Tumor Risk Stratification Research Articles

Molecular Genetics of Follicular-Derived Thyroid Cancer.

Simple SummaryThyroid tumors that derive from follicular cells are not a homogeneous entity, showing variable morphological appearance and different degrees of differentiation. Molecular markers are useful for both diagnostic purposes and prognostic stratification of patients. In presurgical setting, molecular testing of indeterminate thyroid nodules on aspirates provides useful diagnostic information; the molecular analysis on tumor tissues can also reveal the presence of genetic alterations related to patients’ prognosis. In recent years, the molecular characterization of these tumors has acquired even more importance thanks to the introduction of targeted drugs. This review summarizes the current literature on the molecular landscape of follicular-derived thyroid tumors.Thyroid cancer is the most common type of endocrine-related malignancy, whose incidence rates have increased dramatically in the last few decades. Neoplasms of follicular origin generally have excellent prognosis, with the exception of less differentiated tumors. Follicular-derived thyroid cancer can manifest as a variety of morphologically distinct entities, characterized by various degrees of differentiation and invasiveness. Histological evaluation is thus crucial for the definition of patients’ prognosis. However, within each histological subtype, tumor behavior can be highly variable, and, in this respect, molecular characterization can provide insightful information to refine the risk stratification of tumors. In addition to the importance of its prognostic role, molecular testing can be used to support the differential diagnosis of thyroid nodules in the absence of marked cyto-morphological aberrations. Finally, with the advent of targeted drugs, the presence of molecular alterations will guide the therapeutic strategies for patients with advanced tumors who do not respond to standard treatment. This review aims to describe the genetic landscape of follicular-derived thyroid tumors also highlighting differences across histological subtypes.

Interleukin 6 regulates the expression of programmed cell death ligand 1 in thyroid cancer.

Programmed cell death ligand 1 (PD‐L1), inducing T cell exhaustion to facilitate immune escape of tumor cells, is upregulated by interleukin 6 (IL‐6) in T cell lymphoma and ovarian cancer. The purpose of this study is to investigate the expression of IL‐6 and PD‐L1 in thyroid cancer, and whether IL‐6 regulates PD‐L1 expression. As a result, IL‐6 and PD‐L1 were highly expressed in thyroid cancer tissues. Multivariate logistic analysis showed that tumor size, distant metastasis, and risk stratification were significantly associated with IL‐6 expression (P < .05), and multifocality, lymph node metastasis, distant metastasis, risk stratification, and IL‐6 expression were identified as the independent predictors of PD‐L1 expression (P < .05). The invasiveness of thyroid cancer was significantly enhanced after IL‐6 treatment or PD‐L1 overexpression. PD‐L1 positive rate correlated with IL‐6 expression in cancer tissues (P < .001), and after IL‐6 treatment, the PD‐L1 expression in TPC‐1 and BCPAP significantly increased. The mitogen‐activated protein kinase pathway (MAPK) and the Janus‐activated kinase (JAK)–signal transducers and activators of transcription 3 (STAT3) signaling pathways were activated by IL‐6, and the IL‐6–induced PD‐L1 expression decreased after treatment with these two signaling pathway inhibitors. Knockdown of transcription factors c‐Jun and stat3 suppressed the expression of PD‐L1 induced by IL‐6, and these two factors could bind to PD‐L1 gene promoter directly and promote its transcription. It is concluded that IL‐6 and PD‐L1 are overexpressed in thyroid cancer and are related to tumor invasiveness. IL‐6 upregulates PD‐L1 expression through the MAPK and JAK‐STAT3 signaling pathways, which function via transcription factors c‐Jun and stat3.

SOX2 amplification and chromosome 3 gain significantly impact prognosis in esophageal squamous cell carcinoma.

