Search

Immunotherapy is used to treat almost all patients with advanced non-small cell lung cancer (NSCLC); however, identifying robust predictive biomarkers remains challenging. Here we show the predictive capacity of integrating medical imaging, histopathologic and genomic features to predict immunotherapy response using a cohort of 247 patients with advanced NSCLC with multimodal baseline data obtained during diagnostic clinical workup, including computed tomography scan images, digitized programmed death ligand-1 immunohistochemistry slides and known outcomes to immunotherapy. Using domain expert annotations, we developed a computational workflow to extract patient-level features and used a machine-learning approach to integrate multimodal features into a risk prediction model. Our multimodal model (area under the curve (AUC) = 0.80, 95% confidence interval (CI) 0.74–0.86) outperformed unimodal measures, including tumor mutational burden (AUC = 0.61, 95% CI 0.52–0.70) and programmed death ligand-1 immunohistochemistry score (AUC = 0.73, 95% CI 0.65–0.81). Our study therefore provides a quantitative rationale for using multimodal features to improve prediction of immunotherapy response in patients with NSCLC using expert-guided machine learning.

To compare four diffusion-weighted imaging (DWI) sequences for image quality, rectal contour, and lesion conspicuity, and to assess the difference in their signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), and apparent diffusion coefficient (ADC).In this retrospective study of 36 consecutive patients who underwent 3.0 T rectal MRI from January-June 2020, DWI was performed with single-shot echo planar imaging (ss-EPI) (b800 s/mmFor both readers, MUSE b800 scored significantly higher for image quality, rectal contour, and lesion conspicuity compared to ss-EPI; MUSE b800 also scored significantly higher for image quality and rectal contour compared to all other sequences. Lesion conspicuity was equally superior for MUSE b800 and MUSE b1500 compared to the other two sequences. There was good to excellent inter-reader agreement for all qualitative features (к = 0.72-0.88). MUSE b800 had the highest SNR; MUSE b1500 had the highest CNR. A significant difference in ADC was observed between ss-EPI compared to the other sequences (p 0.001) and between MUSE b800 and FOCUS. No significant difference in ADC was found between MUSE b1500 and FOCUS b1500.MUSE b800 improved image quality over ss-EPI and both MUSE b800 and b1500 showed better tumor conspicuity compared to conventional ss-EPI.

Patients with high-grade serous ovarian cancer suffer poor prognosis and variable response to treatment. Known prognostic factors for this disease include homologous recombination deficiency status, age, pathological stage and residual disease status after debulking surgery. Recent work has highlighted important prognostic information captured in computed tomography and histopathological specimens, which can be exploited through machine learning. However, little is known about the capacity of combining features from these disparate sources to improve prediction of treatment response. Here, we assembled a multimodal dataset of 444 patients with primarily late-stage high-grade serous ovarian cancer and discovered quantitative features, such as tumor nuclear size on staining with hematoxylin and eosin and omental texture on contrast-enhanced computed tomography, associated with prognosis. We found that these features contributed complementary prognostic information relative to one another and clinicogenomic features. By fusing histopathological, radiologic and clinicogenomic machine-learning models, we demonstrate a promising path toward improved risk stratification of patients with cancer through multimodal data integration.