhancing volume above thresholds (BPE volume in cm3), and estimating the percentage of enhancing tissue above thresholds relative to total breast volume (BPE%) on each gadolinium-enhanced phase. For the 91 imaging features generated, we compared predictive performance using conditional logistic regression with 80:20 hold-out cross validation and ROC curve analysis. ROC AUC was the figure of merit. Sensitivity, specificity, PPV, and NPV were also computed. All feature pairs were exhaustively searched to identify those with the highest AUC and Youden index. A DeLong test was used to compare predictive performance (AUCs). RESULTS. Women subsequently diagnosed with breast cancer were more likely to have mild, moderate, or marked BPE (odds ratio, 3.0; 95% CI, 0.9-10.0; p = .07). According to ROC curve analysis, a BPE category threshold greater than minimal resulted in a maximized AUC (0.62) in distinguishing cases from control patients. Compared with BPE category, the first gadolinium-enhanced (phase 1) BPE% at the 30% and 40% enhancement ratio thresholds yielded significantly higher AUC values of 0.85 (p = .0007) and 0.84 (p = .0004), respectively. Feature combinations showed similar AUC values with improved sensitivity. CONCLUSION. Preliminary data indicate that quantitative BPE measures may outperform radiologist-assigned category in breast cancer risk prediction. CLINICAL IMPACT. Future risk prediction models that incorporate quantitative measures warrant additional investigation.

Multi-Window CT Based Radiological Traits for Improving Early Detection in Lung Cancer Screening.

RATIONALE AND OBJECTIVES: Evaluate ability of radiological semantic traits assessed on multi-window computed tomography (CT) to predict lung cancer risk. MATERIALS AND METHODS: A total of 199 participants were investigated, including 60 incident lung cancers and 139 benign positive controls. Twenty lung window features and 2 mediastinal window features were extracted and scored on a point scale in three screening rounds. Multivariate logistic regression analysis was used to explore the association of these radiological traits with the risk of developing lung cancer. The areas under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and positive predictive value (PPV) were computed to evaluate the best predictive model. RESULTS: Combining mediastinal window-specific features with the lung window features-based model significantly improves performance compared to individual window features. Model performance is consistent both at baseline and the first follow-up scan, with an AUROC increased from 0.822 to 0.871 (p = 0.009) and from 0.877 to 0.917 (p = 0.008), respectively, for single to multi-window feature models. We also find that the multi-window CT based model showed better specificity and PPV, with PPV at the second follow-up scan improved to 0.953. CONCLUSION: We find combining window semantic features improves model performance in identifying cancerous nodules. We also find that lung window features are more informative compared to mediastinal features in predicting malignancy.

Multiphase computed tomography radiomics of pancreatic intraductal papillary mucinous neoplasms to predict malignancy.