BackgroundWe aimed to investigate the prevalence and prognostic role of Sex determining region Y-box 2 (SOX2) amplification and expression in surgically resected esophageal squamous cell carcinoma (ESCC).MethodsWe evaluated 450 ESCC samples using fluorescence in-situ hybridization and immunohistochemistry for SOX2 gene amplification and protein expression, respectively. The relationships of gene status with various clinicopathological characteristics and patient survival were statistically analyzed.ResultsSOX2 amplifications and chromosome 3 gain were observed in 4.4% and 12.9% of patients with ESCC. SOX2 amplification was associated with later clinical stage, and chromosome 3 gain was associated with earlier clinical stage (P=0.025). Low and high SOX2 expression were found in 28.9% and 24.7% of cases, respectively. SOX2 expression was significantly associated with gene copy number variation (P=0.007). SOX2 amplification was associated with a significantly shorter disease-free survival (DFS) or overall survival (OS). However, chromosome 3 gain was associated with a significantly longer DFS or OS (P<0.001). Multivariate analysis using the Cox proportional hazard model indicated that SOX2 amplification was an independently poorer prognostic factor (DFS, P<0.001, HR 2.638, 95% CI, 1.581–4.403; OS, P<0.001, HR 2.608, 95% CI, 1.562–4.355), along with pathology tumor-node-metastasis (pTNM) stage, whereas chromosome 3 gain was an independently better prognostic factor (DFS, P=0.003, HR 0.486, 95% CI, 0.300–0.789; OS, P=0.003, HR 0.474, 95% CI, 0.289–0.779) for ESCC.ConclusionsThis is the first study wherein SOX2 amplification and chromosome 3 gain in a large cohort of ESCC were evaluated. SOX2 amplification is an independently poorer prognostic factor, whereas chromosome 3 gain is an independently favorable prognostic factor. Our results suggest that SOX2 amplification and chromosome 3 gain are potential biomarkers related to tumor progression and risk stratification in ESCC.

How to identify indolent thyroid tumors unlikely to recur and cause cancer death immediately after surgery-Risk stratification of papillary thyroid carcinoma in young patients.

Current histopathological diagnosis methods cannot distinguish the two types of thyroid carcinoma: clinically significant carcinomas with a potential risk of recurrence, metastasis, and cancer death, and clinically insignificant carcinomas with a slow growth rate. Both thyroid tumors are diagnosed as "carcinoma" in current pathology practice. The clinician usually recommends surgery to the patient and the patient often accepts it because of cancer terminology. The treatment for these clinically insignificant carcinomas does not benefit the patient and negatively impacts society. The author proposed risk stratification of thyroid tumors using the growth rate (Ki-67 labeling index), which accurately differentiates four prognostically relevant risk groups based on the Ki-67 labeling index, ≥30%, ≥10 and <30%, >5 and <10%, and ≤5%. Indolent thyroid tumors with an excellent prognosis have the following four features: young age, early-stage (T1-2 M0), curatively treated, and low proliferation index (Ki-67 labeling index of ≤5%), and are unlikely to recur, metastasize, or cause cancer death. Accurate identification of these indolent tumors helps clinicians select more conservative treatments to avoid unnecessary aggressive (total thyroidectomy followed by radio-active iodine) treatments. Clinicians can alleviate the fears of patients by confirming these four features, including the low proliferation rate, in a pathology report immediately after surgery when patients are most concerned.

New frontiers in imaging including radiomics updates for pancreatic neuroendocrine neoplasms.

