Evaluation of mediastinal lymph node segmentation of heterogeneous CT data with full and weak supervision

Accurate lymph node size estimation is critical for staging cancer patients, initial therapeutic management, and assessing response to therapy. Current standard practice for quantifying lymph node size is based on a variety of criteria that use uni-directional or bi-directional measurements. Segmentation in 3D can provide more accurate evaluations of the lymph node size. Fully convolutional neural networks (FCNs) have achieved state-of-the-art results in segmentation for numerous medical imaging applications, including lymph node segmentation. Adoption of deep learning segmentation models in clinical trials often faces numerous challenges. These include lack of pixel-level ground truth annotations for training, generalizability of the models on unseen test domains due to the heterogeneity of test cases and variation of imaging parameters. In this paper, we studied and evaluated the performance of lymph node segmentation models on a dataset that was completely independent of the one used to create the models. We analyzed the generalizability of the models in the face of a heterogeneous dataset and assessed the potential effects of different disease conditions and imaging parameters. Furthermore, we systematically compared fully-supervised and weakly-supervised methods in this context. We evaluated the proposed methods using an independent dataset comprising 806 mediastinal lymph nodes from 540 unique patients. The results show that performance achieved on the independent test set is comparable to that on the training set. Furthermore, neither the underlying disease nor the heterogeneous imaging parameters impacted the performance of the models. Finally, the results indicate that our weakly-supervised method attains 90%- 91% of the performance achieved by the fully supervised training.

Automated detection, delineation and quantification of whole-body bone metastasis using FDG-PET/CT images

Non-small cell lung cancer (NSCLC) patients with the metastatic spread of disease to the bone have high morbidity and mortality. Stereotactic ablative body radiotherapy increases the progression free survival and overall survival of these patients with oligometastases. FDG-PET/CT, a functional imaging technique combining positron emission tomography (PET) with 18 F-fluorodeoxyglucose (FDG) and computer tomography (CT) provides improved staging and identification of treatment response. It is also associated with reduction in size of the radiotherapy tumour volume delineation compared with CT based contouring in radiotherapy, thus allowing for dose escalation to the target volume with lower doses to the surrounding organs at risk. FDG-PET/CT is increasingly being used for the clinical management of NSCLC patients undergoing radiotherapy and has shown high sensitivity and specificity for the detection of bone metastases in these patients. Here, we present a software tool for detection, delineation and quantification of bone metastases using FDG-PET/CT images. The tool extracts standardised uptake values (SUV) from FDG-PET images for auto-segmentation of bone lesions and calculates volume of each lesion and associated mean and maximum SUV. The tool also allows automatic statistical validation of the auto-segmented bone lesions against the manual contours of a radiation oncologist. A retrospective review of FDG-PET/CT scans of more than 30 candidate NSCLC patients was performed and nine patients with one or more metastatic bone lesions were selected for the present study. The SUV threshold prediction model was designed by splitting the cohort of patients into a subset of 'development' and 'validation' cohorts. The development cohort yielded an optimum SUV threshold of 3.0 for automatic detection of bone metastases using FDG-PET/CT images. The validity of the derived optimum SUV threshold on the validation cohort demonstrated that auto-segmented and manually contoured bone lesions showed strong concordance for volume of bone lesion (r = 0.993) and number of detected lesions (r = 0.996). The tool has various applications in radiotherapy, including but not limited to studies determining optimum SUV threshold for accurate and standardised delineation of bone lesions and in scientific studies utilising large patient populations for instance for investigation of the number of metastatic lesions that can be treated safety with an ablative dose of radiotherapy without exceeding the normal tissue toxicity.

DINs: Deep Interactive Networks for Neurofibroma Segmentation in Neurofibromatosis Type 1 on Whole-Body MRI

Neurofibromatosis type 1 (NF1) is an autosomal dominant tumor predisposition syndrome that involves the central and peripheral nervous systems. Accurate detection and segmentation of neurofibromas are essential for assessing tumor burden and longitudinal tumor size changes. Automatic convolutional neural networks (CNNs) are sensitive and vulnerable as tumors' variable anatomical location and heterogeneous appearance on MRI. In this study, wepropose deep interactive networks (DINs) to address the above limitations. User interactions guide the model to recognize complicated tumors and quickly adapt to heterogeneous tumors. We introduce a simple but effective Exponential Distance Transform (ExpDT) that converts user interactions into guide maps regarded as the spatial and appearance prior. Comparing with popular Euclidean and geodesic distances, ExpDT is more robust to various image sizes, which reserves the distribution of interactive inputs. Furthermore, to enhance the tumor-related features, we design a deep interactive module to propagate the guides into deeper layers. We train and evaluate DINs on three MRI data sets from NF1 patients. The experiment results yield significant improvements of 44% and 14% in DSC comparing with automated and other interactive methods, respectively. We also experimentally demonstrate the efficiency of DINs in reducing user burden when comparing with conventional interactive methods.

