Sarah A. Mattonen

Surgery is the primary treatment for early-stage lung cancer. Adjuvant therapy is offered to patients who are at a high risk of recurrence, however, determining the patients that would benefit from additional therapy is often difficult. In this study, we aimed to develop a clinical decision support system (CDSS) for post-surgery lung cancer prognostication integrating a multi-modality deep learning model (DLM). Pre-operative medical images and clinical, surgical, and pathological information were fed into an externally validated DLM. A CDSS was then developed to display the patient information and DLM results for potential clinical use. Four oncologists evaluated each patient’s recurrence probability, their confidence level, and their post-surgery recommendations both with and without the DLM information. The CDSS DLM information demonstrated the potential to improve user prediction performance and confidence. This exploratory study is the first to integrate a multi-modality DLM for prognostication with a CDSS, as well as the first study of clinician attitudes towards CDSSs for lung cancer.

Background: Patients with early‐stage non‐small cell lung cancer (NSCLC) typically receive surgery as their primary form of treatment. However, studies have shown that a high proportion of these patients will experience a recurrence after their resection, leading to an increased risk of death. Cancer staging is currently the gold standard for establishing a patient's prognosis and can help clinicians determine patients who may benefit from additional therapy. However, medical images which are used to help determine the cancer stage, have been shown to hold unutilized prognostic information that can augment clinical data and better identify high‐risk NSCLC patients. There remains an unmet need for models to incorporate clinical, pathological, surgical, and imaging information, and extend beyond the current staging system to assist clinicians in identifying patients who could benefit from additional therapy immediately after surgery. Purpose: We aimed to determine whether a deep learning model (DLM) integrating FDG PET and CT imaging from the thoracic cavity along with clinical, surgical, and pathological information can predict NSCLC recurrence‐free survival (RFS) and stratify patients into risk groups better than conventional staging. Materials and methods: Surgically resected NSCLC patients enrolled between 2009 and 2018 were retrospectively analyzed from two academic institutions (local institution: 305 patients; external validation: 195 patients). The thoracic cavity (including the lungs, mediastinum, pleural interfaces, and thoracic vertebrae) was delineated on the preoperative FDG PET and CT images and combined with each patient's clinical, surgical, and pathological information. Using the local cohort of patients, a multi‐modal DLM using these features was built in a training cohort ( n = 225), tuned on a validation cohort ( n = 45), and evaluated on testing ( n = 35) and external validation ( n = 195) cohorts to predict RFS and stratify patients into risk groups. The area under the curve (AUC), Kaplan–Meier curves, and log‐rank test were used to assess the prognostic value of the model. The DLM's stratification performance was compared to the conventional staging stratification. Results: The multi‐modal DLM incorporating imaging, pathological, surgical, and clinical data predicted RFS in the testing cohort (AUC = 0.78 [95% CI:0.63–0.94]) and external validation cohort (AUC = 0.66 [95% CI:0.58–0.73]). The DLM significantly stratified patients into high, medium, and low‐risk groups of RFS in both the testing and external validation cohorts (multivariable log‐rank p < 0.001) and outperformed conventional staging. Conventional staging was unable to stratify patients into three distinct risk groups of RFS (testing: p = 0.94; external validation: p = 0.38). Lastly, the DLM displayed the ability to further stratify patients significantly into sub‐risk groups within each stage in the testing (stage I: p = 0.02, stage II: p = 0.03) and external validation (stage I: p = 0.05, stage II: p = 0.03) cohorts. Conclusion: This is the first study to use multi‐modality imaging along with clinical, surgical, and pathological data to predict RFS of NSCLC patients after surgery. The multi‐modal DLM better stratified patients into risk groups of poor outcomes when compared to conventional staging and further stratified patients within each staging classification. This model has the potential to assist clinicians in better identifying patients that may benefit from additional therapy.

Evidence is accumulating in favour of using stereotactic ablative body radiotherapy (SABR) to treat multiple cancer lesions in the lung. Multi-lesion lung SABR plans are complex and require significant resources to create. In this work, we propose a novel two-stage latent transformer framework (LDFormer) for dose prediction of lung SABR plans with varying numbers of lesions. In the first stage, patient anatomical information and the dose distribution are encoded into a latent space. In the second stage, a transformer learns to predict the dose latent from the anatomical latents. Causal attention is modified to adapt to different numbers of lesions. LDFormer outperforms a state-of-the-art generative adversarial network on dose conformality in and around lesions, and the performance gap widens when considering overlapping lesions. LDFormer generates predictions of 3-D dose distributions in under 30s on consumer hardware, and has the potential to assist physicians with clinical decision making, reduce resource costs, and accelerate treatment planning.

Radiomics studies, using features extracted from medical images, are often used for outcome prediction in oncology. Studies frequently use physical phantoms to assess radiomic feature reliability, however, few studies have utilized computer-generated phantoms to assess the impact of image acquisition parameters. Additionally, studies have introduced deep learning approaches to generate CT-realistic textures on computer-generated phantoms. Therefore, we aimed to assess the feasibility of using 4D extended cardiac-torso (XCAT) phantoms with generated realistic textures using a deep learning network adapted from a previous study to analyze the impact of slice thickness on radiomic features. Our dataset consisted of 70 organ maps (training: n=50, validation: n=20) generated from CT images of lung cancer patients. These were used as input for a dual-discriminator conditional-generative adversarial network to synthesize realistic textures in the organ maps. The validated network was used to generate realistic-textured XCAT phantoms. The phantoms were reconstructed using three different slice thicknesses. Pyradiomics was used to extract radiomics features from the tumor of each XCAT phantom. The intraclass correlation coefficient was used to assess the feature reliability for each acquisition protocol. Qualitatively, the generated XCAT phantoms had similar textures to that of the real CT images. The features demonstrated excellent reliability between each acquisition protocol for most feature types with GLCM texture features only showing moderate reliability, however, this may be due to the small sample size of the study. This study showed the feasibility of using generated realistic-textured XCAT phantoms to study the impact of acquisition protocols on radiomic features.

