RESUMO
Efficient molecular targeting therapies for most gastric cancers (GCs) are currently lacking, despite GC being one of the most frequent and often devastating malignancies worldwide. Thus, identification of novel therapeutic targets for GC is in high demand. Recent advancements of high-throughput nucleic acid synthesis methods combined with next-generation sequencing (NGS) platforms have made it feasible to conduct functional genomics screening using large-scale pooled lentiviral libraries aimed at discovering novel cancer therapeutic targets. In this study, we performed NGS-based functional genomics screening for human GC cell lines using an originally constructed 6,399 shRNA library targeting all 2,096 human metabolism genes. Our screening identified aspartyl-tRNA synthetase (DARS) as a possible candidate for a therapeutic target for GC. In-house tissue microarrays containing 346 cases of GC combined with public datasets showed that patients with high expression levels of DARS protein exhibited more advanced clinicopathologic parameters and a worse prognosis, specifically among diffuse-type GC patients. Both in vitro and in vivo experiments concretely evidenced that DARS inhibition achieved robust growth suppression of GC cells. Moreover, RNA sequencing of GC cell lines under shRNA-mediated DARS knockdown suggested that DARS inhibition exerts its effect through the inactivation of multiple p-ERK pathways. This MAPK-related growth suppression by DARS inhibition would also be applicable to other cancers; thus, it is warranted to investigate the expression and clinical significance of DARS in a wide spectrum of malignancies. Taken together, NGS-based high-throughput pooled lentiviral screening showed DARS as a novel prognostic marker and a promising therapeutic target for GC. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Assuntos
Aspartato-tRNA Ligase , Neoplasias Gástricas , Aspartato-tRNA Ligase/genética , Aspartato-tRNA Ligase/metabolismo , Linhagem Celular Tumoral , Detecção Precoce de Câncer , Técnicas de Silenciamento de Genes , Genômica , Humanos , Prognóstico , RNA Interferente Pequeno , Neoplasias Gástricas/tratamento farmacológico , Neoplasias Gástricas/genéticaRESUMO
BACKGROUND: There is no consensus on the necessity of endoscopic sphincterotomy (ES) to prevent post-endoscopic retrograde cholangiopancreatography pancreatitis (PEP) after endoscopic stenting in patients with malignant biliary obstruction. We investigated the incidence of PEP after endoscopic biliary stenting for malignant biliary obstruction with or without ES in a multicenter prospective cohort study. METHODS: We enrolled 807 patients who underwent endoscopic biliary stenting for malignant biliary obstruction with a native papilla at 36 hospitals between April 2017 and March 2018. The incidence of PEP in patients with or without ES was compared for subgroups based on stent type, placement method, and patient background. Univariate and multivariate analysis was performed to investigate the incidence of PEP in all stenting patients. RESULTS: Plastic and metal stents (MS) were inserted in 598 and 209 patients, respectively. The incidence of PEP in patients with or without ES was 7.9% and 7.4%, respectively among all stenting patients. The incidences of PEP with or without ES in plastic stent insertion patients, patients with MS insertion, stent insertions across the papilla, stent insertions across the papilla in patients without main pancreatic duct obstruction, and fully covered MS insertions across the papilla were compared. There was no overall significant difference in the incidence of PEP between those with or without ES. Multivariate logistic regression analysis for the incidence of PEP in all stenting patients revealed obstruction of the main pancreatic duct at the pancreatic head and epinephrine spraying on the papilla were significant factors; there was no significant difference in the incidence of PEP between patients with or without ES. CONCLUSION: Endoscopic sphincterotomy may not contribute to the prevention of PEP after endoscopic biliary stenting for malignant biliary obstruction, even in cases of insertion with a fully covered MS across the papilla.