Imaging Evaluation of Plexiform Neurofibromas in Neurofibromatosis Type 1: A Survey-Based Assessment

OBJECTIVE

To assess imaging utilization practices across clinical specialists in neurofibromatosis type 1 (NF1) for the evaluation of symptomatic and asymptomatic children and adults with or without plexiform neurofibromas (PN).

METHODS

An institutional review board-exempt survey was administered to medical practitioners caring for individuals with NF1 at the Response Evaluation in Neurofibromatosis and Schwannomatosis (REiNS) meeting in September 2019. The survey included questions on respondent demographic data (9 questions), type of imaging obtained for asymptomatic (4 questions) and symptomatic (4 questions) people with and without PN, and utilization of diffusion-weighted imaging (2 questions).

RESULTS

Thirty practitioners participated in the survey. Most were academic neuro-oncologists at high-volume (>10 patients/week) NF1 centers. Of 30 respondents, 26 had access to whole-body MRI (WB-MRI). The most common approach to an asymptomatic person without PN was no imaging (adults: 57% [17/30]; children: 50% [15/30]), followed by a screening WB-MRI (adults: 20% [6/30]; children: 26.7% [8/30]). The most common approach to a person with symptoms or known PN was regional MRI (adults: 90% [27/30]; children: 93% [28/30]), followed by WB-MRI (adults: 20% [6/30]; children: 36.7% [11/30]). WB-MRI was most often obtained to evaluate a symptomatic child with PN (37% [11/30]).

CONCLUSIONS

More than 90% of practitioners indicated they would obtain a regional MRI in a symptomatic patient without known or visible PN. Otherwise, there was little consensus on imaging practices. Given the high prevalence of PN and risk of malignant conversion in this patient population, there is a need to define imaging-based guidelines for optimal clinical care and the design of future clinical trials.

Phase II trial of carboplatin and bevacizumab in patients with breast cancer brain metastases

BACKGROUND

We aimed to examine the safety and efficacy of bevacizumab and carboplatin in patients with breast cancer brain metastases.

METHODS

We enrolled patients with breast cancer and > 1 measurable new or progressive brain metastasis. Patients received bevacizumab 15 mg/kg intravenously (IV) on cycle 1 day 1 and carboplatin IV AUC = 5 on cycle 1 day 8. Patients with HER2-positive disease also received trastuzumab. In subsequent cycles, all drugs were administered on day 1 of each cycle. Contrast-enhanced brain MRI was performed at baseline, 24-96 h after the first bevacizumab dose (day + 1), and every 2 cycles. The primary endpoint was objective response rate in the central nervous system (CNS ORR) by composite criteria. Associations between germline VEGF single nucleotide polymorphisms (rs699947, rs2019063, rs1570360, rs833061) and progression-free survival (PFS) and overall survival (OS) were explored, as were associations between early (day + 1) MRI changes and outcomes.

RESULTS

Thirty-eight patients were enrolled (29 HER2-positive, 9 HER2-negative); all were evaluable for response. The CNS ORR was 63% (95% CI, 46-78). Median PFS was 5.62 months and median OS was 14.10 months. As compared with an Eastern Cooperative Oncology Group performance status (ECOG PS) of 0, patients with ECOG PS 1-2 had significantly worse PFS and OS (all P < 0.01). No significant associations between VEGF genotypes or early MRI changes and clinical outcomes were observed.

CONCLUSIONS

The combination of bevacizumab and carboplatin results in a high rate of durable objective response in patients with brain metastases from breast cancer. This regimen warrants further investigation.

TRIAL REGISTRATION

NCT01004172 . Registered 28 October 2009.

