GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Online Resource
    Online Resource
    NIMG-25. OPTIMIZATION OF ARTIFICIAL INTELLIGENCE ALGORITHMS FOR LOW-RESOURCE/CLINICAL ENVIRONMENTS: FOCUS ON CLINICALLY-RELEVANT GLIOMA REGION DELINEATION
    Oxford University Press (OUP) ; 2022
    In:  Neuro-Oncology Vol. 24, No. Supplement_7 ( 2022-11-14), p. vii167-vii167
    Details
    In: Neuro-Oncology, Oxford University Press (OUP), Vol. 24, No. Supplement_7 ( 2022-11-14), p. vii167-vii167
    Abstract: Diffuse astrocytic glioma are common and aggressive malignant primary brain tumors with grim prognosis. Artificial intelligence (AI) has shown promise across predictive, prognostic, and diagnostic neuro-oncology applications, towards improving patient management. However, clinical translation and deployment are hampered by AI models’ requirements for explicit acceleration cards, which are not typically considered in clinical environments. Here, we seek the execution of AI models in such clinical/low-resource environments, facilitated by mathematical optimizations rather than investing in acceleration cards, and focus on the use case of delineating clinically-relevant regions, namely the entire tumor burden (ETB) and tumor core (TC). METHODS We identified the BraTS20 retrospective cohort of 369 glioma cases, each described by 4 structural multi-parametric MRI (mpMRI) scans (T1,T1Gd,T2,T2-FLAIR). The Generally Nuanced Deep Learning Framework (GaNDLFv0.0.14/PyTorchv1.8.2) was used to train the original AI model (ResUNet), by randomly sampling 40 643 patches from each mpMRI scan. We then investigate the contributions of post-training mathematical optimizations. Quantitative performance evaluation of the original and optimized (GaNDLFv0.0.14/OpenVINOTM-INT8-v2022.1.0) models were based on 125 unseen hold-out cases (BraTS20 validation dataset), using the dice similarity coefficient (DSC), while profiling in a consumer-grade workstation, i.e., typical clinical hardware configuration. RESULTS Negligible delineation performance differences were observed between the original and optimized AI models, for both ETB (DSCoriginal/DSCoptimized= 0.877/0.876) and TC (DSCoriginal/DSCoptimized= 0.773/0.772). However, the optimized model yielded substantial improvements in latency (up to 5.4x faster inference) and 53% less memory footprint. CONCLUSIONS Post-training mathematical optimization of AI models yields substantial gains in latency and memory usage, while maintaining their accuracy. Although we focused on delineation, we anticipate these mathematical optimizations to be applicable in other AI models. Post-training optimization is a promising approach for deploying AI models on consumer-grade CPUs, and hence facilitating their translation in low-resource/clinical environments, potentially contributing to improved patient management, treatment decisions, and response assessment. *author Siddhesh Thakur is an equal contributing first author.