Assuntos
Colestase , Pancreatite , Humanos , Colangiopancreatografia Retrógrada Endoscópica/efeitos adversos , Colangiopancreatografia Retrógrada Endoscópica/métodos , Esfinterotomia Endoscópica/efeitos adversos , Esfinterotomia Endoscópica/métodos , Estudos Prospectivos , Pancreatite/etiologia , Pancreatite/prevenção & controle , Colestase/etiologia , Colestase/prevenção & controle , Colestase/cirurgia , Stents/efeitos adversosRESUMO
OBJECTIVES: The reported incidence of adverse events (AEs) in endoscopic retrograde cholangiopancreatography (ERCP) varies between 2.5% and 14%. The aim of this study was to evaluate the incidence and severity of AEs in biliary ERCP and to specify the risk factors and preventive measures for post-ERCP pancreatitis (PEP). METHODS: Patients with biliary disease with intact papilla were prospectively enrolled at 36 hospitals between April 2017 and March 2018. The primary outcomes were the incidence and severity of AEs. RESULTS: A total of 16,032 ERCP procedures were performed at the 36 hospitals during the study period and 3739 patients were enrolled. The overall incidence of AEs was 10.1% and ERCP-related mortality was 0.08%. PEP developed in 258 cases (6.9%), bleeding in 33 (0.9%), instrumental AEs in 17 (0.5%), infections in 37 (1.0%), cardiovascular AEs in eight (0.2%), pulmonary AEs in eight (0.2%), drug reaction AE in one (0.03%), pain in 15 (0.4%), and other AEs in 15 (0.4%). Multivariable analysis showed significant risk factors for PEP were: female of younger age, pancreatic guidewire-assisted biliary cannulation, temporary guidewire insertion into the pancreatic duct, total procedure time >60 min, and post-ERCP administration of non-steroidal anti-inflammatory drugs. Effective preventive measures were prophylactic pancreatic stenting (PPS) and epinephrine spraying onto the papilla. CONCLUSIONS: In patients with intact papilla who underwent biliary ERCP, the incidence of AEs was 10.1% and the mortality was 0.08%. PPS and epinephrine spraying may prevent PEP. REGISTRATION: This study was registered in the University Hospital Medical Information Network (UMIN000024820).
Assuntos
Colangiopancreatografia Retrógrada Endoscópica , Pancreatite , Colangiopancreatografia Retrógrada Endoscópica/efeitos adversos , Colangiopancreatografia Retrógrada Endoscópica/métodos , Epinefrina , Feminino , Humanos , Incidência , Pancreatite/epidemiologia , Pancreatite/etiologia , Pancreatite/prevenção & controle , Estudos Prospectivos , Fatores de RiscoRESUMO
BACKGROUND AND AIM: Pancreatic ductal adenocarcinoma (PDAC) is difficult to detect in its early stages with the poorest prognosis of all cancers. To improve the prognosis, a precise diagnosis is needed when we suspect PDAC. Although endoscopic ultrasound-guided fine-needle aspiration biopsy (EUS-FNA) is a widely accepted modality for the diagnosis of PDAC, its sensitivity is 85-89%, and approximately 10% of PDAC cases cannot be diagnosed. The main causes that interrupt the diagnosis of PDAC by using EUS-FNA are tumor size, presence of a vessel or the main pancreatic duct along the puncture route, and difficulty in withdrawing anticoagulant. Pancreatic juice cytology (PJC), the sensitivity of which is 33.3-65.8%, is a method for the diagnosis of PDAC cases in which carrying out of EUS-FNA is difficult. To diagnose PDAC appropriately, we need to improve the diagnostic ability of PJC. METHODS: We examined PJC using synthetic secretin for 138 cases of pancreatic tumor and pancreatic non-cancerous diseases. RESULTS: Sensitivity of PJC improved from 50.9% to 74.0% as a result of synthetic secretin loading, and 13 PDAC cases that had not been able to be diagnosed with EUS-FNA could be diagnosed pathologically by PJC. Although there were 12 patients with mild pancreatitis (8.7%) as a complication, all were relieved with conservative treatment. CONCLUSION: Adding synthetic secretin to PJC is useful for cases in which it is difficult to carry out EUS-FNA for PDAC.
