Lennerz, Jochen K.

Context.— Computational pathology combines clinical pathology with computational analysis, aiming to enhance diagnostic capabilities and improve clinical productivity. However, communication barriers between pathologists and developers often hinder the full realization of this potential. Objective.— To propose a standardized framework that improves mutual understanding of clinical objectives and computational methodologies. The goal is to enhance the development and application of computer-aided diagnostic (CAD) tools. Design.— This article suggests pivotal roles for pathologists and computer scientists in the CAD development process. It calls for increased understanding of computational terminologies, processes, and limitations among pathologists. Similarly, it argues that computer scientists should better comprehend the true use cases of the developed algorithms to avoid clinically meaningless metrics. Results.— CAD tools improve pathology practice significantly. Some tools have even received US Food and Drug Administration approval. However, improved understanding of machine learning models among pathologists is essential to prevent misuse and misinterpretation. There is also a need for a more accurate representation of the algorithms’ performance compared to that of pathologists. Conclusions.— A comprehensive understanding of computational and clinical paradigms is crucial for overcoming the translational gap in computational pathology. This mutual comprehension will improve patient care through more accurate and efficient disease diagnosis.

Abstract Recent advances in the field of immuno‐oncology have brought transformative changes in the management of cancer patients. The immune profile of tumours has been found to have key value in predicting disease prognosis and treatment response in various cancers. Multiplex immunohistochemistry and immunofluorescence have emerged as potent tools for the simultaneous detection of multiple protein biomarkers in a single tissue section, thereby expanding opportunities for molecular and immune profiling while preserving tissue samples. By establishing the phenotype of individual tumour cells when distributed within a mixed cell population, the identification of clinically relevant biomarkers with high‐throughput multiplex immunophenotyping of tumour samples has great potential to guide appropriate treatment choices. Moreover, the emergence of novel multi‐marker imaging approaches can now provide unprecedented insights into the tumour microenvironment, including the potential interplay between various cell types. However, there are significant challenges to widespread integration of these technologies in daily research and clinical practice. This review addresses the challenges and potential solutions within a structured framework of action from a regulatory and clinical trial perspective. New developments within the field of immunophenotyping using multiplexed tissue imaging platforms and associated digital pathology are also described, with a specific focus on translational implications across different subtypes of cancer. © 2024 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

AbstractQuantifying tumor‐infiltrating lymphocytes (TILs) in breast cancer tumors is a challenging task for pathologists. With the advent of whole slide imaging that digitizes glass slides, it is possible to apply computational models to quantify TILs for pathologists. Development of computational models requires significant time, expertise, consensus, and investment. To reduce this burden, we are preparing a dataset for developers to validate their models and a proposal to the Medical Device Development Tool (MDDT) program in the Center for Devices and Radiological Health of the U.S. Food and Drug Administration (FDA). If the FDA qualifies the dataset for its submitted context of use, model developers can use it in a regulatory submission within the qualified context of use without additional documentation. Our dataset aims at reducing the regulatory burden placed on developers of models that estimate the density of TILs and will allow head‐to‐head comparison of multiple computational models on the same data. In this paper, we discuss the MDDT preparation and submission process, including the feedback we received from our initial interactions with the FDA and propose how a qualified MDDT validation dataset could be a mechanism for open, fair, and consistent measures of computational model performance. Our experiences will help the community understand what the FDA considers relevant and appropriate (from the perspective of the submitter), at the early stages of the MDDT submission process, for validating stromal TIL density estimation models and other potential computational models. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland. This article has been contributed to by U.S. Government employees and their work is in the public domain in the USA.

Abstract Modern histologic imaging platforms coupled with machine learning methods have provided new opportunities to map the spatial distribution of immune cells in the tumor microenvironment. However, there exists no standardized method for describing or analyzing spatial immune cell data, and most reported spatial analyses are rudimentary. In this review, we provide an overview of two approaches for reporting and analyzing spatial data (raster versus vector‐based). We then provide a compendium of spatial immune cell metrics that have been reported in the literature, summarizing prognostic associations in the context of a variety of cancers. We conclude by discussing two well‐described clinical biomarkers, the breast cancer stromal tumor infiltrating lymphocytes score and the colon cancer Immunoscore, and describe investigative opportunities to improve clinical utility of these spatial biomarkers. © 2023 The Pathological Society of Great Britain and Ireland.