    Type of Medium: Online Resource
    ISSN: 1522-8517 , 1523-5866
    URL: Article
    DOI: 10.1093/neuonc/noac209.643
    Language: English
    Publisher: Oxford University Press (OUP)
    Publication Date: 2022
    detail.hit.zdb_id: 2094060-9
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    NIMG-32. THE FEDERATED TUMOR SEGMENTATION (FETS) INITIATIVE: THE FIRST REAL-WORLD LARGE-SCALE DATA-PRIVATE COLLABORATION FOCUSING ON NEURO-ONCOLOGY
    Oxford University Press (OUP) ; 2021
    In:  Neuro-Oncology Vol. 23, No. Supplement_6 ( 2021-11-12), p. vi135-vi136
    Details
    In: Neuro-Oncology, Oxford University Press (OUP), Vol. 23, No. Supplement_6 ( 2021-11-12), p. vi135-vi136
    Abstract: Robustness and generalizability of artificial intelligent (AI) methods is reliant on the training data size and diversity, which are currently hindered in multi-institutional healthcare collaborations by data ownership and legal concerns. To address these, we introduce the Federated Tumor Segmentation (FeTS) Initiative, as an international consortium using federated learning (FL) for data-private multi-institutional collaborations, where AI models leverage data at participating institutions, without sharing data between them. The initial FeTS use-case focused on detecting brain tumor boundaries in MRI. METHODS The FeTS tool incorporates: 1) MRI pre-processing, including image registration and brain extraction; 2) automatic delineation of tumor sub-regions, by label fusion of pretrained top-performing BraTS methods; 3) tools for manual delineation refinements; 4) model training. 55 international institutions identified local retrospective cohorts of glioblastoma patients. Ground truth was generated using the first 3 FeTS functionality modes as mentioned earlier. Finally, the FL training mode comprises of i) an AI model trained on local data, ii) local model updates shared with an aggregator, which iii) combines updates from all collaborators to generate a consensus model, and iv) circulates the consensus model back to all collaborators for iterative performance improvements. RESULTS The first FeTS consensus model, from 23 institutions with data of 2,200 patients, showed an average improvement of 11.1% in the performance of the model on each collaborator’s validation data, when compared to a model trained on the publicly available BraTS data (n=231). CONCLUSION Our findings support that data increase alone would lead to AI performance improvements without any algorithmic development, hence indicating that the model performance would improve further when trained with all 55 collaborating institutions. FL enables AI model training with knowledge from data of geographically-distinct collaborators, without ever having to share any data, hence overcoming hurdles relating to legal, ownership, and technical concerns of data sharing.
    Type of Medium: Online Resource
    ISSN: 1522-8517 , 1523-5866
    URL: Article
    DOI: 10.1093/neuonc/noab196.532
    Language: English
    Publisher: Oxford University Press (OUP)
    Publication Date: 2021
    detail.hit.zdb_id: 2094060-9
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    TMOD-09. GLIOBLASTOMA BIOPHYSICAL GROWTH ESTIMATION USING DEEP LEARNING-BASED REGRESSION
    Oxford University Press (OUP) ; 2020
    In:  Neuro-Oncology Vol. 22, No. Supplement_2 ( 2020-11-09), p. ii229-ii229
    Details
    In: Neuro-Oncology, Oxford University Press (OUP), Vol. 22, No. Supplement_2 ( 2020-11-09), p. ii229-ii229
    Abstract: Glioblastomas are arguably the most aggressive, infiltrative, and heterogeneous adult brain tumor. Biophysical modeling of glioblastoma growth has shown its predictive value towards clinical endpoints, enabling more informed decision-making. However, the mathematically rigorous formulations of biophysical modeling come with a large computational footprint, hindering their application to clinical studies. METHODS We present a deep learning (DL)-based logistical regression model, to estimate in seconds glioblastoma biophysical growth, defined through three tumor-specific parameters: 1) diffusion coefficient of white matter (Dw), which describes how easily the tumor can infiltrate through the white matter, 2) mass-effect parameter (Mp), which defines the average tumor expansion, and 3) estimated time (T) in number of days that the tumor has been growing. Pre-operative multi-parametric MRI (mpMRI) structural scans (T1, T1-Gd, T1, T2-FLAIR) from 135 subjects of the TCGA-GBM imaging collection are used to quantitatively evaluate our approach. We consider the mpMRI intensities within the region defined by the abnormal T2-FLAIR signal envelope, for training three DL models for the three tumor-specific parameters. Each of our DL models consist of two sets of convolution layers followed by a single max-pooling layer, with a normalized root mean squared error as the minimization metric and evaluated using 10-fold cross validation. We train and validate the DL-based predictions against parameters derived from biophysical inversion models. RESULTS Pearson correlation coefficients between our DL-based estimations and the biophysical parameters were equal to 0.85 for Dw, 0.90 for Mp, and 0.94 for T. CONCLUSION This study unlocks the power of tumor-specific parameters from biophysical tumor growth estimation, paving the way towards their utilization in more clinical studies, while opening the door for leveraging advanced radiomic descriptors in future studies, as well as allowing for significantly faster parameter reconstruction compared to biophysical growth modeling approaches. *denotes equal senior authorship.
