MOSBY enables multi-omic inference and spatial biomarker discovery from whole slide images.

The utility of deep neural nets has been demonstrated for mapping hematoxylin-and-eosin (H&E) stained image features to expression of individual genes. However, these models have not been employed to discover clinically relevant spatial biomarkers. Here we develop MOSBY (Multi-Omic translation of whole slide images for Spatial Biomarker discoverY) that leverages contrastive self-supervised pretraining to extract improved H&E whole slide images features, learns a mapping between image and bulk omic profiles (RNA, DNA, and protein), and utilizes tile-level information to discover spatial biomarkers. We validate MOSBY gene and gene set predictions with spatial transcriptomic and serially-sectioned CD8 IHC image data. We demonstrate that MOSBY-inferred colocalization features have survival-predictive power orthogonal to gene expression, and enable concordance indices highly competitive with survival-trained multimodal networks. We identify and validate (1) an ER stress-associated colocalization feature as a chemotherapy-specific risk factor in lung adenocarcinoma, and (2) the colocalization of T effector cell vs cysteine signatures as a negative prognostic factor in multiple cancer indications. The discovery of clinically relevant biologically interpretable spatial biomarkers showcases the utility of the model in unraveling novel insights in cancer biology as well as informing clinical decision-making.

Palliative Care Clinicians' Views on Metrics for Successful Specialist Palliative Care Delivery in the ICU.

CONTEXT: A quarter of palliative care (PC) clinicians' consultations are now requested from the intensive care unit (ICU). Despite this high usage, a standardized set of quality metrics for PC delivery in the ICU does not exist. OBJECTIVES: To explore PC clinicians' views on how to best measure quality of care delivery in their role as a consultant in the ICU setting. METHODS: Secondary analysis of a parent dataset consisting of qualitative data from semi-structured interviews exploring ways to optimize PC clinicians' role in the ICU. Nineteen participants were recruited across five academic medical centers in the US. Participants included PC physicians (n = 14), nurse practitioners (n = 2), and social workers (n = 3). Thematic analysis with an inductive approach was used to generate themes. RESULTS: We identified two central themes: difficulties in measuring PC quality in the ICU (theme 1) and tension between the role of PC and metrics (theme 2). Theme 1 had two subthemes related to logistical challenges in measuring outcomes and PC clinicians' preference for metrics that incorporate subjective feedback from patients, family members, and the primary ICU team. Theme 2 described how PC clinicians often felt a disconnect between the goal of meeting a metric and their goals in delivering high-quality clinical care. CONCLUSION: Our findings provide insight into PC clinician perspectives on quality metrics and identify major barriers that need to be addressed to successfully implement quality measurement in the ICU setting.

Analysis of cellularity in H&E-stained rat bone marrow tissue via deep learning.

Our objective was to develop an automated deep-learning-based method to evaluate cellularity in rat bone marrow hematoxylin and eosin whole slide images for preclinical safety assessment. We trained a shallow CNN for segmenting marrow, 2 Mask R-CNN models for segmenting megakaryocytes (MKCs), and small hematopoietic cells (SHCs), and a SegNet model for segmenting red blood cells. We incorporated the models into a pipeline that identifies and counts MKCs and SHCs in rat bone marrow. We compared cell segmentation and counts that our method generated to those that pathologists generated on 10 slides with a range of cell depletion levels from 10 studies. For SHCs, we compared cell counts that our method generated to counts generated by Cellpose and Stardist. The median Dice and object Dice scores for MKCs using our method vs pathologist consensus and the inter- and intra-pathologist variation were comparable, with overlapping first-third quartile ranges. For SHCs, the median scores were close, with first-third quartile ranges partially overlapping intra-pathologist variation. For SHCs, in comparison to Cellpose and Stardist, counts from our method were closer to pathologist counts, with a smaller 95% limits of agreement range. The performance of the bone marrow analysis pipeline supports its incorporation into routine use as an aid for hematotoxicity assessment by pathologists. The pipeline could help expedite hematotoxicity assessment in preclinical studies and consequently could expedite drug development. The method may enable meta-analysis of rat bone marrow characteristics from future and historical whole slide images and may generate new biological insights from cross-study comparisons.

Evaluating a couple communication skills training (CCST) intervention for advanced cancer: study protocol for a randomized controlled trial.

BACKGROUND: For patients and their intimate partners, advanced cancer poses significant challenges that can negatively impact both individuals and their relationship. Prior studies have found evidence that couple-based communication skills interventions can to be beneficial for patients and partners. However, these studies have been limited by reliance on in-person treatment delivery and have not targeted couples at high risk for poor outcomes. This study tests the efficacy of a Couples Communication Skills Training (CCST) intervention delivered via videoconference for couples reporting high levels of holding back from discussing cancer-related concerns, a variable associated with poorer psychological and relationship functioning. METHODS: This RCT is designed to evaluate the efficacy of CCST in improving patient and partner relationship functioning (primary outcome). Secondary outcomes include patient and partner psychological functioning and patient symptoms and health care use. We also examine the role of objective and self-reported communication behaviors as mediators of treatment effects. Two hundred thirty patients with advanced lung, gastrointestinal, genitourinary, and breast cancer and their partners will be randomized to CCST or an education control intervention. Participants in both conditions complete self-reported outcome measures at baseline, mid-treatment, post-treatment, and 3 months post-treatment. Objective measures of communication are derived from video-recorded couple conversations collected at baseline and post-treatment. An implementation-related process evaluation (assessing implementation outcomes and potential barriers to/facilitators of implementation) will be conducted to inform future efforts to implement CCST in real-world settings. DISCUSSION: This trial can yield important new knowledge about effective ways to improve patient and partner adjustment to advanced cancer. TRIAL REGISTRATION: This study trial is registered at clinicaltrials.gov (Trial # NCT04590885); registration date: October 19, 2020.

Immune checkpoints and cancer in the immunogenomics era.

Immune checkpoints have been the subject of a wave of new studies. Among these checkpoints are tytotoxic T-lymphocyte-associated antigen 4, checkpoints programmed death-1 and programmed death-ligand 1; their blockades have been approved by the Food and Drug Administration for therapy of melanoma and other types of cancers. Immunogenomics, which combines the latest nucleic acid sequencing strategy with immunotherapy, provides precise information about genomic alterations (e.g. mutations) and enables a paradigm shift of immune checkpoint therapy from tumor types to molecular signatures. Studying these critical checkpoints in relation to genomic mutations and neoantigens has produced groundbreaking results. This article examines these studies and delves into the relationships between immune checkpoint blockade and tumors harboring certain genomic mutations. Moreover, this article reviews recent studies on resistance to immune checkpoint therapy.