Artificial Intelligence-Based Tool for Tumor Detection and Quantitative Tissue Analysis in Colorectal Specimens.

Digital pathology adoption allows for applying computational algorithms to routine pathology tasks. Our study aimed to develop a clinical-grade artificial intelligence (AI) tool for precise multiclass tissue segmentation in colorectal specimens (resections and biopsies) and clinically validate the tool for tumor detection in biopsy specimens. The training data set included 241 precisely manually annotated whole-slide images (WSIs) from multiple institutions. The algorithm was trained for semantic segmentation of 11 tissue classes with an additional module for biopsy WSI classification. Six case cohorts from 5 pathology departments (4 countries) were used for formal and clinical validation, digitized by 4 different scanning systems. The developed algorithm showed high precision of segmentation of different tissue classes in colorectal specimens with composite multiclass Dice score of up to 0.895 and pixel-wise tumor detection specificity and sensitivity of up to 0.958 and 0.987, respectively. In the clinical validation study on multiple external cohorts, the AI tool reached sensitivity of 1.0 and specificity of up to 0.969 for tumor detection in biopsy WSI. The AI tool analyzes most biopsy cases in less than 1 minute, allowing effective integration into clinical routine. We developed and extensively validated a highly accurate, clinical-grade tool for assistive diagnostic processing of colorectal specimens. This tool allows for quantitative deciphering of colorectal cancer tissue for development of prognostic and predictive biomarkers and personalization of oncologic care. This study is a foundation for a SemiCOL computational challenge. We open-source multiple manually annotated and weakly labeled test data sets, representing a significant contribution to the colorectal cancer computational pathology field.

Radiomics for the non-invasive prediction of PD-L1 expression in patients with brain metastases secondary to non-small cell lung cancer.

BACKGROUND: The expression level of the programmed cell death ligand 1 (PD-L1) appears to be a predictor for response to immunotherapy using checkpoint inhibitors in patients with non-small cell lung cancer (NSCLC). As differences in terms of PD-L1 expression levels in the extracranial primary tumor and the brain metastases may occur, a reliable method for the non-invasive assessment of the intracranial PD-L1 expression is, therefore of clinical value. Here, we evaluated the potential of radiomics for a non-invasive prediction of PD-L1 expression in patients with brain metastases secondary to NSCLC. PATIENTS AND METHODS: Fifty-three NSCLC patients with brain metastases from two academic neuro-oncological centers (group 1, n = 36 patients; group 2, n = 17 patients) underwent tumor resection with a subsequent immunohistochemical evaluation of the PD-L1 expression. Brain metastases were manually segmented on preoperative T1-weighted contrast-enhanced MRI. Group 1 was used for model training and validation, group 2 for model testing. After image pre-processing and radiomics feature extraction, a test-retest analysis was performed to identify robust features prior to feature selection. The radiomics model was trained and validated using random stratified cross-validation. Finally, the best-performing radiomics model was applied to the test data. Diagnostic performance was evaluated using receiver operating characteristic (ROC) analyses. RESULTS: An intracranial PD-L1 expression (i.e., staining of at least 1% or more of tumor cells) was present in 18 of 36 patients (50%) in group 1, and 7 of 17 patients (41%) in group 2. Univariate analysis identified the contrast-enhancing tumor volume as a significant predictor for PD-L1 expression (area under the ROC curve (AUC), 0.77). A random forest classifier using a four-parameter radiomics signature, including tumor volume, yielded an AUC of 0.83 ± 0.18 in the training data (group 1), and an AUC of 0.84 in the external test data (group 2). CONCLUSION: The developed radiomics classifiers allows for a non-invasive assessment of the intracranial PD-L1 expression in patients with brain metastases secondary to NSCLC with high accuracy.

BCG invokes superior STING-mediated innate immune response over radiotherapy in a carcinogen murine model of urothelial cancer.

