Applications of Artificial Intelligence in Lung Pathology.

Artificial intelligence/machine learning tools are being created for use in pathology. Some examples related to lung pathology include acid-fast stain evaluation, programmed death ligand-1 (PDL-1) interpretation, evaluating histologic patterns of non-small-cell lung carcinoma, evaluating histologic features in mesothelioma associated with adverse outcomes, predicting response to anti-PDL-1 therapy from hematoxylin and eosin-stained slides, evaluation of tumor microenvironment, evaluating patterns of interstitial lung disease, nondestructive methods for tissue evaluation, and others. There are still some frameworks (regulatory, workflow, and payment) that need to be established for these tools to be integrated into pathology.

Automated Quantitative CD8+ Tumor-Infiltrating Lymphocytes and Tumor Mutation Burden as Independent Biomarkers in Melanoma Patients Receiving Front-Line Anti-PD-1 Immunotherapy.

BACKGROUND: CD8+ tumor-infiltrating lymphocyte (TIL) predicts response to anti-PD-(L)1 therapy. However, there remains no standardized method to assess CD8+ TIL in melanoma, and developing a specific, cost-effective, reproducible, and clinically actionable biomarker to anti-PD-(L)1 remains elusive. We report on the development of automatic CD8+ TIL density quantification via whole slide image (WSI) analysis in advanced melanoma patients treated with front-line anti-PD-1 blockade, and correlation immunotherapy response. METHODS: Seventy-eight patients treated with PD-1 inhibitors in the front-line setting between January 2015 and May 2023 at the University of Pittsburgh Cancer Institute were included. CD8+ TIL density was quantified using an image analysis algorithm on digitized WSI. Targeted next-generation sequencing (NGS) was performed to determine tumor mutation burden (TMB) in a subset of 62 patients. ROC curves were used to determine biomarker cutoffs and response to therapy. Correlation between CD8+ TIL density and TMB cutoffs and response to therapy was studied. RESULTS: Higher CD8+ TIL density was significantly associated with improved response to front-line anti-PD-1 across all time points measured. CD8+ TIL density ≥222.9 cells/mm2 reliably segregated responders and non-responders to front-line anti-PD-1 therapy regardless of when response was measured. In a multivariate analysis, patients with CD8+ TIL density exceeding cutoff had significantly improved PFS with a trend toward improved OS. Similarly, increasing TMB was associated with improved response to anti-PD-1, and a cutoff of 14.70 Mut/Mb was associated with improved odds of response. The correlation between TMB and CD8+ TIL density was low, suggesting that each represented independent predictive biomarkers of response. CONCLUSIONS: An automatic digital analysis algorithm provides a standardized method to quantify CD8+ TIL density, which predicts response to front-line anti-PD-1 therapy. CD8+ TIL density and TMB are independent predictors of response to anti-PD-1 blockade.

Genomic Staging of Multifocal Lung Squamous Cell Carcinomas Is Independent of the Comprehensive Morphologic Assessment.

INTRODUCTION: Morphologic and molecular data for staging of multifocal lung squamous cell carcinomas (LSCCs) are limited. In this study, whole exome sequencing (WES) was used as the gold standard to determine whether multifocal LSCC represented separate primary lung cancers (SPLCs) or intrapulmonary metastases (IPMs). Genomic profiles were compared with the comprehensive morphologic assessment. METHODS: WES was performed on 20 tumor pairs of multifocal LSCC and matched normal lymph nodes using the Illumina NovaSeq6000 S4-Xp (Illumina, San Diego, CA). WES clonal and subclonal analysis data were compared with histologic assessment by 16 thoracic pathologists. In addition, the immune gene profiling of the study cases was characterized by the HTG EdgeSeq Precision Immuno-Oncology Panel. RESULTS: By WES data, 11 cases were classified as SPLC and seven cases as IPM. Two cases were technically suboptimal. Analysis revealed marked genomic and immunogenic heterogeneity, but immune gene expression profiles highly correlated with mutation profiles. Tumors classified as IPM have a large number of shared mutations (ranging from 33.5% to 80.7%). The agreement between individual morphologic assessments for each case and WES was 58.3%. One case was unanimously interpreted morphologically as IPM and was in agreement with WES. In a further 17 cases, the number of pathologists whose morphologic interpretation was in agreement with WES ranged from two (one case) to 15 pathologists (one case) per case. Pathologists showed a fair interobserver agreement in the morphologic staging of multiple LSCCs, with an overall kappa of 0.232. CONCLUSIONS: Staging of multifocal LSCC based on morphologic assessment is unreliable. Comprehensive genomic analyses should be adopted for the staging of multifocal LSCC.