To illustrate the applications of various imaging tools including conventional MDCT, MRI including DWI, CT & MRI radiomics, FDG & DOTATATE PET-CT for diagnosis, staging, grading, prognostication, treatment planning and assessing treatment response in cases of pancreatic neuroendocrine neoplasms (PNENs). Gastroenteropancreatic neuroendocrine neoplasms (GEP NENs) are very diverse clinically & biologically. Their treatment and prognosis depend on staging and primary site, as well as histological grading, the importance of which is also reflected in the recently updated WHO classification of GEP NENs. Grade 3 poorly differentiated neuroendocrine carcinomas (NECs) are aggressive & nearly always advanced at diagnosis with poor prognosis; whereas Grades-1 and 2 well-differentiated neuroendocrine tumors (NETs) can be quite indolent. Grade 3 well-differentiated NETs represent a new category of neoplasm with an intermediate prognosis. Importantly, the evidence suggest grade heterogeneity can occur within a given tumor and even grade progression can occur over time. Emerging evidence suggests that several non-invasive qualitative and quantitative imaging features on CT, dual-energy CT (DECT), MRI, PET and somatostatin receptor imaging with new tracers, as well as texture analysis, may be useful to grade, prognosticate, and accurately stage primary NENs. Imaging features may also help to inform choice of treatment and follow these neoplasms post-treatment. GEP NENs treatment and prognosis depend on the stage as well as histological grade of the tumor. Traditional ways of imaging evaluation for diagnosis and staging does not yet yield sufficient information to replace operative and histological evaluation. Recognition of important qualitative imaging features together with quantitative features and advanced imaging tools including functional imaging with DWI MRI, DOTATATE PET/CT, texture analysis with radiomics and radiogenomic features appear promising for more accurate staging, tumor risk stratification, guiding management and assessing treatment response.

Management of Deep Margin Involvement and or Perineural Invasion in Cutaneous Squamous Cell Carcinoma in the Head and Neck in a Single Unit: 12 Years’ Experience

INTRODUCTION: The eighth edition of American Joint Committee on Cancer guidelines separated cutaneous squamous cell carcinoma in the head and neck (cHNSCCs) into its own entity within head and neck malignancies with the aim of improving tumor risk stratification. The lack of precise prognostic estimates for cHNSCCs prevents clear guidance on the clinical approach to cHNSCCs resulting in heterogeneity of management. OBJECTIVE: Detailed review of the historical management of cHNSCCs in a single tertiary skin cancer center with the aim of creating a treatment algorithm that provides guidance in selecting the appropriate workup and treatment while minimizing unnecessary treatment and resulting morbidity. METHODS: Retrospective review of our institutional pathology database from January 2007 to December 2019 of all recorded head and neck cutaneous lesions excised by St Helens & Knowsley Teaching Hospitals NHS Foundation Trust Plastic Surgery Department. Primary outcomes include recurrence rates and cHNSCC-related mortality. RESULTS: A total of 442 lesions of cHNSCCs from 216 patients excised from the head and neck region were excised during the study period and 164 cHNSCCs had deep margin involvement ± perineural invasion. Median age was 78 years (49–98 years). Median follow-up was 23 months (0–153 months), 9 patients (4%) were lost to follow-up. Seven patients (3%) died before their first 3-monthly follow-up appointment was due. Thirty-nine patients (18%) were immunosuppressed, 10 were solid organ transplant recipients. One hundred thirteen patients (52%) were deceased at the time of review, 25 (22%) died directly or from complications of cHNSCCs. Out of 164 cHNSCCS, majority had deep margin involvement (77%, n = 126), 21% (n = 35) had both deep margin and perineural involvement. Only 5 patients (3%) had cHNSCCs with features of perineural invasion but adequate margins. Forty-five patients (27.4%) in the positive cohort (deep margin involvement ± perineural invasion) went on to develop local, regional, or distant recurrence with a median disease-free interval of 7.7 months (0.5–58 months). Overall recurrence rate was 14.5% (n = 64/442) with a false-negative rate of 6.8% (n = 19/278), The scalp was the most common primary tumor site to recur (45%), followed by the ear (27%) and face (23%). Fifty percent of primary tumors that recurred were moderately differentiated compared with 19% which were poorly differentiated. CONCLUSIONS: Our study demonstrates increased recurrence risk of both scalp and ear cHNSCCs, which warrant calls for more aggressive surgical measures, that is, primary excision with a wide margin down to periosteum with flap reconstruction with adjuvant radiotherapy. Routine sentinel lymph node biopsy in high-risk cHNSCCs could play a role in locoregional control.