Radiation and bacillus Calmette-Guérin (BCG) instillations are used clinically for treatment of urothelial carcinoma, but the precise mechanisms by which they activate an immune response remain elusive. The role of the cGAS-STING pathway has been implicated in both BCG and radiation-induced immune response; however, comparison of STING pathway molecules and the immune landscape following treatment in urothelial carcinoma has not been performed. We therefore comprehensively analyzed the local immune response in the bladder tumor microenvironment following radiotherapy and BCG instillations in a well-established spontaneous murine model of urothelial carcinoma to provide insight into activation of STING-mediated immune response. Mice were exposed to the oral carcinogen, BBN, for 12 weeks prior to treatment with a single 15 Gy dose of radiation or three intravesical instillations of BCG (1 × 108 CFU). At sacrifice, tumors were staged by a urologic pathologist and effects of therapy on the immune microenvironment were measured using the NanoString Myeloid Innate Immunity Panel and immunohistochemistry. Clinical relevance was established by measuring immune biomarker expression of cGAS and STING on a human tissue microarray consisting of BCG-treated non-muscle-invasive urothelial carcinomas. BCG instillations in the murine model elevated STING and downstream STING-induced interferon and pro-inflammatory molecules, intratumoral M1 macrophage and T-cell accumulation, and complete tumor eradication. In contrast, radiotherapy caused no changes in STING pathway or innate immune gene expression; rather, it induced M2 macrophage accumulation and elevated FoxP3 expression characteristic of immunosuppression. In human non-muscle-invasive bladder cancer, STING protein expression was elevated at baseline in patients who responded to BCG therapy and increased further after BCG therapy. Overall, these results show that STING pathway activation plays a key role in effective BCG-induced immune response and strongly indicate that the effects of BCG on the bladder cancer immune microenvironment are more beneficial than those induced by radiation. © 2021 The Pathological Society of Great Britain and Ireland.

[Intrauterine fetal demise in extensive SARS-CoV-2-associated placental maternal vascular malperfusion in the setting of SARS-CoV-2 placentitis (severe acute respiratory syndrome coronavirus 2)]. / Intrauteriner Fruchttod bei massiver SARS-CoV-2-assoziierter ("severe acute respiratory syndrome coronavirus 2") plazentarer maternaler Malperfusion im Rahmen einer SARS-CoV-2-Plazentitis.

We report a case of a placenta with extensive maternal vascular malperfusion and chronic histiocytic intervillositis corresponding to SARS-CoV­2 placentitis in the context of fetal demise at 31 weeks of gestation. Placental swamp and PCR of the placental parenchyma, umbilical cord and amnion-chorion membrane showed SARS-CoV-2- and B­betacoronavirus-specific RNA. Maternal vascular malperfusion has been described in cases of SARS-CoV­2 infection; however, the manifested severity of this case in the setting of a severe SARS-CoV­2 placentitis is rare. It emphasizes the need of a maternal prophylactic anticoagulation.

Tumour immune microenvironment in primary and metastatic papillary renal cell carcinoma.

AIMS: Among renal cell carcinoma (RCC) the tumour immune microenvironment has been best characterised in clear cell RCC. In this study we investigated the expression of several immune markers, including PD-L1, FoxP3 and CD8 in primary and metastatic papillary RCC. METHODS AND RESULTS: Three tissue microarrays were constructed from 78 cases with primary papillary RCC and paired metastatic tumour (24 cases) from 78 patients treated between 1982 and 2014. Immunohistochemistry analysis was performed using commercially available antibodies for PD-L1 (clone E1L3N), FoxP3, CD8 and Ki-67. Markers expression level in tumour and/or associated immune cells was analysed by tissue type (non-tumour versus primary tumour versus metastatic tumour) and correlated to clinicopathological features and outcome. CONCLUSION: We found PD-L1 expression in up to one-quarter of primary and metastatic papillary RCC. On univariate analysis, CD8/FoxP3 ratio >1 was associated with favourable outcome, whereas papillary RCCs with high numbers of dual CD8/Ki-67-positive lymphocytes showed an increased likelihood for tumour progression and overall and cancer-related mortality. The association of CD8/FoxP3 ratio >1 and high count of CD8/Ki-67 with outcome remained significant on multivariate analysis when adjusting for stage, grade and patient's age.

