Association of artificial intelligence-powered and manual quantification of programmed death-ligand 1 (PD-L1) expression with outcomes in patients treated with nivolumab ± ipilimumab.

Assessment of programmed death ligand 1 (PD-L1) expression by immunohistochemistry (IHC) has emerged as an important predictive biomarker across multiple tumor types. However, manual quantitation of PD-L1 positivity can be difficult and leads to substantial inter-observer variability. Although the development of artificial intelligence (AI) algorithms may mitigate some of the challenges associated with manual assessment and improve the accuracy of PD-L1 expression scoring, use of AI-based approaches to oncology biomarker scoring and drug development has been sparse, primarily due to the lack of large-scale clinical validation studies across multiple cohorts and tumor types. We developed AI-powered algorithms to evaluate PD-L1 expression on tumor cells by IHC and compared it with manual IHC scoring in urothelial carcinoma, non-small cell lung cancer, melanoma, and squamous cell carcinoma of the head and neck (prospectively determined during the phase II and III CheckMate clinical trials). 1,746 slides were retrospectively analyzed, the largest investigation of digital pathology algorithms on clinical trial datasets performed to date. AI-powered quantification of PD-L1 expression on tumor cells identified more PD-L1-positive samples compared with manual scoring at cutoffs of ≥1% and ≥5% in most tumor types. Additionally, similar improvements in response and survival were observed in patients identified as PD-L1-positive compared with PD-L1-negative using both AI-powered and manual methods, while improved associations with survival were observed in patients with certain tumor types identified as PD-L1-positive using AI-powered scoring only. Our study demonstrates the potential for implementation of digital pathology-based methods in future clinical practice to identify more patients who would benefit from treatment with immuno-oncology therapy compared with current guidelines using manual assessment.

Digital pathology and artificial intelligence in translational medicine and clinical practice.

Traditional pathology approaches have played an integral role in the delivery of diagnosis, semi-quantitative or qualitative assessment of protein expression, and classification of disease. Technological advances and the increased focus on precision medicine have recently paved the way for the development of digital pathology-based approaches for quantitative pathologic assessments, namely whole slide imaging and artificial intelligence (AI)-based solutions, allowing us to explore and extract information beyond human visual perception. Within the field of immuno-oncology, the application of such methodologies in drug development and translational research have created invaluable opportunities for deciphering complex pathophysiology and the discovery of novel biomarkers and drug targets. With an increasing number of treatment options available for any given disease, practitioners face the growing challenge of selecting the most appropriate treatment for each patient. The ever-increasing utilization of AI-based approaches substantially expands our understanding of the tumor microenvironment, with digital approaches to patient stratification and selection for diagnostic assays supporting the identification of the optimal treatment regimen based on patient profiles. This review provides an overview of the opportunities and limitations around implementing AI-based methods in biomarker discovery and patient selection and discusses how advances in digital pathology and AI should be considered in the current landscape of translational medicine, touching on challenges this technology may face if adopted in clinical settings. The traditional role of pathologists in delivering accurate diagnoses or assessing biomarkers for companion diagnostics may be enhanced in precision, reproducibility, and scale by AI-powered analysis tools.

The development of a home-based therapeutic platform for multiple myeloma.

BACKGROUND: Multiple Myeloma (MM) accounts for 1-2% of all malignancies but is the second most common hematological malignancy. It is characterized by a proliferation of malignant plasma cells. The treatment paradigm of MM in Australia is traditionally hospital-based, complex, and costly. While MM comprises 1-2% of cancer diagnoses, it appears in the top 10 cancer diagnoses requiring hospital admission. The cumulative time spent receiving treatment is a significant burden for patients. The ability to receive treatment at home and maximize time away from hospital-based settings is a key preference for patients receiving anticancer therapies over a prolonged period of time. METHODS: The Peter MacCallum Cancer Centre and Royal Melbourne Hospital's combined Clinical Hematology Unit has collaborated with their Hospital in the Home departments to develop several innovative programs to address this. RESULTS: We describe our current active programs and potential developments in home-based MM therapy. CONCLUSION: We have enabled large numbers of patients to receive complex therapies in their own home and the COVID-19 pandemic has increased the pace of the roll out without any compromise in safety. We anticipate that the next raft of immunotherapies will be able to transition into the @Home treatment setting in the coming years.