Tenofovir Douche as HIV Preexposure Prophylaxis for Receptive Anal Intercourse: Safety, Acceptability, Pharmacokinetics, and Pharmacodynamics (DREAM 01).

BACKGROUND: Despite highly effective HIV preexposure prophylaxis (PrEP) options, no options provide on-demand, nonsystemic, behaviorally congruent PrEP that many desire. A tenofovir-medicated rectal douche before receptive anal intercourse may provide this option. METHODS: Three tenofovir rectal douches-220 mg iso-osmolar product A, 660 mg iso-osmolar product B, and 660 mg hypo-osmolar product C-were studied in 21 HIV-negative men who have sex with men. We sampled blood and colorectal tissue to assess safety, acceptability, pharmacokinetics, and pharmacodynamics. RESULTS: The douches had high acceptability without toxicity. Median plasma tenofovir peak concentrations for all products were several-fold below trough concentrations associated with oral tenofovir disoproxil fumarate (TDF). Median colon tissue mucosal mononuclear cell (MMC) tenofovir-diphosphate concentrations exceeded target concentrations from 1 hour through 3 to 7 days after dosing. For 6-7 days after a single product C dose, MMC tenofovir-diphosphate exceeded concentrations expected with steady-state oral TDF 300 mg on-demand 2-1-1 dosing. Compared to predrug baseline, HIV replication after ex vivo colon tissue HIV challenge demonstrated a concentration-response relationship with 1.9 log10 maximal effect. CONCLUSIONS: All 3 tenofovir douches achieved tissue tenofovir-diphosphate concentrations and colorectal antiviral effect exceeding oral TDF and with lower systemic tenofovir. Tenofovir douches may provide a single-dose, on-demand, behaviorally congruent PrEP option, and warrant continued development. Clinical Trials Registration . NCT02750540.

Computational pathology in 2030: a Delphi study forecasting the role of AI in pathology within the next decade.

BACKGROUND: Artificial intelligence (AI) is rapidly fuelling a fundamental transformation in the practice of pathology. However, clinical integration remains challenging, with no AI algorithms to date in routine adoption within typical anatomic pathology (AP) laboratories. This survey gathered current expert perspectives and expectations regarding the role of AI in AP from those with first-hand computational pathology and AI experience. METHODS: Perspectives were solicited using the Delphi method from 24 subject matter experts between December 2020 and February 2021 regarding the anticipated role of AI in pathology by the year 2030. The study consisted of three consecutive rounds: 1) an open-ended, free response questionnaire generating a list of survey items; 2) a Likert-scale survey scored by experts and analysed for consensus; and 3) a repeat survey of items not reaching consensus to obtain further expert consensus. FINDINGS: Consensus opinions were reached on 141 of 180 survey items (78.3%). Experts agreed that AI would be routinely and impactfully used within AP laboratory and pathologist clinical workflows by 2030. High consensus was reached on 100 items across nine categories encompassing the impact of AI on (1) pathology key performance indicators (KPIs) and (2) the pathology workforce and specific tasks performed by (3) pathologists and (4) AP lab technicians, as well as (5) specific AI applications and their likelihood of routine use by 2030, (6) AI's role in integrated diagnostics, (7) pathology tasks likely to be fully automated using AI, and (8) regulatory/legal and (9) ethical aspects of AI integration in pathology. INTERPRETATION: This systematic consensus study details the expected short-to-mid-term impact of AI on pathology practice. These findings provide timely and relevant information regarding future care delivery in pathology and raise key practical, ethical, and legal challenges that must be addressed prior to AI's successful clinical implementation. FUNDING: No specific funding was provided for this study.

CD8 + T-cell Density Is an Independent Predictor of Survival and Response to Adjuvant Chemotherapy in Stage III Colon Cancer.

