Radiomic Analysis to Predict Histopathologically Confirmed Pseudoprogression in Glioblastoma Patients.

Purpose: Pseudoprogression mimicking recurrent glioblastoma remains a diagnostic challenge that may adversely confound or delay appropriate treatment or clinical trial enrollment. We sought to build a radiomic classifier to predict pseudoprogression in patients with primary isocitrate dehydrogenase wild type glioblastoma. Methods and Materials: We retrospectively examined a training cohort of 74 patients with isocitrate dehydrogenase wild type glioblastomas with brain magnetic resonance imaging including dynamic contrast enhanced T1 perfusion before resection of an enhancing lesion indeterminate for recurrent tumor or pseudoprogression. A recursive feature elimination random forest classifier was built using nested cross-validation without and with O6-methylguanine-DNA methyltransferase status to predict pseudoprogression. Results: A classifier constructed with cross-validation on the training cohort achieved an area under the receiver operating curve of 81% for predicting pseudoprogression. This was further improved to 89% with the addition of O6-methylguanine-DNA methyltransferase status into the classifier. Conclusions: Our results suggest that radiomic analysis of contrast T1-weighted images and magnetic resonance imaging perfusion images can assist the prompt diagnosis of pseudoprogression. Validation on external and independent data sets is necessary to verify these advanced analyses, which can be performed on routinely acquired clinical images and may help inform clinical treatment decisions.

Diagnostic value of radiomics and machine learning with dynamic contrast-enhanced magnetic resonance imaging for patients with atypical ductal hyperplasia in predicting malignant upgrade.

PURPOSE: To investigate whether radiomics features extracted from magnetic resonance imaging (MRI) of patients with biopsy-proven atypical ductal hyperplasia (ADH) coupled with machine learning can differentiate high-risk lesions that will upgrade to malignancy at surgery from those that will not, and to determine if qualitatively and semi-quantitatively assessed imaging features, clinical factors, and image-guided biopsy technical factors are associated with upgrade rate. METHODS: This retrospective study included 127 patients with 139 breast lesions yielding ADH at biopsy who were assessed with multiparametric MRI prior to biopsy. Two radiologists assessed all lesions independently and with a third reader in consensus according to the BI-RADS lexicon. Univariate analysis and multivariate modeling were performed to identify significant radiomic features to be included in a machine learning model to discriminate between lesions that upgraded to malignancy on surgery from those that did not. RESULTS: Of 139 lesions, 28 were upgraded to malignancy at surgery, while 111 were not upgraded. Diagnostic accuracy was 53.6%, specificity 79.2%, and sensitivity 15.3% for the model developed from pre-contrast features, and 60.7%, 86%, and 22.8% for the model developed from delta radiomics datasets. No significant associations were found between any radiologist-assessed lesion parameters and upgrade status. There was a significant correlation between the number of specimens sampled during biopsy and upgrade status (p = 0.003). CONCLUSION: Radiomics analysis coupled with machine learning did not predict upgrade status of ADH. The only significant result from this analysis is between the number of specimens sampled during biopsy procedure and upgrade status at surgery.

MRI-based machine learning radiomics can predict HER2 expression level and pathologic response after neoadjuvant therapy in HER2 overexpressing breast cancer.

BACKGROUND: To use clinical and MRI radiomic features coupled with machine learning to assess HER2 expression level and predict pathologic response (pCR) in HER2 overexpressing breast cancer patients receiving neoadjuvant chemotherapy (NAC). METHODS: This retrospective study included 311 patients. pCR was defined as no residual invasive carcinoma in the breast or axillary lymph nodes (ypT0/isN0). Radiomics/statistical analysis was performed using MATLAB and CERR software. After ROC and correlation analysis, selected radiomics parameters were advanced to machine learning modelling alongside clinical MRI-based parameters (lesion type, multifocality, size, nodal status). For predicting pCR, the data was split into a training and test set (80:20). FINDINGS: The overall pCR rate was 60.5% (188/311). The final model to predict HER2 heterogeneity utilised three MRI parameters (two clinical, one radiomic) for a sensitivity of 99.3% (277/279), specificity of 81.3% (26/32), and diagnostic accuracy of 97.4% (303/311). The final model to predict pCR included six MRI parameters (two clinical, four radiomic) for a sensitivity of 86.5% (32/37), specificity of 80.0% (20/25), and diagnostic accuracy of 83.9% (52/62) (test set); these results were independent of age and ER status, and outperformed the best model developed using clinical parameters only (p=0.029, comparison of proportion Chi-squared test). INTERPRETATION: The machine learning models, including both clinical and radiomics MRI features, can be used to assess HER2 expression level and can predict pCR after NAC in HER2 overexpressing breast cancer patients. FUNDING: NIH/NCI (P30CA008748), Susan G. Komen Foundation, Breast Cancer Research Foundation, Spanish Foundation Alfonso Martin Escudero, European School of Radiology.

