Is Brucella excreted in cattle faeces? - Evidence from Punjab, India

Brucellosis is a neglected zoonosis that affects animals and people in much of the underdeveloped world. The disease is endemic in cattle in Punjab, India and controlling it is a public health challenge. Dairy farmers and farm labour commonly handle cattle faeces with bare hands and personal protective equipments are not used. No studies have been conducted about the shedding of Brucella species in faeces of sero positive cattle in the state. This study aimed to isolate and identify the Brucella species from faeces of sero positive cattle in Punjab, India. Faecal samples were collected from 350 Brucella sero positive cattle in Ludhiana district of Punjab, India. Isolation was performed using a pre-enriched Brucella selective broth medium as well as Brucella selective medium agar plates containing horse serum and Brucella selective supplements. Isolates were identified using Gram staining technique and rapid slide agglutination test, and then confirmed by using bcsp31 and 16s rRNA genus specific PCR. Isolates were further identified up to species level by using Bruce-Ladder multiplex PCR. Fourteen Brucella species were isolated, all of which showed coccobacilli on gram staining, positive rapid slide agglutination test and amplification of bcsp31 and 16s rRNA genes. Of the 14 isolates, 11 were identified as Brucella abortus and 3 were identified as Brucella melitensis. The study demonstrates that animal faeces could pose a potential risk for animal and human health and faeces of seropositive cattle must be handled with care.

Using Bayesian Neural Networks to Select Features and Compute Credible Intervals for Personalized Survival Prediction

An Individual Survival Distribution (ISD) models a patient's personalized survival probability at all future time points. Previously, ISD models have been shown to produce accurate and personalized survival estimates (for example, time to relapse or to death) in several clinical applications. However, off-the-shelf neural-network-based ISD models are usually opaque models due to their limited support for meaningful feature selection and uncertainty estimation, which hinders their wide clinical adoption. Here, we introduce a Bayesian-neural-network-based ISD (BNN-ISD) model that produces accurate survival estimates but also quantifies the uncertainty in model's parameter estimation, which can be used to (1) rank the importance of the input features to support feature selection and (2) compute credible intervals around ISDs for clinicians to assess the model's confidence in its prediction. Our BNN-ISD model utilized sparsity-inducing priors to learn a sparse set of weights to enable feature selection. We provide empirical evidence, on 2 synthetic and 3 real-world clinical datasets, that BNN-ISD system can effectively select meaningful features and compute trustworthy credible intervals of the survival distribution for each patient. We observed that our approach accurately recovers feature importance in the synthetic datasets and selects meaningful features for the real-world clinical data as well, while also achieving state-of-the-art survival prediction performance. We also show that these credible regions can aid in clinical decision-making by providing a gauge of the uncertainty of the estimated ISD curves.

Learning Individual Survival Models from PanCancer Whole Transcriptome Data

PURPOSE

Personalized medicine attempts to predict survival time for each patient, based on their individual tumor molecular profile. We investigate whether our survival learner in combination with a dimension reduction method can produce useful survival estimates for a variety of patients with cancer.

EXPERIMENTAL DESIGN

This article provides a method that learns a model for predicting the survival time for individual patients with cancer from the PanCancer Atlas: given the (16,335 dimensional) gene expression profiles from 10,173 patients, each having one of 33 cancers, this method uses unsupervised nonnegative matrix factorization (NMF) to reexpress the gene expression data for each patient in terms of 100 learned NMF factors. It then feeds these 100 factors into the Multi-Task Logistic Regression (MTLR) learner to produce cancer-specific models for each of 20 cancers (with >50 uncensored instances); this produces "individual survival distributions" (ISD), which provide survival probabilities at each future time for each individual patient, which provides a patient's risk score and estimated survival time.

RESULTS

Our NMF-MTLR concordance indices outperformed the VAECox benchmark by 14.9% overall. We achieved optimal survival prediction using pan-cancer NMF in combination with cancer-specific MTLR models. We provide biological interpretation of the NMF model and clinical implications of ISDs for prognosis and therapeutic response prediction.

CONCLUSIONS

NMF-MTLR provides many benefits over other models: superior model discrimination, superior calibration, meaningful survival time estimates, and accurate probabilistic estimates of survival over time for each individual patient. We advocate for the adoption of these cancer survival models in clinical and research settings.

Formal mentorship in Canadian radiology residency programmes

AIM

To characterise formal mentorship programmes in Canadian radiology residency programmes, to evaluate residents' perspectives on formal mentorship, and to identify ways to optimise mentorship during radiology training.

MATERIALS AND METHODS

An anonymous survey was distributed to radiology resident representatives of the Canadian Association of Radiologists (CAR) Resident and Fellow Section (RFS). Questions pertained to the presence and structure of formal mentorship programmes at each participant's institution.

RESULTS

The survey was distributed to 33 radiology residents, of which 30 responded. All 16 accredited radiology residency programmes in Canada were represented. Of these programmes, 12 (75%) had formal mentorship programmes and four (25%) did not. The structure of formal mentorship programmes varied among institutions including one-on-one and group mentoring. For 33% of residency programmes, the programme director assigned the mentor and mentee groups. Only 33% of respondents had the option of choosing their mentor. Lack of funding and lack of time were the two main perceived barriers by residents to maintaining mentorship relationships.

CONCLUSION

Although not all radiology residency programmes in Canada have a formal mentorship programme, most have a form of structured mentorship in place. As formal mentorship programmes improve overall mentorship experience during residency, they can lead to improved research productivity, fellowship, and career preparation, as well as work-life balance for Canadian radiology residents.

Federated learning enables big data for rare cancer boundary detection

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

The influence of anastomotic techniques on postoperative anastomotic complications: Results of the Oesophago-Gastric Anastomosis Audit

BACKGROUND

The optimal anastomotic techniques in esophagectomy to minimize rates of anastomotic leakage and conduit necrosis are not known. The aim of this study was to assess whether the anastomotic technique was associated with anastomotic failure after esophagectomy in the international Oesophago-Gastric Anastomosis Audit cohort.

METHODS

This prospective observational multicenter cohort study included patients undergoing esophagectomy for esophageal cancer over 9 months during 2018. The primary exposure was the anastomotic technique, classified as handsewn, linear stapled, or circular stapled. The primary outcome was anastomotic failure, namely a composite of anastomotic leakage and conduit necrosis, as defined by the Esophageal Complications Consensus Group. Multivariable logistic regression modeling was used to identify the association between anastomotic techniques and anastomotic failure, after adjustment for confounders.