We assessed CD8 + T-cell density in 351 resected stage II to III colon cancers from 2011 to 2015 and correlated the findings with disease-free survival and survival effect of adjuvant chemotherapy. Most tumors (70%) had high/intermediate CD8 + T-cell density, and this was significantly associated with mismatch repair deficiency compared with tumors with low CD8 + T-cell density (28% vs. 13%, P =0.003). Fewer tumors with high/intermediate CD8 + T-cell density had adverse histologic features compared with tumors with low CD8 + T-cell density including high tumor budding (16% vs. 27%) and venous (22% vs. 35%), lymphatic (54% vs. 65%), and perineural (23% vs. 33%) invasion (all with P <0.05). In the stage III cohort, high/intermediate CD8 + T-cell density was an independent predictor of disease-free survival on multivariate analysis (hazard ratio: 0.39, 0.21 to 0.71 95% CI, P =0.002). For stage III patients with high/intermediate CD8 + T-cell density, adjuvant chemotherapy was significantly associated with improved disease-free survival (hazard ratio: 0.28, 0.11 to 0.74 95% CI, P =0.01) whereas stage III patients with low CD8 + T-cell density did not have improved survival with adjuvant chemotherapy. In conclusion, in stage III colon cancer, CD8 + T-cell density is an independent prognostic biomarker for disease-free survival and may help to identify patients who benefit from adjuvant chemotherapy.

Quantitative Pathologic Analysis of Digitized Images of Colorectal Carcinoma Improves Prediction of Recurrence-Free Survival.

BACKGROUND & AIMS: To examine whether quantitative pathologic analysis of digitized hematoxylin and eosin slides of colorectal carcinoma (CRC) correlates with clinicopathologic features, molecular alterations, and prognosis. METHODS: A quantitative segmentation algorithm (QuantCRC) was applied to 6468 digitized hematoxylin and eosin slides of CRCs. Fifteen parameters were recorded from each image and tested for associations with clinicopathologic features and molecular alterations. A prognostic model was developed to predict recurrence-free survival using data from the internal cohort (n = 1928) and validated on an internal test (n = 483) and external cohort (n = 938). RESULTS: There were significant differences in QuantCRC according to stage, histologic subtype, grade, venous/lymphatic/perineural invasion, tumor budding, CD8 immunohistochemistry, mismatch repair status, KRAS mutation, BRAF mutation, and CpG methylation. A prognostic model incorporating stage, mismatch repair, and QuantCRC resulted in a Harrell's concordance (c)-index of 0.714 (95% confidence interval [CI], 0.702-0.724) in the internal test and 0.744 (95% CI, 0.741-0.754) in the external cohort. Removing QuantCRC from the model reduced the c-index to 0.679 (95% CI, 0.673-0.694) in the external cohort. Prognostic risk groups were identified, which provided a hazard ratio of 2.24 (95% CI, 1.33-3.87, P = .004) for low vs high-risk stage III CRCs and 2.36 (95% CI, 1.07-5.20, P = .03) for low vs high-risk stage II CRCs, in the external cohort after adjusting for established risk factors. The predicted median 36-month recurrence rate for high-risk stage III CRCs was 32.7% vs 13.4% for low-risk stage III and 15.8% for high-risk stage II vs 5.4% for low-risk stage II CRCs. CONCLUSIONS: QuantCRC provides a powerful adjunct to routine pathologic reporting of CRC. A prognostic model using QuantCRC improves prediction of recurrence-free survival.

Interactive Multimedia Reporting Technical Considerations: HIMSS-SIIM Collaborative White Paper.

Despite technological advances in the analysis of digital images for medical consultations, many health information systems lack the ability to correlate textual descriptions of image findings linked to the actual images. Images and reports often reside in separate silos in the medical record throughout the process of image viewing, report authoring, and report consumption. Forward-thinking centers and early adopters have created interactive reports with multimedia elements and embedded hyperlinks in reports that connect the narrative text with the related source images and measurements. Most of these solutions rely on proprietary single-vendor systems for viewing and reporting in the absence of any encompassing industry standards to facilitate interoperability with the electronic health record (EHR) and other systems. International standards have enabled the digitization of image acquisition, storage, viewing, and structured reporting. These provide the foundation to discuss enhanced reporting. Lessons learned in the digital transformation of radiology and pathology can serve as a basis for interactive multimedia reporting (IMR) across image-centric medical specialties. This paper describes the standard-based infrastructure and communications to fulfill recently defined clinical requirements through a consensus from an international workgroup of multidisciplinary medical specialists, informaticists, and industry participants. These efforts have led toward the development of an Integrating the Healthcare Enterprise (IHE) profile that will serve as a foundation for interoperable interactive multimedia reporting.

