Locoregional Recurrence Prediction Using a Deep Neural Network of Radiological and Radiotherapy Images

Diagnostic performance of a deep-learning model using 18F-FDG PET/CT for evaluating recurrence after radiation therapy in patients with lung cancer

OBJECTIVE

We developed a deep learning model for distinguishing radiation therapy (RT)-related changes and tumour recurrence in patients with lung cancer who underwent RT, and evaluated its performance.

METHODS

We retrospectively recruited 308 patients with lung cancer with RT-related changes observed on 18F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET/CT) performed after RT. Patients were labelled as positive or negative for tumour recurrence through histologic diagnosis or clinical follow-up after 18F-FDG PET/CT. A two-dimensional (2D) slice-based convolutional neural network (CNN) model was created with a total of 3329 slices as input, and performance was evaluated with five independent test sets.

RESULTS

For the five independent test sets, the area under the curve (AUC) of the receiver operating characteristic curve, sensitivity, and specificity were in the range of 0.98-0.99, 95-98%, and 87-95%, respectively. The region determined by the model was confirmed as an actual recurred tumour through the explainable artificial intelligence (AI) using gradient-weighted class activation mapping (Grad-CAM).

CONCLUSION

The 2D slice-based CNN model using 18F-FDG PET imaging was able to distinguish well between RT-related changes and tumour recurrence in patients with lung cancer.

Methodological evaluation of original articles on radiomics and machine learning for outcome prediction based on positron emission tomography (PET)

AIM

Despite a vast number of articles on radiomics and machine learning in positron emission tomography (PET) imaging, clinical applicability remains limited, partly owing to poor methodological quality. We therefore systematically investigated the methodology described in publications on radiomics and machine learning for PET-based outcome prediction.

METHODS

A systematic search for original articles was run on PubMed. All articles were rated according to 17 criteria proposed by the authors. Criteria with >2 rating categories were binarized into "adequate" or "inadequate". The association between the number of "adequate" criteria per article and the date of publication was examined.

RESULTS

One hundred articles were identified (published between 07/2017 and 09/2023). The median proportion of articles per criterion that were rated "adequate" was 65% (range: 23-98%). Nineteen articles (19%) mentioned neither a test cohort nor cross-validation to separate training from testing. The median number of criteria with an "adequate" rating per article was 12.5 out of 17 (range, 4-17), and this did not increase with later dates of publication (Spearman's rho, 0.094; p = 0.35). In 22 articles (22%), less than half of the items were rated "adequate". Only 8% of articles published the source code, and 10% made the dataset openly available.

CONCLUSION

Among the articles investigated, methodological weaknesses have been identified, and the degree of compliance with recommendations on methodological quality and reporting shows potential for improvement. Better adherence to established guidelines could increase the clinical significance of radiomics and machine learning for PET-based outcome prediction and finally lead to the widespread use in routine clinical practice.

Machine Learning and Nomogram Prognostic Modeling for 2-Year Head and Neck Cancer-Specific Survival Using Electronic Health Record Data: A Multisite Study

PURPOSE

There is limited knowledge of the prediction of 2-year cancer-specific survival (CSS) in the head and neck cancer (HNC) population. The aim of this study is to develop and validate machine learning models and a nomogram for the prediction of 2-year CSS in patients with HNC using real-world data collected by major teaching and tertiary referral hospitals in New South Wales (NSW), Australia.

MATERIALS AND METHODS

Data collected in oncology information systems at multiple NSW Cancer Centres were extracted for 2,953 eligible adults diagnosed between 2000 and 2017 with squamous cell carcinoma of the head and neck. Death data were sourced from the National Death Index using record linkage. Machine learning and Cox regression/nomogram models were developed and internally validated in Python and R, respectively.

RESULTS

Machine learning models demonstrated highest performance (C-index) in the larynx and nasopharynx cohorts (0.82), followed by the oropharynx (0.79) and the hypopharynx and oral cavity cohorts (0.73). In the whole HNC population, C-indexes of 0.79 and 0.70 and Brier scores of 0.10 and 0.27 were reported for the machine learning and nomogram model, respectively. Cox regression analysis identified age, T and N classification, and time-corrected biologic equivalent dose in two gray fractions as independent prognostic factors for 2-year CSS. N classification was the most important feature used for prediction in the machine learning model followed by age.

CONCLUSION

Machine learning and nomogram analysis predicted 2-year CSS with high performance using routinely collected and complete clinical information extracted from oncology information systems. These models function as visual decision-making tools to guide radiotherapy treatment decisions and provide insight into the prediction of survival outcomes in patients with HNC.

Prediction of Incomplete Response of Primary Tumour Based on Clinical and Radiomics Features in Inoperable Head and Neck Cancers after Definitive Treatment

Radical treatment of patients diagnosed with inoperable and locally advanced head and neck cancers (LAHNC) is still a challenge for clinicians. Prediction of incomplete response (IR) of primary tumour would be of value to the treatment optimization for patients with LAHNC. Aim of this study was to develop and evaluate models based on clinical and radiomics features for prediction of IR in patients diagnosed with LAHNC and treated with definitive chemoradiation or radiotherapy. Clinical and imaging data of 290 patients were included into this retrospective study. Clinical model was built based on tumour and patient related features. Radiomics features were extracted based on imaging data, consisting of contrast- and non-contrast-enhanced pre-treatment CT images, obtained in process of diagnosis and radiotherapy planning. Performance of clinical and combined models were evaluated with area under the ROC curve (AUROC). Classification performance was evaluated using 5-fold cross validation. Model based on selected clinical features including ECOG performance, tumour stage T3/4, primary site: oral cavity and tumour volume were significantly predictive for IR, with AUROC of 0.78. Combining clinical and radiomics features did not improve model’s performance, achieving AUROC 0.77 and 0.68 for non-contrast enhanced and contrast-enhanced images respectively. The model based on clinical features showed good performance in IR prediction. Combined model performance suggests that real-world imaging data might not yet be ready for use in predictive models.