RESULTS

Of the 2238 esophagectomies, the anastomosis was handsewn in 27.1%, linear stapled in 21.0%, and circular stapled in 51.9%. Anastomotic techniques differed significantly by the anastomosis sites (P < .001), with the majority of neck anastomoses being handsewn (69.9%), whereas most chest anastomoses were stapled (66.3% circular stapled and 19.3% linear stapled). Rates of anastomotic failure differed significantly among the anastomotic techniques (P < .001), from 19.3% in handsewn anastomoses, to 14.0% in linear stapled anastomoses, and 12.1% in circular stapled anastomoses. This effect remained significant after adjustment for confounding factors on multivariable analysis, with an odds ratio of 0.63 (95% CI, 0.46-0.86; P = .004) for circular stapled versus handsewn anastomosis. However, subgroup analysis by anastomosis site suggested that this effect was predominantly present in neck anastomoses, with anastomotic failure rates of 23.2% versus 14.6% versus 5.9% for handsewn versus linear stapled anastomoses versus circular stapled neck anastomoses, compared with 13.7% versus 13.8% versus 12.2% for chest anastomoses.

CONCLUSIONS

Handsewn anastomoses appear to be independently associated with higher rates of anastomotic failure compared with stapled anastomoses. However, this effect seems to be largely confined to neck anastomoses, with minimal differences between techniques observed for chest anastomoses. Further research into standardization of anastomotic approach and techniques may further improve outcomes.

Stable and Discriminatory Radiomic Features from the Tumor and Its Habitat Associated with Progression-Free Survival in Glioblastoma: A Multi-Institutional Study

BACKGROUND AND PURPOSE

Glioblastoma is an aggressive brain tumor, with no validated prognostic biomarkers for survival before surgical resection. Although recent approaches have demonstrated the prognostic ability of tumor habitat (constituting necrotic core, enhancing lesion, T2/FLAIR hyperintensity subcompartments) derived radiomic features for glioblastoma survival on treatment-naive MR imaging scans, radiomic features are known to be sensitive to MR imaging acquisitions across sites and scanners. In this study, we sought to identify the radiomic features that are both stable across sites and discriminatory of poor and improved progression-free survival in glioblastoma tumors.

MATERIALS AND METHODS

We used 150 treatment-naive glioblastoma MR imaging scans (Gadolinium-T1w, T2w, FLAIR) obtained from 5 sites. For every tumor subcompartment (enhancing tumor, peritumoral FLAIR-hyperintensities, necrosis), a total of 316 three-dimensional radiomic features were extracted. The training cohort constituted studies from 4 sites (n = 93) to select the most stable and discriminatory radiomic features for every tumor subcompartment. These features were used on a hold-out cohort (n = 57) to evaluate their ability to discriminate patients with poor survival from those with improved survival.

RESULTS

Incorporating the most stable and discriminatory features within a linear discriminant analysis classifier yielded areas under the curve of 0.71, 0.73, and 0.76 on the test set for distinguishing poor and improved survival compared with discriminatory features alone (areas under the curve of 0.65, 0.54, 0.62) from the necrotic core, enhancing tumor, and peritumoral T2/FLAIR hyperintensity, respectively.

CONCLUSIONS

Incorporating stable and discriminatory radiomic features extracted from tumors and associated habitats across multisite MR imaging sequences may yield robust prognostic classifiers of patient survival in glioblastoma tumors.

Management dilemmas of tracheal paraganglioma: a case report and review of literature

Paragangliomas of the trachea are rare neoplasms and can present to the clinician with acute airway problems. These neoplasms sometimes are misdiagnosed by general practitioners as asthmatic exacerbation. We present the case of a 66-year-old woman who presented to us with a history of dyspnoea at rest in the supine position and on exertion and a productive cough. This was diagnosed as bronchial asthma and she was treated with corticosteroid inhalers for four months by her GP. She was subsequently evaluated by computed tomography of the neck and thorax, which revealed an intratracheal enhancing lesion measuring around 11 mm in the lower cervical trachea. Fibreoptic bronchoscopy showed a mass lesion at the level of mid trachea. A low tracheostomy was followed by telescopic examination and the mass was resected using coablation. Histology of the mass was reported as paraganglioma. Difficulties encountered and literature review of various management options are presented in this report.

Textbook outcome following oesophagectomy for cancer: international cohort study

Background

Textbook outcome has been proposed as a tool for the assessment of oncological surgical care. However, an international assessment in patients undergoing oesophagectomy for oesophageal cancer has not been reported. This study aimed to assess textbook outcome in an international setting.

Methods

Patients undergoing curative resection for oesophageal cancer were identified from the international Oesophagogastric Anastomosis Audit (OGAA) from April 2018 to December 2018. Textbook outcome was defined as the percentage of patients who underwent a complete tumour resection with at least 15 lymph nodes in the resected specimen and an uneventful postoperative course, without hospital readmission. A multivariable binary logistic regression model was used to identify factors independently associated with textbook outcome, and results are presented as odds ratio (OR) and 95 per cent confidence intervals (95 per cent c.i.).

Results

Of 2159 patients with oesophageal cancer, 39.7 per cent achieved a textbook outcome. The outcome parameter ‘no major postoperative complication’ had the greatest negative impact on a textbook outcome for patients with oesophageal cancer, compared to other textbook outcome parameters. Multivariable analysis identified male gender and increasing Charlson comorbidity index with a significantly lower likelihood of textbook outcome. Presence of 24-hour on-call rota for oesophageal surgeons (OR 2.05, 95 per cent c.i. 1.30 to 3.22; P = 0.002) and radiology (OR 1.54, 95 per cent c.i. 1.05 to 2.24; P = 0.027), total minimally invasive oesophagectomies (OR 1.63, 95 per cent c.i. 1.27 to 2.08; P &lt; 0.001), and chest anastomosis above azygous (OR 2.17, 95 per cent c.i. 1.58 to 2.98; P &lt; 0.001) were independently associated with a significantly increased likelihood of textbook outcome.

Conclusion

Textbook outcome is achieved in less than 40 per cent of patients having oesophagectomy for cancer. Improvements in centralization, hospital resources, access to minimal access surgery, and adoption of newer techniques for improving lymph node yield could improve textbook outcome.

