3D Texture Feature-Based Lymph Node Automated Detection in Head and Neck Cancer Analysis

Wang, Yibin; Zamiela, Christian; Thomas, Toms Vengaloor; Duggar, William N; Roberts, Paul; Bian, Linkan; Wang, Haifeng

doi:10.1109/bibm49941.2020.9313482

Cited by 8 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, gains may be realized in the efficiency of care when the time needed for surgery and then pathology is not required for a patient's treatment course. Here and previously, we demonstrate a budding methodology that can already very reliably detect the overall presence of ECE within a given CT [35,36]. The potential of this technology stands to impact not only the effectiveness of current HNC paradigms but may also adjust them in favor of less toxicity, better QOL, care efficiency, and even healthcare costs.…”

Section: Discussionmentioning

confidence: 68%

“…The machine learning architecture utilized in this study is described in great detail in a more technical publication with one exception in that our Hounsfield unit (HU) threshold during training was modified to be -200 to 200 rather than -400 to 400 [35,36]. For a general description, the current model consists of a multilayer gradient mapping-guided explainable network (GMGENet) architecture (Figure 1) involving a volume extractor that defines the volume of interest (VOI) for analysis within the CT dataset and a classifier layer that evaluates voxels within the VOI to produce a patient-level output prediction of the presence of ECE as affirmative or negative.…”

Section: Machine Learning Architecture and Explainabilitymentioning

confidence: 99%

See 1 more Smart Citation

Preoperative Prediction and Identification of Extracapsular Extension in Head and Neck Cancer Patients: Progress and Potential

Duggar¹,

Thomas²,

Wang³

et al. 2023

Cureus

Self Cite

View full text Add to dashboard Cite

BackgroundThis study aimed to demonstrate both the potential and development progress in the identification of extracapsular nodal extension in head and neck cancer patients prior to surgery. MethodologyA deep learning model has been developed utilizing multilayer gradient mapping-guided explainable network architecture involving a volume extractor. In addition, the gradient-weighted class activation mapping approach has been appropriated to generate a heatmap of anatomic regions indicating why the algorithm predicted extension or not. ResultsThe prediction model shows excellent performance on the testing dataset with high values of accuracy, the area under the curve, sensitivity, and specificity of 0.926, 0.945, 0.924, and 0.930, respectively. The heatmap results show potential usefulness for some select patients but indicate the need for further training as the results may be misleading for other patients. ConclusionsThis work demonstrates continued progress in the identification of extracapsular nodal extension in diagnostic computed tomography prior to surgery. Continued progress stands to see the obvious potential realized where not only can unnecessary multimodality therapy be avoided but necessary therapy can be guided on a patient-specific level with information that currently is not available until postoperative pathology is complete.

show abstract

Section: Discussionmentioning

confidence: 68%

Section: Machine Learning Architecture and Explainabilitymentioning

confidence: 99%

Preoperative Prediction and Identification of Extracapsular Extension in Head and Neck Cancer Patients: Progress and Potential

Duggar¹,

Thomas²,

Wang³

et al. 2023

Cureus

Self Cite

View full text Add to dashboard Cite

show abstract

“…Bielak et al investigated the impact of various magnetic resonance imaging sequences on auto-segmentation of lymph nodes and found a maximum DSC of 0.58 28 . Similarly, Wang et al integrated the extraction of various imaging features into a DL-CNN and achieved a mean DSC score of 0.94 for the highest performing model 29 . As computed tomography scans are acquired during the radiotherapy planning process, we chose to use contrast-enhanced, diagnostic HN-CT scans for the training of our DL-CNN.…”

Section: Discussionmentioning

confidence: 99%

Auto-Detection and Segmentation of Involved Lymph Nodes in HPV-Associated Oropharyngeal Cancer Using a Convolutional Deep Learning Neural Network