Past and present of risk stratification of gastrointestinal stromal tumors and its clinical value

Gastrointestinal stromal tumor (GIST) is the most common soft tissue sarcoma in the gastrointestinal tract. Biological behavior of GIST is varied. It is very important to accurately assess the risk of recurrence and metastasis after resection of primary tumor in order to guide adjuvant therapy and predict prognosis. With increasing understanding of the biological behavior of GIST, the risk stratification criterion has undergone continuous reform and improvement since its introduction. In the early stage, clinical parameters such as tumor size and mitotic rate were formulated as risk stages, and then tumor site, tumor rupture and other factors were included to form a more accurate AFIP standard and modified NIH risk stratification. Recently, more researches have used new statistical methods such as nomogram and contour maps, which more accurately predict risk of recurrence and better guide adjuvant treatment. Thus, individualized treatment of GIST becomes possible.

Risk stratification of thymic epithelial tumors by using a nomogram combined with radiomic features and TNM staging.

To construct and validate a nomogram model that integrated the CT radiomic features and the TNM staging for risk stratification of thymic epithelial tumors (TETs). A total of 136 patients with pathology-confirmed TETs who underwent CT examination were collected from two institutions. According to the WHO pathological classification criteria, patients were classified into low-risk and high-risk groups. The TNM staging was determined in terms of the 8th edition AJCC/UICC staging criteria. LASSO regression was performed to extract the optimal features correlated to risk stratification among the 704 radiomic features calculated. A nomogram model was constructed by combining the Radscore and the TNM staging. The clinical performance was evaluated by ROC analysis, calibration curve, and decision curve analysis (DCA). The Kaplan-Meier (KM) analysis was employed for survival analysis. Five optimal features identified by LASSO regression were employed to calculate the Radscore correlated to risk stratification. The nomogram model showed a better performance in both training cohort (AUC = 0.84, 95%CI 0.75-0.91) and external validation cohort (AUC = 0.79, 95%CI 0.69-0.88). The calibration curve and DCA analysis indicated a better accuracy of the nomogram model for risk stratification than either Radscore or the TNM staging alone. The KM analysis showed a significant difference between the two groups stratified by the nomogram model (p = 0.02). A nomogram model that integrated the radiomic signatures and the TNM staging could serve as a reliable model of risk stratification in predicting the prognosis of patients with TETs. • The radiomic features could be associated with the TET pathophysiology. • TNM staging and Radscore could independently stratify the risk of TETs. • The nomogram model is more objective and more comprehensive than previous methods.

Criteria for risk stratification of vulvar and vaginal smooth muscle tumors: a follow-up study with application to leiomyoma variants, smooth muscle tumors of uncertain malignant potential, and leiomyosarcomas

Data have shown that uterine diagnostic criteria are universal for smooth muscle tumors (SMTs) originating in the ovary, vulva, vagina, broad ligament, and other supportive connective tissueand that uterine criteria outperform site-specific criteria for vulvar and vaginal SMTs. Classic benign and malignant spindled SMTs were well represented in our recent study comparing uterine and site-specific criteria in vulvovaginal SMTs, but leiomyoma variants and smooth muscle tumors of uncertain malignant potential (STUMPs) were relatively few. Therefore, we evaluated additional leiomyoma variants, STUMPs, and leiomyosarcomas from 17 patients (10 vaginal and 7 vulvar). The 10 vaginal tumors (59%) comprised cellular leiomyoma (n=2), leiomyoma with bizarre nuclei (n=3), STUMP (n=1), and leiomyosarcoma (n=4). The 7 vulvar tumors (41%) comprised leiomyoma with bizarre nuclei (n=3), STUMP (n=1), and leiomyosarcoma (n=3). Follow-up was available for 13 patients (76.5%) ranging from 1 to 97 months (mean: 17.3; median: 7). Follow-up for some patients with leiomyosarcoma was limited (≤4 months for 4 patients). One vaginal STUMP locally recurred after 19 months, and 2 patients diagnosed with leiomyosarcoma developed distant metastases. All remaining patients had either no evidence of disease at last follow-up (10 patients, 58.8%) or their status was unknown (4 patients, 23.5%). Uterine criteria are valid for vulvovaginal leiomyoma variants and STUMPsand more appropriately classified these tumors than site-specific criteria. Our combined findings from the current and previous studies support use of uterine diagnostic thresholds for the entire spectrum of vulvovaginal SMTs.