Textbook outcome following oesophagectomy for cancer: international cohort study

BACKGROUND

Textbook outcome has been proposed as a tool for the assessment of oncological surgical care. However, an international assessment in patients undergoing oesophagectomy for oesophageal cancer has not been reported. This study aimed to assess textbook outcome in an international setting.

METHODS

Patients undergoing curative resection for oesophageal cancer were identified from the international Oesophagogastric Anastomosis Audit (OGAA) from April 2018 to December 2018. Textbook outcome was defined as the percentage of patients who underwent a complete tumour resection with at least 15 lymph nodes in the resected specimen and an uneventful postoperative course, without hospital readmission. A multivariable binary logistic regression model was used to identify factors independently associated with textbook outcome, and results are presented as odds ratio (OR) and 95 per cent confidence intervals (95 per cent c.i.).

RESULTS

Of 2159 patients with oesophageal cancer, 39.7 per cent achieved a textbook outcome. The outcome parameter 'no major postoperative complication' had the greatest negative impact on a textbook outcome for patients with oesophageal cancer, compared to other textbook outcome parameters. Multivariable analysis identified male gender and increasing Charlson comorbidity index with a significantly lower likelihood of textbook outcome. Presence of 24-hour on-call rota for oesophageal surgeons (OR 2.05, 95 per cent c.i. 1.30 to 3.22; P = 0.002) and radiology (OR 1.54, 95 per cent c.i. 1.05 to 2.24; P = 0.027), total minimally invasive oesophagectomies (OR 1.63, 95 per cent c.i. 1.27 to 2.08; P < 0.001), and chest anastomosis above azygous (OR 2.17, 95 per cent c.i. 1.58 to 2.98; P < 0.001) were independently associated with a significantly increased likelihood of textbook outcome.

CONCLUSION

Textbook outcome is achieved in less than 40 per cent of patients having oesophagectomy for cancer. Improvements in centralization, hospital resources, access to minimal access surgery, and adoption of newer techniques for improving lymph node yield could improve textbook outcome.

Author's Reply to "MoNuSAC2020: A Multi-Organ Nuclei Segmentation and Classification Challenge"

We had released MoNuSAC2020 as one of the largest publicly available, manually annotated, curated, multi-class, and multi-instance medical image segmentation datasets. Based on this dataset, we had organized a challenge at the International Symposium on Biomedical Imaging (ISBI) 2020. Along with the challenge participants, we had published an article summarizing the results and findings of the challenge (Verma et al., 2021). Foucart et al. (2022) in their "Analysis of the MoNuSAC 2020 challenge evaluation and results: metric implementation errors" have pointed ways in which the computation of the segmentation performance metric for the challenge can be corrected or improved. After a careful examination of their analysis, we have found a small bug in our code and an erroneous column-header swap in one of our result tables. Here, we present our response to their analysis, and issue an errata. After fixing the bug the challenge rankings remain largely unaffected. On the other hand, two of Foucart et al.'s other suggestions are good for future consideration, but it is not clear that those should be immediately implemented. We thank Foucart et al. for their detailed analysis to help us fix the two errors.

Thrombocytopenia as a Prognostic Marker in Patients with Acute Encephalitis at a Tertiary Care Centre in Northern India

Encephalitis is challenging to manage given the diversity of clinical and epidemiologic features. Various predictors of outcome have been studied so far including thrombocytopenia, cerebral edema, hypoglycaemia, development of status epilepticus and need for endotracheal intubation. Thrombocytopenia represents one of the potentially modifiable risk factors for poor prognosis in encephalitis. A better understanding of the epidemiology of this devastating disease and identification of predictors of outcome and management of reversible factors will pave the way for better management of the disease.

MATERIAL

A total of 98 Hospitalised patients of Acute Encephalitis were enrolled in the study. Diagnoses were confirmed by CSF and Neuroimaging studies. Platelet count &lt;150,000/cumm was considered as thrombocytopenia. Mild, moderate and severe thrombocytopenia was categorized at platelet count 100,000-150,000, 50,000-100,000 and &lt;50,000/ cumm, respectively. Outcome at discharge was assessed using the Modified Ranking Score, categorized into 3 groups - good (0-2), fair (3-4), and poor (5-6). Chi-square, ANOVA and Independent samples 't'-tests were used to compare the data.

OBSERVATION

Mean age of patients was 34.06±18.76 (range 14-85) years. Majority of patients were males (54.1). Mean GCS at admission was 9.41±1.90. Acute viral encephalitis(unclassified) (n=33; 33.7%), Scrub typhus (n=24; 24.5%) and Japanese encephalitis virus (n=12; 12.2%) were the most common underlying etiologies. A total of 74 (75.5%) patients had thrombocytopenia. Mild, moderate and severe thrombocytopenia was seen in 34 (34.7%), 30 (30.6%) and 10 (10.2%) cases. Thrombocytopenia was significantly higher in Dengue and Scrub as compared to other etiologies. Thrombocytopenia and its severity showed a significant association with lower GCS and higher mRS scores indicating a poor outcome.

CONCLUSION

Thrombocytopenia is associated with a poor clinical status and adverse outcomes in patients with encephalitis of all causes.

Computer extracted features of nuclear morphology in hematoxylin and eosin images distinguish Stage II and IV colon tumors

We assessed the utility of quantitative features of colon cancer nuclei, extracted from digitized hematoxylin and eosin-stained whole slide images (WSIs), to distinguish between Stage II from Stage IV colon cancers. Our discovery cohort comprised 100 Stage II and Stage IV colon cancer cases sourced from the University Hospitals Cleveland Medical Center (UHCMC). We performed initial (independent) model validation on 51 (143) Stage II and 79 (54) Stage IV colon cancer cases from UHCMC (The Cancer Genome Atlas's Colon Adenocarcinoma, TCGA-COAD, cohort). Our approach comprised the following steps, (1) a fully convolutional deep neural network with VGG-18 architecture was trained to locate cancer on WSIs, (2) another deep-learning model based on Mask-RCNN with Resnet-50 architecture was used to segment all nuclei from within the identified cancer region, (3) a total of 26,641 quantitative morphometric features pertaining to nuclear shape, size, and texture were extracted from within and outside tumor nuclei, (4) a random forest classifier was trained to distinguish between Stage II and Stage IV colon cancers using the 5 most discriminatory features selected by the Wilcoxon rank-sum test. Our trained classifier using these top 5 features yielded an AUC of 0.81 and 0.78, respectively, on the held-out cases in UHCMC and TCGA validation sets. For 197 TCGA-COAD cases, the Cox-proportional hazards model yielded a hazard ratio of 2.20 (95% CI: 1.24-3.88) with a concordance index of 0.71 using only top-five features for risk stratification of overall survival. The Kaplan-Meier estimate also showed statistically significant separation between the low-risk and high-risk patients with a log-rank p-value of 0.0097. Finally, unsupervised clustering of the top-five features revealed that Stage IV colon cancers with peritoneal spread were morphologically more similar to Stage II colon cancers with no long-term metastases than Stage IV colon cancers with hematogenous spread. This article is protected by copyright. All rights reserved.

