Artificial Intelligence Detected the Relationship Between Nuclear Morphological Features and Molecular Abnormalities of Papillary Thyroid Carcinoma.

Papillary thyroid carcinoma (PTC) is the most common type of thyroid carcinoma and has characteristic nuclear features. Genetic abnormalities of PTC affect recent molecular target therapeutic strategy towards RET-altered cases, and they affect clinical prognosis and progression. However, there has been insufficient objective analysis of the correlation between genetic abnormalities and nuclear features. Using our newly developed methods, we studied the correlation between nuclear morphology and molecular abnormalities of PTC with the aim of predicting genetic abnormalities of PTC. We studied 72 cases of PTC and performed genetic analysis to detect BRAF p.V600E mutation and RET fusions. Nuclear features of PTC, such as nuclear grooves, pseudo-nuclear inclusions, and glassy nuclei, were also automatically detected by deep learning models. After analyzing the correlation between genetic abnormalities and nuclear features of PTC, logistic regression models could be used to predict gene abnormalities. Nuclear features were accurately detected with over 0.90 of AUCs in every class. The ratio of glassy nuclei to nuclear groove and the ratio of pseudo-nuclear inclusion to glassy nuclei were significantly higher in cases that were positive for RET fusions (p = 0.027, p = 0.043, respectively) than in cases that were negative for RET fusions. RET fusions were significantly predicted by glassy nuclei/nuclear grooves, pseudo-nuclear inclusions/glassy nuclei, and age (p = 0.023). Our deep learning models could accurately detect nuclear features. Genetic abnormalities had a correlation with nuclear features of PTC. Furthermore, our artificial intelligence model could significantly predict RET fusions of classic PTC.

Targeted Next-Generation Sequencing of Flat Urothelial Lesions Reveals Putative Pathobiological Pathways, Potential Biomarkers, and Rational Therapeutic Targets.

Flat urothelial lesions are controversial diagnostic and prognostic urologic entities whose importance relies mainly on their ability to progress to muscle-invasive tumors via urothelial carcinoma in situ (CIS). However, the carcinogenetic progression of preneoplastic flat urothelial lesions is not well established. Moreover, predictive biomarkers and therapeutic targets of the highly recurrent and aggressive urothelial CIS lesion are lacking. Using a targeted next-generation sequencing (NGS) panel of 17 genes directly involved in bladder cancer pathogenesis, we investigated alterations of genes and pathways with clinical and carcinogenic implications on 119 samples of flat urothelium, including normal urothelium (n = 7), reactive atypia (n = 10), atypia of unknown significance ( n = 34), dysplasia ( n = 23), and CIS (n = 45). The majority of the flat lesions were tumor-associated but grossly/microscopically or temporally separated from the main tumor. Mutations were compared across flat lesions and concerning the concomitant urothelial tumor. Associations between genomic mutations and recurrence after intravesical bacillus Calmette-Guerin treatment were estimated with Cox regression analysis. TERT promoter mutations were highly prevalent in intraurothelial lesions but not in the normal or reactive urothelium, suggesting that it is a critical driver mutation in urothelial tumorigenesis. We found that synchronous atypia of unknown significance-dysplasia-CIS lesions without concomitant papillary urothelial carcinomas had a similar genomic profile that differed from atypia of unknown significance-dysplasia lesions associated with papillary urothelial carcinomas, which harbored significantly more FGFR3, ARID1A, and PIK3CA mutations. KRAS G12C and ERBB2 S310F/Y mutations were exclusively detected in CIS and were associated with recurrence after bacillus Calmette-Guerin treatment (P = .0006 and P = .01, respectively). This targeted NGS study revealed critical mutations involved in the carcinogenetic progression of flat lesions with putative pathobiological pathways. Importantly, KRAS G12C and ERBB2 S310F/Y mutations were identified as potential prognostic and therapeutic biomarkers for urothelial carcinoma.

Use of Artificial Intelligence for the Interpretable Prediction of the Pathologic Diagnosis and Molecular Abnormalities of Flat Urothelial Lesions.