Collaborative, Multidisciplinary Evaluation of Cancer Variants Through Virtual Molecular Tumor Boards Informs Local Clinical Practices.

PURPOSEThe cancer research community is constantly evolving to better understand tumor biology, disease etiology, risk stratification, and pathways to novel treatments. Yet the clinical cancer genomics field has been hindered by redundant efforts to meaningfully collect and interpret disparate data types from multiple high-throughput modalities and integrate into clinical care processes. Bespoke data models, knowledgebases, and one-off customized resources for data analysis often lack adequate governance and quality control needed for these resources to be clinical grade. Many informatics efforts focused on genomic interpretation resources for neoplasms are underway to support data collection, deposition, curation, harmonization, integration, and analytics to support case review and treatment planning.METHODSIn this review, we evaluate and summarize the landscape of available tools, resources, and evidence used in the evaluation of somatic and germline tumor variants within the context of molecular tumor boards.RESULTSMolecular tumor boards (MTBs) are collaborative efforts of multidisciplinary cancer experts equipped with genomic interpretation resources to aid in the delivery of accurate and timely clinical interpretations of complex genomic results for each patient, within an institution or hospital network. Virtual MTBs (VMTBs) provide an online forum for collaborative governance, provenance, and information sharing between experts outside a given hospital network with the potential to enhance MTB discussions. Knowledge sharing in VMTBs and communication with guideline-developing organizations can lead to progress evidenced by data harmonization across resources, crowd-sourced and expert-curated genomic assertions, and a more informed and explainable usage of artificial intelligence.CONCLUSIONAdvances in cancer genomics interpretation aid in better patient and disease classification, more streamlined identification of relevant literature, and a more thorough review of available treatments and predicted patient outcomes.

Female genital tract rhabdomyosarcoma in childhood and adolescence: A single center experience.

e22518 Background: Rhabdomyosarcoma is a rare tumor in children and adolescents, presenting 3% to 4% of all pediatric cancers. The female genital tract is considered as a favorable site of childhood RMS. The outcome has improved significantly during the last two decades, attributed to risk stratification and multimodality management of these challenging tumors. Here we present the clinical features and treatment results of girls with genital tract rhabdomyosarcoma to discuss. Methods: Fourteen girls with vaginal and uterine servical rhabdomyosarcoma younger than 18 years of age diagnosed and followed up between the years of 1995 and 2019 were included in this analysis. The clinical features and treatment results of patients were recorded from patient files and hospital information system retrospectively. Results: There were seven cases with vaginal and seven with uterin cervical carcinoma. All patients presented with polypoid masses protruding from the vagina. Median age of patients at diagnosis was 71 months (range 8-200 months). The IRS modified TNM staging was stage I for all the patients. All cases had embryonic type of RMS except one with alveolar type. All patients were treated with surgery and adjuvant chemotherapy, three received radiotherapy additionally. All achieved complete remission. Four patients experienced tumor relapse, 1 patient died with progressive disease. The median follow-up time was 75 months (7-271 months) for 13 patients who were alive with remission. Conclusions: Rhabdomyosarcoma is a rare sarcoma with a higher incidence in children and adolescents. With current treatment strategies, female genital tract rhabdomyosarcomas have a good prognosis. Favorable prognostic factors such as early stage at diagnosis and a favorable histology may contribute to the excellent observed survival. All parties who had involved on the care of these girls must be aware of the high survival with proper treatment to avoid treatment related morbidities and mortalities. Because of the rareness of the disease we wanted to share our experience.