Ultrastructural visualization of chromatin in cancer pathogenesis using a simple small-molecule fluorescent probe.

Imaging chromatin organization at the molecular-scale resolution remains an important endeavor in basic and translational research. Stochastic optical reconstruction microscopy (STORM) is a powerful superresolution imaging technique to visualize nanoscale molecular organization down to the resolution of ~20 to 30 nm. Despite the substantial progress in imaging chromatin organization in cells and model systems, its routine application on assessing pathological tissue remains limited. It is, in part, hampered by the lack of simple labels that consistently generates high-quality STORM images on the highly processed clinical tissue. We developed a fast, simple, and robust small-molecule fluorescent probe-cyanine 5-conjugated Hoechst-for routine superresolution imaging of nanoscale nuclear architecture on clinical tissue. We demonstrated the biological and clinical significance of imaging superresolved chromatin structure in cancer development and its potential clinical utility for cancer risk stratification.

Pembrolizumab plus azacitidine in patients with chemotherapy refractory metastatic colorectal cancer: a single-arm phase 2 trial and correlative biomarker analysis.

BACKGROUND: DNA mismatch repair proficient (pMMR) metastatic colorectal cancer (mCRC) is not responsive to pembrolizumab monotherapy. DNA methyltransferase inhibitors can promote antitumor immune responses. This clinical trial investigated whether concurrent treatment with azacitidine enhances the antitumor activity of pembrolizumab in mCRC. METHODS: We conducted a phase 2 single-arm trial evaluating activity and tolerability of pembrolizumab plus azacitidine in patients with chemotherapy-refractory mCRC (NCT02260440). Patients received pembrolizumab 200 mg IV on day 1 and azacitidine 100 mg SQ on days 1-5, every 3 weeks. A low fixed dose of azacitidine was chosen in order to reduce the possibility of a direct cytotoxic effect of the drug, since the main focus of this study was to investigate its potential immunomodulatory effect. The primary endpoint of this study was overall response rate (ORR) using RECIST v1.1., and secondary endpoints were progression-free survival (PFS) and overall survival (OS). Tumor tissue was collected pre- and on-treatment for correlative studies. RESULTS: Thirty chemotherapy-refractory patients received a median of three cycles of therapy. One patient achieved partial response (PR), and one patient had stable disease (SD) as best confirmed response. The ORR was 3%, median PFS was 1.9 months, and median OS was 6.3 months. The combination regimen was well-tolerated, and 96% of treatment-related adverse events (TRAEs) were grade 1/2. This trial was terminated prior to the accrual target of 40 patients due to lack of clinical efficacy. DNA methylation on-treatment as compared to pre-treatment decreased genome wide in 10 of 15 patients with paired biopsies and was significantly lower in gene promoter regions after treatment. These promoter demethylated genes represented a higher proportion of upregulated genes, including several immune gene sets, endogenous retroviral elements, and cancer-testis antigens. CD8+ TIL density trended higher on-treatment compared to pre-treatment. Higher CD8+ TIL density at baseline was associated with greater likelihood of benefit from treatment. On-treatment tumor demethylation correlated with the increases in tumor CD8+ TIL density. CONCLUSIONS: The combination of pembrolizumab and azacitidine is safe and tolerable with modest clinical activity in the treatment for chemotherapy-refractory mCRC. Correlative studies suggest that tumor DNA demethylation and immunomodulation occurs. An association between tumor DNA demethylation and tumor-immune modulation suggests immune modulation and may result from treatment with azacitidine. Trial registration ClinicalTrials.gov, NCT02260440. Registered 9 October 2014, https://clinicaltrials.gov/ct2/show/NCT02260440 .

SPaRTAN, a computational framework for linking cell-surface receptors to transcriptional regulators.