A Machine Learning Approach to Liver Histological Evaluation Predicts Clinically Significant Portal Hypertension in NASH Cirrhosis.

BACKGROUND AND AIMS: The hepatic venous pressure gradient (HVPG) is the standard for estimating portal pressure but requires expertise for interpretation. We hypothesized that HVPG could be extrapolated from liver histology using a machine learning (ML) algorithm. APPROACH AND RESULTS: Patients with NASH with compensated cirrhosis from a phase 2b trial were included. HVPG and biopsies from baseline and weeks 48 and 96 were reviewed centrally, and biopsies evaluated with a convolutional neural network (PathAI, Boston, MA). Using trichrome-stained biopsies in the training set (n = 130), an ML model was developed to recognize fibrosis patterns associated with HVPG, and the resultant ML HVPG score was validated in a held-out test set (n = 88). Associations between the ML HVPG score with measured HVPG and liver-related events, and performance of the ML HVPG score for clinically significant portal hypertension (CSPH) (HVPG ≥ 10 mm Hg), were determined. The ML-HVPG score was more strongly correlated with HVPG than hepatic collagen by morphometry (ρ = 0.47 vs. ρ = 0.28; P < 0.001). The ML HVPG score differentiated patients with normal (0-5 mm Hg) and elevated (5.5-9.5 mm Hg) HVPG and CSPH (median: 1.51 vs. 1.93 vs. 2.60; all P < 0.05). The areas under receiver operating characteristic curve (AUROCs) (95% CI) of the ML-HVPG score for CSPH were 0.85 (0.80, 0.90) and 0.76 (0.68, 0.85) in the training and test sets, respectively. Discrimination of the ML-HVPG score for CSPH improved with the addition of a ML parameter for nodularity, Enhanced Liver Fibrosis, platelets, aspartate aminotransferase (AST), and bilirubin (AUROC in test set: 0.85; 95% CI: 0.78, 0.92). Although baseline ML-HVPG score was not prognostic, changes were predictive of clinical events (HR: 2.13; 95% CI: 1.26, 3.59) and associated with hemodynamic response and fibrosis improvement. CONCLUSIONS: An ML model based on trichrome-stained liver biopsy slides can predict CSPH in patients with NASH with cirrhosis.

Hospital in the home-based management of acute diverticulitis: a safe and effective alternative to inpatient care.

BACKGROUND: The traditional approach to management of acute uncomplicated diverticulitis involves admission to hospital, antibiotic therapy, gut rest and monitoring for the development of complications. Despite evidence to suggest this can safely be performed in an outpatient setting, inpatient care remains standard practice in Australia potentially due to a variety of factors (van Dijk et al. 2018; Cirocchi et al. 2019). Hospital in the home (HIH) allows patients requiring complex care including intravenous antibiotics, intravenous fluids and complex pain relief to be managed at home. This study examined the safety and efficacy of HIH-based care for acute diverticulitis over a 16-year period. METHODOLOGY: A retrospective review of cases of acute diverticulitis managed under our HIH service from the period of 1st of January 2004 to 20th of October 2020 was completed. Baseline descriptive data relating to age, co-morbidities and severity of diverticulitis was collected. Details of medical treatment provided and subsequent complications were also collected. RESULTS: During the study period, 23 patients with acute diverticulitis were treated under the HIH unit. Among the study population, the median age was 60 (interquartile range 15) with a slight female predominance (n = 13, 56.5%). This represented the first presentation in 60.9% of patients. Average length of stay was 3.6 days (SD = 1.0) with no acute complications recorded in the study period. Two patients (8.7%) had further episodes of acute diverticulitis within 60 days. CONCLUSION: In this study, the lack of complications demonstrated indicates that HIH-based management of acute diverticulitis may be a viable and safe alternative to inpatient care.

Human-interpretable image features derived from densely mapped cancer pathology slides predict diverse molecular phenotypes.

