NIMG-26. IMPROVING THE GENERALIZABILITY OF DEEP LEARNING FOR T2-LESION SEGMENTATION OF GLIOMAS IN THE POST-TREATMENT SETTING

2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi134-vi134
Author(s):  
Jacob Ellison ◽  
Francesco Caliva ◽  
Pablo Damasceno ◽  
Tracy Luks ◽  
Marisa LaFontaine ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Response Assessment ◽  
Training Transfer ◽  
Post Treatment ◽  
Treatment Setting ◽  
Newly Diagnosed ◽  
Lesion Segmentation ◽  
Cross Sectional ◽  
Segmentation Accuracy

Abstract Although current advances for automated glioma lesion segmentation and volumetric measurements using deep learning have yielded high performance on newly-diagnosed patients, response assessment in neuro-oncology still relies on manually-drawn, cross-sectional areas of the tumor because these models do not generalize to patients in the post-treatment setting, where they are most needed in the clinic. Surgical resections, adjuvant treatment, or disease progression can alter the characteristics of these lesions on T2-weighted imaging, causing measures of segmentation accuracy, typically measured by Dice coefficients of overlap (DCs), to drop by ~15%. To improve the generalizability of T2-lesion segmentation to patients with glioma post-treatment, we evaluated the effects of: 1) training with different proportions of newly-diagnosed and treated gliomas, 2) applying transfer learning from pre- to post-treatment domains, and 3) incorporating a loss term that spatially weights the lesion boundaries with greater emphasis in training. Using 425 patients (208 newly-diagnosed, 217 post-Tx, with 25 treated patients withheld as a test set) and a top-performing model previously trained on newly-diagnosed gliomas, we found that DCs increased by 10% (to 0.84) then plateaued after including ~25% of post-treatment patients in training. Transfer learning (pre-training on newly-diagnosed and finetuning with post-treatment data) significantly improved Hausdorf distances (HDs), a measure more sensitive to changes at the lesion boundaries, by 17% after including 26% post-treatment images in training, while DCs remained similar. Although modifying our loss functions with boundary-weighted penalizations resulted in comparable DCs to using standard DC loss, HD measures were further reduced by 26%, suggesting that HDs may be a more sensitive metric to subtle changes in segmentation accuracy than DCs. Current work is evaluating their utility in providing accurate volumes for real-time response assessment in the clinic using workflows that have recently been deployed on our clinical PACs system.

Bladder cancer treatment response assessment using deep learning in CT with transfer learning

2017 ◽  
Author(s):  
Kenny H. Cha ◽  
Lubomir M. Hadjiiski ◽  
Heang-Ping Chan ◽  
Ravi K. Samala ◽  
Richard H. Cohan ◽  
...  
Keyword(s):  
Bladder Cancer ◽  
Deep Learning ◽  
Cancer Treatment ◽  
Treatment Response ◽  
Transfer Learning ◽  
Response Assessment ◽  
Treatment Response Assessment

scholarly journals Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning

Diagnostics ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 1621
Author(s):  
Riaan Zoetmulder ◽  
Praneeta R. Konduri ◽  
Iris V. Obdeijn ◽  
Efstratios Gavves ◽  
Ivana Išgum ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Detection Rate ◽  
Posterior Circulation ◽  
Lesion Detection ◽  
The Other ◽  
Lesion Volume ◽  
Learning Approaches ◽  
Lesion Segmentation ◽  
Anterior Circulation

Final lesion volume (FLV) is a surrogate outcome measure in anterior circulation stroke (ACS). In posterior circulation stroke (PCS), this relation is plausibly understudied due to a lack of methods that automatically quantify FLV. The applicability of deep learning approaches to PCS is limited due to its lower incidence compared to ACS. We evaluated strategies to develop a convolutional neural network (CNN) for PCS lesion segmentation by using image data from both ACS and PCS patients. We included follow-up non-contrast computed tomography scans of 1018 patients with ACS and 107 patients with PCS. To assess whether an ACS lesion segmentation generalizes to PCS, a CNN was trained on ACS data (ACS-CNN). Second, to evaluate the performance of only including PCS patients, a CNN was trained on PCS data. Third, to evaluate the performance when combining the datasets, a CNN was trained on both datasets. Finally, to evaluate the performance of transfer learning, the ACS-CNN was fine-tuned using PCS patients. The transfer learning strategy outperformed the other strategies in volume agreement with an intra-class correlation of 0.88 (95% CI: 0.83–0.92) vs. 0.55 to 0.83 and a lesion detection rate of 87% vs. 41–77 for the other strategies. Hence, transfer learning improved the FLV quantification and detection rate of PCS lesions compared to the other strategies.

scholarly journals Colorectal cancer pain upon diagnosis and after treatment: a cross-sectional comparison with healthy matched controls

2022 ◽  
Author(s):  
Maria Lopez-Garzon ◽  
Paula Postigo-Martin ◽  
Ángela González-Santos ◽  
Manuel Arroyo-Morales ◽  
Alexander Achalandabaso-Ochoa ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Body Composition ◽  
Cancer Pain ◽  
Lean Mass ◽  
Matched Control ◽  
Post Treatment ◽  
Newly Diagnosed ◽  
Cross Sectional ◽  
Skeletal Muscle Index ◽  
Dominant Side