BACKGROUND: Intraductal papillary mucinous neoplasms (IPMNs) are non-invasive pancreatic precursor lesions that can potentially develop into invasive pancreatic ductal adenocarcinoma. Currently, the International Consensus Guidelines (ICG) for IPMNs provides the basis for evaluating suspected IPMNs on computed tomography (CT) imaging. Despite using the ICG, it remains challenging to accurately predict whether IPMNs harbor high grade or invasive disease which would warrant surgical resection. A supplementary quantitative radiological tool, radiomics, may improve diagnostic accuracy of radiological evaluation of IPMNs. We hypothesized that using CT whole lesion radiomics features in conjunction with the ICG could improve the diagnostic accuracy of predicting IPMN histology. AIM: To evaluate whole lesion CT radiomic analysis of IPMNs for predicting malignant histology compared to International Consensus Guidelines. METHODS: Fifty-one subjects who had pancreatic surgical resection at our institution with histology demonstrating IPMN and available preoperative CT imaging were included in this retrospective cohort. Whole lesion semi-automated segmentation was performed on each preoperative CT using Healthmyne software (Healthmyne, Madison, WI). Thirty-nine relevant radiomic features were extracted from each lesion on each available contrast phase. Univariate analysis of the 39 radiomics features was performed for each contrast phase and values were compared between malignant and benign IPMN groups using logistic regression. Conventional quantitative and qualitative CT measurements were also compared between groups, via χ 2 (categorical) and Mann Whitney U (continuous) variables. RESULTS: Twenty-nine subjects (15 males, age 71 ± 9 years) with high grade or invasive tumor histology comprised the "malignant" cohort, while 22 subjects (11 males, age 70 ± 7 years) with low grade tumor histology were included in the "benign" cohort. Radiomic analysis showed 18/39 precontrast, 19/39 arterial phase, and 21/39 venous phase features differentiated malignant from benign IPMNs (P < 0.05). Multivariate analysis including only ICG criteria yielded two significant variables: thickened and enhancing cyst wall and enhancing mural nodule < 5 mm with an AUC (95%CI) of 0.817 (0.709-0.926). Multivariable post contrast radiomics achieved an AUC (95%CI) of 0.87 (0.767-0.974) for a model including arterial phase radiomics features and 0.834 (0.716-0.953) for a model including venous phase radiomics features. Combined multivariable model including conventional variables and arterial phase radiomics features achieved an AUC (95%CI) of 0.93 (0.85-1.0) with a 5-fold cross validation AUC of 0.90. CONCLUSION: Multi-phase CT radiomics evaluation could play a role in improving predictive capability in diagnosing malignancy in IPMNs. Future larger studies may help determine the clinical significance of our findings.

High metabolic tumor volume is associated with decreased efficacy of axicabtagene ciloleucel in large B-cell lymphoma.

High metabolic tumor volume (MTV) predicts worse outcomes in lymphoma treated with chemotherapy. However, it is unknown if this holds for patients treated with axicabtagene ciloleucel (axi-cel), an anti-CD19 targeted chimeric antigen receptor T-cell therapy. The primary objective of this retrospective study was to investigate the relationship between MTV and survival (overall survival [OS] and progression-free survival [PFS]) in patients with relapsed/refractory large B-cell lymphoma (LBCL) treated with axi-cel. Secondary objectives included finding the association of MTV with response rates and toxicity. The MTV values on baseline positron emission tomography of 96 patients were calculated via manual methodology using commercial software. Based on a median MTV cutoff value of 147.5 mL in the first cohort (n = 48), patients were divided into high and low MTV groups. Median follow-up for survivors was 24.98 months (range, 10.59-51.02 months). Patients with low MTV had significantly superior OS (hazard ratio [HR], 0.25; 95% confidence interval [CI], 0.10-0.66) and PFS (HR, 0.40; 95% CI, 0.18-0.89). Results were successfully validated in a second cohort of 48 patients with a median follow-up for survivors of 12.03 months (range, 0.89-25.74 months). Patients with low MTV were found to have superior OS (HR, 0.14; 95% CI, 0.05-0.42) and PFS (HR, 0.29; 95% CI, 0.12-0.69). In conclusion, baseline MTV is associated with OS and PFS in axi-cel recipients with LBCL.

Peritumoral and intratumoral radiomic features predict survival outcomes among patients diagnosed in lung cancer screening.

The National Lung Screening Trial (NLST) demonstrated that screening with low-dose computed tomography (LDCT) is associated with a 20% reduction in lung cancer mortality. One potential limitation of LDCT screening is overdiagnosis of slow growing and indolent cancers. In this study, peritumoral and intratumoral radiomics was used to identify a vulnerable subset of lung patients associated with poor survival outcomes. Incident lung cancer patients from the NLST were split into training and test cohorts and an external cohort of non-screen detected adenocarcinomas was used for further validation. After removing redundant and non-reproducible radiomics features, backward elimination analyses identified a single model which was subjected to Classification and Regression Tree to stratify patients into three risk-groups based on two radiomics features (NGTDM Busyness and Statistical Root Mean Square [RMS]). The final model was validated in the test cohort and the cohort of non-screen detected adenocarcinomas. Using a radio-genomics dataset, Statistical RMS was significantly associated with FOXF2 gene by both correlation and two-group analyses. Our rigorous approach generated a novel radiomics model that identified a vulnerable high-risk group of early stage patients associated with poor outcomes. These patients may require aggressive follow-up and/or adjuvant therapy to mitigate their poor outcomes.