Novel MRI deformation-heterogeneity radiomic features are associated with molecular subgroups and overall survival in pediatric medulloblastoma: Preliminary findings from a multi-institutional study

Introduction

Medulloblastoma (MB) is a malignant, heterogenous brain tumor. Advances in molecular profiling have led to identifying four molecular subgroups of MB (WNT, SHH, Group 3, Group 4), each with distinct clinical behaviors. We hypothesize that (1) aggressive MB tumors, growing heterogeneously, induce pronounced local structural deformations in the surrounding parenchyma, and (b) these local deformations as captured on Gadolinium (Gd)-enhanced-T1w MRI are independently associated with molecular subgroups, as well as overall survival in MB patients.

Methods

In this work, a total of 88 MB studies from 2 institutions were analyzed. Following tumor delineation, Gd-T_1w scan for every patient was registered to a normal age-specific T_1w-MRI template via deformable registration. Following patient-atlas registration, local structural deformations in the brain parenchyma were obtained for every patient by computing statistics from deformation magnitudes obtained from every 5mm annular region, 0 < d < 60 mm, where d is the distance from the tumor infiltrating edge.

Results

Multi-class comparison via ANOVA yielded significant differences between deformation magnitudes obtained for Group 3, Group 4, and SHH molecular subgroups, observed up to 60-mm outside the tumor edge. Additionally, Kaplan-Meier survival analysis showed that the local deformation statistics, combined with the current clinical risk-stratification approaches (molecular subgroup information and Chang's classification), could identify significant differences between high-risk and low-risk survival groups, achieving better performance results than using any of these approaches individually.

Discussion

These preliminary findings suggest there exists significant association of our tumor-induced deformation descriptor with overall survival in MB, and that there could be an added value in using the proposed radiomic descriptor along with the current risk classification approaches, towards more reliable risk assessment in pediatric MB.

MoNuSAC2020: A Multi-Organ Nuclei Segmentation and Classification Challenge

Detecting various types of cells in and around the tumor matrix holds a special significance in characterizing the tumor micro-environment for cancer prognostication and research. Automating the tasks of detecting, segmenting, and classifying nuclei can free up the pathologists' time for higher value tasks and reduce errors due to fatigue and subjectivity. To encourage the computer vision research community to develop and test algorithms for these tasks, we prepared a large and diverse dataset of nucleus boundary annotations and class labels. The dataset has over 46,000 nuclei from 37 hospitals, 71 patients, four organs, and four nucleus types. We also organized a challenge around this dataset as a satellite event at the International Symposium on Biomedical Imaging (ISBI) in April 2020. The challenge saw a wide participation from across the world, and the top methods were able to match inter-human concordance for the challenge metric. In this paper, we summarize the dataset and the key findings of the challenge, including the commonalities and differences between the methods developed by various participants. We have released the MoNuSAC2020 dataset to the public.

NIMG-60. PREDICTING OVERALL SURVIVAL IN GLIOBLASTOMA USING HISTOPATHOLOGY VIA AN END-TO-END DEEP LEARNING PIPELINE: A LARGE MULTI-COHORT STUDY

PURPOSE

Glioblastoma is an aggressive and universally fatal tumor. Morphological information as captured from cellular regions on surgically resected histopathology slides has the ability to reveal the inherent heterogeneity in Glioblastoma and thus has prognostic implications. In this work, we hypothesized that capturing morphological attributes from high cellularity regions on Hematoxylin and Eosin (H&E)-stained digitized tissue slides using an end-to-end deep-learning pipeline will enable risk-stratification of GBM tumors based on overall survival.

METHODS

A large multi-cohort study consisting of N=514 H&E-stained digitized tissue slides along with overall-survival data (OS) was obtained from the Ivy Glioblastoma atlas project (Ivy-GAP (N=41)), TCGA (N=379), and CPTAC (N=94). Our deep-learning pipeline consisted of two stages. First stage involved segmenting cellular tumor (CT) from necrotic-regions and background using Resnet-18 model, while the second stage involved predicting OS, using only the segmented CT regions identified in the first stage. For the segmentation stage, we leveraged the Ivy-GAP cohort, where CT annotations confirmed by expert neuropathologists were available, to serve as the training set. Using this training model, the CT regions on the remaining cohort (TCGA, CPTAC) (i.e. test set) were identified. For the survival-prediction stage, the last layer of ResNet18 model was replaced with a cox layer (ResNet-Cox), and further fine-tuned using OS and censor information. Independent validation of ResNet-Cox was performed on two hold-out sites from TCGA and one from CPTAC.

RESULTS

Our segmentation model achieved an accuracy of 0.89 in reliably identifying CT regions on the validation data. The segmented CT regions on the test cohort were further confirmed by two experts. Our ResNet-Cox model achieved a concordance-index of 0.73 on MD Anderson Cancer Center (N=60), 0.71 on Henry Ford Hospital (N=96), and 0.68 on CPTAC data (N=41).

CONCLUSION

Deep-learning features captured from cellular tumor of H&E-stained histopathology images may predict survival in Glioblastoma.