The identity and functions of specialized cell types are dependent on the complex interplay between signaling and transcriptional networks. Recently single-cell technologies have been developed that enable simultaneous quantitative analysis of cell-surface receptor expression with transcriptional states. To date, these datasets have not been used to systematically develop cell-context-specific maps of the interface between signaling and transcriptional regulators orchestrating cellular identity and function. We present SPaRTAN (Single-cell Proteomic and RNA based Transcription factor Activity Network), a computational method to link cell-surface receptors to transcription factors (TFs) by exploiting cellular indexing of transcriptomes and epitopes by sequencing (CITE-seq) datasets with cis-regulatory information. SPaRTAN is applied to immune cell types in the blood to predict the coupling of signaling receptors with cell context-specific TFs. Selected predictions are validated by prior knowledge and flow cytometry analyses. SPaRTAN is then used to predict the signaling coupled TF states of tumor infiltrating CD8+ T cells in malignant peritoneal and pleural mesotheliomas. SPaRTAN enhances the utility of CITE-seq datasets to uncover TF and cell-surface receptor relationships in diverse cellular states.

Dissecting the Business Case for Adoption and Implementation of Digital Pathology: A White Paper from the Digital Pathology Association.

We believe the switch to a digital pathology (DP) workflow is imminent and it is essential to understand the economic implications of conversion. Many aspects of the adoption of DP will be disruptive and have a direct financial impact, both in short term costs, such as investment in equipment and personnel, and long term revenue potential, such as improved productivity and novel tests. The focus of this whitepaper is to educate pathologists, laboratorians and other stakeholders about the business and monetary considerations of converting to a digital pathology workflow. The components of a DP business plan will be thoroughly summarized, and guidance will be provided on how to build a case for adoption and implementation as well as a roadmap for transitioning from an analog to a digital pathology workflow in various laboratory settings. It is important to clarify that this publication is not intended to list prices although some financials will be mentioned as examples. The authors encourage readers who are evaluating conversion to a DP workflow to use this paper as a foundational guide for conducting a thorough and complete assessment while incorporating in current market pricing. Contributors to this paper analyzed peer-reviewed literature and data collected from various institutions, some of which are mentioned. Digital pathology will change the way we practice through facilitating patient access to expert pathology services and enabling image analysis tools and assays to aid in diagnosis, prognosis, risk stratification and therapeutic selection. Together, they will result in the delivery of valuable information from which to make better decisions and improve the health of patients.

Combined histopathological risk score using TP53 protein expression, CD8+ T cell density and intratumoral budding is an independent predictor of neoadjuvant therapy response in rectal adenocarcinoma.

AIMS: Neoadjuvant therapy is the recommended treatment for locally advanced rectal adenocarcinoma; however, there remains significant variability in response to therapy. Tumour protein 53 (TP53) has been associated with therapy response and prognosis with conflicting data. Recently, we demonstrated that immune cell density and intratumoral budding (ITB) are predictive factors in rectal cancer. We investigated the predictive value of TP53 immunohistochemistry with CD8+ T cell density and ITB on pretreatment biopsies of rectal adenocarcinoma for response to neoadjuvant therapy. METHODS AND RESULTS: Pretreatment biopsies of rectal adenocarcinoma from 117 patients with neoadjuvant therapy were analysed for TP53 expression by immunohistochemistry, ITB, CD8+ T cell density and mismatch repair protein (MMR) status. Most rectal adenocarcinomas displayed aberrant TP53 expression (86 of 117, 74%). Compared to wild-type TP53, aberrant TP53 expression was associated with proficient MMR status (P = 0.003) and low CD8+ T cell density (P = 0.001). Aberrant TP53 was significantly associated with a partial to poor response to neoadjuvant therapy [odds ratio (OR) = 2.42, 95% confidence interval (CI) = 1.04-5.62, P = 0.04]. A combined histopathological risk score (HRS) was created using CD8+ T cell density, ITB and TP53 expression. Patients were separated into low (none to one factor) and high (two to three factors) HRS categories. In the multivariable model, patients with a high HRS were 3.25-fold more likely to have a partial or poor response to neoadjuvant therapy (95% CI = 1.48-7.11, P = 0.003). CONCLUSIONS: Our study demonstrates that aberrant TP53 expression, high ITB and low CD8+ T cell density in pretreatment biopsies can help predict response to neoadjuvant therapy. These biomarkers may be helpful in identifying patients at risk for therapy resistance.

Crohn's disease-associated ATG16L1 T300A genotype is associated with improved survival in gastric cancer.