NIMG-07. LONG-TERM FOLLOW-UP OF SCHWANNOMA GROWTH BEHAVIOR IN ADULT NEUROFIBROMATOSIS TYPE 2 AND SCHWANNOMATOSIS PATIENTS USING WHOLE-BODY MRI

BACKGROUND

Neurofibromatosis type 2 (NF2) and schwannomatosis (SWN) are related genetic tumor predisposition syndromes caused by distinct germline pathogenic variants on chromosome 22. Both conditions are characterized by the presence of cranial, peripheral, and/or spinal nerve schwannomas. The long-term growth behavior of schwannomas is unknown but knowledge thereof would help guide patient surveillance and selection for treatment and improvement of clinical trial design. Whole-body MRI (WBMRI) can detect whole-body schwannoma burden in a single image acquisition session.

METHODS

12 NF2 and 10 SWN patients who underwent a WBMRI between 2007-2010 underwent a repeat WBMRI between 2018-2019. Schwannomas were segmented on short tau inversion recovery (STIR) sequences. Tumor volume was calculated using a three-dimensional tumor quantification software (3DQI). Tumor growth and shrinkage were defined as a volume change ≥ 20% over the entire study period.

RESULTS

Median time between scans was 10 years. A total of 103 schwannomas (46 NF2-associated, 57 SWN-associated) were analyzed. In both NF2 and SWN, 50% of tumors grew. Median growth was 88.3% in NF2 and 100.4% in SWN. All growing NF2-associated schwannomas grew in the setting of exposure to systemic therapy whereas only one growing SWN-associated tumor had been treated systemically. Excluding resected tumors, 19.4% of schwannomas shrank. Median shrinkage was 48.5% in NF2 and 37.4% in SWN. All shrinking NF2-associated tumors had been treated with systemic therapy whereas none of the shrinking SWN-associated tumors had been. 19 new tumors (7 NF2-associated, 12 SWN-associated) developed in 8 patients.

CONCLUSIONS

Half of NF2- and SWN-associated schwannomas grow significantly over a decade. In NF2 patients, growth occurs despite systemic treatment whereas, in SWN patients, schwannomas may shrink spontaneously without treatment. These findings may suggest a more aggressive tumor phenotype in NF2. Continued patient enrollment and correlation of MRI findings with functional outcomes and hormone exposure history are ongoing.

Abstract P3-08-03: Dissecting the heterogeneity of metaplastic breast cancer: A morphological, immunohistochemical and genomic analysis of a large cohort

Although rare, Metaplastic Breast Carcinomas (MBC) account for significant global breast cancer mortality. This subgroup is extremely heterogeneous and by definition exhibits metaplastic change to squamous and/or mesenchymal elements, including but not limited to spindle, squamous, chondroid, osseous and rhabdomyoid elements. The WHO working group recognizes that the current classification is inadequate and in the interim, has suggested a purely descriptive classification. The mixed epithelial-mesenchymal morphology has led to speculation that MBC represent 'stem cell tumours'; in support of this, MBC have been shown to have a CD44+/CD24-/low phenotype. Clinically, patients present with tumours that are larger (higher stage), have increased likelihood of distant metastases at presentation and overall, have a reduced 5-year survival rate compared to Invasive Carcinoma-NST. Hence, this is a unique subtype with poor outcome but without a robust classification or understanding of the biology to aid clinical management. We present a detailed morphological, immunohistochemical and genomic analysis of a large series of MBC (n=347), as amassed through the Asia-Pacific MBC consortium. We consider our morphological dissection using the WHO subtyping guidelines and show that an increasing number of phenotypes in a mixed MBC (classified as WHO_1) significantly associates with a poor prognosis. Immunohistochemical analysis showed that a pure spindle (WHO_5) is significantly less likely to express vimentin, CK5/6, CK14, and CK19 than a mixed WHO_1 with spindle features. Similarly, a WHO_1 with chondroid features is less likely to express EGFR than WHO_1 with chondroid features and rhabdoid or osseous differentiation. Across the cohort, positivity for the AE1/3 antibody and a lack of EGFR expression both significantly associate with a better outcome. We report no significant association between patient age at diagnosis and breast cancer specific survival, nor between age and specific WHO MBC subtypes. We report a significant association between WHO_1 types and increasing tumour grade, and also between tumour size and grade, with tumour size being a highly significant prognostic indicator in this cohort. Our exome sequencing confirms a significant enrichment for TP53 and PTEN mutations in MBC, and intriguingly for concurrent mutations of TP53, PTEN and PIK3CA. A novel enrichment for NF1 mutations is also presented. In summary, we provide a thorough assessment of a large cohort of MBC, including morphology, survival, IHC and exome sequencing, and present our analysis contextualized by the WHO guidelines, extending the existing knowledge base of this rare tumour type.