Computational methods have made substantial progress in improving the accuracy and throughput of pathology workflows for diagnostic, prognostic, and genomic prediction. Still, lack of interpretability remains a significant barrier to clinical integration. We present an approach for predicting clinically-relevant molecular phenotypes from whole-slide histopathology images using human-interpretable image features (HIFs). Our method leverages >1.6 million annotations from board-certified pathologists across >5700 samples to train deep learning models for cell and tissue classification that can exhaustively map whole-slide images at two and four micron-resolution. Cell- and tissue-type model outputs are combined into 607 HIFs that quantify specific and biologically-relevant characteristics across five cancer types. We demonstrate that these HIFs correlate with well-known markers of the tumor microenvironment and can predict diverse molecular signatures (AUROC 0.601-0.864), including expression of four immune checkpoint proteins and homologous recombination deficiency, with performance comparable to 'black-box' methods. Our HIF-based approach provides a comprehensive, quantitative, and interpretable window into the composition and spatial architecture of the tumor microenvironment.

A Machine Learning Approach Enables Quantitative Measurement of Liver Histology and Disease Monitoring in NASH.

BACKGROUND AND AIMS: Manual histological assessment is currently the accepted standard for diagnosing and monitoring disease progression in NASH, but is limited by variability in interpretation and insensitivity to change. Thus, there is a critical need for improved tools to assess liver pathology in order to risk stratify NASH patients and monitor treatment response. APPROACH AND RESULTS: Here, we describe a machine learning (ML)-based approach to liver histology assessment, which accurately characterizes disease severity and heterogeneity, and sensitively quantifies treatment response in NASH. We use samples from three randomized controlled trials to build and then validate deep convolutional neural networks to measure key histological features in NASH, including steatosis, inflammation, hepatocellular ballooning, and fibrosis. The ML-based predictions showed strong correlations with expert pathologists and were prognostic of progression to cirrhosis and liver-related clinical events. We developed a heterogeneity-sensitive metric of fibrosis response, the Deep Learning Treatment Assessment Liver Fibrosis score, which measured antifibrotic treatment effects that went undetected by manual pathological staging and was concordant with histological disease progression. CONCLUSIONS: Our ML method has shown reproducibility and sensitivity and was prognostic for disease progression, demonstrating the power of ML to advance our understanding of disease heterogeneity in NASH, risk stratify affected patients, and facilitate the development of therapies.

A multisite validation of whole slide imaging for primary diagnosis using standardized data collection and analysis.

CONTEXT: Text-based reporting and manual arbitration for whole slide imaging (WSI) validation studies are labor intensive and do not allow for consistent, scalable, and repeatable data collection or analysis. OBJECTIVE: The objective of this study was to establish a method of data capture and analysis using standardized codified checklists and predetermined synoptic discordance tables and to use these methods in a pilot multisite validation study. METHODS AND STUDY DESIGN: Fifteen case report form checklists were generated from the College of American Pathology cancer protocols. Prior to data collection, all hypothetical pairwise comparisons were generated, and a level of harm was determined for each possible discordance. Four sites with four pathologists each generated 264 independent reads of 33 cases. Preestablished discordance tables were applied to determine site by site and pooled accuracy, intrareader/intramodality, and interreader intramodality error rates. RESULTS: Over 10,000 hypothetical pairwise comparisons were evaluated and assigned harm in discordance tables. The average difference in error rates between WSI and glass, as compared to ground truth, was 0.75% with a lower bound of 3.23% (95% confidence interval). Major discordances occurred on challenging cases, regardless of modality. The average inter-reader agreement across sites for glass was 76.5% (weighted kappa of 0.68) and for digital it was 79.1% (weighted kappa of 0.72). CONCLUSION: These results demonstrate the feasibility and utility of employing standardized synoptic checklists and predetermined discordance tables to gather consistent, comprehensive diagnostic data for WSI validation studies. This method of data capture and analysis can be applied in large-scale multisite WSI validations.

Can digital pathology result in cost savings? A financial projection for digital pathology implementation at a large integrated health care organization.