AbstractThe clinical significance of the tumor‐immune interaction in breast cancer is now established, and tumor‐infiltrating lymphocytes (TILs) have emerged as predictive and prognostic biomarkers for patients with triple‐negative (estrogen receptor, progesterone receptor, and HER2‐negative) breast cancer and HER2‐positive breast cancer. How computational assessments of TILs might complement manual TIL assessment in trial and daily practices is currently debated. Recent efforts to use machine learning (ML) to automatically evaluate TILs have shown promising results. We review state‐of‐the‐art approaches and identify pitfalls and challenges of automated TIL evaluation by studying the root cause of ML discordances in comparison to manual TIL quantification. We categorize our findings into four main topics: (1) technical slide issues, (2) ML and image analysis aspects, (3) data challenges, and (4) validation issues. The main reason for discordant assessments is the inclusion of false‐positive areas or cells identified by performance on certain tissue patterns or design choices in the computational implementation. To aid the adoption of ML for TIL assessment, we provide an in‐depth discussion of ML and image analysis, including validation issues that need to be considered before reliable computational reporting of TILs can be incorporated into the trial and routine clinical management of patients with triple‐negative breast cancer. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

PURPOSE Increased awareness of the distinct tumor biology for adolescents and young adults (AYAs) with cancer has led to improvement in outcomes for this population. However, in cholangiocarcinoma (CCA), a paucity of data exist on the AYA population. To our knowledge, we present the largest study to date on AYA disease biology, treatment patterns, and survival outcomes in CCA. METHODS A multi-institutional cohort of patients with CCA diagnosed with intrahepatic cholangiocarcinoma (ICC) or extrahepatic cholangiocarcinoma (ECC) was used for analysis. Retrospective chart review was conducted on patients who were 50 years old and younger (young; n = 124) and older than 50 years (older; n = 723). RESULTS Among 1,039 patients screened, 847 patients met eligibility (72% ICC, 28% ECC). Young patients had a larger median tumor size at resection compared with older patients (4.2 v 3.6 cm; P = .048), more commonly had N1 disease (65% v 43%; P = .040), and were more likely to receive adjuvant therapy (odds ratio, 4.0; 95% CI, 1.64 to 9.74). Tumors of young patients were more likely to harbor an FGFR2 fusion, BRAF mutation, or ATM mutation ( P < .05 for each). Young patients were more likely to receive palliative systemic therapy (96% v 69%; P < .001), targeted therapy (23% v 8%; P < .001), and treatment on a clinical trial (31% v 19%; P = .004). Among patients who presented with advanced disease, young patients had a higher median overall survival compared with their older counterparts (17.7 v 13.5 months; 95% CI, 12.6 to 22.6 v 11.4 to 14.8; P = .049). CONCLUSION Young patients with CCA had more advanced disease at resection, more commonly received both adjuvant and palliative therapies, and demonstrated improved survival compared with older patients. Given the low clinical trial enrollment and poor outcomes among some AYA cancer populations, data to the contrary in CCA are highly encouraging.

Abstract Background Treatment patterns for intrahepatic cholangiocarcinoma (ICC) and extrahepatic cholangiocarcinoma (ECC) differ, but limited studies exist comparing them. This study examines differences in molecular profiling rates and treatment patterns in these populations, focusing on use of adjuvant, liver-directed, targeted, and investigational therapies. Methods This multicenter collaboration included patients with ICC or ECC treated at 1 of 8 participating institutions. Retrospective data were collected on risk factors, pathology, treatments, and survival. Comparative statistical tests were 2-sided. Results Among 1039 patients screened, 847 patients met eligibility (ICC = 611, ECC = 236). Patients with ECC were more likely than those with ICC to present with early stage disease (53.8% vs 28.0%), undergo surgical resection (55.1% vs 29.8%), and receive adjuvant chemoradiation (36.5% vs 4.2%) (all P &lt; .00001). However, they were less likely to undergo molecular profiling (50.3% vs 64.3%) or receive liver-directed therapy (17.9% vs 35.7%), targeted therapy (4.7% vs 18.9%), and clinical trial therapy (10.6% vs 24.8%) (all P &lt; .001). In patients with recurrent ECC after surgery, the molecular profiling rate was 64.5%. Patients with advanced ECC had a shorter median overall survival than those with advanced ICC (11.8 vs 15.1 months; P &lt; .001). Conclusions Patients with advanced ECC have low rates of molecular profiling, possibly in part because of insufficient tissue. They also have low rates of targeted therapy use and clinical trial enrollment. While these rates are higher in advanced ICC, the prognosis for both subtypes of cholangiocarcinoma remains poor, and a pressing need exists for new effective targeted therapies and broader access to clinical trials.