Abstract Background The current study sought to explore whether cancer pain (CP) already exists in patients at colorectal cancer (CRC) diagnosis before treatment compared with patients with colorectal cancer (CRC) after treatment and a healthy matched control group. The study also sought to examine whether factors related to physical health status could enhance pain processes. Methods An observational cross-sectional study was conducted following the STROBE checklist. Twenty-nine newly diagnosed and forty post-treatment patients with CRC and 40 healthy age/sex-matched controls were included for comparison. Pain, local muscle function, and body composition outcomes were assessed by a physiotherapist with > 3 years of experience. ANCOVA and Kruskal–Wallis tests were performed, with Bonferroni and Dunn-Bonferroni post hoc analyses and Cohen’s d and Hedge’s effect size, as appropriate. Results The analysis detected lower values of pressure pain threshold (PPT) points, the PPT index, and abdominal strength and higher values of self-reported abdominal pain in newly diagnosed patients, with even more marked results observed in the post-treatment patients, where lower lean mass and skeletal muscle index values were also found than those in the healthy matched controls (p < 0.05). In the post-treatment and healthy matched control groups, positive associations were observed between the PPT lumbar dominant side points and abdominal isometric strength and lean mass, and negative associations were observed between the lumbar dominant side points and body fat (p < 0.05). Conclusion Upon diagnosis, patients with CRC already show signs of hyperalgesia and central sensitization and deteriorated physical conditions and body composition, and this state could be aggravated by subsequent treatments.

scholarly journals Deep learning-based quantification of temporalis muscle has prognostic value in patients with glioblastoma

2021 ◽  
Author(s):  
Ella Mi ◽  
Radvile Mauricaite ◽  
Lillie Pakzad-Shahabi ◽  
Jiarong Chen ◽  
Andrew Ho ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prognostic Value ◽  
Cancer Survival ◽  
Neck Muscle ◽  
Data Sets ◽  
Temporalis Muscle ◽  
Cross Sectional ◽  
External Data ◽  
Segmentation Accuracy ◽  
Muscle Cross Sectional Area

Abstract Background Glioblastoma is the commonest malignant brain tumour. Sarcopenia is associated with worse cancer survival, but manually quantifying muscle on imaging is time-consuming. We present a deep learning-based system for quantification of temporalis muscle, a surrogate for skeletal muscle mass, and assess its prognostic value in glioblastoma. Methods A neural network for temporalis segmentation was trained with 366 MRI head images from 132 patients from 4 different glioblastoma data sets and used to quantify muscle cross-sectional area (CSA). Association between temporalis CSA and survival was determined in 96 glioblastoma patients from internal and external data sets. Results The model achieved high segmentation accuracy (Dice coefficient 0.893). Median age was 55 and 58 years and 75.6 and 64.7% were males in the in-house and TCGA-GBM data sets, respectively. CSA was an independently significant predictor for survival in both the in-house and TCGA-GBM data sets (HR 0.464, 95% CI 0.218–0.988, p = 0.046; HR 0.466, 95% CI 0.235–0.925, p = 0.029, respectively). Conclusions Temporalis CSA is a prognostic marker in patients with glioblastoma, rapidly and accurately assessable with deep learning. We are the first to show that a head/neck muscle-derived sarcopenia metric generated using deep learning is associated with oncological outcomes and one of the first to show deep learning-based muscle quantification has prognostic value in cancer.

Deep Learning for text in limted data settings

2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Text Classification ◽  
State Of The Art ◽  
Time Series Forecasting ◽  
Text Data ◽  
Performance Levels

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.

Rethinking the Dice Loss for Deep Learning Lesion Segmentation in Medical Images

2021 ◽  
Vol 26 (1) ◽  
pp. 93-102
Author(s):  
Yue Zhang ◽  
Shijie Liu ◽  
Chunlai Li ◽  
Jianyu Wang
Keyword(s):  
Deep Learning ◽  
Medical Images ◽  
Lesion Segmentation

scholarly journals Deep Transfer Learning Based Intrusion Detection System for Electric Vehicular Networks

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4736
Author(s):  
Sk. Tanzir Mehedi ◽  
Adnan Anwar ◽  
Ziaur Rahman ◽  
Kawsar Ahmed
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Intrusion Detection ◽  
Real Time ◽  
Transfer Learning ◽  
Security Requirements ◽  
Detection Accuracy ◽  
Area Network ◽  
Complex Data ◽  
Network Intrusion

The Controller Area Network (CAN) bus works as an important protocol in the real-time In-Vehicle Network (IVN) systems for its simple, suitable, and robust architecture. The risk of IVN devices has still been insecure and vulnerable due to the complex data-intensive architectures which greatly increase the accessibility to unauthorized networks and the possibility of various types of cyberattacks. Therefore, the detection of cyberattacks in IVN devices has become a growing interest. With the rapid development of IVNs and evolving threat types, the traditional machine learning-based IDS has to update to cope with the security requirements of the current environment. Nowadays, the progression of deep learning, deep transfer learning, and its impactful outcome in several areas has guided as an effective solution for network intrusion detection. This manuscript proposes a deep transfer learning-based IDS model for IVN along with improved performance in comparison to several other existing models. The unique contributions include effective attribute selection which is best suited to identify malicious CAN messages and accurately detect the normal and abnormal activities, designing a deep transfer learning-based LeNet model, and evaluating considering real-world data. To this end, an extensive experimental performance evaluation has been conducted. The architecture along with empirical analyses shows that the proposed IDS greatly improves the detection accuracy over the mainstream machine learning, deep learning, and benchmark deep transfer learning models and has demonstrated better performance for real-time IVN security.

scholarly journals Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Young-Gon Kim ◽  
Sungchul Kim ◽  
Cristina Eunbee Cho ◽  
In Hye Song ◽  
Hee Jin Lee ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Frozen Section ◽  
Medical Center ◽  
External Validation ◽  
Model Performance ◽  
Classification Model ◽  
Training Dataset

AbstractFast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.

Sign in / Sign up

Export Citation Format

Share Document