Assuntos
Carcinoma Ductal Pancreático/diagnóstico , Hormônios , Suco Pancreático/citologia , Neoplasias Pancreáticas/diagnóstico , Secretina , Medicamentos Sintéticos , Adulto , Idoso , Idoso de 80 Anos ou mais , Citodiagnóstico , Aspiração por Agulha Fina Guiada por Ultrassom Endoscópico , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Prospectivos , Sensibilidade e EspecificidadeAssuntos
Infecções por Coronavirus/prevenção & controle , Endoscopia Gastrointestinal/métodos , Recursos em Saúde , Saúde Ocupacional/estatística & dados numéricos , Pandemias/prevenção & controle , Equipamento de Proteção Individual/estatística & dados numéricos , Pneumonia Viral/prevenção & controle , Síndrome Respiratória Aguda Grave/prevenção & controle , COVID-19 , Infecções por Coronavirus/epidemiologia , Feminino , Pessoal de Saúde , Humanos , Masculino , Pandemias/estatística & dados numéricos , Equipamento de Proteção Individual/economia , Pneumonia Viral/epidemiologia , Organização Mundial da SaúdeAssuntos
COVID-19/prevenção & controle , Endoscopia Gastrointestinal , Controle de Infecções/métodos , Transmissão de Doença Infecciosa do Paciente para o Profissional/prevenção & controle , Equipamento de Proteção Individual , Aerossóis , Desenho de Equipamento , Humanos , Máscaras , Pandemias , SARS-CoV-2Assuntos
Anticorpos Monoclonais Humanizados/efeitos adversos , Ductos Biliares Extra-Hepáticos , Biópsia/métodos , Colangiopancreatografia Retrógrada Endoscópica/métodos , Colangite Esclerosante , Endossonografia/métodos , Idoso de 80 Anos ou mais , Anticorpos Monoclonais Humanizados/uso terapêutico , Ductos Biliares Extra-Hepáticos/diagnóstico por imagem , Ductos Biliares Extra-Hepáticos/patologia , Colangite Esclerosante/sangue , Colangite Esclerosante/induzido quimicamente , Colangite Esclerosante/diagnóstico , Humanos , Testes de Função Hepática/métodos , Masculino , Pessoa de Meia-Idade , Neoplasias/tratamento farmacológico , Receptor de Morte Celular Programada 1/antagonistas & inibidores , Tomografia Computadorizada por Raios X/métodosRESUMO
Variations in color and texture of histopathology images are caused by differences in staining conditions and imaging devices between hospitals. These biases decrease the robustness of machine learning models exposed to out-of-domain data. To address this issue, we introduce a comprehensive histopathology image dataset named PathoLogy Images of Scanners and Mobile phones (PLISM). The dataset consisted of 46 human tissue types stained using 13 hematoxylin and eosin conditions and captured using 13 imaging devices. Precisely aligned image patches from different domains allowed for an accurate evaluation of color and texture properties in each domain. Variation in PLISM was assessed and found to be significantly diverse across various domains, particularly between whole-slide images and smartphones. Furthermore, we assessed the improvement in domain shift using a convolutional neural network pre-trained on PLISM. PLISM is a valuable resource that facilitates the precise evaluation of domain shifts in digital pathology and makes significant contributions towards the development of robust machine learning models that can effectively address challenges of domain shift in histological image analysis.
Assuntos
Técnicas Histológicas , Processamento de Imagem Assistida por Computador , Aprendizado de Máquina , Redes Neurais de Computação , Coloração e Rotulagem , Humanos , Amarelo de Eosina-(YS) , Processamento de Imagem Assistida por Computador/métodos , HistologiaRESUMO
Background: Photodynamic therapy (PDT) has advanced through the utilization of photosensitizers and specific-wavelength light (≥ 600 nm). However, the widespread adoption of PDT is still impeded by high equipment costs and stringent laser safety requirements. Porphyrins, crucial in PDT, have another absorbance peak of blue light (λ = 380 - 500 nm). This peak corresponds to the wavelength of narrow-band imaging (NBI) (λ = 390 - 445 nm), an image-enhancement technology integrated into endoscopes by Olympus Medical Systems. The study aimed to investigate the potential of widely adopted NBI as a PDT light source for superficial cancers via endoscopes. Methods: Esophageal and biliary cancers were selected for investigation. Human esophageal cancer cell lines (KYSE30, KYSE70, KYSE170) and cholangiocarcinoma cell lines (HuCCT-1, KKU-213) were subjected to verteporfin-mediated PDT under NBI light (λ = 390 - 445 nm). Assessments included spectrometry, crystal violet staining, and fluorescein imaging of singlet oxygen generation and apoptosis. Results: Verteporfin exhibited a peak (λ = 436 nm) consistent with the NBI spectrum, suggesting compatibility with NBI light. NBI light significantly inhibited the growth of esophageal and biliary cancer cells. The half-maximum effective concentration (EC50) values (5 J/cm2) for KYSE30, KYSE70, KYSE170, HuCCT-1, and KKU-213 were calculated as 2.78 ± 0.37µM, 1.76 ± 1.20 µM, 0.77 ± 0.16 µM, 0.65 ± 0.18 µM, and 0.32 ± 0.04 µM, respectively. Verteporfin accumulation in mitochondria, coupled with singlet oxygen generation and observed apoptotic changes, suggests effective PDT under NBI light. Conclusions: NBI is a promising PDT light source for superficial cancers via endoscopes.