Characterization of glycine-N-acyltransferase like 1 (GLYATL1) in prostate cancer.

BACKGROUND: Recent microarray and sequencing studies of prostate cancer showed multiple molecular alterations during cancer progression. It is critical to evaluate these molecular changes to identify new biomarkers and targets. We performed analysis of glycine-N-acyltransferase like 1 (GLYATL1) expression in various stages of prostate cancer in this study and evaluated the regulation of GLYATL1 by androgen. METHOD: We performed in silico analysis of cancer gene expression profiling and transcriptome sequencing to evaluate GLYATL1 expression in prostate cancer. Furthermore, we performed immunohistochemistry using specific GLYATL1 antibody using high-density prostate cancer tissue microarray containing primary and metastatic prostate cancer. We also tested the regulation of GLYATL1 expression by androgen and ETS transcription factor ETV1. In addition, we performed RNA-sequencing of GLYATL1 modulated prostate cancer cells to evaluate the gene expression and changes in molecular pathways. RESULTS: Our in silico analysis of cancer gene expression profiling and transcriptome sequencing we revealed an overexpression of GLYATL1 in primary prostate cancer. Confirming these findings by immunohistochemistry, we show that GLYATL1 is overexpressed in primary prostate cancer compared with metastatic prostate cancer and benign prostatic tissue. Low-grade cancers had higher GLYATL1 expression compared to high-grade prostate tumors. Our studies showed that GLYATL1 is upregulated upon androgen treatment in LNCaP prostate cancer cells which harbors ETV1 gene rearrangement. Furthermore, ETV1 knockdown in LNCaP cells showed downregulation of GLYATL1 suggesting potential regulation of GLYATL1 by ETS transcription factor ETV1. Transcriptome sequencing using the GLYATL1 knockdown prostate cancer cell lines LNCaP showed regulation of multiple metabolic pathways. CONCLUSIONS: In summary, our study characterizes the expression of GLYATL1 in prostate cancer and explores the regulation of its regulation in prostate cancer showing role for androgen and ETS transcription factor ETV1. Future studies are needed to decipher the biological significance of these findings.

Incidence and distribution of UroSEEK gene panel in a multi-institutional cohort of bladder urothelial carcinoma.

Noninvasive approaches for early detection of bladder cancer are actively being investigated. We recently developed a urine- based molecular assay for the detection and surveillance of bladder neoplasms (UroSEEK). UroSEEK is designed to detect alterations in 11 genes that include most common genetic alterations in bladder cancer. In this study, we analyzed 527 cases, including 373 noninvasive and 154 invasive urothelial carcinomas of bladder from transurethral resections or cystectomies performed at four institutions (1991-2016). Two different mutational analysis assays of a representative tumor area were performed: first, a singleplex PCR assay for evaluation of the TERT promoter region (TERTSeqS) and second, a multiplex PCR assay using primers designed to amplify regions of interest of 10 (FGFR3, PIK3CA, TP53, HRAS, KRAS, ERBB2, CDKN2A, MET, MLL, and VHL) genes (UroSeqS). Overall, 92% of all bladder tumors were positive for at least one genetic alteration in the UroSEEK panel. We found TERT promoter mutations in 77% of low-grade noninvasive papillary carcinomas, with a relatively lower incidence of 65% in high-grade noninvasive papillary carcinomas and carcinomas in situ; p = 0.017. Seventy-two percent of pT1 and 63% of muscle-invasive bladder tumors harbored TERT promoter mutations with g.1295228C>T alteration being the most common in all groups. FGFR3 and PIK3CA mutations were more frequent in low-grade noninvasive papillary carcinomas compared with high-grade noninvasive papillary carcinomas and carcinomas in situ (p < 0.0001), while the opposite was true for TP53 (p < 0.0001). Significantly higher rates of TP53 and CDKN2A mutation rates (p = 0.005 and 0.035, respectively) were encountered in muscle-invasive bladder tumors compared with those of pT1 stage. The overwhelming majority of all investigated tumors showed at least one mutation among UroSEEK assay genes, confirming the comprehensive coverage of the panel and supporting its potential utility as a noninvasive urine-based assay.