Improved characterization of sub-centimeter enhancing breast masses on MRI with radiomics and machine learning in BRCA mutation carriers.

OBJECTIVES: To investigate whether radiomics features extracted from MRI of BRCA-positive patients with sub-centimeter breast masses can be coupled with machine learning to differentiate benign from malignant lesions using model-free parameter maps. METHODS: In this retrospective study, BRCA-positive patients who had an MRI from November 2013 to February 2019 that led to a biopsy (BI-RADS 4) or imaging follow-up (BI-RADS 3) for sub-centimeter lesions were included. Two radiologists assessed all lesions independently and in consensus according to BI-RADS. Radiomics features were calculated using open-source CERR software. Univariate analysis and multivariate modeling were performed to identify significant radiomics features and clinical factors to be included in a machine learning model to differentiate malignant from benign lesions. RESULTS: Ninety-six BRCA mutation carriers (mean age at biopsy = 45.5 ± 13.5 years) were included. Consensus BI-RADS classification assessment achieved a diagnostic accuracy of 53.4%, sensitivity of 75% (30/40), specificity of 42.1% (32/76), PPV of 40.5% (30/74), and NPV of 76.2% (32/42). The machine learning model combining five parameters (age, lesion location, GLCM-based correlation from the pre-contrast phase, first-order coefficient of variation from the 1st post-contrast phase, and SZM-based gray level variance from the 1st post-contrast phase) achieved a diagnostic accuracy of 81.5%, sensitivity of 63.2% (24/38), specificity of 91.4% (64/70), PPV of 80.0% (24/30), and NPV of 82.1% (64/78). CONCLUSIONS: Radiomics analysis coupled with machine learning improves the diagnostic accuracy of MRI in characterizing sub-centimeter breast masses as benign or malignant compared with qualitative morphological assessment with BI-RADS classification alone in BRCA mutation carriers. KEY POINTS: • Radiomics and machine learning can help differentiate benign from malignant breast masses even if the masses are small and morphological features are benign. • Radiomics and machine learning analysis showed improved diagnostic accuracy, specificity, PPV, and NPV compared with qualitative morphological assessment alone.

Effects of orientation change during environmental learning on age-related difference in spatial memory.

It has been suggested that older adults suffer a greater degree of decline in environmental learning when navigating in an environment than when reading a map of the environment. However, the two types of spatial learning differ not only in perspectives (i.e., navigation is done with a ground-level perspective; a map is read from an aerial perspective) but also in orientations (i.e., orientations vary during navigation; spatial information is drawn from a single orientation in a map), making it unclear which factor critically affects older adults' spatial learning. The present study addressed this issue by having younger and older participants learn the layout of a large-scale environment through an aerial movie that contained changes in orientations from which the environment was depicted. Results showed that older participants' memories for the environmental layout were as distorted as those created through a ground-level movie (which involved the same orientation changes), whereas they formed more accurate memories through another aerial movie in which an orientation was fixed. By contrast, younger participants learned the environment equally well from the three movies. Taken together, these findings suggest that there is age-related alteration specifically in the ability to process multiple orientations of an environment while encoding its layout in memory. It is inferred that this alteration stems from functional deterioration of the medial temporal lobe, and possibly that of posterior cingulate areas as well (e.g., the retrosplenial cortex), in late adulthood.

Minkowski functionals: An MRI texture analysis tool for determination of the aggressiveness of breast cancer.