NIMG-54. RADIOMIC FEATURES FROM LESION HABITAT PREDICT RESPONSE TO COMBINATION OF NIVOLUMAB AND BEVACIZUMAB IN PATIENTS WITH RECURRENT GLIOBLASTOMA: A FEASIBILITY STUDY

PURPOSE

The use of immunotherapy in glioblastoma management is under active investigation. Glioblastomas are “cold” tumors, meaning that they have inactivated or fewer tumor infiltrative lymphocytes in addition to substantial tumor necrosis, attributing to their poor response to immunotherapy. A significant challenge is the apriori identification of Glioblastoma patients who will respond favorably to immunotherapy. In this work, we evaluated the ability of computerized MRI-based quantitative features (radiomics) extracted from the lesion habitat (including enhancing lesion, necrosis, and peritumoral hyperintensities) to predict response and progression-free survival (PFS) in recurrent GBM patients treated with combination of Nivolumab and Bevacizumab.

METHODS

Immunotherapy response assessment in neuro-oncology (iRANO) criteria along with PFS were used to analyze n=50 patients enrolled in a randomized clinical trial where patients received Nivolumab with either standard or low dose Bevacizumab. These patients were assessed to see if they had complete response, partial response, stable disease (i.e. responders, n=31), or disease progression (i.e. non-responders, n=19). Lesion habitat constituting necrotic core, enhancing tumor, and edema were delineated by expert radiologist on Gd-T1w, T2w and FLAIR MRI scans. COLIAGE radiomic features from each of the delineated regions were selected using minimum redundancy maximum relevance (mRMR) via cross-validation, to segregate non-responder patients from responders. A multivariable cox proportional hazard model was used to predict survival (PFS).

RESULTS

CoLlAGe correlation, sum average, and sum variance features (capture local heterogeneity) from the lesion habitat, were found to segregate non-responder patients from responders with an accuracy of 86%, followed by 80% using features from peritumoral hyperintensities and 78% from enhancing tumor. In our survival analysis, C-index of 0.688 was obtained using features from the entire lesion habitat, followed by peritumoral hyperintensities (0.675) and enhancing tumor (0.656).

CONCLUSION

Radiomic features from the lesion habitat may predict response to combination of Nivolumab and Bevacizumab in recurrent Glioblastomas.

Postoperative outcomes in oesophagectomy with trainee involvement

BACKGROUND

The complexity of oesophageal surgery and the significant risk of morbidity necessitates that oesophagectomy is predominantly performed by a consultant surgeon, or a senior trainee under their supervision. The aim of this study was to determine the impact of trainee involvement in oesophagectomy on postoperative outcomes in an international multicentre setting.

METHODS

Data from the multicentre Oesophago-Gastric Anastomosis Study Group (OGAA) cohort study were analysed, which comprised prospectively collected data from patients undergoing oesophagectomy for oesophageal cancer between April 2018 and December 2018. Procedures were grouped by the level of trainee involvement, and univariable and multivariable analyses were performed to compare patient outcomes across groups.

RESULTS

Of 2232 oesophagectomies from 137 centres in 41 countries, trainees were involved in 29.1 per cent of them (n = 650), performing only the abdominal phase in 230, only the chest and/or neck phases in 130, and all phases in 315 procedures. For procedures with a chest anastomosis, those with trainee involvement had similar 90-day mortality, complication and reoperation rates to consultant-performed oesophagectomies (P = 0.451, P = 0.318, and P = 0.382, respectively), while anastomotic leak rates were significantly lower in the trainee groups (P = 0.030). Procedures with a neck anastomosis had equivalent complication, anastomotic leak, and reoperation rates (P = 0.150, P = 0.430, and P = 0.632, respectively) in trainee-involved versus consultant-performed oesophagectomies, with significantly lower 90-day mortality in the trainee groups (P = 0.005).

CONCLUSION

Trainee involvement was not found to be associated with significantly inferior postoperative outcomes for selected patients undergoing oesophagectomy. The results support continued supervised trainee involvement in oesophageal cancer surgery.

NEIM-01. PREDICTION OF RESPONSE TO COMBINATION OF NIVOLUMAB AND BEVACIZUMAB IN PATIENTS WITH RECURRENT GLIOBLASTOMA VIA RADIOMIC ANALYSIS ON CLINICAL MRI SCANS

PURPOSE

The use of immunotherapy in glioblastoma management is under active investigation. Glioblastomas are “cold” tumors, meaning that they have inactivated or fewer tumor infiltrative lymphocytes in addition to substantial tumor necrosis, attributing to their poor response to immunotherapy. A significant challenge is the apriori identification of Glioblastoma patients who will respond favorably to immunotherapy. In this work, we evaluated the ability of computerized MRI-based quantitative features (radiomics) extracted from the lesion habitat (including enhancing lesion, necrosis, and peritumoral hyperintensities) to predict response and progression-free survival (PFS) in recurrent GBM patients treated with combination of Nivolumab and Bevacizumab.

METHODS

Immunotherapy response assessment in neuro-oncology (iRANO) criteria along with PFS were used to analyze n=50 patients enrolled in a randomized clinical trial where patients received Nivolumab with either standard or low dose Bevacizumab. These patients were assessed to see if they had complete response, partial response, stable disease (i.e. responders, n=31), or disease progression (i.e. non-responders, n=19). Lesion habitat constituting necrotic core, enhancing tumor, and edema were delineated by expert radiologist on Gd-T1w, T2w and FLAIR MRI scans. COLIAGE radiomic features from each of the delineated regions were selected using minimum redundancy maximum relevance (mRMR) via cross-validation, to segregate non-responder patients from responders. A multivariable cox proportional hazard model was used to predict survival (PFS).

RESULTS

CoLlAGe correlation, sum average, and sum variance features (capture local heterogeneity) from the lesion habitat, were found to segregate non-responder patients from responders with an accuracy of 86%, followed by 80% using features from peritumoral hyperintensities and 78% from enhancing tumor. In our survival analysis, C-index of 0.688 was obtained using features from the entire lesion habitat, followed by peritumoral hyperintensities (0.675) and enhancing tumor (0.656).

CONCLUSION

Radiomic features from the lesion habitat may predict response to combination of Nivolumab and Bevacizumab in recurrent Glioblastomas.