Citation Format: McCart Reed AE, Kalaw E, Nones K, Bettington M, Lim M, Bennett J, Johnstone K, Kutasovic JR, Kazakoff S, Xu QC, Saunus JM, Reid LE, Black D, Niland C, Ferguson K, Gresshoff I, Raghavendra A, Liu JC, Kalinowski L, Reid AS, Davidson M, Pearson JV, Yamaguchi R, Harris G, Tse G, Papadimos D, Pathmanathan R, Pathmanathan N, Tan PH, Fox S, O'Toole S, Waddell N, Simpson PT, Lakhani SR. Dissecting the heterogeneity of metaplastic breast cancer: A morphological, immunohistochemical and genomic analysis of a large cohort [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P3-08-03.

Hybridization in bottlenose dolphins-A case study of Tursiops aduncus × T. truncatus hybrids and successful backcross hybridization events

The bottlenose dolphin, genus Tursiops is one of the best studied of all the Cetacea with a minimum of two species widely recognised. Common bottlenose dolphins (T. truncatus), are the cetacean species most frequently held in captivity and are known to hybridize with species from at least 6 different genera. In this study, we document several intra-generic hybridization events between T. truncatus and T. aduncus held in captivity. We demonstrate that the F1 hybrids are fertile and can backcross producing apparently healthy offspring, thereby showing introgressive inter-specific hybridization within the genus. We document that female F1 hybrids can reach sexual maturity at 4 yr and 3 mo of age, and can become pregnant and give birth before being fully weaned. The information presented has implications for understanding hybrid reticulation among cetacean species and practical implications for captive facilities housing either Tursiops species or hybrids thereof.

An Assessment of Imaging Informatics for Precision Medicine in Cancer

Objectives: Precision medicine requires the measurement, quantification, and cataloging of medical characteristics to identify the most effective medical intervention. However, the amount of available data exceeds our current capacity to extract meaningful information. We examine the informatics needs to achieve precision medicine from the perspective of quantitative imaging and oncology. Methods: The National Cancer Institute (NCI) organized several workshops on the topic of medical imaging and precision medicine. The observations and recommendations are summarized herein. Results: Recommendations include: use of standards in data collection and clinical correlates to promote interoperability; data sharing and validation of imaging tools; clinician's feedback in all phases of research and development; use of open-source architecture to encourage reproducibility and reusability; use of challenges which simulate real-world situations to incentivize innovation; partnership with industry to facilitate commercialization; and education in academic communities regarding the challenges involved with translation of technology from the research domain to clinical utility and the benefits of doing so. Conclusions: This article provides a survey of the role and priorities for imaging informatics to help advance quantitative imaging in the era of precision medicine. While these recommendations were drawn from oncology, they are relevant and applicable to other clinical domains where imaging aids precision medicine.

Towards an alternative testing strategy for nanomaterials used in nanomedicine: lessons from NanoTEST

In spite of recent advances in describing the health outcomes of exposure to nanoparticles (NPs), it still remains unclear how exactly NPs interact with their cellular targets. Size, surface, mass, geometry, and composition may all play a beneficial role as well as causing toxicity. Concerns of scientists, politicians and the public about potential health hazards associated with NPs need to be answered. With the variety of exposure routes available, there is potential for NPs to reach every organ in the body but we know little about the impact this might have. The main objective of the FP7 NanoTEST project ( www.nanotest-fp7.eu ) was a better understanding of mechanisms of interactions of NPs employed in nanomedicine with cells, tissues and organs and to address critical issues relating to toxicity testing especially with respect to alternatives to tests on animals. Here we describe an approach towards alternative testing strategies for hazard and risk assessment of nanomaterials, highlighting the adaptation of standard methods demanded by the special physicochemical features of nanomaterials and bioavailability studies. The work has assessed a broad range of toxicity tests, cell models and NP types and concentrations taking into account the inherent impact of NP properties and the effects of changes in experimental conditions using well-characterized NPs. The results of the studies have been used to generate recommendations for a suitable and robust testing strategy which can be applied to new medical NPs as they are developed.

