Deep learning approach of diffusion-weighted imaging as an outcome predictor in laryngeal and hypopharyngeal cancer patients with radiotherapy-related curative treatment: a preliminary study

Early prediction of radiotherapy outcomes in pharyngeal cancer using deep learning on baseline [18F]Fluorodeoxyglucose positron emission Tomography/Computed tomography

OBJECTIVES

This study aimed to develop an integrated segmentation-free deep learning (DL) framework to predict multiple aspects of radiotherapy outcome in pharyngeal cancer patients by analyzing pretreatment 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography-computed tomography (PET/CT).

METHODS

We utilized baseline 18F-FDG-PET/CT scans from patients newly diagnosed with oropharyngeal or hypopharyngeal cancer. The study cohort comprised 162 patients for training and 32 for validation, all of whom completed definitive chemoradiotherapy or radiotherapy for organ-preservation. Following image augmentation, fused PET and CT images were used to train three distinct DL models. An ensemble voting classifier was then employed to predict local recurrence (LR), neck lymph node relapse (NR), and distant metastases (DM). Model performance was evaluated using receiver operating characteristic curve analysis.

RESULTS

With a median follow-up of 36 months, the training cohort experienced, LR in 45 (27.8 %), NR in 32 (19.8 %), and DM in 21 (13.0 %) patients. By optimizing single models and finalizing with an ensemble voting classifier, the area under the curve for the occurrence of LR, NR, and DM was 0.850, 0.878, and 0.893, whereas the accuracy for the three endpoints were 87.5 %, 68.8 %, and 78.1 %, respectively.

CONCLUSIONS

By utilizing baseline 18F-FDG-PET/CT, our proposed DL models can provide a supplemental prediction for various therapeutic outcome in patients with pharyngeal cancer undergoing radiotherapy-based treatment. The accuracy for NR and DM predictions requires further optimization through additional technological breakthrough or combing clinical parameters. External validation is an important future step to confirm the model's generalizability and clinical utility.

The clinical utility of diffusion-weighted imaging in diagnosing and predicting treatment response of laryngeal and hypopharyngeal carcinoma: A systematic review and meta-analysis

PURPOSE

Laryngeal and Hypopharyngeal Carcinomas (LC/HPC) constitute about 24 % of head and neck cancers, causing more than 90,000 annual deaths worldwide. Diffusion-Weighted Imaging (DWI), is currently widely studied in oncologic imaging and can aid in distinguishing cellular tumors from other tissues. Our objective was to review the effectiveness of DWI in three areas: diagnosing, predicting prognosis, and predicting treatment response in patients with LC/HPC.

METHODS

A systematic search was conducted in PubMed, Web of Science, and Embase. A meta-analysis by calculating Standardized Mean Difference (SMD) and 95 % Confidence Interval (CI) was conducted on diagnostic studies.

RESULTS

A total of 16 studies were included. All diagnostic studies (n = 9) were able to differentiate between the LC/HPC and other benign laryngeal/hypopharyngeal lesions. These studies found that LC/HPC had lower Apparent Diffusion Coefficient (ADC) values than non-cancerous lesions. Our meta-analysis of 7 diagnostic studies, that provided ADC values of malignant and non-malignant tissues, demonstrated significantly lower ADC values in LC/HPC compared to non-malignant lesions (SMD = -1.71, 95 %CI: [-2.00, -1.42], ADC cut-off = 1.2 × 103 mm2/s). Furthermore, among the studies predicting prognosis, 67 % (4/6) accurately predicted outcomes based on pretreatment ADC values. Similarly, among studies predicting treatment response, 50 % (2/4) successfully predicted outcomes based on pretreatment ADC values. Overall, the studies that looked at prognosis or treatment response in LC/HPC found a positive correlation between pretreatment ADC values in larynx/hypopharynx and favorable outcomes.

CONCLUSION

DWI aids significantly in the LC/HPC diagnosis. However, further research is needed to establish DWI's reliability in predicting prognosis and treatment response in patients with LC/HPC.