BACKGROUND: A non-synonymous single nucleotide polymorphism of the ATG16L1 gene, T300A, is a major Crohn's disease (CD) susceptibility allele, and is known to be associated with increased apoptosis induction in the small intestinal crypt base in CD subjects and mouse models. We hypothesized that ATG16L1 T300A genotype also correlates with increased tumor apoptosis and therefore could lead to superior clinical outcome in cancer subjects. METHODS: T300A genotyping by Taqman assay was performed for gastric carcinoma subjects who underwent resection from two academic medical centers. Transcriptomic analysis was performed by RNA-seq on formalin-fixed paraffin-embedded cancerous tissue. Tumor apoptosis and autophagy were determined by cleaved caspase-3 and p62 immunohistochemistry, respectively. The subjects' genotypes were correlated with demographics, various histopathologic features, transcriptome, and clinical outcome. FINDINGS: Of the 220 genotyped subjects, 163 (74%) subjects carried the T300A allele(s), including 55 (25%) homozygous and 108 (49%) heterozygous subjects. The T300A/T300A subjects had superior overall survival than the other groups. Their tumors were associated with increased CD-like lymphoid aggregates and increased tumor apoptosis without concurrent increase in tumor mitosis or defective autophagy. Transcriptomic analysis showed upregulation of WNT/ß-catenin signaling and downregulation of PPAR, EGFR, and inflammatory chemokine pathways in tumors of T300A/T300A subjects. INTERPRETATION: Gastric carcinoma of subjects with the T300A/T300A genotype is associated with repressed EGFR and PPAR pathways, increased tumor apoptosis, and improved overall survival. Genotyping gastric cancer subjects may provide additional insight for clinical stratification.

Validated Indices for Histopathologic Activity Predict Development of Colorectal Neoplasia in Ulcerative Colitis.

BACKGROUND AND AIMS: To correlate histologic activity in surveillance colonoscopies with the development of colorectal neoplasia in ulcerative colitis [UC]. METHODS: Colorectal biopsies during surveillance [N = 764] from 52 UC patients with colorectal neoplasia were compared to 122 patients without neoplasia enrolled in a prospective natural history registry. All biopsies were scored using validated histologic scoring systems (Geboes score, Nancy histopathologic index [NHI], and Robarts histopathologic index [RHI]). Clinical, endoscopic, and histologic data were correlated with the development of colorectal neoplasia. RESULTS: In multivariable analysis, mean RHI (hazard ratio [HR] 1.07 for each 1-unit increase in RHI, 95% confidence interval [CI] 1.03-1.12, p = 0.002) and mean NHI [HR 1.89 for each 1-unit increase in NHI, 95% CI 1.34-2.67, p = 0.002] for the entire surveillance period were significantly associated with colorectal neoplasia development. Shorter surveillance interval and increasing age were associated with increased risk of neoplasia development whereas mean Mayo endoscopic score was not significant. To generate a clinically useful measure of neoplasia risk, mean histologic activity in the preceding 5 years before the study endpoint was correlated with neoplasia development. In the preceding 5 years of surveillance, a mean RHI ≥ 8 had a 7.53-fold increased risk [95% CI 2.56-12.16, p < 0.001] and mean NHI ≥ 1.9 had a 5.89-fold increased risk [95% CI 2.18-15.92, p < 0.001] of developing colorectal neoplasia. CONCLUSIONS: Persistent histologic activity during multiple surveillance episodes is an independent predictor of colorectal neoplasia. Mean RHI and mean NHI during a 5-year colonoscopic surveillance period can be used to assess risk for colorectal neoplasia and optimize UC surveillance.

Development and initial validation of a deep learning algorithm to quantify histological features in colorectal carcinoma including tumour budding/poorly differentiated clusters.