RESUMO
(1) Background: There is controversy regarding stent placement for unresectable malignant hilar biliary obstruction (UMHBO). We mainly use the partial stent-in-stent (PSIS) method with an uncovered self-expandable metallic stent (UCSEMS) based on the drainage area and patency period. In this study, we investigated the usefulness and safety of the PSIS method. (2) Methods: In total, 59 patients who underwent the PSIS method for UMHBO at our hospital were included in the study. The technical success rate, clinical success rate, time to recurrent biliary obstruction (TRBO) and overall survival (OS) from the first placement, factors affecting TRBO and OS, and early complications within 30 days after the procedure were evaluated retrospectively. (3) Results: The technical and clinical success rates were 100% and 96.6%, respectively, with a TRBO of 121 days [95% confidence interval: 82-231] and an OS of 194 days [95% confidence interval: 113-305] after the first placement. Early complications occurred in nine patients (15.3%), including five cases of cholangitis, three cases of pancreatitis, and one case of cholecystitis. (4) Conclusions: The PSIS method for UMHBO is safe and useful with high technical and clinical success rates.
RESUMO
Objective Abdominal ultrasonography (AUS) is used to screen for abdominal diseases owing to its low cost, safety, and accessibility. However, the detection rate of pancreatic disease using AUS is unsatisfactory. We evaluated the visualization area of the pancreas and the efficacy of manipulation techniques for AUS with fusion imaging. Methods Magnetic resonance imaging (MRI) volume data were obtained from 20 healthy volunteers in supine and right lateral positions. The MRI volume data were transferred to an ultrasound machine equipped with a fusion imaging software program. We evaluated the visualization area of the pancreas before and after postural changes using AUS with fusion imaging and assessed the liquid-filled stomach method using 500 ml of de-aerated water in 10 randomly selected volunteers. Patients This study included 20 healthy volunteers (19 men and 1 woman) with a mean age of 33.0 (21-37.5) years old. Results Fusion imaging revealed that the visualization area of the entire pancreas using AUS was 55%, which significantly improved to 75% with a postural change and 90% when using the liquid-filled stomach method (p=0.043). Gastrointestinal gas is the main obstacle for visualization of the pancreas. Conclusion Fusion imaging objectively demonstrated that manipulation techniques can improve pancreatic visualization.
RESUMO
The prognostic factors associated with severe-to-fatal post-endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP) remain unclear despite the extensive number of studies on PEP. In total, 3739 ERCP patients with biliary disease with an intact papilla and indicated for ERCP were prospectively enrolled at 36 centers from April 2017 to March 2018. Those with acute pancreatitis diagnosed before ERCP, altered gastrointestinal anatomy, and an American Society of Anesthesiologists (ASA) physical status > 4 were excluded. Univariate and multivariate logistic regression analyses were performed on patient-related factors, operator-related factors, procedure-related factors, and preventive measures to identify potential prognostic factors for severe-to-fatal PEP. Multivariate analyses revealed pancreatic guidewire-assisted biliary cannulation (OR 13.59, 95% CI 4.21-43.83, p < 0.001), post-ERCP non-steroidal anti-inflammatory drug (NSAID) administration (OR 11.54, 95% CI 3.83-34.81, p < 0.001), and previous pancreatitis (OR 6.94, 95% CI 1.45-33.33, p = 0.015) as significant risk factors for severe-to-fatal PEP. Preventive measures included endoscopic biliary sphincterotomy (EST; OR 0.29, 95% CI, 0.11-0.79, p = 0.015) and prophylactic pancreatic stents (PPSs; OR 0.11, 95% CI, 0.01-0.87, p = 0.036). In biliary ERCP, pancreatic guidewire-assisted biliary cannulation, NSAID administration after ERCP, and previous pancreatitis were risk factors for severe-to-fatal PEP, whereas EST and PPS were significant preventive measures for severe-to-fatal PEP.