BACKGROUND: Digital pathology offers potential improvements in workflow and interpretive accuracy. Although currently digital pathology is commonly used for research and education, its clinical use has been limited to niche applications such as frozen sections and remote second opinion consultations. This is mainly due to regulatory hurdles, but also to a dearth of data supporting a positive economic cost-benefit. Large scale adoption of digital pathology and the integration of digital slides into the routine anatomic/surgical pathology "slide less" clinical workflow will occur only if digital pathology will offer a quantifiable benefit, which could come in the form of more efficient and/or higher quality care. AIM: As a large academic-based health care organization expecting to adopt digital pathology for primary diagnosis upon its regulatory approval, our institution estimated potential operational cost savings offered by the implementation of an enterprise-wide digital pathology system (DPS). METHODS: Projected cost savings were calculated for the first 5 years following implementation of a DPS based on operational data collected from the pathology department. Projected savings were based on two factors: (1) Productivity and lab consolidation savings; and (2) avoided treatment costs due to improvements in the accuracy of cancer diagnoses among nonsubspecialty pathologists. Detailed analyses of incremental treatment costs due to interpretive errors, resulting in either a false positive or false negative diagnosis, was performed for melanoma and breast cancer and extrapolated to 10 other common cancers. RESULTS: When phased in over 5-years, total cost savings based on anticipated improvements in pathology productivity and histology lab consolidation were estimated at $12.4 million for an institution with 219,000 annual accessions. The main contributing factors to these savings were gains in pathologist clinical full-time equivalent capacity impacted by improved pathologist productivity and workload distribution. Expanding the current localized specialty sign-out model to an enterprise-wide shared general/subspecialist sign-out model could potentially reduce costs of incorrect treatment by $5.4 million. These calculations were based on annual over and under treatment costs for breast cancer and melanoma estimated to be approximately $26,000 and $11,000/case, respectively, and extrapolated to $21,500/case for other cancer types. CONCLUSIONS: The projected 5-year total cost savings for our large academic-based health care organization upon fully implementing a DPS was approximately $18 million. If the costs of digital pathology acquisition and implementation do not exceed this value, the return on investment becomes attractive to hospital administrators. Furthermore, improved patient outcome enabled by this technology strengthens the argument supporting adoption of an enterprise-wide DPS.

Highly multiplexed single-cell analysis of formalin-fixed, paraffin-embedded cancer tissue.

Limitations on the number of unique protein and DNA molecules that can be characterized microscopically in a single tissue specimen impede advances in understanding the biological basis of health and disease. Here we present a multiplexed fluorescence microscopy method (MxIF) for quantitative, single-cell, and subcellular characterization of multiple analytes in formalin-fixed paraffin-embedded tissue. Chemical inactivation of fluorescent dyes after each image acquisition round allows reuse of common dyes in iterative staining and imaging cycles. The mild inactivation chemistry is compatible with total and phosphoprotein detection, as well as DNA FISH. Accurate computational registration of sequential images is achieved by aligning nuclear counterstain-derived fiducial points. Individual cells, plasma membrane, cytoplasm, nucleus, tumor, and stromal regions are segmented to achieve cellular and subcellular quantification of multiplexed targets. In a comparison of pathologist scoring of diaminobenzidine staining of serial sections and automated MxIF scoring of a single section, human epidermal growth factor receptor 2, estrogen receptor, p53, and androgen receptor staining by diaminobenzidine and MxIF methods yielded similar results. Single-cell staining patterns of 61 protein antigens by MxIF in 747 colorectal cancer subjects reveals extensive tumor heterogeneity, and cluster analysis of divergent signaling through ERK1/2, S6 kinase 1, and 4E binding protein 1 provides insights into the spatial organization of mechanistic target of rapamycin and MAPK signal transduction. Our results suggest MxIF should be broadly applicable to problems in the fields of basic biological research, drug discovery and development, and clinical diagnostics.

The relative distribution of membranous and cytoplasmic met is a prognostic indicator in stage I and II colon cancer.