BACKGROUND: This work aims to see whether Minkowski Functionals can be used to distinguish between cancer types before chemotherapy treatment has begun, and whether a response to treatment can be predicted by an initial scan alone. METHODS: Fat-nulled T1w 3T DCE-MRI scans were taken of 100 cases of biopsy confirmed breast cancer and a series of binary images created on lesion containing slices. Minkowski Functionals were calculated for each binary image and the change in these values as the binary threshold was raised was described using 6(th) order polynomials. These polynomials were used to compare between patient subgroups, for triple negative breast cancer (TNBC) status, chemotherapy response, biopsy grade, nodal status, and lymphovascular invasion status. RESULTS: When using Minkowski Functionals statistically significant (P < 0.05) differences were found between TNBC status, biopsy grade, and lymphovascular invasion status subgroups for all methodologies. The analysis performance did not appear to be affected by the number of threshold steps used. Most notably, very strong differences (P ≤ 0.01) were found between TNBC and other intrinsic subtype patients. When analyzed with a binary logistic regression model, an area under the curve value of 0.917 (0.846-0.987, 95% confidence interval) for TNBC classification was found. CONCLUSION: The method of texture analysis presented here provides a novel way to characterize tumors, and demonstrates clear differences between cancer groups which are detectable before treatment begins, and can help with treatment planning as a valuable prognosis tool.

Dynamics in atomic signaling games.

We study an atomic signaling game under stochastic evolutionary dynamics. There are a finite number of players who repeatedly update from a finite number of available languages/signaling strategies. Players imitate the most fit agents with high probability or mutate with low probability. We analyze the long-run distribution of states and show that, for sufficiently small mutation probability, its support is limited to efficient communication systems. We find that this behavior is insensitive to the particular choice of evolutionary dynamic, a property that is due to the game having a potential structure with a potential function corresponding to average fitness. Consequently, the model supports conclusions similar to those found in the literature on language competition. That is, we show that efficient languages eventually predominate the society while reproducing the empirical phenomenon of linguistic drift. The emergence of efficiency in the atomic case can be contrasted with results for non-atomic signaling games that establish the non-negligible possibility of convergence, under replicator dynamics, to states of unbounded efficiency loss.

Can probiotic yogurt prevent diarrhoea in children on antibiotics? A double-blind, randomised, placebo-controlled study.

OBJECTIVE: To estimate the efficacy of a probiotic yogurt compared to a pasteurised yogurt for the prevention of antibiotic-associated diarrhoea in children. DESIGN AND SETTING: This was a multisite, randomised, double-blind, placebo-controlled clinical trial conducted between September 2009 and 2012. The study was conducted through general practices and pharmacies in Launceston, Tasmania, Australia. PARTICIPANTS AND INTERVENTIONS: Children (aged 1-12 years) prescribed antibiotics, were randomised to receive 200 g/day of either yogurt (probiotic) containing Lactobacillus rhamnosus GG (LGG), Bifidobacterium lactis (Bb-12) and Lactobacillus acidophilus (La-5) or a pasteurised yogurt (placebo) for the same duration as their antibiotic treatment. OUTCOMES: Stool frequency and consistency were recorded for the duration of treatment plus 1 week. Primary outcome was stool frequency and consistency, classified at different levels of diarrhoea severity. Due to the small number of cases of diarrhoea, comparisons between groups were made using Fisher's exact analysis. RESULTS: 72 children commenced and 70 children (36 placebo and 34 probiotic) completed the trial. There were no incidents of severe diarrhoea (stool consistency ≥6, ≥3 stools/day for ≥2 consecutive days) in the probiotic group and six in the placebo group (Fisher's exact p=0.025). There was also only one episode of minor diarrhoea (stool consistency ≥5, ≥2 stools/day for ≥2 days in the probiotic group compared to 21 in the placebo group (Fisher's exact p<0.001). The probiotic group reported fewer adverse events (1 had abdominal pain, 1 vomited and 1 had headache) than the placebo group (6 had abdominal pain, 4 had loss of appetite and 1 had nausea). CONCLUSIONS: A yogurt combination of LGG, La-5 and Bb-12 is an effective method for reducing the incidence of antibiotic-associated diarrhoea in children. TRIAL REGISTRATION NUMBER: Australian New Zealand Clinical Trials Registry ACTRN12609000281291.