Abstract Background Laboratory medicine has reached the era where promises of artificial intelligence and machine learning (AI/ML) seem palpable. Currently, the primary responsibility for risk-benefit assessment in clinical practice resides with the medical director. Unfortunately, there is no tool or concept that enables diagnostic quality assessment for the various potential AI/ML applications. Specifically, we noted that an operational definition of laboratory diagnostic quality – for the specific purpose of assessing AI/ML improvements – is currently missing. Methods A session at the 3rd Strategic Conference of the European Federation of Laboratory Medicine in 2022 on “ AI in the Laboratory of the Future” prompted an expert roundtable discussion. Here we present a conceptual diagnostic quality framework for the specific purpose of assessing AI/ML implementations. Results The presented framework is termed diagnostic quality model (DQM) and distinguishes AI/ML improvements at the test, procedure, laboratory, or healthcare ecosystem level. The operational definition illustrates the nested relationship among these levels. The model can help to define relevant objectives for implementation and how levels come together to form coherent diagnostics. The affected levels are referred to as scope and we provide a rubric to quantify AI/ML improvements while complying with existing, mandated regulatory standards. We present 4 relevant clinical scenarios including multi-modal diagnostics and compare the model to existing quality management systems. Conclusions A diagnostic quality model is essential to navigate the complexities of clinical AI/ML implementations. The presented diagnostic quality framework can help to specify and communicate the key implications of AI/ML solutions in laboratory diagnostics.

PURPOSE Patients with progressive or recurrent meningiomas have limited systemic therapy options. Focal adhesion kinase (FAK) inhibition has a synthetic lethal relationship with NF2 loss. Given the predominance of NF2 mutations in meningiomas, we evaluated the efficacy of GSK2256098, a FAK inhibitor, as part of the first genomically driven phase II study in recurrent or progressive grade 1-3 meningiomas. PATIENTS AND METHODS Eligible patients whose tumors screened positively for NF2 mutations were treated with GSK2256098, 750 mg orally twice daily, until progressive disease. Efficacy was evaluated using two coprimary end points: progression-free survival at 6 months (PFS6) and response rate by Macdonald criteria, where PFS6 was evaluated separately within grade-based subgroups: grade 1 versus 2/3 meningiomas. Per study design, the FAK inhibitor would be considered promising in this patient population if either end point met the corresponding decision criteria for efficacy. RESULTS Of 322 patients screened for all mutation cohorts of the study, 36 eligible and evaluable patients with NF2 mutations were enrolled and treated: 12 grade 1 and 24 grade 2/3 patients. Across all grades, one patient had a partial response and 24 had stable disease as their best response to treatment. In grade 1 patients, the observed PFS6 rate was 83% (10/12 patients; 95% CI, 52 to 98). In grade 2/3 patients, the observed PFS6 rate was 33% (8/24 patients; 95% CI, 16 to 55). The study met the PFS6 efficacy end point both for the grade 1 and the grade 2/3 cohorts. Treatment was well tolerated; seven patients had a maximum grade 3 adverse event that was at least possibly related to treatment with no grade 4 or 5 events. CONCLUSION GSK2256098 was well tolerated and resulted in an improved PFS6 rate in patients with recurrent or progressive NF2-mutated meningiomas, compared with historical controls. The criteria for promising activity were met, and FAK inhibition warrants further evaluation for this patient population.

Abstract Purpose: Selective FGFR inhibitors are effective against cholangiocarcinomas that harbor gene alterations in FGFR2. Clinical trials suggest that expression of wild-type FGFR mRNA can predict sensitivity to FGFR inhibitors, but this biomarker has not been well characterized in cholangiocarcinoma. This study explores the prevalence of FGFR mRNA overexpression in cholangiocarcinoma, its role in predicting sensitivity to FGFR inhibitors, and its association with immune markers. Experimental Design: Tissue microarrays of intrahepatic (ICC) and extrahepatic cholangiocarcinomas (ECC) resected between 2004 and 2015 were used to evaluate FGFR1–4 mRNA expression levels by RNA in situ hybridization (ISH). Expression levels of FGFR2 mRNA were correlated with FGFR2 fusion status and with patient outcomes. Immune markers expression was assessed by IHC and CSF1 and CSF1 receptor expression were examined by RNA ISH. Results: Among 94 patients with resected cholangiocarcinoma, the majority had ICC (77%). FGFR2 fusions were identified in 23% of ICCs and 5% of ECCs. High levels of FGFR mRNA in FGFR2 fusion–negative ICC/ECC were seen for: FGFR1 (ICC/ECC: 15%/0%), FGFR2 (ICC/ECC: 57%/0%), FGFR3 (ICC/ECC: 53%/18%), and FGFR4 (ICC/ECC: 32%/0%). Overall, 62% of fusion-negative cholangiocarcinomas showed high levels of FGFR mRNA. In patients with advanced FGFR2 fusion–positive ICC, high levels of FGFR2 mRNA did not correlate with clinical benefit. FGFR2 fusion–positive tumors showed a paucity of PD-L1 on tumor cells. Conclusions: FGFR mRNA overexpression occurs frequently in cholangiocarcinoma in the absence of genetic alterations in FGFR. This study identifies a molecular subpopulation in cholangiocarcinoma for which further investigation of FGFR inhibitors is merited outside currently approved indications.