PURPOSE: The association hepatocyte growth factor receptor (Met) tyrosine kinase with prognosis and survival in colon cancer is unclear, due in part to the limitation of detection methods used. In particular, conventional chromagenic immunohistochemistry (IHC) has several limitations including the inability to separate compartmental measurements. Measurement of membrane, cytoplasm, and nuclear levels of Met could offer a superior approach to traditional IHC. EXPERIMENTAL DESIGN: Fluorescent-based IHC for Met was done in 583 colon cancer patients in a tissue microarray format. Using curvature and intensity-based image analysis, the membrane, nuclear, and cytoplasm were segmented. Probability distributions of Met within each compartment were determined, and an automated scoring algorithm was generated. An optimal score cutpoint was calculated using 500-fold crossvalidation of a training and test data set. For comparison with conventional IHC, a second array from the same tissue microarray block was 3,3'-diaminobenzidine immunostained for Met. RESULTS: In crossvalidated and univariate Cox analysis, the membrane relative to cytoplasm Met score was a significant predictor of survival in stage I (hazard ratio, 0.16; P = 0.006) and in stage II patients (hazard ratio, 0.34; P < or = 0.0005). Similar results were found with multivariate analysis. Met in the membrane alone was not a significant predictor of outcome in all patients or within stage. In the 3,3'-diaminobenzidine-stained array, no associations were found with Met expression and survival. CONCLUSIONS: These data indicate that the relative subcellular distribution of Met, as measured by novel automated image analysis, may be a valuable biomarker for estimating colon cancer prognosis.

Visual, cognitive, and language assessments at 39 months: a follow-up study of children fed formulas containing long-chain polyunsaturated fatty acids to 1 year of age.

OBJECTIVE: Docosahexaenoic acid (DHA) and arachidonic acid (ARA) are long-chain polyunsaturated fatty acids found in breast milk and recently added to infant formulas. Their importance in infant nutrition was recognized by the rapid accretion of these fatty acids in the brain during the first postnatal year, reports of enhanced intellectual development in breastfed children, and recognition of the physiologic importance of DHA in visual and neural systems from studies in animal models. These considerations led to clinical trials to evaluate whether infant formulas that are supplemented with DHA or both DHA and ARA would enhance visual and cognitive development or whether conversion of linoleic acid and alpha-linolenic acid, the essential fatty acid precursors of ARA and DHA, respectively, at the levels found in infant formulas is sufficient to support adequately visual and cognitive development. Visual and cognitive development were not different with supplementation in some studies, whereas other studies reported benefits of adding DHA or both DHA and ARA to formula. One of the first trials with term infants that were fed formula supplemented with DHA or both DHA and ARA evaluated growth, visual acuity (Visual Evoked Potential; Acuity Card Procedure), mental and motor development (Bayley Scales of Infant Development), and early language development (MacArthur Communicative Developmental Inventories). Growth, visual acuity, and mental and motor development were not different among the 3 formula groups or between the breastfed and formula-fed infants in the first year of life. At 14 months of age, infants who were fed the formula with DHA but no ARA had lower vocabulary production and comprehension scores than infants who were fed the unsupplemented control formula or who were breastfed, respectively. The present follow-up study evaluated IQ, receptive and expressive vocabulary, visual-motor function, and visual acuity of children from the original trial when they reached 39 months of age. METHODS: Infants were randomized within 1 week after birth and fed a control formula (n = 65), one containing DHA (n = 65), or one containing both ARA and DHA (n = 66) to 1 year of age. A comparison group (n = 80) was exclusively breastfed for at least 3 months after which the infants continued to be exclusively breastfed or were supplemented with and/or weaned to infant formula. At 39 months, standard tests of IQ (Stanford Binet IQ), receptive vocabulary (Peabody Picture Vocabulary Test-Revised), expressive vocabulary (mean length of utterance), visual-motor function (Beery Visual-Motor Index), and visual acuity (Acuity Card Procedure) were administered. Growth, red blood cell fatty acid levels, and morbidity also were evaluated. RESULTS: Results were analyzed using analysis of variance or linear regression models. The regression model for IQ, receptive and expressive language, and the visual-motor index controlled for site, birth weight, sex, maternal education, maternal age, and the child's age at testing. The regression model for visual acuity controlled for site only. A variable selection model also identified which of 22 potentially prognostic variables among different categories (feeding groups, the child and family demographics, indicators of illness since birth, and environment) were most influential for IQ and expressive vocabulary. A total of 157 (80%) of the 197 infants studied at 12 months participated in this follow-up study. Characteristics of the families were representative of US families with children up to 5 years of age, and there were no differences in the demographic or family characteristics among the randomized formula groups. As expected, the formula and breastfed groups differed in ethnicity, marital status, parental education, and the prevalence of smoking. Sex, ethnicity, gestational age at birth, and birth weight for those who participated at 39 months did not differ from those who did not. The 12-month Bayley mental and motor scores and 14-month vocabulary scores of the children who participated also were were not different from those who did not. At 39 months, IQ, receptive and expressive language, visual-motor function, and visual acuity were not different among the 3 randomized formula groups or between the breastfed and formula groups. The adjusted means for the control, ARA+DHA, DHA, and breastfed groups were as follows: IQ scores, 104, 101, 100, 106; Peabody Picture Vocabulary Test, 99.2, 97.2, 95.1, 97.4; mean length of utterance, 3.64, 3.75, 3.93, 4.08; the visual-motor index, 2.26, 2.24, 2.05, 2.40; and visual acuity (cycles/degree), 30.4, 27.9, 27.5, 28.6, respectively. IQ was positively associated with female sex and maternal education and negatively associated with the number of siblings and exposure to cigarette smoking in utero and/or postnatally. Expressive language also was positively associated with maternal education and negatively associated with the average hours in child care per week and hospitalizations since birth but only when the breastfed group was included in the analysis. The associations between maternal education and child IQ scores are consistent with previous reports as are the associations between prenatal exposure to cigarette smoke and IQ and early language development. Approximately one third of the variance for IQ was explained by sex, maternal education, the number of siblings, and exposure to cigarette smoke. Growth achievement, red blood cell fatty acid levels, and morbidity did not differ among groups. CONCLUSIONS: We reported previously that infants who were fed an unsupplemented formula or one with DHA or with both DHA and ARA through 12 months or were breastfed showed no differences in mental and motor development, but those who were fed DHA without ARA had lower vocabulary scores on a standardized, parent-report instrument at 14 months of age when compared with infants who were fed the unsupplemented formula or who were breastfed. When the infants were reassessed at 39 months using age-appropriate tests of receptive and expressive language as well as IQ, visual-motor function and visual acuity, no differences among the formula groups or between the formula and breastfed groups were found. The 14-month observation thus may have been a transient effect of DHA (without ARA) supplementation on early vocabulary development or may have occurred by chance. The absence of differences in growth achievement adds to the evidence that DHA with or without ARA supports normal growth in full-term infants. In conclusion, adding both DHA and ARA when supplementing infant formulas with long-chain polyunsaturated fatty acids supports visual and cognitive development through 39 months.