Paving the way for application of next generation risk assessment to safety decision-making for cosmetic ingredients

Next generation risk assessment (NGRA) is an exposure-led, hypothesis-driven approach that has the potential to support animal-free safety decision-making. However, significant effort is needed to develop and test the in vitro and in silico (computational) approaches that underpin NGRA to enable confident application in a regulatory context. A workshop was held in Montreal in 2019 to discuss where effort needs to be focussed and to agree on the steps needed to ensure safety decisions made on cosmetic ingredients are robust and protective. Workshop participants explored whether NGRA for cosmetic ingredients can be protective of human health, and reviewed examples of NGRA for cosmetic ingredients. From the limited examples available, it is clear that NGRA is still in its infancy, and further case studies are needed to determine whether safety decisions are sufficiently protective and not overly conservative. Seven areas were identified to help progress application of NGRA, including further investments in case studies that elaborate on scenarios frequently encountered by industry and regulators, including those where a ‘high risk’ conclusion would be expected. These will provide confidence that the tools and approaches can reliably discern differing levels of risk. Furthermore, frameworks to guide performance and reporting should be developed.

Abstract 3: Deep learning-based integration of esophageal cancer morphology with genomics

Esophageal cancer is a major cause of cancer mortality world-wide. Even with advanced treatment options available, patients with esophageal cancer have a poor 5-year survival rate of 16%. Genomic studies of esophageal cancer have revealed frequently mutated genes involved in different oncogenic pathways. In this study, we attempted to predict genomic alterations, pathological and clinical features directly from H&E-stained whole slide images (WSIs) of individual esophageal cancer cases by utilizing modern deep learning methods. We used WSIs with esophageal cancer obtained from TCGA and annotated cancerous epithelial and stromal components separately for esophageal adenocarcinoma (EAC) and squamous cell carcinoma (ESCC) (n= 25 cases for each) to create a training set. Subsequently, patches of size 256×256 pixels were extracted, and a U-Net convolutional neural network (CNN) was trained for semantic segmentation of tumor epithelium and stromal pixels. Tumor epithelium regions identified by the first U-Net CNN were fed into a Squeezenet model to learn to distinguish between EAC and ESCC in the training phase. Finally, for each subtype (EAC and ESCC), separate Densenet models were trained to predict gene mutation status. We also trained independent Densenet models to predict tumor stage, grade, and survival outcome from the tumor epithelial patches. After training, we tested these models on an independent validation set obtained from TCGA (n = 99) and UCSF (n = 25) patients, ensuring patient level separation between the training and the validation sets. We obtained an average AUC of 0.90 and 0.87 for epithelium vs. stromal and EAC vs. ESCC classification, respectively, on the validation datasets. These models enabled us to predict tumor stage, grade, and survival outcome with an accuracy of &gt; 0.9. TP53 gene alterations were detected in over 50% of esophageal cancer cases, and our model was able to predict TP53 gene mutation status on WSIs with an AUC of 0.91. Overall, this study demonstrates how deep learning algorithms can aid in better understanding and predicting key biological and clinical features of aggressive malignancies at both population and individual patient level. This integration of artificial intelligence with molecular and histopathologic features could also help to accelerate precision cancer diagnosis and treatment in the clinical setting.

Citation Format: Ruchika Verma, Wei Wu, Neeraj Kumar, Elizabeth Yu, Won-Tak Choi, Sarah Umetsu, Trever Bivona. Deep learning-based integration of esophageal cancer morphology with genomics [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 3.

Mortality from esophagectomy for esophageal cancer across low, middle, and high-income countries: An international cohort study

BACKGROUND

No evidence currently exists characterising global outcomes following major cancer surgery, including esophageal cancer. Therefore, this study aimed to characterise impact of high income countries (HIC) versus low and middle income countries (LMIC) on the outcomes following esophagectomy for esophageal cancer.

METHOD

This international multi-center prospective study across 137 hospitals in 41 countries included patients who underwent an esophagectomy for esophageal cancer, with 90-day follow-up. The main explanatory variable was country income, defined according to the World Bank Data classification. The primary outcome was 90-day postoperative mortality, and secondary outcomes were composite leaks (anastomotic leak or conduit necrosis) and major complications (Clavien-Dindo Grade III - V). Multivariable generalized estimating equation models were used to produce adjusted odds ratios (ORs) and 95% confidence intervals (CI95%).

RESULTS

Between April 2018 to December 2018, 2247 patients were included. Patients from HIC were more significantly older, with higher ASA grade, and more advanced tumors. Patients from LMIC had almost three-fold increase in 90-day mortality, compared to HIC (9.4% vs 3.7%, p < 0.001). On adjusted analysis, LMIC were independently associated with higher 90-day mortality (OR: 2.31, CI95%: 1.17-4.55, p = 0.015). However, LMIC were not independently associated with higher rates of anastomotic leaks (OR: 1.06, CI95%: 0.57-1.99, p = 0.9) or major complications (OR: 0.85, CI95%: 0.54-1.32, p = 0.5), compared to HIC.

CONCLUSION

Resections in LMIC were independently associated with higher 90-day postoperative mortality, likely reflecting a failure to rescue of these patients following esophagectomy, despite similar composite anastomotic leaks and major complication rates to HIC. These findings warrant further research, to identify potential issues and solutions to improve global outcomes following esophagectomy for cancer.

Comparison of short-term outcomes from the International Oesophago-Gastric Anastomosis Audit (OGAA), the Esophagectomy Complications Consensus Group (ECCG), and the Dutch Upper Gastrointestinal Cancer Audit (DUCA)

BACKGROUND

The Esophagectomy Complications Consensus Group (ECCG) and the Dutch Upper Gastrointestinal Cancer Audit (DUCA) have set standards in reporting outcomes after oesophagectomy. Reporting outcomes from selected high-volume centres or centralized national cancer programmes may not, however, be reflective of the true global prevalence of complications. This study aimed to compare complication rates after oesophagectomy from these existing sources with those of an unselected international cohort from the Oesophago-Gastric Anastomosis Audit (OGAA).

METHODS

The OGAA was a prospective multicentre cohort study coordinated by the West Midlands Research Collaborative, and included patients undergoing oesophagectomy for oesophageal cancer between April and December 2018, with 90 days of follow-up.