HoLy-Net: Segmentation of histological images of diffuse large B-cell lymphoma.

Over the last years, there has been large progress in automated segmentation and classification methods in histological whole slide images (WSIs) stained with hematoxylin and eosin (H&E). Current state-of-the-art (SOTA) techniques are based on diverse datasets of H&E-stained WSIs of different types of predominantly solid cancer. However, there is a scarcity of methods and datasets enabling segmentation of tumors of the lymphatic system (lymphomas). Here, we propose a solution for segmentation of diffuse large B-cell lymphoma (DLBCL), the most common non-Hodgkin's lymphoma. Our method applies to both H&E-stained slides and to a broad range of markers stained with immunohistochemistry (IHC). While IHC staining is an important tool in cancer diagnosis and treatment decisions, there are few automated segmentation and classification methods for IHC-stained WSIs. To address the challenges of nuclei segmentation in H&E- and IHC-stained DLBCL images, we propose HoLy-Net - a HoVer-Net-based deep learning model for lymphoma segmentation. We train two different models, one for segmenting H&E- and one for IHC-stained images and compare the test results with the SOTA methods as well as with the original version of HoVer-Net. Subsequently, we segment patient WSIs and perform single cell-level analysis of different cell types to identify patient-specific tumor characteristics such as high level of immune infiltration. Our method outperforms general-purpose segmentation methods for H&E staining in lymphoma WSIs (with an F1 score of 0.899) and is also a unique automated method for IHC slide segmentation (with an F1 score of 0.913). With our solution, we provide a new dataset we denote LyNSeC (lymphoma nuclear segmentation and classification) containing 73,931 annotated cell nuclei from H&E and 87,316 from IHC slides. Our method and dataset open up new avenues for quantitative, large-scale studies of morphology and microenvironment of lymphomas overlooked by the current automated segmentation methods.

Cystic Pelvic Masses in Men: A Presentation of Uncommon Cases and a Literature Review.

Unclear cystic masses in the pelvis in male patients are a rare situation and could be of benign or malignant origin. The underlying diseases demand for specific diagnostic and therapeutic approaches. We present a case series of 3 male patients with different clinical symptoms (perineal pain, urinary retention and a large scrotal cyst) related to cystic lesions in the pelvic region. On all patients initial histopathological workup was unclear. All patients underwent surgery with complete resection of the tumor which revealed a broad spectrum of histopathological findings: unusual form of cystic adenocarcinoma of the prostate, malignant transformation of a dysontogenetic cyst, and finally a very rare diagnosis of a malignant tumor of the Cowper gland. This case series and literature review provide clues for a possible diagnostic and therapeutic approach in the case of unclear pelvic cystic masses and could support urologists during the therapy selection in the future.

TERT RNAscope analysis of sub-centimetric papillary thyroid carcinomas and synchronous lymph node metastases.

BACKGROUND: Sub-centrimetric papillary thyroid carcinomas usually have a good prognosis with a cancer specific survival of > 99%, however in up to 65% of patients, lymph node metastases can be observed. Molecular alterations in BRAF, TERT and TP53 are associated with worse clinicopathological outcome in patients with papillary thyroid carcinoma. MATERIAL AND METHODS: Twenty-two cases of papillary thyroid carcinomas measuring ≤ 1 cm with synchronous lymph node metastases were examined regarding morphological patterns and immunohistochemical status of p53, Ki-67, and BRAF V600E status. TERT RNA expression in lymph node metastases were evaluated by RNAScope®. RESULTS: Morphological patterns were heterogeneous in both primary tumors and lymph node metastases. Proliferation indices measured by Ki-67 were low. Both primary and lymph node metastases were wild type for p53 by immunohistochemical analysis. No lymph node metastasis showed TERT expression by RNAScope®. CONCLUSIONS: Our data indicate that TERT expression is not involved in the development early lymph node metastasis in patients with sub-centimetric PTC.