Hypoxia-inducible factor-1-dependent regulation of the multidrug resistance (MDR1) gene.

The microenvironment of rapidly growing tumors is associated with increased energy demand and diminished vascular supply, resulting in focal areas of prominent hypoxia. A number of hypoxia-responsive genes have been associated with growing tumors, and here we demonstrate that the multidrug resistance (MDR1) gene product P-glycoprotein, a Mr approximately 170,000 transmembrane protein associated with tumor resistance to chemotherapeutics, is induced by ambient hypoxia. Initial studies using quantitative microarray analysis of RNA revealed an approximately 7-fold increase in MDR in epithelial cells exposed to hypoxia (pO(2) 20 torr, 18 h). These findings were further confirmed at the mRNA and protein level. P-Glycoprotein function was studied by analysis of verapamil-inhibitable efflux of digoxin and rhodamine 123 in intact T84 cells and revealed that hypoxia enhances P-glycoprotein function by as much as 7 +/- 0.4-fold over normoxia. Subsequent studies confirmed hypoxia-elicited MDR1 gene induction and increased P-glycoprotein expression in nontransformed, primary cultures of human microvascular endothelial cells, and analysis of multicellular spheroids subjected to hypoxia revealed increased resistance to doxorubicin. Examination of the MDR1 gene identified a binding site for hypoxia inducible factor-1 (HIF-1), and inhibition of HIF-1 expression by antisense oligonucleotides resulted in significant inhibition of hypoxia-inducible MDR1 expression and a nearly complete loss of basal MDR1 expression. Studies using luciferase promoter constructs revealed a significant increase in activity in cells subjected to hypoxia, and such hypoxia inducibility was lost in truncated constructs lacking the HIF-1 site and in HIF-1 binding site mutants. Extensions of these studies also identified a role for Sp1 in this hypoxia response. Taken together, these data indicate that the MDR1 gene is hypoxia responsive, and such results may identify hypoxia-elicited P-glycoprotein expression as a pathway for resistance of some tumors to chemotherapeutics.