RESULTS

The OGAA study included 2247 oesophagectomies across 137 hospitals in 41 countries. Comparisons with the ECCG and DUCA found differences in baseline demographics between the three cohorts, including age, ASA grade, and rates of chronic pulmonary disease. The OGAA had the lowest rates of neoadjuvant treatment (OGAA 75.1 per cent, ECCG 78.9 per cent, DUCA 93.5 per cent; P < 0.001). DUCA exhibited the highest rates of minimally invasive surgery (OGAA 57.2 per cent, ECCG 47.9 per cent, DUCA 85.8 per cent; P < 0.001). Overall complication rates were similar in the three cohorts (OGAA 63.6 per cent, ECCG 59.0 per cent, DUCA 62.2 per cent), with no statistically significant difference in Clavien-Dindo grades (P = 0.752). However, a significant difference in 30-day mortality was observed, with DUCA reporting the lowest rate (OGAA 3.2 per cent, ECCG 2.4 per cent, DUCA 1.7 per cent; P = 0.013).

CONCLUSION

Despite differences in rates of co-morbidities, oncological treatment strategies, and access to minimal-access surgery, overall complication rates were similar in the three cohorts.

Laparoscopic Surgeries in Urology: Initial Burgeoning Experience at National Transplant Centre, Nepal

Background This study focuses on experience of laparoscopic surgery at Shahid Dharma Bhakta National Transplant Centre (SDNTC), Nepal; which could enable us to gain knowledge regarding its benefits over conventional surgery. The present study revealed the frequency of various forms of laparoscopic surgeries done at our centre. Moreover, this study accomplishes laparoscopic donor nephrectomy "a historical milestone achieved in Nepal for kidney transplantation on 18th November 2018" which was the first Laparoscopic donor nephrectomy done in Nepal by Nepalese team. Objective The present study assesses the feasibility and safety of laparoscopic surgery at government hospital of Nepal. Method This hospital based cross-sectional study included all patients of age group 10 to 60 years, coming to outpatient department of SDNTC and those having indications for nephrectomy. We excluded patient having previous history of open surgeries of kidney, bleeding disorders, uncontrolled Diabetes Mellitus and uncontrolled Hypertension. The study duration was 15 months from November 2017 to January 2019. The total number of patients enrolled in the study was fifty where transperitoneal laparoscopic surgery was performed in all 50 patients. The demographic data, indications for surgery, duration of surgery, complications of surgery and perioperative outcomes were analyzed. Result Out of 50 cases, 34 (68%) underwent simple lap nephrectomy, 6 (12%) were lap pyeloplasty, 6 (12%) lap nephrectomy along with ureterectomy of long segment of diseased ureter, 1 (2%) lap radical nephrectomy, 1 (2%) lap donor nephrectomy for kidney transplantation, 1 (2%) lap heminephrectomy and 1 (2%) lap nephrectomy for hydronephrotic non functioning left crossed ectopia. Amongst all nephrectomies, 27 (54%) patients were operated on right side while 23 (46%) patients on left. The median age of the patient was 38.56 years. Out of total cases 32 (64%) were male and 18 (36%) female. The median operative time and hospital stay was 122.3 minutes and 5 days respectively. The median estimated blood loss was 74.1 cc. Only one patient required blood transfusion intra-operatively. 2 (4%) patients were converted to open surgery. Conclusion Laparoscopic surgery is feasible and safe procedure in government setup hospital with less cumbersome procedure and minimum complications associated with it.

Reproducibility analysis of multi-institutional paired expert annotations and radiomic features of the Ivy Glioblastoma Atlas Project (Ivy GAP) dataset

PURPOSE

The availability of radiographic magnetic resonance imaging (MRI) scans for the Ivy Glioblastoma Atlas Project (Ivy GAP) has opened up opportunities for development of radiomic markers for prognostic/predictive applications in glioblastoma (GBM). In this work, we address two critical challenges with regard to developing robust radiomic approaches: (a) the lack of availability of reliable segmentation labels for glioblastoma tumor sub-compartments (i.e., enhancing tumor, non-enhancing tumor core, peritumoral edematous/infiltrated tissue) and (b) identifying "reproducible" radiomic features that are robust to segmentation variability across readers/sites.

ACQUISITION AND VALIDATION METHODS

From TCIA's Ivy GAP cohort, we obtained a paired set (n = 31) of expert annotations approved by two board-certified neuroradiologists at the Hospital of the University of Pennsylvania (UPenn) and at Case Western Reserve University (CWRU). For these studies, we performed a reproducibility study that assessed the variability in (a) segmentation labels and (b) radiomic features, between these paired annotations. The radiomic variability was assessed on a comprehensive panel of 11 700 radiomic features including intensity, volumetric, morphologic, histogram-based, and textural parameters, extracted for each of the paired sets of annotations. Our results demonstrated (a) a high level of inter-rater agreement (median value of DICE ≥0.8 for all sub-compartments), and (b) ≈24% of the extracted radiomic features being highly correlated (based on Spearman's rank correlation coefficient) to annotation variations. These robust features largely belonged to morphology (describing shape characteristics), intensity (capturing intensity profile statistics), and COLLAGE (capturing heterogeneity in gradient orientations) feature families.

DATA FORMAT AND USAGE NOTES

We make publicly available on TCIA's Analysis Results Directory (https://doi.org/10.7937/9j41-7d44), the complete set of (a) multi-institutional expert annotations for the tumor sub-compartments, (b) 11 700 radiomic features, and (c) the associated reproducibility meta-analysis.

POTENTIAL APPLICATIONS

The annotations and the associated meta-data for Ivy GAP are released with the purpose of enabling researchers toward developing image-based biomarkers for prognostic/predictive applications in GBM.

Technical Note: MRQy - An open-source tool for quality control of MR imaging data

PURPOSE

There is an increasing availability of large imaging cohorts [such as through The Cancer Imaging Archive (TCIA)] for computational model development and imaging research. To ensure development of generalizable computerized models, there is a need to quickly determine relative quality differences in these cohorts, especially when considering MRI datasets which can exhibit wide variations in image appearance. The purpose of this study is to present a quantitative quality control tool, MRQy, to help interrogate MR imaging datasets for: (a) site- or scanner-specific variations in image resolution or image contrast, and (b) imaging artifacts such as noise or inhomogeneity; which need correction prior to model development.

METHODS

Unlike existing imaging quality control tools, MRQy has been generalized to work with images from any body region to efficiently extract a series of quality measures (e.g., noise ratios, variation metrics) and MR image metadata (e.g., voxel resolution and image dimensions). MRQy also offers a specialized HTML5-based front-end designed for real-time filtering and trend visualization of quality measures.