Clinical significance of serial tumor next generation sequencing (NGS) in 155 pediatric cancer patients.

e13666 Background: Molecular profiling using NGS technology is critical for tumor diagnosis, risk stratification, and treatment selection. There are limited data in childhood cancers regarding evolution of genomic changes under the selective pressure of chemoradiotherapy. Here we report on serial testing of hematologic and solid pediatric tumor specimens across the spectrum of diagnosis, during treatment and disease relapse. Methods: Since 2016, 2,144 somatic NGS assays from 1,727 unique cancer patients were performed using the Comprehensive Hematological Malignancy Panel (CHMP) or the Comprehensive Solid Tumor Panel (CSTP). Serial tumor analysis was performed on 155 patients. All tumors were profiled for SNVs/indels, copy number alterations (CNAs), and fusions. The clinical impact on diagnosis, prognosis, and therapy was assessed. Results: 85 and 70 patients were tested with CHMP and CSTP, respectively. 86.5% (134/155) of patients underwent 1 subsequent genetic testing, while 13.5% (21/155) were serially tested for 3 - 6 times. Relapsed or therapy-refractory tumor was the most common indication for repeat CHMP and CSTP analysis of tumor genomics (64.5%, 100/155), primarily to survey for new targetable cancer driver mutations. The second most common reason for serial testing with CHMP was to monitor clonal evolution for patients with bone marrow failure syndromes and/or myelodysplastic syndromes, which resulted in a new cancer diagnosis in 14.6% (6/41) patients. For CSTP, the second most common reason for serial testing was to test a different part of the same tumor for tumors with histologic and/or radiographic heterogeneity (27.1%, 19/70). Of all patients with serial testing, 70 had at least one clinically significant new SNV/indel, 44 had distinct CNAs, and 4 had new clinically actionable fusions. Overall, clinically significant new results were detected in 81 (52.3%) patients, including 53 patients with new clonal changes indicating disease evolution, 31 of diagnostic significance, 9 of prognostic significance, and 8 suggesting new treatment options. Conclusions: Taken together, these data highlight the clinical importance of serial testing of pediatric tumors for potential biomarkers that may impact patients’ care at various time points across the spectrum of their diseases.

High Expression of Interleukin-12A and Its Association with the Clinicopathology and Prognosis of Differentiated Thyroid Cancer

Background: The inflammatory microenvironment is closely related to the occurrence and development of cancer. Members of the interleukin-12 (IL-12) cytokine family play synergistic or antagonistic roles in the tumor microenvironment, in the form of classic heterodimers or newly discovered monomers or homodimers. Objective: The purpose of this study was to investigate the association between IL-12A and the clinicopathology and prognosis of differentiated thyroid cancer (DTC). Methods: A total of 101 pathologically confirmed DTC patients were included in this study. Immunohistochemistry was performed to assess IL-12A expression in DTC and corresponding paracancerous tissues. The associations of IL-12A with clinicopathology and prognosis were evaluated. Results: IL-12A was expressed in both normal thyroid tissues and DTC, but its expression level was significantly higher in DTC than in normal thyroid tissues (p < 0.001). IL-12A was positively correlated with tumor size (p = 0.027), risk stratification (p = 0.020), and TNM (Tumor-Node-Metastasis) stage (p = 0.024), but not with age, sex, pathological type, multifocality, extrathyroid extension, lymph node metastasis, and distant metastasis (all p > 0.05). Lymphocytic thyroiditis was found in 26/101 patients (25.7%), which was negatively associated with IL-12A expression (p = 0.018). Multivariate logistic regression analysis showed that risk stratification was the significant independent predictor of IL-12A expression. The rate of disease persistence or recurrence (P&R) was 13/101 (12.9%), and a positive relationship was found between IL-12A expression and P&R (p = 0.020). Disease-free survival was affected by factors such as tumor size, extrathyroid extension, tumor stage (T stage), and IL-12A expression, with p values of 0.006, 0.048, 0.002, and 0.012, respectively. Multivariate Cox proportional-hazards analysis showed that tumor size ≥2 cm (hazard ratio [HR] = 4.041 [95% CI: 1.144–14.274], p = 0.031) and high IL-12A expression (HR = 4.027 [95% CI 1.014–15.994], p = 0.049) were independent predictors of prognosis of DTC patients. Conclusions: IL-12A is highly expressed in DTC and is associated with disease aggressiveness. In addition, IL-12A is an independent predictor of the outcome of DTC.

Mohs Surgery versus Standard Local Excision for Basal Cell Carcinoma, Squamous Cell Carcinoma, and Melanoma Skin Cancer.