AIMS: To develop and validate a deep learning algorithm to quantify a broad spectrum of histological features in colorectal carcinoma. METHODS AND RESULTS: A deep learning algorithm was trained on haematoxylin and eosin-stained slides from tissue microarrays of colorectal carcinomas (N = 230) to segment colorectal carcinoma digitised images into 13 regions and one object. The segmentation algorithm demonstrated moderate to almost perfect agreement with interpretations by gastrointestinal pathologists, and was applied to an independent test cohort of digitised whole slides of colorectal carcinoma (N = 136). The algorithm correctly classified mucinous and high-grade tumours, and identified significant differences between mismatch repair-proficient and mismatch repair-deficient (MMRD) tumours with regard to mucin, inflammatory stroma, and tumour-infiltrating lymphocytes (TILs). A cutoff of >44.4 TILs per mm2 carcinoma gave a sensitivity of 88% and a specificity of 73% in classifying MMRD carcinomas. Algorithm measures of tumour budding (TB) and poorly differentiated clusters (PDCs) outperformed TB grade derived from routine sign-out, and compared favourably with manual counts of TB/PDCs with regard to lymphatic, venous and perineural invasion. Comparable associations were seen between algorithm measures of TB/PDCs and manual counts of TB/PDCs for lymph node metastasis (all P < 0.001); however, stronger correlations were seen between the proportion of positive lymph nodes and algorithm measures of TB/PDCs. Stronger associations were also seen between distant metastasis and algorithm measures of TB/PDCs (P = 0.004) than between distant metastasis and TB (P = 0.04) and TB/PDC counts (P = 0.06). CONCLUSIONS: Our results highlight the potential of deep learning to identify and quantify a broad spectrum of histological features in colorectal carcinoma.

Artificial Intelligence-Based Screening for Mycobacteria in Whole-Slide Images of Tissue Samples.

OBJECTIVES: This study aimed to develop and validate a deep learning algorithm to screen digitized acid fast-stained (AFS) slides for mycobacteria within tissue sections. METHODS: A total of 441 whole-slide images (WSIs) of AFS tissue material were used to develop a deep learning algorithm. Regions of interest with possible acid-fast bacilli (AFBs) were displayed in a web-based gallery format alongside corresponding WSIs for pathologist review. Artificial intelligence (AI)-assisted analysis of another 138 AFS slides was compared to manual light microscopy and WSI evaluation without AI support. RESULTS: Algorithm performance showed an area under the curve of 0.960 at the image patch level. More AI-assisted reviews identified AFBs than manual microscopy or WSI examination (P < .001). Sensitivity, negative predictive value, and accuracy were highest for AI-assisted reviews. AI-assisted reviews also had the highest rate of matching the original sign-out diagnosis, were less time-consuming, and were much easier for pathologists to perform (P < .001). CONCLUSIONS: This study reports the successful development and clinical validation of an AI-based digital pathology system to screen for AFBs in anatomic pathology material. AI assistance proved to be more sensitive and accurate, took pathologists less time to screen cases, and was easier to use than either manual microscopy or viewing WSIs.

Altered Expression of the Epithelial Mucin MUC1 Accompanies Endoscopic Recurrence of Postoperative Crohn's Disease.

BACKGROUND: MUC1-glycoprotein is expressed at low levels and in fully glycosylated form on epithelial cells. Inflammation causes MUC1 overexpression and hypoglycosylation. We hypothesized that overexpression of hypoglycosylated MUC1 would be found in postoperative Crohn's disease (CD) recurrence and could be considered an additional biomarker of recurrence severity. METHODS: We examined archived neo-terminal ileum biopsies from patients with prior ileocecal resection who had postoperative endoscopic assessment of CD recurrence and given a Rutgeerts ileal recurrence score. Consecutive tissue sections were stained using 2 different anti-MUC1 antibodies, HMPV that recognizes all forms of MUC1 and 4H5 that recognizes only inflammation-associated hypoglycosylated MUC1. RESULTS: A total of 71 postoperative CD patients were evaluated. There was significant increase in MUC1 expression of both glycosylated/normal (P<0.0001) and hypoglycosylated/abnormal (P<0.0001) forms in patients with severe endoscopic CD recurrence (i3+i4), ileal score i2, compared with patients in endoscopic remission (i0+i1). Results were similar regardless of anti-TNF-α use. Although MUC1 expression and Rutgeerts scores were in agreement when characterizing the majority of cases, there were a few exceptions where MUC1 expression was characteristic of more severe recurrence than implied by Rutgeerts score. CONCLUSIONS: MUC1 is overexpressed and hypoglycosylated in neo-terminal ileum tissue of patients with postoperative CD recurrence. Increased levels are associated with more severe endoscopic recurrence scores, and this is not influenced by anti-TNF-α use. Discrepancies found between Rutgeerts scores and MUC1 expression suggest that addition of MUC1 as a biomarker of severity of postoperative CD recurrence may improve categorization of recurrence status and consequently treatment decisions.