RESULTS

MRQy was used to evaluate (a) n = 133 brain MRIs from TCIA (7 sites) and (b) n = 104 rectal MRIs (3 local sites). MRQy measures revealed significant site-specific variations in both cohorts, indicating potential batch effects. Before processing, MRQy measures could be used to identify each of the seven sites within the TCIA cohort with 87.5%, 86.4%, 90%, 93%, 90%, 60%, and 92.9% accuracy and the three sites within the rectal cohort with 91%, 82.8%, and 88.9% accuracy using unsupervised clustering. After processing, none of the sites could be distinctively clustered via MRQy measures in either cohort; suggesting that batch effects had been largely accounted for. Marked differences in specific MRQy measures were also able to identify outlier MRI datasets that needed to be corrected for common acquisition artifacts.

CONCLUSIONS

MRQy is designed to be a standalone, unsupervised tool that can be efficiently run on a standard desktop computer. It has been made freely accessible and open-source at http://github.com/ccipd/MRQy for community use and feedback.

Tumor Habitat-derived Radiomic Features at Pretreatment MRI That Are Prognostic for Progression-free Survival in Glioblastoma Are Associated with Key Morphologic Attributes at Histopathologic Examination: A Feasibility Study

Purpose

To identify radiomic features extracted from the tumor habitat on routine MR images that are prognostic for progression-free survival (PFS) and to assess their morphologic basis with corresponding histopathologic attributes in glioblastoma (GBM).

Materials and Methods

In this retrospective study, 156 pretreatment GBM MR images (gadolinium-enhanced T1-weighted, T2-weighted, and fluid-attenuated inversion recovery [FLAIR] images) were curated. Of these 156 images, 122 were used for training (90 from The Cancer Imaging Archive and 32 from the Cleveland Clinic, acquired between December 1, 2011, and May 1, 2018) and 34 were used for validation. The validation set was obtained from the Ivy Glioblastoma Atlas Project database, for which the percentage extent of 11 histologic attributes was available on corresponding histopathologic specimens of the resected tumor. Following expert annotations of the tumor habitat (necrotic core, enhancing tumor, and FLAIR-hyperintense subcompartments), 1008 radiomic descriptors (eg, Haralick texture features, Laws energy features, co-occurrence of local anisotropic gradient orientations [CoLIAGe]) were extracted from the three MRI sequences. The top radiomic features were obtained from each subcompartment in the training set on the basis of their ability to risk-stratify patients according to PFS. These features were then concatenated to create a radiomics risk score (RRS). The RRS was independently validated on a holdout set. In addition, correlations (P < .05) of RRS features were computed, with the percentage extent of the 11 histopathologic attributes, using Spearman correlation analysis.

Results

RRS yielded a concordance index of 0.80 on the validation set and constituted radiomic features, including Laws (capture edges, waves, ripple patterns) and CoLIAGe (capture disease heterogeneity) from enhancing tumor and FLAIR hyperintensity. These radiomic features were correlated with histopathologic attributes associated with disease aggressiveness in GBM, particularly tumor infiltration (P = .0044) and hyperplastic blood vessels (P = .0005).

Conclusion

Preliminary findings demonstrated significant associations of prognostic radiomic features with disease-specific histologic attributes, with implications for risk-stratifying patients with GBM for personalized treatment decisions. Supplemental material is available for this article. © RSNA, 2020.

High electromagnetic interference shielding of poly(ether-sulfone)/multi-walled carbon nanotube nanocomposites fabricated by an eco-friendly route

High-performance polymer matrix nanocomposites based on poly(ether-sulfone) (PES) matrix reinforced with multi-walled carbon nanotubes (MWCNTs) were fabricated using planetary ball mill followed by hot pressing. Their electrical properties and the electromagnetic interference shielding effectiveness (EMI-SE) were investigated and discussed. A percolation threshold of about 0.65 vol% MWCNT was obtained. The electrical conductivity was increased by more than ten orders of magnitude at the percolation threshold and to approximately 0.01 S cm^-1 at 6.67 vol% (or 10 wt%) MWCNT. This is a significant improvement. The highest EMI-SE of about 29-30 dB (both in the X-band and K_u-band) was obtained for the 6.67 vol% MWCNT filled nanocomposites with a thickness of 0.9 mm. The specific EMI-SE of these nanocomposites were found to be higher than the literature values. The thermal stability and the char yield (measured at 900 °C) of the nanocomposites were found to be more than 470 °C and 40.6%, respectively.

A Multi-Organ Nucleus Segmentation Challenge

Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net, FCN, and Mask-RCNN were popularly used, typically based on ResNet or VGG base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

Radiogenomic-Based Survival Risk Stratification of Tumor Habitat on Gd-T1w MRI Is Associated with Biological Processes in Glioblastoma

PURPOSE

To (i) create a survival risk score using radiomic features from the tumor habitat on routine MRI to predict progression-free survival (PFS) in glioblastoma and (ii) obtain a biological basis for these prognostic radiomic features, by studying their radiogenomic associations with molecular signaling pathways.

EXPERIMENTAL DESIGN

Two hundred three patients with pretreatment Gd-T1w, T2w, T2w-FLAIR MRI were obtained from 3 cohorts: The Cancer Imaging Archive (TCIA; n = 130), Ivy GAP (n = 32), and Cleveland Clinic (n = 41). Gene-expression profiles of corresponding patients were obtained for TCIA cohort. For every study, following expert segmentation of tumor subcompartments (necrotic core, enhancing tumor, peritumoral edema), 936 3D radiomic features were extracted from each subcompartment across all MRI protocols. Using Cox regression model, radiomic risk score (RRS) was developed for every protocol to predict PFS on the training cohort (n = 130) and evaluated on the holdout cohort (n = 73). Further, Gene Ontology and single-sample gene set enrichment analysis were used to identify specific molecular signaling pathway networks associated with RRS features.

RESULTS

Twenty-five radiomic features from the tumor habitat yielded the RRS. A combination of RRS with clinical (age and gender) and molecular features (MGMT and IDH status) resulted in a concordance index of 0.81 (P < 0.0001) on training and 0.84 (P = 0.03) on the test set. Radiogenomic analysis revealed associations of RRS features with signaling pathways for cell differentiation, cell adhesion, and angiogenesis, which contribute to chemoresistance in GBM.

CONCLUSIONS

Our findings suggest that prognostic radiomic features from routine Gd-T1w MRI may also be significantly associated with key biological processes that affect response to chemotherapy in GBM.