Flat urothelial lesions are important because of their potential for carcinogenesis and development into invasive urothelial carcinomas. However, it is difficult for pathologists to detect early flat urothelial changes and accurately diagnose flat urothelial lesions. To predict the pathologic diagnosis and molecular abnormalities of flat urothelial lesions from pathologic images, artificial intelligence with an interpretable method was used. Next-generation sequencing on 110 hematoxylin and eosin-stained slides of normal urothelium and flat urothelial lesions, including atypical urothelium, dysplasia, and carcinoma in situ, detected 17 types of molecular abnormalities. To generate an interpretable prediction, a new method for segmenting urothelium and a new pathologic criteria-based artificial intelligence (PCB-AI) model was developed. κ Statistics and accuracy measurements were used to evaluate the ability of the model to predict the pathologic diagnosis. The likelihood ratio test was performed to evaluate the logistic regression models for predicting molecular abnormalities. The diagnostic prediction of the PCB-AI model was almost in perfect agreement with the pathologists' diagnoses (weighted κ = 0.98). PCB-AI significantly predicted some molecular abnormalities in an interpretable manner, including abnormalities of TP53 (P = 0.02), RB1 (P = 0.04), and ERCC2 (P = 0.04). Thus, this study developed a new method of obtaining accurate urothelial segmentation, interpretable prediction of pathologic diagnosis, and interpretable prediction of molecular abnormalities.

Pathologic Image Classification of Flat Urothelial Lesions Using Pathologic Criteria-Based Deep Learning.

OBJECTIVES: Pathologic diagnosis of flat urothelial lesions is subject to high interobserver variability. We expected that deep learning could improve the accuracy and consistency of such pathologic diagnosis, although the learning process is a black box. We therefore propose a new approach for pathologic image classification incorporating the diagnostic process of the pathologist into a deep learning method. METHODS: A total of 267 H&E-stained slides of normal urothelium and urothelial lesions from 127 cases were examined. Six independent convolutional neural networks were trained to classify pathologic images according to six pathologic criteria. We then used these networks in the main training for the final diagnosis. RESULTS: Compared with conventional manual analysis, our method significantly improved the classification accuracy of images of flat urothelial lesions. The automated classification showed almost perfect agreement (weighted κ = 0.98) with the consensus reading. In addition, our approach provides the advantages of reliable diagnosis corresponding to histologic interpretation. CONCLUSIONS: We used deep learning to establish an automated subtype classifier for flat urothelial lesions that successfully combines traditional morphologic approaches and complex deep learning to achieve a learning mechanism that seems plausible to the pathologist.

Renal Leukemic Infiltration Overlapping Acute Focal Bacterial Nephritis during Myelodysplastic Syndrome: An Autopsy Case Report.

Renal leukemic infiltration is uncommon in myeloid neoplasms, including myelodysplastic syndromes (MDS). A 76-year-old male patient was admitted to our hospital with complaints of fever and dyspnea. He was diagnosed with MDS with multilineage dysplasia and acute focal bacterial nephritis (AFBN) based on clinical, laboratory, and radiological investigations. Antibiotic treatment temporarily improved his condition, but the radiological image of AFBN remained. His condition gradually deteriorated into multiple organ failure, and he unfortunately died on the 31st day of hospitalization. Autopsy findings revealed significantly increased p53-positive blasts in the bone marrow and renal parenchyma overlapping AFBN, suggesting leukemic transformation and renal infiltration. This case emphasizes the need to review the diagnosis when antibiotic treatment is ineffective in MDS patients with AFBN.

Intrathoracic lipoma of the chest wall that appeared relatively rapidly and could be resected and diagnosed by minimally invasive thoracoscopic surgery: A case report.