Can initial apparent diffusion coefficient and tumour volume predict future metastases in treatment-naive patients with laryngeal squamous cell carcinoma

Purpose

To evaluate the predictive capability of the apparent diffusion coefficient (ADC) at initial diagnosis in treatment-naive patients with laryngeal squamous cell carcinoma (LSCC) for the development of future metastases.

Material and methods

Magnetic resonance images of patients with pathologically proven non-metastatic, treatmentnaive LSCC were retrospectively evaluated. Follow-up positron emission tomography scans were assessed for the scanning of metastases.

Results

A total of 37 patients (32 males and 5 females) with a mean age of 62.8 ± 8.9 years were enrolled. Mean tumour volume and ADC were 4.8 ± 62 cm3 and 0.72 ± 0.51 × 10-3 mm2/s, respectively. Six local and 8 distant metastases were detected in a mean follow-up period of 17.5 ± 10.2 months. A significant association between ADC and the presence distant metastases (p = 0.046) and local metastases (p = 0.042) was found. The difference in mean ADC values between future metastatic and non-metastatic initial tumours was significant (p = 0.017).

Conclusions

Pre-treatment ADC values and volume of the initial tumour might provide early information about the development of future metastases in patients with LSCC in this series.

Comparing three-dimensional and two-dimensional deep-learning, radiomics, and fusion models for predicting occult lymph node metastasis in laryngeal squamous cell carcinoma based on CT imaging: a multicentre, retrospective, diagnostic study

Background

The occult lymph node metastasis (LNM) of laryngeal squamous cell carcinoma (LSCC) affects the treatment and prognosis of patients. This study aimed to comprehensively compare the performance of the three-dimensional and two-dimensional deep learning models, radiomics model, and the fusion models for predicting occult LNM in LSCC.

Methods

In this retrospective diagnostic study, a total of 553 patients with clinical N0 stage LSCC, who underwent surgical treatment without distant metastasis and multiple primary cancers, were consecutively enrolled from four Chinese medical centres between January 01, 2016 and December 30, 2020. The participant data were manually retrieved from medical records, imaging databases, and pathology reports. The study cohort was divided into a training set (n = 300), an internal test set (n = 89), and two external test sets (n = 120 and 44, respectively). The three-dimensional deep learning (3D DL), two-dimensional deep learning (2D DL), and radiomics model were developed using CT images of the primary tumor. The clinical model was constructed based on clinical and radiological features. Two fusion strategies were utilized to develop the fusion model: the feature-based DLRad_FB model and the decision-based DLRad_DB model. The discriminative ability and correlation of 3D DL, 2D DL and radiomics features were analysed comprehensively. The performances of the predictive models were evaluated based on the pathological diagnosis.

Findings

The 3D DL features had superior discriminative ability and lower internal redundancy compared to 2D DL and radiomics features. The DLRad_DB model achieved the highest AUC (0.89-0.90) among all the study sets, significantly outperforming the clinical model (AUC = 0.73-0.78, P = 0.0001-0.042, Delong test). Compared to the DLRad_DB model, the AUC values for the DLRad_FB, 3D DL, 2D DL, and radiomics models were 0.82-0.84 (P = 0.025-0.46), 0.86-0.89 (P = 0.75-0.97), 0.83-0.86 (P = 0.029-0.66), and 0.79-0.82 (P = 0.0072-0.10), respectively in the study sets. Additionally, the DLRad_DB model exhibited the best sensitivity (82-88%) and specificity (79-85%) in the test sets.

Interpretation

The decision-based fusion model DLRad_DB, which combines 3D DL, 2D DL, radiomics, and clinical data, can be utilized to predict occult LNM in LSCC. This has the potential to minimize unnecessary lymph node dissection and prophylactic radiotherapy in patients with cN0 disease.

Funding

National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.

A Combined Model Integrating Radiomics and Deep Learning Based on Contrast-Enhanced CT for Preoperative Staging of Laryngeal Carcinoma

RATIONALE AND OBJECTIVES

Accurate staging of laryngeal carcinoma can inform appropriate treatment decision-making. We developed a radiomics model, a deep learning (DL) model, and a combined model (incorporating radiomics features and DL features) based on the venous-phase CT images and explored the performance of these models in stratifying patients with laryngeal carcinoma into stage I-II and stage III-IV, and also compared these models with radiologists.