A LUHMES 3D dopaminergic neuronal model for neurotoxicity testing allowing long-term exposure and cellular resilience analysis

Several shortcomings of current Parkinson’s disease (PD) models limit progress in identification of environmental contributions to disease pathogenesis. The conditionally immortalized cell line LUHMES promises to make human dopaminergic neuronal cultures more easily available, but these cells are difficult to culture for extended periods of time. We overcame this problem by culturing them in 3D with minor medium modifications. The 3D neuronal aggregates allowed penetration by small molecules and sufficient oxygen and nutrient supply for survival of the innermost cells. Using confocal microscopy, gene expression, and flow cytometry, we characterized the 3D model and observed a highly reproducible differentiation process. Visualization and quantification of neurites in aggregates was achieved by adding 2 % red fluorescent protein-transfected LUHMES cells. The mitochondrial toxicants and established experimental PD agents, rotenone and MPP⁺, perturbed genes involved in one-carbon metabolism and transsulfuration pathways (ASS1, CTH, and SHTM2) as in 2D cultures. We showed, for the first time in LUHMES, down-regulation of mir-7, a miRNA known to target alpha-synuclein and to be involved in PD. This was observed as early as 12 h after rotenone exposure, when pro-apoptotic mir-16 and rotenone-sensitive mir-210 were not yet significantly perturbed. Finally, washout experiments demonstrated that withdrawal of rotenone led to counter-regulation of mir-7 and ASS1, CTH, and SHTM2 genes. This suggests a possible role of these genes in direct cellular response to the toxicant, and the model appears to be suitable to address the processes of resilience and recovery in neurotoxicology and Parkinson’s disease in future studies.

Iterative mesh transformation for 3D segmentation of livers with cancers in CT images

Segmentation of diseased liver remains a challenging task in clinical applications due to the high inter-patient variability in liver shapes, sizes and pathologies caused by cancers or other liver diseases. In this paper, we present a multi-resolution mesh segmentation algorithm for 3D segmentation of livers, called iterative mesh transformation that deforms the mesh of a region-of-interest (ROI) in a progressive manner by iterations between mesh transformation and contour optimization. Mesh transformation deforms the 3D mesh based on the deformation transfer model that searches the optimal mesh based on the affine transformation subjected to a set of constraints of targeting vertices. Besides, contour optimization searches the optimal transversal contours of the ROI by applying the dynamic-programming algorithm to the intersection polylines of the 3D mesh on 2D transversal image planes. The initial constraint set for mesh transformation can be defined by a very small number of targeting vertices, namely landmarks, and progressively updated by adding the targeting vertices selected from the optimal transversal contours calculated in contour optimization. This iterative 3D mesh transformation constrained by 2D optimal transversal contours provides an efficient solution to a progressive approximation of the mesh of the targeting ROI. Based on this iterative mesh transformation algorithm, we developed a semi-automated scheme for segmentation of diseased livers with cancers using as little as five user-identified landmarks. The evaluation study demonstrates that this semi-automated liver segmentation scheme can achieve accurate and reliable segmentation results with significant reduction of interaction time and efforts when dealing with diseased liver cases.

Analysis of the perception of institutional function for health sector reform in Nigeria

Institutional function reflects the institution's understanding of the world around it, its ability to locate itself within that world and to make decisions in relation to it. Three dimensions of institutional function were identified as management, environmental mastery and service delivery. This study analysed the perception of institutional function of four hospitals in Nigeria by 507 healthcare professionals and managers and its influence on the implementation of the health sector reform programme in the country. The respondents were doctors and dentists (30%), nurses (27.2%), pharmacists (8.9%), managers (15.5%) and other allied healthcare workers (18.4%). The overall perception of institutional function was 56.3%. The perceptions of the three dimensions of institutional function were management 52.7%, environmental mastery 50.8% and service delivery 62.6%. Three out of 12 statements on institutional function had levels of perception that were lower than 50%. These were adequacy of management skills (49.7%), functioning management information systems that are used in management decision-making (47.9%) and degree of autonomy for the hospitals (42.4%). There is the need to strengthen the institutional function of Nigerian hospitals, especially the acquisition of management skills by the healthcare professionals and managers, management information systems and autonomy for the hospitals.