RESUMO
Screening endoscopy has advanced to facilitate improvements in the detection and prognosis of gastric cancer. However, most early gastric cancers (EGCs) have subtle morphological or color features that are difficult to detect by white-light imaging (WLI); thus, even well-trained endoscopists can miss EGC when using this conventional endoscopic approach. This review summarizes the current and future status of linked color imaging (LCI), a new image-enhancing endoscopy (IEE) method, for gastric screening. LCI has been shown to produce bright images even at a distant view and provide excellent visibility of gastric cancer due to high color contrast relative to the surrounding tissue. LCI delineates EGC as orange-red and intestinal metaplasia as purple, regardless of a history of Helicobacter pylori (Hp) eradication, and contributes to the detection of superficial EGC. Moreover, LCI assists in the determination of Hp infection status, which is closely related to the risk of developing gastric cancer. Transnasal endoscopy (ultra-thin) using LCI is also useful for identifying gastric neoplastic lesions. Recently, several prospective studies have demonstrated that LCI has a higher detection ratio for gastric cancer than WLI. We believe that LCI should be used in routine upper gastrointestinal endoscopies.
Assuntos
Neoplasias Gástricas , Humanos , Neoplasias Gástricas/diagnóstico por imagem , Neoplasias Gástricas/patologia , Cor , Estudos Prospectivos , Detecção Precoce de Câncer , Endoscopia GastrointestinalRESUMO
Endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) is a common technique for diagnosing pancreatic lesions with high accuracy and a low incidence of procedural adverse events. However, occasional adverse events, particularly bleeding, may occur. Procedures for hypervascular lesions are considered important, but their risks are unknown. We aimed to evaluate the safety and diagnostic yield of EUS-FNB for hypervascular pancreatic solid lesions. This study included 301 patients with 308 solid pancreatic lesions who underwent EUS-FNB between May 2011 and December 2018. We performed propensity-score matching to balance clinical differences between hypervascular and hypovascular lesions and analyzed 52 lesions. We compared the safety and diagnostic performance of propensity score-matched cohorts. The sensitivity, specificity, and accuracy rates of EUS-FNB for hypervascular lesions were 94.7%, 100%, and 96.2%, and those for hypovascular lesions were 80.0%, 100%, and 84.6%, respectively. There was no difference in diagnostic performance between hypervascular and hypovascular lesions. Furthermore, adverse events occurred in only one patient (pancreatitis) in the hypovascular group. There were no significant differences in the occurrence of adverse events between hypervascular and hypovascular lesions (0% vs. 3.8%, p = 1.000). Therefore, EUS-FNB may be safe with a high diagnostic yield, even for hypervascular solid pancreatic lesions.
RESUMO
The stomach is an important digestive organ with various biological functions. However, because of the complexity of its cellular and glandular composition, its precise cellular biology has yet to be elucidated. In this study, we conducted single-cell RNA sequencing (scRNA-seq) and subcellular-level spatial transcriptomics analysis of the human stomach and constructed the largest dataset to date: a stomach encyclopedia. This dataset consists of approximately 380,000 cells from scRNA-seq and the spatial transcriptome, enabling integrated analyses of transcriptional and spatial information of gastric and metaplastic cells. This analysis identified LEFTY1 as an uncharacterized stem cell marker, which was confirmed through lineage tracing analysis. A wide variety of cell-cell interactions between epithelial and stromal cells, including PDGFRA+BMP4+WNT5A+ fibroblasts, was highlighted in the developmental switch of intestinal metaplasia. Our extensive dataset will function as a fundamental resource in investigations of the stomach, including studies of development, aging, and carcinogenesis.
