Deep convolutional neural networks for automatic segmentation of thoracic organs‐at‐risk in radiation oncology – use of non‐domain transfer learning

Vu, Charles C.; Siddiqui, Z.A.; Zamdborg, Leonid; Thompson, Andrew; Quinn, Thomas J.; Castillo, Edward M.; Guerrero, Thomas

doi:10.1002/acm2.12871

Cited by 18 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the performance of AccuContour TM -based and denoising-based auto-segmentation was below a satisfactory level for the esophagus. Previous studies have reported that the DSCs of deep-learning-based auto-segmentation do not exceed 0.8 for the esophagus [ 40 , 46 , 47 , 48 , 49 ]. Due to the absence of a consistent intensity contrast between the esophagus and neighboring tissues in non-contrast CT images, the boundaries between the esophagus and surrounding soft tissues are not well-defined.…”

Section: Discussionmentioning

confidence: 99%

Impact of Denoising on Deep-Learning-Based Automatic Segmentation Framework for Breast Cancer Radiotherapy Planning

Lee

Choi

et al. 2022

Cancers

View full text Add to dashboard Cite

Objective: This study aimed to investigate the segmentation accuracy of organs at risk (OARs) when denoised computed tomography (CT) images are used as input data for a deep-learning-based auto-segmentation framework. Methods: We used non-contrast enhanced planning CT scans from 40 patients with breast cancer. The heart, lungs, esophagus, spinal cord, and liver were manually delineated by two experienced radiation oncologists in a double-blind manner. The denoised CT images were used as input data for the AccuContourTM segmentation software to increase the signal difference between structures of interest and unwanted noise in non-contrast CT. The accuracy of the segmentation was assessed using the Dice similarity coefficient (DSC), and the results were compared with those of conventional deep-learning-based auto-segmentation without denoising. Results: The average DSC outcomes were higher than 0.80 for all OARs except for the esophagus. AccuContourTM-based and denoising-based auto-segmentation demonstrated comparable performance for the lungs and spinal cord but showed limited performance for the esophagus. Denoising-based auto-segmentation for the liver was minimal but had statistically significantly better DSC than AccuContourTM-based auto-segmentation (p < 0.05). Conclusions: Denoising-based auto-segmentation demonstrated satisfactory performance in automatic liver segmentation from non-contrast enhanced CT scans. Further external validation studies with larger cohorts are needed to verify the usefulness of denoising-based auto-segmentation.

show abstract

Section: Discussionmentioning

confidence: 99%

Impact of Denoising on Deep-Learning-Based Automatic Segmentation Framework for Breast Cancer Radiotherapy Planning

Lee

Choi

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“…Additionally, some researchers proposed to integrate the knowledge about how features should behave in generating prediction as attribution priors into DL training (33). Finally, noting that some knowledge learned from relative domains is also informative for the target tasks, transfer learning is an effective approach to leverage such knowledge in DL training (35)(36)(37)(38).…”

Section: Discussionmentioning

confidence: 99%

Biologically-informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post-treatment glioblastoma

Wang

Argenziano

Yoon

et al. 2022

Preprint

View full text Add to dashboard Cite

Intratumoral heterogeneity presents a major challenge to diagnosis and treatment of glioblastoma (GBM). Such heterogeneity is further exacerbated upon the recurrence of GBM, where treatment-induced reactive changes produce additional intratumoral heterogeneity that is ambiguous to differentiate on clinical imaging. There is an urgent need to develop non-invasive approaches to map the heterogeneous landscape of histopathological alterations throughout the entire lesion for each patient. We propose to predictively fuse MRI with the underlying intratumoral heterogeneity in recurrent GBM using machine learning (ML) by leveraging unique image-localized biopsies with their associated locoregional MRI features. To this end, we develop BioNet, a biologically informed multi-task framework combining Bayesian neural networks and semi-supervised adversarial autoencoders, to predict regional distributions of three tissue-specific gene modules: proliferating tumor, reactive/inflammatory cells, and infiltrated brain tissue. BioNet provides insight into how to integrate implicit and hierarchical domain knowledge, which is difficult to incorporate into ML models through existing methods. The proposed architecture further addresses challenges in exploiting latent feature structures from limited labeled image-localized biopsy samples, which lead to improvements in prediction accuracy. BioNet performs signiﬁcantly better than existing methods on cross-validation and blind test datasets, shows generalizability that surpasses other models, and is adaptable to different types of data or tasks. Prediction maps of gene modules from BioNet provide accurate predictions of intratumoral heterogeneity, which can improve surgical planning and localization of diagnostic biopsies, as well as inform neuro-oncological treatment assessment for each patient. These results also highlight the emerging role of ML in precision medicine.

show abstract

“…The most recent approaches for CT lung segmentation show a clear predominance of learning algorithms capable of directly learning the distribution of the data used for training. Methodologies inspired on U-net [ 154 ] cover the majority of deep learning-based attempts [ 155 , 156 , 157 , 158 , 159 , 160 , 161 , 162 , 163 , 164 , 165 ]. To increase the complexity of the feature extraction task, the encoder module could reuse transferred weights from pre-trained networks, as in the works by Vu et al [ 163 ] and Jalali et al [ 166 ], where the VGG-16 and ResNet-34 models were adopted to work as encoder blocks, respectively.…”

Section: Computer-aided Decision Systemsmentioning

confidence: 99%

“…Methodologies inspired on U-net [ 154 ] cover the majority of deep learning-based attempts [ 155 , 156 , 157 , 158 , 159 , 160 , 161 , 162 , 163 , 164 , 165 ]. To increase the complexity of the feature extraction task, the encoder module could reuse transferred weights from pre-trained networks, as in the works by Vu et al [ 163 ] and Jalali et al [ 166 ], where the VGG-16 and ResNet-34 models were adopted to work as encoder blocks, respectively. More investigations on improvements in typical convolutional blocks can also be found, integrating residual blocks [ 164 , 167 ], inception modules with dense connections [ 162 ], and squeeze-and-excitation blocks to target specific thoracic organs at risk [ 165 ].…”

Section: Computer-aided Decision Systemsmentioning

confidence: 99%

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

Silva

Pereira

Neves

et al. 2022

JPM

View full text Add to dashboard Cite

Advancements in the development of computer-aided decision (CAD) systems for clinical routines provide unquestionable benefits in connecting human medical expertise with machine intelligence, to achieve better quality healthcare. Considering the large number of incidences and mortality numbers associated with lung cancer, there is a need for the most accurate clinical procedures; thus, the possibility of using artificial intelligence (AI) tools for decision support is becoming a closer reality. At any stage of the lung cancer clinical pathway, specific obstacles are identified and “motivate” the application of innovative AI solutions. This work provides a comprehensive review of the most recent research dedicated toward the development of CAD tools using computed tomography images for lung cancer-related tasks. We discuss the major challenges and provide critical perspectives on future directions. Although we focus on lung cancer in this review, we also provide a more clear definition of the path used to integrate AI in healthcare, emphasizing fundamental research points that are crucial for overcoming current barriers.

show abstract

Deep convolutional neural networks for automatic segmentation of thoracic organs‐at‐risk in radiation oncology – use of non‐domain transfer learning

Cited by 18 publications

References 12 publications

Impact of Denoising on Deep-Learning-Based Automatic Segmentation Framework for Breast Cancer Radiotherapy Planning

Impact of Denoising on Deep-Learning-Based Automatic Segmentation Framework for Breast Cancer Radiotherapy Planning

Biologically-informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post-treatment glioblastoma

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

Contact Info

Product

Resources

About