Serum IgG4 Subclass Deficiency Defines a Distinct, Commonly Encountered, Severe Inflammatory Bowel Disease Subtype.

BACKGROUND: Immunoglobulin G subclass 4 (IgG4) is hypothesized to play an immunomodulatory role, downregulating humoral immune responses. The role of this anti-inflammatory molecule in inflammatory bowel disease (IBD) has not been fully characterized. We sought to define alterations in serum IgG4 in patients with IBD and their association with multiyear disease severity. METHODS: We analyzed metadata derived from curated electronic health records from consented patients with IBD prospectively followed at a tertiary center over a 10-year time period. Patients with IBD with IgG4 serum levels available formed the study population. Demographics and multiyear clinical data were collected and analyzed. We stratified patients with IBD with low, normal, or high serum IgG4 levels. RESULTS: We found IgG4 characterized in 1193 patients with IBD and low IgG4 levels in 233 patients (20%) and elevated IgG4 levels in 61 patients (5%). An IgG4 deficiency did not significantly correlate with other antibody deficiencies. In a multiple Poisson regression analysis, low IgG4 was associated with more years on biologic agents (P = 0.002) and steroids (P = 0.049) and more hospital admissions (P < 0.001), clinic visits (P = 0.010), outpatient antibiotic prescriptions (P < 0.001), and CD-related surgeries (P = 0.011) during the study period after controlling for certain confounders. Elevated IgG4 was only associated with primary sclerosing cholangitis (P = 0.011). A cohort of patients with IgG4-deficient severe IBD received intravenous Ig replacement therapy, which benefited and was continued in 10 out of 11 individuals. CONCLUSIONS: An IgG4 subclass deficiency, distinct from other antibody deficiencies, occurred commonly in a referral IBD population and was associated with multiple markers of disease severity. This is the first association of IgG4 subclass deficiency with an inflammatory disease process. Further work is needed to define the mechanistic role of IgG4 deficiency in this severe IBD subgroup.

Intratumoral budding and automated CD8-positive T-cell density in pretreatment biopsies can predict response to neoadjuvant therapy in rectal adenocarcinoma.

Tumor budding and CD8-positive (+) T-cells are recognized as prognostic factors in colorectal adenocarcinoma. We assessed CD8+ T-cell density and intratumoral budding in pretreatment rectal cancer biopsies to determine if they are predictive biomarkers for response to neoadjuvant therapy and survival. Pretreatment biopsies of locally advanced rectal adenocarcinoma from 117 patients were evaluated for CD8+ T-cell density using automated quantitative digital image analysis and for intratumoral budding and correlated with clinicopathological variables on postneoadjuvant surgical resection specimens, response to neoadjuvant therapy, and survival. Patients with high CD8+ T-cell density (≥157 per mm2) on biopsy were significantly more likely to exhibit complete/near complete response to neoadjuvant therapy (66% vs. 33%, p = 0.001) and low tumor stage (0 or I) on resection (62% vs. 30%, p = 0.001) compared with patients with low CD8+ T-cell density. High CD8+ T-cell density was an independent predictor of response to neoadjuvant therapy with a 2.63 higher likelihood of complete response (95% CI 1.04-6.65, p = 0.04) and a 3.66 higher likelihood of complete/near complete response (95% CI 1.60-8.38, p = 0.002). The presence of intratumoral budding on biopsy was significantly associated with a reduced likelihood of achieving complete/near complete response to neoadjuvant therapy (odds ratio 0.36, 95% CI 0.13-0.97, p = 0.048). Patients with intratumoral budding on biopsy had a significantly reduced disease-free survival compared with patients without intratumoral budding (5-year survival 39% vs 87%, p < 0.001). In the multivariable model, the presence of intratumoral budding on biopsy was associated with a 3.35-fold increased risk of tumor recurrence (95% CI 1.25-8.99, p = 0.02). In conclusion, CD8+ T-cell density and intratumoral budding in pretreatment biopsies of rectal adenocarcinoma are independent predictive biomarkers of response to neoadjuvant therapy and intratumoral budding associates with patient survival. These biomarkers may be helpful in selecting patients who will respond to neoadjuvant therapy and identifying patients at risk for recurrence.