Frequency and functional characterization of fusion genes in squamous cell carcinoma of the lung.

INTRODUCTION: In contrast to lung adenocarcinoma (LUAD), targetable genetic alterations are less frequently detected in squamous cell carcinoma of the lung (LUSC). Over the last years, gene fusions have become promising targets in many solid cancers. Here, we analysed a cohort of LUSC, identified recurrent fusion genes and functionally characterised these tumour genomes. METHODS: A subset of 1608 squamous cell carcinomas of the lung was analysed by means of the FusionPlex® Lung Panel to identify potentially targetable gene fusions using targeted next-generation sequencing. Cases harbouring recurrent gene fusions were further analysed using FISH, Cytoscan HD arrays and cell culture experiments. RESULTS: We found both, known and novel gene fusions in about 3 % of the cases. Known fusions occurring in lung cancer included ALK::EML4, EGFRvIII, EZR::ROS1 and FGFR3::TACC. We further identified recurrent gene fusions of currently unknown biological function, involving EGFR::VSTM2A and NSD3::FGFR1 and showed that the occurrence of the EGFR::VSTM2A fusion is accompanied by high-level amplification of EGFR. Our analyses further revealed that the genomes of these LUSC patients are chromosomally unstable, which leads us to believe that such non-actionable genomic rearrangements may be a result of "chromosomal chaos" most probably not representing exclusive cancer-driving genes in this cancer entity. CONCLUSIONS: We emphasise that caution should be taken when novel fusions are found and that the appearance of new gene fusions should always be interpreted in the molecular context of the respective disease.

Impact of FAPI-46/dual-tracer PET/CT imaging on radiotherapeutic management in esophageal cancer.

BACKGROUND: Fibroblast activation protein (FAP) is expressed in the tumor microenvironment (TME) of various cancers. In our analysis, we describe the impact of dual-tracer imaging with Gallium-68-radiolabeled inhibitors of FAP (FAPI-46-PET/CT) and fluorodeoxy-D-glucose (FDG-PET/CT) on the radiotherapeutic management of primary esophageal cancer (EC). METHODS: 32 patients with EC, who are scheduled for chemoradiation, received FDG and FAPI-46 PET/CT on the same day (dual-tracer protocol, 71%) or on two separate days (29%) We compared functional tumor volumes (FTVs), gross tumor volumes (GTVs) and tumor stages before and after PET-imaging. Changes in treatment were categorized as "minor" (adaption of radiation field) or "major" (change of treatment regimen). Immunohistochemistry (IHC) staining for FAP was performed in all patients with available tissue. RESULTS: Primary tumor was detected in all FAPI-46/dual-tracer scans and in 30/32 (93%) of FDG scans. Compared to the initial staging CT scan, 12/32 patients (38%) were upstaged in nodal status after the combination of FDG and FAPI-46 PET scans. Two lymph node metastases were only visible in FAPI-46/dual-tracer. New distant metastasis was observed in 2/32 (6%) patients following FAPI-4 -PET/CT. Our findings led to larger RT fields ("minor change") in 5/32 patients (16%) and changed treatment regimen ("major change") in 3/32 patients after FAPI-46/dual-tracer PET/CT. GTVs were larger in FAPI-46/dual-tracer scans compared to FDG-PET/CT (mean 99.0 vs. 80.3 ml, respectively (p < 0.001)) with similar results for nuclear medical FTVs. IHC revealed heterogenous FAP-expression in all specimens (mean H-score: 36.3 (SD 24.6)) without correlation between FAP expression in IHC and FAPI tracer uptake in PET/CT. CONCLUSION: We report first data on the use of PET with FAPI-46 for patients with EC, who are scheduled to receive RT. Tumor uptake was high and not depending on FAP expression in TME. Further, FAPI-46/dual-tracer PET had relevant impact on management in this setting. Our data calls for prospective evaluation of FAPI-46/dual-tracer PET to improve clinical outcomes of EC.