Repeatability of Quantitative Imaging Features in Prostate Magnetic Resonance Imaging.

Background: Multiparametric magnetic resonance imaging (mpMRI) has emerged as a non-invasive modality to diagnose and monitor prostate cancer. Quantitative metrics on the regions of abnormality have shown to be useful descriptors to discriminate clinically significant cancers. In this study, we evaluate the reproducibility of quantitative imaging features using repeated mpMRI on the same patients. Methods: We retrospectively obtained the deidentified records of patients, who underwent two mpMRI scans within 2 weeks of the first baseline scan. The patient records were obtained as deidentified data (including imaging), obtained through the TCIA (The Cancer Imaging Archive) repository and analyzed in our institution with an institutional review board-approved Health Insurance Portability and Accountability Act-compliant retrospective study protocol. Indicated biopsied regions were used as a marker for our study radiologists to delineate the regions of interest. We extracted 307 quantitative features in each mpMRI modality [T2-weighted MR sequence image (T2w) and apparent diffusion coefficient (ADC) with b values of 0 and 1,400 mm/s2] across the two sequential scans. Concordance correlation coefficients (CCCs) were computed on the features extracted from sequential scans. Redundant features were removed by computing the coefficient of determination (R 2) among them and replaced with a feature that had the highest dynamic range within intercorrelated groups. Results: We have assessed the reproducibility of quantitative imaging features among sequential scans and found that habitat region characterization improves repeatability in ADC maps. There were 19 T2w features and two ADC features in radiologist drawn regions (native raw image), compared to 18 T2w and 15 ADC features in habitat regions (sphere), which were reproducible (CCC ≥0.65) and non-redundant (R 2 ≥ 0.99). We also found that z-transformation of the images prior to feature extraction reduced the number of reproducible features with no detrimental effect. Conclusion: We have shown that there are quantitative imaging features that are reproducible across sequential prostate mpMRI acquisition at a preset level of filters. We also found that a habitat approach improves feature repeatability in ADC. A validated set of reproducible image features in mpMRI will allow us to develop clinically useful disease risk stratification, enabling the possibility of using imaging as a surrogate to invasive biopsies.

Correction: Acidity promotes tumour progression by altering macrophage phenotype in prostate cancer.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

18F-FDG PET/CT Habitat Radiomics Predicts Outcome of Patients with Cervical Cancer Treated with Chemoradiotherapy.

PURPOSE: To determine if quantitative features extracted from pretherapy fluorine 18 fluorodeoxyglucose (18F-FDG) PET/CT estimate prognosis in patients with locally advanced cervical cancer treated with chemoradiotherapy. MATERIALS AND METHODS: In this retrospective study, PET/CT images and outcomes were curated from 154 patients with locally advanced cervical cancer, who underwent chemoradiotherapy from two institutions between March 2008 and June 2016, separated into independent training (n = 78; mean age, 51 years ± 13 [standard deviation]) and testing (n = 76; mean age, 50 years ± 10) cohorts. Radiomic features were extracted from PET, CT, and habitat (subregions with different metabolic characteristics) images that were derived by fusing PET and CT images. Parsimonious sets of these features were identified by the least absolute shrinkage and selection operator analysis and used to generate predictive radiomics signatures for progression-free survival (PFS) and overall survival (OS) estimation. Prognostic validation of the radiomic signatures as independent prognostic markers was performed using multivariable Cox regression, which was expressed as nomograms, together with other clinical risk factors. RESULTS: The radiomics nomograms constructed with T stage, lymph node status, and radiomics signatures resulted in significantly better performance for the estimation of PFS (Harrell concordance index [C-index], 0.85 for training and 0.82 for test) and OS (C-index, 0.86 for training and 0.82 for test) compared with International Federation of Gynecology and Obstetrics staging system (C-index for PFS, 0.70 for training [P = .001] and 0.70 for test [P = .002]; C-index for OS, 0.73 for training [P < .001] and 0.70 for test [P < .001]), respectively. CONCLUSION: Prognostic models were generated and validated from quantitative analysis of 18F-FDG PET/CT habitat images and clinical data, and may have the potential to identify the patients who need more aggressive treatment in clinical practice, pending further validation with larger prospective cohorts.Supplemental material is available for this article.© RSNA, 2020.