    Type of Medium: Online Resource
    ISSN: 1522-8517 , 1523-5866
    URL: Article
    DOI: 10.1093/neuonc/noaa215.960
    Language: English
    Publisher: Oxford University Press (OUP)
    Publication Date: 2020
    detail.hit.zdb_id: 2094060-9
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 4
    Online Resource
    Online Resource
    Multi-institutional noninvasive in vivo characterization of IDH , 1p/19q, and EGFRvIII in glioma using neuro-Cancer Imaging Phenomics Toolkit (neuro-CaPTk)
    Oxford University Press (OUP) ; 2020
    In:  Neuro-Oncology Advances Vol. 2, No. Supplement_4 ( 2020-12-31), p. iv22-iv34
    Details
    In: Neuro-Oncology Advances, Oxford University Press (OUP), Vol. 2, No. Supplement_4 ( 2020-12-31), p. iv22-iv34
    Abstract: Gliomas represent a biologically heterogeneous group of primary brain tumors with uncontrolled cellular proliferation and diffuse infiltration that renders them almost incurable, thereby leading to a grim prognosis. Recent comprehensive genomic profiling has greatly elucidated the molecular hallmarks of gliomas, including the mutations in isocitrate dehydrogenase 1 and 2 (IDH1 and IDH2), loss of chromosomes 1p and 19q (1p/19q), and epidermal growth factor receptor variant III (EGFRvIII). Detection of these molecular alterations is based on ex vivo analysis of surgically resected tissue specimen that sometimes is not adequate for testing and/or does not capture the spatial tumor heterogeneity of the neoplasm. Methods We developed a method for noninvasive detection of radiogenomic markers of IDH both in lower-grade gliomas (WHO grade II and III tumors) and glioblastoma (WHO grade IV), 1p/19q in IDH-mutant lower-grade gliomas, and EGFRvIII in glioblastoma. Preoperative MRIs of 473 glioma patients from 3 of the studies participating in the ReSPOND consortium (collection I: Hospital of the University of Pennsylvania [HUP: n = 248], collection II: The Cancer Imaging Archive [TCIA; n = 192] , and collection III: Ohio Brain Tumor Study [OBTS, n = 33]) were collected. Neuro-Cancer Imaging Phenomics Toolkit (neuro-CaPTk), a modular platform available for cancer imaging analytics and machine learning, was leveraged to extract histogram, shape, anatomical, and texture features from delineated tumor subregions and to integrate these features using support vector machine to generate models predictive of IDH, 1p/19q, and EGFRvIII. The models were validated using 3 configurations: (1) 70–30% training–testing splits or 10-fold cross-validation within individual collections, (2) 70–30% training–testing splits within merged collections, and (3) training on one collection and testing on another. Results These models achieved a classification accuracy of 86.74% (HUP), 85.45% (TCIA), and 75.15% (TCIA) in identifying EGFRvIII, IDH, and 1p/19q, respectively, in configuration I. The model, when applied on combined data in configuration II, yielded a classification success rate of 82.50% in predicting IDH mutation (HUP + TCIA + OBTS). The model when trained on TCIA dataset yielded classification accuracy of 84.88% in predicting IDH in HUP dataset. Conclusions Using machine learning algorithms, high accuracy was achieved in the prediction of IDH, 1p/19q, and EGFRvIII mutation. Neuro-CaPTk encompasses all the pipelines required to replicate these analyses in multi-institutional settings and could also be used for other radio(geno)mic analyses.
    Type of Medium: Online Resource
    ISSN: 2632-2498
    URL: Article
    DOI: 10.1093/noajnl/vdaa128
    Language: English
    Publisher: Oxford University Press (OUP)
    Publication Date: 2020
    detail.hit.zdb_id: 3009682-0
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...