Basal cell carcinoma, squamous cell carcinoma, and melanoma represent the three most common skin cancers that occur on the face. The most common surgical treatments for facial skin cancers are Mohs' surgery and standard local excision. The effective utilization of either of these techniques is based on tumor and patient risk stratification incorporating known risk factors for occult invasion and local recurrence, combined with patient comorbidities, expectations, and desires. Best available evidence highlights multiple and consistent risk factors for each specific skin cancer type, and dictate local control rates reported in the literature. Recognizing gaps in the literature, we compare and review surgical treatment guidelines and data for standard local excision versus Mohs' surgery for cutaneous nonmelanoma and melanoma skin cancer. This article serves as a resource for optimal therapeutic decision making for surgical management of skin cancer on the face.

Computed tomography-based radiomics model for discriminating the risk stratification of gastrointestinal stromal tumors.

The pathological risk degree of gastrointestinal stromal tumors (GISTs) has become an issue of great concern. Computed tomography (CT) is beneficial for showing adjacent tissues in detail and determining metastasis or recurrence of GISTs, but its function is still limited. Radiomics has recently shown a great potential in aiding clinical decision-making. The purpose of our study is to develop and validate CT-based radiomics models for GIST risk stratification. Three hundred and sixty-six patients clinically suspected of primary GISTs from January 2013 to February 2018 were retrospectively enrolled, among which data from 140 patients were eventually analyzed after exclusion. Data from patient CT images were partitioned based on the National Institutes of Health Consensus Classification, including tumor segmentation, radiomics feature extraction and selection. A radiomics model was then proposed and validated. The radiomics signature demonstrated discriminative performance for advanced and nonadvanced GISTs with an area under the curve (AUC) of 0.935 [95% confidence interval (CI) 0.870-1.000] and an accuracy of 90.2% for validation cohort. The radiomics signature demonstrated favorable performance for the risk stratification of GISTs with an AUC of 0.809 (95% CI 0.777-0.841) and an accuracy of 67.5% for the validation cohort. Radiomics analysis could capture features of the four risk categories of GISTs. Meanwhile, this CT-based radiomics signature showed good diagnostic accuracy to distinguish between nonadvanced and advanced GISTs, as well as the four risk stratifications of GISTs. Our findings highlight the potential of a quantitative radiomics analysis as a complementary tool to achieve an accurate diagnosis for GISTs.

Thyroid Nodules with Isolated Macrocalcifications: Malignancy Risk of Isolated Macrocalcifications and Postoperative Risk Stratification of Malignant Tumors Manifesting as Isolated Macrocalcifications.

ObjectiveTo determine the malignancy risk of isolated macrocalcifications (a calcified nodule with complete posterior acoustic shadowing) detected on ultrasonography (US) and to evaluate the postoperative American Thyroid Association (ATA) risk stratification of malignant tumors manifesting as isolated macrocalcifications.Materials and MethodsA total of 3852 thyroid nodules (≥ 1 cm) of 3061 consecutive patients who had undergone biopsy between January 2011 and June 2018 were included in this study. We assessed the prevalence, malignancy rate, and size distribution of isolated macrocalcifications and evaluated the histopathologic features and postoperative ATA risk stratification of malignant tumors manifesting as isolated macrocalcifications.ResultsIsolated macrocalcifications were found in 38 (1.2%) of the 3061 patients. Final diagnosis was established in 30 (78.9%) nodules; seven malignant tumors were diagnosed as papillary thyroid carcinomas (PTCs). The malignancy rate of the isolated macrocalcifications was 23.3% in the 30 nodules with final diagnoses and 18.4% in all nodules. Among the six surgically-treated malignant tumors, five (83.3%) had an extrathyroidal extension (ETE) (minor ETE 1, gross ETE 4), and two (33.3%) had macroscopic lymph node metastasis. Four (66.7%) malignant tumors were categorized as high-risk tumors, one as an intermediate-risk tumor, and one as a low-risk tumor using the ATA risk stratification. Histopathologically, out of the six malignant tumors, ossifications were noted in four (66.7%) and predominant calcifications in two (33.3%).ConclusionThe US pattern of isolated macrocalcifications (≥ 1 cm) showed an intermediate malignancy risk (at least 18.4%). All malignant tumors were PTCs, and most showed an aggressive behavior and a high or intermediate postoperative ATA risk.