Objectives: In those undergoing treatment for head and neck cancer (HNC), sarcopenia is a strong prognostic factor for outcomes and mortality. This review identified working definitions and methods used to objectively assess sarcopenia in HNC. Method: The scoping review was performed in accordance with Arksey and O’Malley’s five-stage methodology and the Joanna Briggs Institute guidelines. Information sources: Eligible studies were identified using MEDLINE, Embase, Scopus, Cochrane Library, and CINAHL databases. Study selection: Inclusion criteria represented studies of adult HNC patients in which sarcopenia was listed as an outcome, full-text articles written in English, and empirical research studies with a quantitative design. Data extraction: Eligible studies were assessed using a proprietary data extraction form. General information, article details and characteristics, and details related to the concept of the scoping review were extracted in an iterative process. Results: Seventy-six studies published internationally from 2016 to 2021 on sarcopenia in HNC were included. The majority were retrospective (n = 56; 74%) and the prevalence of sarcopenia ranged from 3.8% to 78.7%. Approximately two-thirds of studies used computed tomography (CT) to assess sarcopenia. Skeletal muscle index (SMI) at the third lumbar vertebra (L3) (n = 53; 70%) was the most prevalent metric used to identify sarcopenia, followed by SMI at the third cervical vertebra (C3) (n = 4; 5%). Conclusions: Currently, the most effective strategy to assess sarcopenia in HNC depends on several factors, including access to resources, patient and treatment characteristics, and the prognostic significance of outcomes used to represent sarcopenia. Skeletal muscle mass (SMM) measured at C3 may represent a practical, precise, and cost-effective biomarker for the detection of sarcopenia. However, combining SMM measurements at C3 with other sarcopenic parameters—including muscle strength and physical performance–may provide a more accurate risk profile for sarcopenia assessment and allow for a greater understanding of this condition in HNC.

PurposeWe developed a model integrating multimodal quantitative imaging features from tumor and nontumor regions, qualitative features, and clinical data to improve the risk stratification of patients with resectable non-small cell lung cancer (NSCLC).ApproachWe retrospectively analyzed 135 patients [mean age, 69 years (43 to 87, range); 100 male patients and 35 female patients] with NSCLC who underwent upfront surgical resection between 2008 and 2012. The tumor and peritumoral regions on both preoperative CT and FDG PET-CT and the vertebral bodies L3 to L5 on FDG PET were segmented to assess the tumor and bone marrow uptake, respectively. Radiomic features were extracted and combined with clinical and CT qualitative features. A random survival forest model was developed using the top-performing features to predict the time to recurrence/progression in the training cohort (n = 101), validated in the testing cohort (n = 34) using the concordance, and compared with a stage-only model. Patients were stratified into high- and low-risks of recurrence/progression using Kaplan–Meier analysis.ResultsThe model, consisting of stage, three wavelet texture features, and three wavelet first-order features, achieved a concordance of 0.78 and 0.76 in the training and testing cohorts, respectively, significantly outperforming the baseline stage-only model results of 0.67 (p < 0.005) and 0.60 (p = 0.008), respectively. Patients at high- and low-risks of recurrence/progression were significantly stratified in both the training (p < 0.005) and the testing (p = 0.03) cohorts.ConclusionsOur radiomic model, consisting of stage and tumor, peritumoral, and bone marrow features from CT and FDG PET-CT significantly stratified patients into low- and high-risk of recurrence/progression.

Diffuse intrinsic pontine gliomas (DIPGs) are lethal pediatric brain tumors. Presently, MRI is the mainstay of disease diagnosis and surveillance. We identify clinically significant computational features from MRI and create a prognostic machine learning model. We isolated tumor volumes of T1-post-contrast (T1) and T2-weighted (T2) MRIs from 177 treatment-naïve DIPG patients from an international cohort for model training and testing. The Quantitative Image Feature Pipeline and PyRadiomics was used for feature extraction. Ten-fold cross-validation of least absolute shrinkage and selection operator Cox regression selected optimal features to predict overall survival in the training dataset and tested in the independent testing dataset. We analyzed model performance using clinical variables (age at diagnosis and sex) only, radiomics only, and radiomics plus clinical variables. All selected features were intensity and texture-based on the wavelet-filtered images (3 T1 gray-level co-occurrence matrix (GLCM) texture features, T2 GLCM texture feature, and T2 first-order mean). This multivariable Cox model demonstrated a concordance of 0.68 (95% CI: 0.61–0.74) in the training dataset, significantly outperforming the clinical-only model (C = 0.57 [95% CI: 0.49–0.64]). Adding clinical features to radiomics slightly improved performance (C = 0.70 [95% CI: 0.64–0.77]). The combined radiomics and clinical model was validated in the independent testing dataset (C = 0.59 [95% CI: 0.51–0.67], Noether’s test P = .02). In this international study, we demonstrate the use of radiomic signatures to create a machine learning model for DIPG prognostication. Standardized, quantitative approaches that objectively measure DIPG changes, including computational MRI evaluation, could offer new approaches to assessing tumor phenotype and serve a future role for optimizing clinical trial eligibility and tumor surveillance.