The occurrence of lipoma in the thoracic cavity is relatively rare, and it is clinically difficult to distinguish it from liposarcoma. We report a case of intrathoracic lipoma that was pathologically diagnosed and differentiated from liposarcoma after minimally invasive thoracoscopic tumour resection. A 35-year-old male patient without any symptoms was referred to our hospital due to an abnormal shadow on chest x-ray. Computed tomography showed a low-attenuated round-shaped mass of 3.6 cm × 2.3 cm in diameter in the left chest wall. On magnetic resonance imaging, the mass was displayed as a high, high and low signal mass on T1-weighted imaging (WI), T2WI and T2WI with fat suppression, respectively. We suspected a chest wall-type lipoma, but because it appeared in a relatively short period of time and we thought it could be liposarcoma, we performed minimally invasive thoracoscopic surgery for diagnosis and treatment. The tumour was a stalked tumour with a capsule, contiguous to the wall pleura with only a single cord-like structure. The majority of the tumour was found free in the pleural cavity. The tumour was diagnosed as a lipoma by histopathological examination.

Immune Cells Profiles in the Different Sites of COVID-19-Affected Lung Lobes in a Single Patient.

Whereas the COVID-19 disease pathophysiology is under investigation, it is important to identify the pathways of viral transmission and inflammation from the pre-illness to the disease-onset stages. We analyzed five lung lobes from a patient with COVID-19 who finally died after prolonged lung protective ventilation. Pathological examination revealed moderate inflammation in upper lung lobes and uneven yet severe inflammation and diffuse alveolar damage in lower lung lobes. SARS-CoV-2 was detected at higher levels not in severely, but rather moderately inflamed middle lung lobes, and immunohistochemistry and bulk RNA-sequencing results showed that immune cells were detected at higher levels in lower lung lobes. The mRNA expression of cytokine families varied. We found an increase in keratin 5- or aquaporin 3-expressing basal cells in the severely inflamed lower lung lobes, and the alveolar stromal tissues were filled with them. Thus, this analysis of lung samples from a patient helps to determine the COVID-19 pathophysiology at a specific time point, and the virus localization and inflammatory responses at each site of the lungs provide various important indications.

Clinicopathological and Molecular Characteristics of Macroscopically Yellowish-Colored Chromophobe Renal Cell Carcinoma Compared to Non-Yellowish-Colored Chromophobe Renal Cell Carcinoma.

Each histological variant of renal cell tumors has a unique color. The yellowish color of clear cell renal cell carcinoma (CCRCC) is explained by the presence of intracytoplasmic lipid and glycogen accumulation. Color changes in CCRCC are correlated with clinicopathological and metabolic changes, as well as biological behavior. We analyzed and compared the clinical, histopathological, and immunohistochemical features and gene expression profiles, in lipid metabolism of yellowish-colored ChRCC (ChRCC-Y), non-yellowish-colored ChRCC (ChRCC-N), and CCRCC. Of 14 ChRCCs, we retrieved 6 ChRCC-Ys. Patients with ChRCC-Y are younger than those with ChRCC-N, and the tumor is not predominant in males. ChRCC-Ys are smaller than ChRRC-Ns. Three ChRCC-Ys exhibited individual discrete tubule formation. No ChRCC-Ns exhibited individual discrete tubule formation. Two of 6 ChRCC-Ys showed relatively diffuse adipophilin positivity. No ChRCC-Ns demonstrated diffuse positivity for adipophilin. The expression of SCD, FDFT1, and E2F1 showed a tendency to be lower in ChRCC-Y than in ChRCC-N. The expression of PDGFB showed a tendency to be higher in ChRCC-Y than in ChRCC-N. This study demonstrated ChRCC-Y did not indicate an increase in lipid and cholesterol metabolism and that ChRCC-Y did not have the common molecular alteration of CCRCC. The absence of such metabolic acceleration in ChRCC-Y might support the biological indolent behavior. Furthermore, we revealed that macroscopic color changes might be correlated with various clinicopathological features and immunohistochemical and molecular changes from different perspectives. We believe further characterization of RCC, including tumor heterogeneity, is needed to improve the management of patients with RCC.

Detection of HPV infection in urothelial carcinoma using RNAscope: Clinicopathological characterization.