A Shallow Convolutional Neural Network Predicts Prognosis of Lung Cancer Patients in Multi-Institutional CT-Image Data.

Lung cancer is the most common fatal malignancy in adults worldwide, and non-small cell lung cancer (NSCLC) accounts for 85% of lung cancer diagnoses. Computed tomography (CT) is routinely used in clinical practice to determine lung cancer treatment and assess prognosis. Here, we developed LungNet, a shallow convolutional neural network for predicting outcomes of NSCLC patients. We trained and evaluated LungNet on four independent cohorts of NSCLC patients from four medical centers: Stanford Hospital (n = 129), H. Lee Moffitt Cancer Center and Research Institute (n = 185), MAASTRO Clinic (n = 311) and Charité - Universitätsmedizin (n=84). We show that outcomes from LungNet are predictive of overall survival in all four independent survival cohorts as measured by concordance indices of 0.62, 0.62, 0.62 and 0.58 on cohorts 1, 2, 3, and 4, respectively. Further, the survival model can be used, via transfer learning, for classifying benign vs malignant nodules on the Lung Image Database Consortium (n = 1010), with improved performance (AUC=0.85) versus training from scratch (AUC=0.82). LungNet can be used as a noninvasive predictor for prognosis in NSCLC patients and can facilitate interpretation of CT images for lung cancer stratification and prognostication.

Radiological semantics discriminate clinically significant grade prostate cancer.

BACKGROUND: Identification of imaging traits to discriminate clinically significant prostate cancer is challenging due to the multi focal nature of the disease. The difficulty in obtaining a consensus by the Prostate Imaging and Data Systems (PI-RADS) scores coupled with disagreements in interpreting multi-parametric Magnetic Resonance Imaging (mpMRI) has resulted in increased variability in reporting findings and evaluating the utility of this imaging modality in detecting clinically significant prostate cancer. This study assess the ability of radiological traits (semantics) observed on multi-parametric Magnetic Resonance images (mpMRI) to discriminate clinically significant prostate cancer. METHODS: We obtained multi-parametric MRI studies from 103 prostate cancer patients with 167 targeted biopsies from a single institution. The study was approved by our Institutional Review Board (IRB) for retrospective analysis. The biopsy location had been identified and marked by a clinical radiologist for targeted biopsy based on initial study interpretation. Using the target locations, two study radiologists independently re-evaluated the scans and scored 16 semantic traits on a point scale (up to 5 levels) based on mpMRI images. The semantic traits describe size, shape, and border characteristics of the prostate lesion, as well as presence of disease around lymph nodes (lymphadenopathy). We built a linear classifier model on these semantic traits and related to pathological outcome to identify clinically significant tumors (Gleason Score ≥ 7). The discriminatory ability of the predictors was tested using cross validation method randomly repeated and ensemble values were reported. We then compared the performance of semantic predictors with the PI-RADS predictors. RESULTS: We found several semantic features individually discriminated high grade Gleason score (ADC-intensity, Homogeneity, early-enhancement, T2-intensity and extraprostatic extention), these univariate predictors had an average area under the receiver operator characteristics (AUROC) ranging from 0.54 to 0.68. Multivariable semantic predictors with three features (ADC-intensity; T2-intensity, enhancement homogenicity) had an average AUROC of 0.7 [0.43, 0.94]. The PI-RADS based predictor had average AUROC of 0.6 [0.47, 0.75]. CONCLUSION: We find semantics traits are related to pathological findings with relatively higher reproducibility between radiologists. Multivariable predictors formed on these traits shows higher discriminatory ability compared to PI-RADS scores.