Blocking the angiopoietin-2-dependent integrin ß-1 signaling axis abrogates small cell lung cancer invasion and metastasis.

Small cell lung cancer (SCLC) is the most aggressive lung cancer entity with an extremely limited therapeutic outcome. Most patients are diagnosed at an extensive stage. However, the molecular mechanisms driving SCLC invasion and metastasis remain largely elusive. We used an autochthonous SCLC mouse model and matched samples from patients with primary and metastatic SCLC to investigate the molecular characteristics of tumor metastasis. We demonstrate that tumor cell invasion and liver metastasis in SCLC are triggered by an Angiopoietin-2 (ANG-2)/Integrin ß-1-dependent pathway in tumor cells, mediated by focal adhesion kinase/Src kinase signaling. Strikingly, CRISPR-Cas9 KO of Integrin ß-1 or blocking Integrin ß-1 signaling by an anti-ANG-2 treatment abrogates liver metastasis formation in vivo. Interestingly, analysis of a unique collection of matched samples from patients with primary and metastatic SCLC confirmed a strong increase of Integrin ß-1 in liver metastasis in comparison with the primary tumor. We further show that ANG-2 blockade combined with PD-1-targeted by anti-PD-1 treatment displays synergistic treatment effects in SCLC. Together, our data demonstrate a fundamental role of ANG-2/Integrin ß-1 signaling in SCLC cells for tumor cell invasion and liver metastasis and provide a potentially new effective treatment strategy for patients with SCLC.

Artificial intelligence for tumour tissue detection and histological regression grading in oesophageal adenocarcinomas: a retrospective algorithm development and validation study.

BACKGROUND: Oesophageal adenocarcinoma and adenocarcinoma of the oesophagogastric junction are among the most common malignant epithelial tumours. Most patients receive neoadjuvant therapy before complete tumour resection. Histological assessment after resection includes identification of residual tumour tissue and areas of regressive tumour, data which are used to calculate a clinically relevant regression score. We developed an artificial intelligence (AI) algorithm for tumour tissue detection and tumour regression grading in surgical specimens from patients with oesophageal adenocarcinoma or adenocarcinoma of the oesophagogastric junction. METHODS: We used one training cohort and four independent test cohorts to develop, train, and validate a deep learning tool. The material consisted of histological slides from surgically resected specimens from patients with oesophageal adenocarcinoma and adenocarcinoma of the oesophagogastric junction from three pathology institutes (two in Germany, one in Austria) and oesophageal cancer cohort of The Cancer Genome Atlas (TCGA). All slides were from neoadjuvantly treated patients except for those from the TCGA cohort, who were neoadjuvant-therapy naive. Data from training cohort and test cohort cases were extensively manually annotated for 11 tissue classes. A convolutional neural network was trained on the data using a supervised principle. First, the tool was formally validated using manually annotated test datasets. Next, tumour regression grading was assessed in a retrospective cohort of post-neoadjuvant therapy surgical specimens. The grading of the algorithm was compared with that of a group of 12 board-certified pathologists from one department. To further validate the tool, three pathologists processed whole resection cases with and without AI assistance. FINDINGS: Of the four test cohorts, one included 22 manually annotated histological slides (n=20 patients), one included 62 sides (n=15), one included 214 slides (n=69), and the final one included 22 manually annotated histological slides (n=22). In the independent test cohorts the AI tool had high patch-level accuracy for identifying both tumour and regression tissue. When we validated the concordance of the AI tool against analyses by a group of pathologists (n=12), agreement was 63·6% (quadratic kappa 0·749; p<0·0001) at case level. The AI-based regression grading triggered true reclassification of resected tumour slides in seven cases (including six cases who had small tumour regions that were initially missed by pathologists). Use of the AI tool by three pathologists increased interobserver agreement and substantially reduced diagnostic time per case compared with working without AI assistance. INTERPRETATION: Use of our AI tool in the diagnostics of oesophageal adenocarcinoma resection specimens by pathologists increased diagnostic accuracy, interobserver concordance, and significantly reduced assessment time. Prospective validation of the tool is required. FUNDING: North Rhine-Westphalia state, Federal Ministry of Education and Research of Germany, and the Wilhelm Sander Foundation.