EUS tissue acquisition: From A to B.

EUS-guided tissue acquisition (EUS-TA) has made rapid development since its introduction in the early 1990s. The technique is widely accepted and invaluable for staging and diagnosis of a variety of upper gastrointestinal and mediastinal lesions. Fine-needle aspiration (FNA) has long been the gold standard, but due to its limitations such as the inability to retain stroma and associated cellular architecture, novel biopsy needles (FNB) were designed. Overall, FNA and FNB needles perform seemingly equally in terms of diagnostic accuracy, however, the second-generation FNB needles require less passes. The third-generation FNB needles (crown-cut needle types) seem to be preferable to FNA needles as well as to the second-generation FNB needles, when larger histological specimens and preserved tissue architecture are required. EUS-TA is constantly under development, and new applications of this technique include tumor risk stratification according to its genetic profile as well as minimally invasive creation of patient-derived organoids, hallmarks of personized medicine. It remains yet to be shown, whether these applications will lead to a decisive shift from aspiration to biopsy, i.e., from A to B.

Using Machine Learning to Identify True Somatic Variants from Next-Generation Sequencing.

Molecular profiling has become essential for tumor risk stratification and treatment selection. However, cancer genome complexity and technical artifacts make identification of real variants a challenge. Currently, clinical laboratories rely on manual screening, which is costly, subjective, and not scalable. We present a machine learning-based method to distinguish artifacts from bona fide single-nucleotide variants (SNVs) detected by next-generation sequencing from nonformalin-fixed paraffin-embedded tumor specimens. A cohort of 11278 SNVs identified through clinical sequencing of tumor specimens was collected and divided into training, validation, and test sets. Each SNV was manually inspected and labeled as either real or artifact as part of clinical laboratory workflow. A 3-class (real, artifact, and uncertain) model was developed on the training set, fine-tuned with the validation set, and then evaluated on the test set. Prediction intervals reflecting the certainty of the classifications were derived during the process to label "uncertain" variants. The optimized classifier demonstrated 100% specificity and 97% sensitivity over 5587 SNVs of the test set. Overall, 1252 of 1341 true-positive variants were identified as real, 4143 of 4246 false-positive calls were deemed artifacts, whereas only 192 (3.4%) SNVs were labeled as "uncertain," with zero misclassification between the true positives and artifacts in the test set. We presented a computational classifier to identify variant artifacts detected from tumor sequencing. Overall, 96.6% of the SNVs received definitive labels and thus were exempt from manual review. This framework could improve quality and efficiency of the variant review process in clinical laboratories.

Gene Signatures in Cutaneous Malignancies

In this review, we will discuss the recent advances in the identification of landmark gene signatures in cutaneous melanoma and in the discovery of those relevant to cutaneous squamous cell carcinoma (cSCC). Melanoma and cSCC are the most important cutaneous malignancies when considering morbidity and mortality. They are responsible for the greatest number of skin cancer related deaths. Over the past several years, a number of gene signatures have been identified showing great promise in terms of tumor molecular classification and risk stratification of patients to anticipate best therapeutic modalities. These gene signatures have allowed a personalized medicine approach to a comprehensive decision-making process for these patients. Prediction of the prognosis and therapeutic response of patients with melanoma and high-risk cSCC will be aided by the elucidation and utilization of these gene signatures.

Next generation pathology: artificial intelligence enhances histopathology practice.

Deep learning algorithms have shown benefits for pathology in the context of risk stratification of tumors. Although the results are promising, several steps have to be made to confirm clinical utility. In a recent issue of The Journal of Pathology, Colling et al present a perspective manuscript providing a roadmap to routine use of artificial intelligence in histopathology. In this commentary, we aimed to put these key points in the context of recent findings of AI and digital image analysis studies. © 2019 Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.