Taku¹,

Wahid²,

Dijk³

et al. 2022

Preprint

View full text Add to dashboard Cite

Purpose: Segmentation of involved lymph nodes on head and neck computed tomography (HN-CT) scans is necessary for the radiotherapy treatment planning of human papilloma virus (HPV) associated oropharynx cancers (OPC). We aimed to train a deep learning convolutional neural network (DL-CNN) to identify and segment involved lymph nodes on contrast-enhanced HN-CT scans. Methods: 90 patients who underwent levels II-IV neck dissection for newly diagnosed, clinically node-positive, HPV-OPC were identified. Ground-truth segmentation of all radiographically and pathologically involved nodes was manually performed on pre-surgical HN-CT scans, which were randomly divided into training/validation dataset (n=70) and testing dataset (n=20). A 5-fold cross validation was used to train 5 separate DL-CNN sub-models based on a residual U-net architecture. Validation and testing segmentation masks were compared to ground-truth segmentation masks using overlap-based, volume-based, and distance-based metrics. A lymph auto-detection model was developed by thresholding segmentation model outputs, and 20 node-negative HN-CT scans were added to the test set to further evaluate auto-detection capabilities. Model discrimination of lymph node positive and negative HN-CT scans was evaluated using the area under the receiver operating characteristic curve (AUC). Results: In the DL-CNN validation phase, all sub-models yielded segmentation masks with median DSC > 0.90 and median volume similarity score of > 0.95. In the testing phase, the DL-CNN produced consensus segmentation masks with median Dice of 0.92 (IQR, 0.89-0.95), median volume similarity of 0.97 (IQR, 0.94-0.99), and median Hausdorff distance of 4.52 mm (IQR, 1.22-8.38). The detection model achieved an AUC of 0.98. Conclusion: The results from this single-institution study demonstrate the successful automation of lymph node segmentation for patients with HPV-OPC using a DL-CNN. Future studies, including external validation using a larger dataset, are necessary to clarify the role of the DL-CNN in the routine radiation oncology treatment planning workflow.

show abstract

“…We selected VOIs based on the slice of nose 3 centimeters upward and the slice of acromial 3 centimeters downward. Figure 2 demonstrates the segmented VOIs (Wang et al, 2020(Wang et al, , 2021. though the standard deviations were a bit higher, all the performance metrics significantly outperformed other models.…”

Section: Data Preparation and Preprocessingmentioning

confidence: 99%

A Gradient Mapping Guided Explainable Deep Neural Network for Extracapsular Extension Identification in 3D Head and Neck Cancer Computed Tomography Images

Wang¹,

Rahman²,

Duggar³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Diagnosis and treatment management for head and neck squamous cell carcinoma (HNSCC) is guided by routine diagnostic head and neck computed tomography (CT) scans to identify tumor and lymph node features. Extracapsular extension (ECE) is a strong predictor of patients' survival outcomes with HN-SCC. It is essential to detect the occurrence of ECE as it changes staging and management for the patients. Current clinical ECE detection relies on visual identification and pathologic confirmation conducted by radiologists. Machine learning (ML)-based ECE diagnosis has shown high potential in the recent years. However, manual annotation of lymph node region is a required data preprocessing step in most of the current ML-based ECE diagnosis studies. In addition, this manual annotation process is time-consuming, labor-intensive, and error-prone. Therefore, in this paper, we propose a Gradient Mapping Guided Explainable Network (GMGENet) framework to perform ECE identification automatically without requiring annotated lymph node region information. The gradient-weighted class activation mapping (Grad-CAM) technique is proposed to guide the deep learning algorithm to focus on the regions that are highly

show abstract

3D Texture Feature-Based Lymph Node Automated Detection in Head and Neck Cancer Analysis

Cited by 8 publications

References 19 publications

Preoperative Prediction and Identification of Extracapsular Extension in Head and Neck Cancer Patients: Progress and Potential

Preoperative Prediction and Identification of Extracapsular Extension in Head and Neck Cancer Patients: Progress and Potential

Auto-Detection and Segmentation of Involved Lymph Nodes in HPV-Associated Oropharyngeal Cancer Using a Convolutional Deep Learning Neural Network

A Gradient Mapping Guided Explainable Deep Neural Network for Extracapsular Extension Identification in 3D Head and Neck Cancer Computed Tomography Images

Contact Info

Product

Resources

About