Digital droplet PCR-based quantification of ccfHPV-DNA as liquid biopsy in HPV-driven cervical and vulvar cancer.

PURPOSE: More than 99% of cervical cancers and up to 40% of vulvar cancers are human papillomavirus (HPV) related. HPV 16 and 18 are the most relevant subtypes. Novel technologies allow the detection of minimal amounts of circulating cell-free HPV DNA (ccfHPV-DNA). The aim of this study was to evaluate ccfHPV-DNA assessed by droplet digital PCR (ddPCR) as a biomarker for molecular therapy monitoring in early, advanced, relapsed and metastatic HPV-driven cervical and vulvar cancer. METHODS: Inclusion criteria of the study were histologically proven HPV 16/18-driven cervical and vulvar cancer with first diagnosed disease, newly diagnosed recurrence, or progression of disease. Blood samples were taken pre- and post-therapeutically. Circulating cell-free HPV DNA was quantified using ddPCR and the results were correlated with clinical data. RESULTS: The mean copy number of ccfHPV-DNA was 838.6 (± 3089.1) in pretreatment and 2.3 (± 6.4) in post-treatment samples (p < 0.05). The copy number of ccfHPV-DNA increased with higher FIGO stages (p < 0.05), which are commonly used for clinical staging/assessment. Furthermore, we compared the distribution of copy numbers between T-stage 1 versus T-stage 2/3. We could show higher copy number level of ccfHPV-DNA in T-stage 2/3 (p < 0.05). CONCLUSIONS: Therapy monitoring with determination of ccfHPV-DNA by ddPCR with a small amount of plasma reflects response to therapy and appears feasible for patients in advanced cancer stages of cervical and vulvar cancer. This promising tool should be examined as marker of therapy monitoring in particular in novel HPV-directed therapies.

An international multi-institutional validation study of the algorithm for prostate cancer detection and Gleason grading.

Pathologic examination of prostate biopsies is time consuming due to the large number of slides per case. In this retrospective study, we validate a deep learning-based classifier for prostate cancer (PCA) detection and Gleason grading (AI tool) in biopsy samples. Five external cohorts of patients with multifocal prostate biopsy were analyzed from high-volume pathology institutes. A total of 5922 H&E sections representing 7473 biopsy cores from 423 patient cases (digitized using three scanners) were assessed concerning tumor detection. Two tumor-bearing datasets (core n = 227 and 159) were graded by an international group of pathologists including expert urologic pathologists (n = 11) to validate the Gleason grading classifier. The sensitivity, specificity, and NPV for the detection of tumor-bearing biopsies was in a range of 0.971-1.000, 0.875-0.976, and 0.988-1.000, respectively, across the different test cohorts. In several biopsy slides tumor tissue was correctly detected by the AI tool that was initially missed by pathologists. Most false positive misclassifications represented lesions suspicious for carcinoma or cancer mimickers. The quadratically weighted kappa levels for Gleason grading agreement for single pathologists was 0.62-0.80 (0.77 for AI tool) and 0.64-0.76 (0.72 for AI tool) for the two grading datasets, respectively. In cases where consensus for grading was reached among pathologists, kappa levels for AI tool were 0.903 and 0.855. The PCA detection classifier showed high accuracy for PCA detection in biopsy cases during external validation, independent of the institute and scanner used. High levels of agreement for Gleason grading were indistinguishable between experienced genitourinary pathologists and the AI tool.

