Multi-resolution deep learning characterizes tertiary lymphoid structures and their prognostic relevance in solid tumors.

BACKGROUND: Tertiary lymphoid structures (TLSs) are dense accumulations of lymphocytes in inflamed peripheral tissues, including cancer, and are associated with improved survival and response to immunotherapy in various solid tumors. Histological TLS quantification has been proposed as a novel predictive and prognostic biomarker, but lack of standardized methods of TLS characterization hampers assessment of TLS densities across different patients, diseases, and clinical centers. METHODS: We introduce an approach based on HookNet-TLS, a multi-resolution deep learning model, for automated and unbiased TLS quantification and identification of germinal centers in routine hematoxylin and eosin stained digital pathology slides. We developed HookNet-TLS using n = 1019 manually annotated TCGA slides from clear cell renal cell carcinoma, muscle-invasive bladder cancer, and lung squamous cell carcinoma. RESULTS: Here we show that HookNet-TLS automates TLS quantification across multiple cancer types achieving human-level performance and demonstrates prognostic associations similar to visual assessment. CONCLUSIONS: HookNet-TLS has the potential to be used as a tool for objective quantification of TLS in routine H&E digital pathology slides. We make HookNet-TLS publicly available to promote its use in research.

Tertiary lymphoid structures (TLS) are dense accumulations of immune cells within a cancer. They have been associated with patient survival and treatment effectiveness. Quantification of TLS in cancer microscopy images may therefore aid clinical decision-making. However, no consensus for defining TLS in such images exists leading to inconsistent and variable findings across different labs and studies. We developed a computational tool for automated and objective TLS quantification in cancer images. The tool, called HookNet-TLS, integrates information from multiple image resolutions, which resembles the process of how a pathologist would identify these structures using a microscope. HookNet-TLS detected TLS similarly to trained researchers in three different tumor types. We provided access to HookNet-TLS to facilitate its development and use for TLS assessment in clinical decision-making and research into the role of TLS in cancer.

Dynamics of T cell repertoire renewal following autologous hematopoietic stem cell transplantation in multiple sclerosis.

Autologous hematopoietic stem cell transplantation (aHSCT) is a highly effective treatment of multiple sclerosis (MS). It depletes autoreactive cells and subsequently renews adaptive immune cells. The possible proinflammatory potential of surviving T cells early after aHSCT has not been studied. Here, we examined the dynamics of new and surviving T cells in 27 patients after aHSCT by multidimensional flow cytometry, T cell receptor (TCR) sequencing, specificity testing, telomere length profiling, and HLA genotyping. Early after aHSCT, naïve T cells are barely detectable, whereas effector memory (EM) T cells quickly reconstitute to pre-aHSCT values. EM CD4+ T cells early after aHSCT have shorter telomeres, have higher expression of senescence and exhaustion markers, and proliferate less than those before aHSCT. We find a median TCR repertoire overlap of 26% between the early post-aHSCT EM CD4+ T cells and pre-aHSCT, indicating persistence of EM CD4+ T cells early after transplantation. The EM CD4+ TCR repertoire overlap declines to 15% at 12 months after aHSCT, whereas the naïve TCR repertoire entirely renews. HLA-DR-associated EM CD4+ T cell reactivity toward MS-related antigens decreased after aHSCT, whereas reactivity toward EBV increased. Our data show substantial survival of pre-aHSCT EM CD4+ T cells early after transplantation but complete renewal of the T cell repertoire by nascent T cells later.

NK Cells and Innate-Like T Cells After Autologous Hematopoietic Stem Cell Transplantation in Multiple Sclerosis.

Multiple sclerosis (MS) is an autoimmune disease of the central nervous system, in which autoreactive T and B cells play important roles. Other lymphocytes such as NK cells and innate-like T cells appear to be involved as well. To name a few examples, CD56bright NK cells were described as an immunoregulatory NK cell subset in MS while innate-like T cells in MS were described in brain lesions and with proinflammatory signatures. Autologous hematopoietic stem cell transplantation (aHSCT) is a procedure used to treat MS. This procedure includes hematopoietic stem/progenitor cell (HSPC) mobilization, then high-dose chemotherapy combined with anti-thymocyte globulin (ATG) and subsequent infusion of the patients own HSPCs to reconstitute a functional immune system. aHSCT inhibits MS disease activity very effectively and for long time, presumably due to elimination of autoreactive T cells. Here, we performed multidimensional flow cytometry experiments in peripheral blood lymphocytes of 27 MS patients before and after aHSCT to address its potential influence on NK and innate-like T cells. After aHSCT, the relative frequency and absolute numbers of CD56bright NK cells rise above pre-aHSCT levels while all studied innate-like T cell populations decrease. Hence, our data support an enhanced immune regulation by CD56bright NK cells and the efficient reduction of proinflammatory innate-like T cells by aHSCT in MS. These observations contribute to our current understanding of the immunological effects of aHSCT in MS.