MATERIALS AND METHODS

Three hundreds and nineteen patients with pathologically confirmed laryngeal carcinoma were randomly divided into a training set (n = 223) and a test set (n = 96). In the training set, the radiomics features with inter- and intraclass correlation coefficients (ICCs)> 0.75 were screened by Spearman correlation analysis and recursive feature elimination (RFE); then support vector machine (SVM) classifier was applied to develop the radiomics model. The DL model was built using ResNet 18 by the cropped 2D regions of interest (ROIs) in the maximum tumor ROI slices and the last fully connected layer of this network served as the DL feature extractor. Finally, a combined model was developed by pooling the radiomics features and extracted DL features to predict the staging.

RESULTS

The area under the curves (AUCs) for radiomics model, DL model, and combined model in the test set were 0.704 (95% confidence interval [CI]: 0.588-0.820), 0.724 (95% CI: 0.613-0.835), and 0.849 (95% CI: 0.755-0.943), respectively. The combined model outperformed the radiomics model and the DL model in discriminating stage I-II from stage III-IV (p = 0.031 and p = 0.020, respectively). Only the combined model performed significantly better than radiologists (p < 0.050 for both).

CONCLUSION

The combined model can help tailor the therapeutic strategy for laryngeal carcinoma patients by enabling more accurate preoperative staging.

Advances in Image-Based Artificial Intelligence in Otorhinolaryngology-Head and Neck Surgery: A Systematic Review

OBJECTIVE

To update the literature and provide a systematic review of image-based artificial intelligence (AI) applications in otolaryngology, highlight its advances, and propose future challenges.

DATA SOURCES

Web of Science, Embase, PubMed, and Cochrane Library.

REVIEW METHODS

Studies written in English, published between January 2020 and December 2022. Two independent authors screened the search results, extracted data, and assessed studies.

RESULTS

Overall, 686 studies were identified. After screening titles and abstracts, 325 full-text studies were assessed for eligibility, and 78 studies were included in this systematic review. The studies originated from 16 countries. Among these countries, the top 3 were China (n = 29), Korea (n = 8), the United States, and Japan (n = 7 each). The most common area was otology (n = 35), followed by rhinology (n = 20), pharyngology (n = 18), and head and neck surgery (n = 5). Most applications of AI in otology, rhinology, pharyngology, and head and neck surgery mainly included chronic otitis media (n = 9), nasal polyps (n = 4), laryngeal cancer (n = 12), and head and neck squamous cell carcinoma (n = 3), respectively. The overall performance of AI in accuracy, the area under the curve, sensitivity, and specificity were 88.39 ± 9.78%, 91.91 ± 6.70%, 86.93 ± 11.59%, and 88.62 ± 14.03%, respectively.

CONCLUSION

This state-of-the-art review aimed to highlight the increasing applications of image-based AI in otorhinolaryngology head and neck surgery. The following steps will entail multicentre collaboration to ensure data reliability, ongoing optimization of AI algorithms, and integration into real-world clinical practice. Future studies should consider 3-dimensional (3D)-based AI, such as 3D surgical AI.

Current State of Artificial Intelligence in Clinical Applications for Head and Neck MR Imaging

Due primarily to the excellent soft tissue contrast depictions provided by MRI, the widespread application of head and neck MRI in clinical practice serves to assess various diseases. Artificial intelligence (AI)-based methodologies, particularly deep learning analyses using convolutional neural networks, have recently gained global recognition and have been extensively investigated in clinical research for their applicability across a range of categories within medical imaging, including head and neck MRI. Analytical approaches using AI have shown potential for addressing the clinical limitations associated with head and neck MRI. In this review, we focus primarily on the technical advancements in deep-learning-based methodologies and their clinical utility within the field of head and neck MRI, encompassing aspects such as image acquisition and reconstruction, lesion segmentation, disease classification and diagnosis, and prognostic prediction for patients presenting with head and neck diseases. We then discuss the limitations of current deep-learning-based approaches and offer insights regarding future challenges in this field.