BACKGROUND: Human papillomavirus (HPV) is a well-established mucosotropic carcinogen, but its impact on urothelial neoplasm is unclear. We aimed to clarify the clinical and pathological features of HPV-related urothelial carcinoma (UC). METHODS: Tissue samples of 228 cases of UC were obtained from the bladder, upper and lower urinary tract, and metastatic sites to construct a tissue microarray. The samples were analyzed for the presence of HPV by a highly sensitive and specific mRNA in situ hybridization (RISH) technique (RNAscope) with a probe that can detect 18 varieties of high-risk HPV. We also conducted immunohistochemistry (IHC) for a major HPV capsid antibody and DNA-PCR. RESULTS: The HPV detection rates varied among the methods; probably due to low HPV copy numbers in UC tissues and the insufficient specificity and sensitivity of the IHC and PCR assays. The RISH method had the highest accuracy and identified HPV infection in 12 (5.2%) of the cases. The histopathological analysis of the HPV-positive UC showed six cases of usual type UC, five cases of UC with squamous differentiation (UC_SqD), and one case of micropapillary UC. The HPV detection rate was six-fold higher in the cases of UC_SqD than in the other variants of UC (odds ratio [OR] =8.9, p = 0.002). In addition, HPV infection showed a significant association with tumor grade (OR =9.8, p = 0.03) and stage (OR =4.7, p = 0.03) of UC. Moreover, the metastatic rate was higher in HPV-positive than in negative UC (OR =3.4). CONCLUSION: These data indicate that although the incidence of HPV infection in UC is low, it is significantly associated with squamous differentiation and poor prognosis. Furthermore, our observations show that RNAscope is an ideal method for HPV detection in UC compared with the other standard approaches such as IHC and PCR assays.

Paneth-like cells in renal cell carcinomas and in cysts associated with acquired cystic kidney disease: Clinicopathologic analysis, comparative study and description of precursor lesions.

Paneth-like cells (PLCs) are different from Paneth cells (PCs) and contain Paneth-like granules, which have been reported in non-neoplastic conditions and in neoplasms of various organs. PLCs have been reported in clear cell renal cell carcinoma (CCRCC), but not in non-CCRCC, including acquired cystic disease-associated renal cell carcinoma (ACD-RCC). We analyzed clinicopathological features of 24 acquired cystic disease-associated renal cell carcinoma (ACD-RCC) with PLCs (ACD-RCCP+) and compared with those of 23 ACD-RCCs without PLCs (ACD-RCCP-). Approximately half of ACD-RCCs had PLCs and that almost all kidneys harboring ACD-RCC had cysts with PLCs. The fact that many ACD-RCCs and the cysts had PLCs is further evidence that the cyst with vacuoles and complex architecture might be a precursor lesion for ACD-RCC. The presence of PLCs may provide additional morphologic clue for distinguishing ACD-RCC from PRCC in challenging differential diagnostic workup in acquired cystic disease of the kidney setting.

Novel Application of Loop-mediated Isothermal Amplification for Rapid Detection of Gene Translocation.

Identification of fusion genes in cancer is essential for pathological diagnosis and clinical therapy. Although methods for detection of fusion genes, such as fluorescence in situ hybridization (FISH) and real-time polymerase chain reaction (PCR), have been developed in last two decades, these methods are not ideal for detection of these genetic alterations owing to their high cost and time-consuming procedures. In this study, we developed novel application for detection of gene translocations using loop-mediated isothermal amplification (LAMP). We verified the amplified DNA products of echinoderm microtubule-associated protein-like 4 and anaplastic lymphoma kinase (EML4-ALK), synaptotagmin and synovial sarcoma, X breakpoint (SYT-SSX), and immunoglobulin heavy chain gene and B cell leukemia/lymphoma 2 (IgH/BCL2) by real-time PCR, agarose-gel electrophoresis, and the naked eye after the LAMP procedure. Fusion genes were detected in samples diluted 103 times within 60 min. Because of the advantages of rapid amplification, simple operation, and easy detection without requiring sophisticated equipment or technical skill, LAMP may have potential applications as an on-site analytical approach in hospitals for pathological diagnosis and decision making regarding appropriate therapeutic approachs.