Lymphatic Vessel Invasion in Routine Pathology Reports of Papillary Thyroid Cancer.

Purpose: It is not mandatory to report lymphatic vessel invasion in pathology reports of papillary thyroid cancer (PTC) according to the current Union for International Cancer Control (UICC) TNM (tumor, nodes, and metastases) classification. However, there is some evidence for its correlation with lymph node metastasis (LNM) and prognosis. The aim of this study was to explore the clinical implication of lymphatic vessel invasion documentation of PTC because pathology reports play a pivotal role in postsurgical clinical decision-making in endocrine tumor boards. Methods: Patients undergoing postoperative radioiodine treatment for PTC at the University Hospital of Cologne, Germany between December 2015 and March 2020 were identified. Pathology reports were screened for documentation of lymphatic vessel invasion. Demographics and clinicopathologic data of patients documented, including lymphatic vessel invasion and lymph nodal involvement were analyzed. Results: A total of 578 patients were identified and included. Lymphatic vessel invasion was reported in pathology reports of 366 (63.3%) and omitted in 112 (36.7%) patients. Positive lymphatic vessel invasion (L1) was diagnosed in 67 (18.3%) of 366 patients and was documented as absent (L0) in 299 (81.7%) patients. Lymph nodal (N) status was positive (N+) in 126 (45.6%) and negative (N0) in 150 (54.3%) of these patients. In 54 (80.6%) L1 cases N+ status and in 137 (65.6%) L0 cases N0 status was diagnosed. In 13 (19.4%) cases with L1 status, there were no LNMs (L1 N0). In total, 72 (34.4%) patients had LNM despite L0 status (L0 N+). The sensitivity and specificity of LVI reporting for LNM were 0.42 and 0.91, respectively. Conclusion: In routine pathology reports of PTC used for indication to postoperative radioiodine treatment by a German endocrine tumor board, lymphatic vessel invasion was found to be reported inconsistently and mostly as L0. L1 diagnoses, however, reliably correlated with reported LNM and might, thus, be relevant for clinical decision-making. For this reason, we advocate for standardized pathologic reassessment of lymphatic vessel invasion, in particular for cases where lymph nodes are not included in the pathologic specimen and if L0 is documented.

Radiomics for the noninvasive prediction of the BRAF mutation status in patients with melanoma brain metastases.

BACKGROUND: The BRAF V600E mutation is present in approximately 50% of patients with melanoma brain metastases and an important prerequisite for response to targeted therapies, particularly BRAF inhibitors. As heterogeneity in terms of BRAF mutation status may occur in melanoma patients, a wild-type extracranial primary tumor does not necessarily rule out a targetable mutation in brain metastases using BRAF inhibitors. We evaluated the potential of MRI radiomics for a noninvasive prediction of the intracranial BRAF mutation status. METHODS: Fifty-nine patients with melanoma brain metastases from two university brain tumor centers (group 1, 45 patients; group 2, 14 patients) underwent tumor resection with subsequent genetic analysis of the intracranial BRAF mutation status. Preoperative contrast-enhanced MRI was manually segmented and analyzed. Group 1 was used for model training and validation, group 2 for model testing. After radiomics feature extraction, a test-retest analysis was performed to identify robust features prior to feature selection. Finally, the best performing radiomics model was applied to the test data. Diagnostic performances were evaluated using receiver operating characteristic (ROC) analyses. RESULTS: Twenty-two of 45 patients (49%) in group 1, and 8 of 14 patients (57%) in group 2 had an intracranial BRAF V600E mutation. A linear support vector machine classifier using a six-parameter radiomics signature yielded an area under the ROC curve of 0.92 (sensitivity, 83%; specificity, 88%) in the test data. CONCLUSIONS: The developed radiomics classifier allows a noninvasive prediction of the intracranial BRAF V600E mutation status in patients with melanoma brain metastases with high diagnostic performance.