View this article online at wileyonlinelibrary.com.

There is a moderate association between tumour molecular biomarkers and algorithmically assessed imaging features.

Purpose To determine whether a multivariate machine learning-based model using computer-extracted features of pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict pathologic complete response (pCR) to neoadjuvant therapy (NAT) in breast cancer patients. Methods Institutional review board approval was obtained for this retrospective study of 288 breast cancer patients at our institution who received NAT and had a pre-treatment breast MRI. A comprehensive set of 529 radiomic features was extracted from each patient’s pretreatment MRI. The patients were divided into equal groups to form a training set and an independent test set. Two multivariate machine learning models (logistic regression and a support vector machine) based on imaging features were trained to predict pCR in (a) all patients with NAT, (b) patients with neoadjuvant chemotherapy (NACT), and (c) triple negative or human epidermal growth factor receptor 2-positive (TN/HER2+) patients who had NAT. The multivariate models were tested using the independent test set, and the area under the receiver operating characteristics (ROC) curve (AUC) was calculated. Results Out of the 288 patients, 64 achieved pCR. The AUC values for predicting pCR in TN/HER+ patients who received NAT were significant (.707, 95%CI: 0.582–0.833, p < 0.002). Conclusions The multivariate models based on pre-treatment MRI features were able to predict pCR in TN/HER2+ patients.

There is a very strong effect of selecting data for training on performance of CNNs in a multi-institutional setting. Determination of the reasons behind this effect requires additional comprehensive investigation.

Recent analysis identified distinct genomic subtypes of lower-grade glioma tumors which are associated with shape features. In this study, we propose a fully automatic way to quantify tumor imaging characteristics using deep learning-based segmentation and test whether these characteristics are predictive of tumor genomic subtypes.We used preoperative imaging and genomic data of 110 patients from 5 institutions with lower-grade gliomas from The Cancer Genome Atlas. Based on automatic deep learning segmentations, we extracted three features which quantify two-dimensional and three-dimensional characteristics of the tumors. Genomic data for the analyzed cohort of patients consisted of previously identified genomic clusters based on IDH mutation and 1p/19q co-deletion, DNA methylation, gene expression, DNA copy number, and microRNA expression. To analyze the relationship between the imaging features and genomic clusters, we conducted the Fisher exact test for 10 hypotheses for each pair of imaging feature and genomic subtype. To account for multiple hypothesis testing, we applied a Bonferroni correction. P-values lower than 0.005 were considered statistically significant.We found the strongest association between RNASeq clusters and the bounding ellipsoid volume ratio (p < 0.0002) and between RNASeq clusters and margin fluctuation (p < 0.005).In addition, we identified associations between bounding ellipsoid volume ratio and all tested molecular subtypes (p < 0.02) as well as between angular standard deviation and RNASeq cluster (p < 0.02). In terms of automatic tumor segmentation that was used to generate the quantitative image characteristics, our deep learning algorithm achieved a mean Dice coefficient of 82% which is comparable to human performance.

Purpose:To determine whether deep learning models can distinguish between breast cancer molecular subtypes based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Materials and methods:In this institutional review board-approved single-center study, we analyzed DCE-MR images of 270 patients at our institution. Lesions of interest were identified by radiologists. The task was to automatically determine whether the tumor is of the Luminal A subtype or of another subtype based on the MR image patches representing the tumor. Three different deep learning approaches were used to classify the tumor according to their molecular subtypes: learning from scratch where only tumor patches were used for training, transfer learning where networks pre-trained on natural images were fine-tuned using tumor patches, and off-the-shelf deep features where the features extracted by neural networks trained on natural images were used for classification with a support vector machine. Network architectures utilized in our experiments were GoogleNet, VGG, and CIFAR. We used 10-fold crossvalidation method for validation and area under the receiver operating characteristic (AUC) as the measure of performance. Results:The best AUC performance for distinguishing molecular subtypes was 0.65 (95% CI:[0.57,0.71]) and was achieved by the off-the-shelf deep features approach. The highest AUC performance for training from scratch was 0.58 (95% CI:[0.51,0.64]) and the best AUC performance for transfer learning was 0.60 (95% CI:[0.52,0.65]) respectively. For the off-the-shelf approach, the features extracted from the fully connected layer performed the best. Conclusion:Deep learning may play a role in discovering radiogenomic associations in breast cancer.

Breast tumor segmentation based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a challenging problem and an active area of research. Particular challenges, similarly as in other segmentation problems, include the class-imbalance problem as well as confounding background in DCE-MR images. To address these issues, we propose a mask-guided hierarchical learning (MHL) framework for breast tumor segmentation via fully convolutional networks (FCN). Specifically, we first develop an FCN model to generate a 3D breast mask as the region of interest (ROI) for each image, to remove confounding information from input DCE-MR images. We then design a two-stage FCN model to perform coarse-to-fine segmentation for breast tumors. Particularly, we propose a Dice-Sensitivity-like loss function and a reinforcement sampling strategy to handle the class-imbalance problem. To precisely identify locations of tumors that underwent a biopsy, we further propose an FCN model to detect two landmarks located at two nipples. We finally select the biopsied tumor based on both identified landmarks and segmentations. We validate our MHL method on 272 patients, achieving a mean Dice similarity coefficient (DSC) of 0.72 which is comparable to mutual DSC between expert radiologists. Using the segmented biopsied tumors, we also demonstrate that the automatically generated masks can be applied to radiogenomics and can identify luminal A subtype from other molecular subtypes with the similar accuracy with the analysis based on semi-manual tumor segmentation.

Background:As artificial intelligence (AI) approaches in research increase and AI becomes more integrated into medicine, there is a need to understand perspectives from members of the Canadian public and medical community. The aim of this project was to investigate current perspectives on ethical issues surrounding AI in health care. Methods:In this qualitative study, adult patients with meningioma and their caregivers were recruited consecutively (August 2018-February 2019) from a neurosurgical clinic in Toronto. Health care providers caring for these patients were recruited through snowball sampling. Based on a nonsystematic literature search, we constructed 3 vignettes that sought participants' views on hypothetical issues surrounding potential AI applications in health care. The vignettes were presented to participants in interviews, which lasted 15-45 minutes. Responses were transcribed and coded for concepts, frequency of response types and larger concepts emerging from the interview. Results:We interviewed 30 participants: 18 patients, 7 caregivers and 5 health care providers. For each question, a variable number of responses were recorded. The majority of participants endorsed nonconsented use of health data but advocated for disclosure and transparency. Few patients and caregivers felt that allocation of health resources should be done via computerized output, and a majority stated that it was inappropriate to delegate such decisions to a computer. Almost all participants felt that selling health data should be prohibited, and a minority stated that less privacy is acceptable for the goal of improving health. Certain caveats were identified, including the desire for deidentification of data and use within trusted institutions.Interpretation: In this preliminary study, patients and caregivers reported a mixture of hopefulness and concern around the use of AI in health care research, whereas providers were generally more skeptical. These findings provide a point of departure for institutions adopting health AI solutions to consider the ethical implications of this work by understanding stakeholders' perspectives. Abstract Research OPEN CMAJ OPEN, 8(1) E91 Affiliations: Division of Neurosurgery (McCradden,