Assuntos
Neoplasias Gástricas , Transcriptoma , Humanos , Transcriptoma/genética , Perfilação da Expressão Gênica , Neoplasias Gástricas/genética , Carcinogênese , Análise de Célula Única , Análise de Sequência de RNARESUMO
Jaundice is caused by excess circulating bilirubin, known as hyperbilirubinemia. This symptom is sometimes caused by a critical hepatobiliary disorder, and is generally identified as yellowish sclera when bilirubin levels increase more than 3 mg/dL. It is difficult to identify jaundice accurately, especially via telemedicine. This study aimed to identify and quantify jaundice by trans-conjunctiva optical imaging. Patients with jaundice (total bilirubin ≥3 mg/dL) and normal control subjects (total bilirubin <3 mg/dL) were prospectively enrolled from June 2021 to July 2022. We took bilateral conjunctiva imaging with a built-in camera on a smartphone (1st generation iPhone SE) under normal white light conditions without any restrictions. We processed the images using an Algorithm Based on Human Brain (ABHB) (Zeta Bridge Corporation, Tokyo, Japan) and converted them into a hue degree of Hue Saturation Lightness (HSL) color space. A total of 26 patients with jaundice (9.57 ± 7.11 mg/dL) and 25 control subjects (0.77 ± 0.35 mg/dL) were enrolled in this study. The causes of jaundice among the 18 male and 8 female subjects (median age 61 yrs.) included hepatobiliary cancer (n = 10), chronic hepatitis or cirrhosis (n = 6), pancreatic cancer (n = 4), acute liver failure (n = 2), cholelithiasis or cholangitis (n = 2), acute pancreatitis (n = 1), and Gilbert's syndrome (n = 1). The maximum hue degree (MHD) optimal cutoff to identify jaundice was 40.8 (sensitivity 81% and specificity 80%), and the AUROC was 0.842. The MHD was moderately correlated to total serum bilirubin (TSB) levels (rS = 0.528, p < 0.001). TSB level (≥5 mg/dL) can be estimated by the formula 21.1603 - 0.7371 × 56.3-MHD2. In conclusion, the ABHB-based MHD of conjunctiva imaging identified jaundice using an ordinary smartphone without any specific attachments and deep learning. This novel technology could be a helpful diagnostic tool in telemedicine or self-medication.
RESUMO
Alpha-fetoprotein (AFP) and des-gamma-carboxyprothrombin (DCP) are widely used as tumor markers to diagnose hepatocellular carcinoma (HCC). Some advanced HCCs demonstrate neither AFP nor DCP. This study investigated the characteristics and prognosis of AFP (<20 ng/mL) and DCP (<40 mAU/ml) double-negative HCC (DNHC) in higher-stage HCC. Between April 2012 and March 2022, 419 consecutive patients were enrolled with newly diagnosed HCC and 372 patients were selected that were diagnosed by histopathology and/or imaging. AFP-negative, DCP-negative, and double-negative HCC were identified in 262 patients (70.4%), 143 patients (38.2%), and 120 patients (32.3%), respectively. In higher-BCLC stages (BCLC-B, C, and D), 17 patients (14.7%) were DNHC. Although there was no difference in BCLC staging, there were more cases under TNM Stage III in DNHC (71.0% vs. 41.4%, p = 0.026). The median maximum tumor diameter was smaller in DNHC [3.2 (1.8−5.0) vs. 5.5 (3.5−9.0) cm, p = 0.001] and their median survival time was significantly better, even in higher-stage HCC [47.0 (24.0−84.0) vs. 19.0 (14.0−30.0) months, p = 0.027). DNHC in higher-BCLC stage HCC is independent of BCLC staging, characterized by a tumor diameter < 5 cm, and is treatable with a good prognosis.
RESUMO
Numerous cancer histopathology specimens have been collected and digitized over the past few decades. A comprehensive evaluation of the distribution of various cells in tumor tissue sections can provide valuable information for understanding cancer. Deep learning is suitable for achieving these goals; however, the collection of extensive, unbiased training data is hindered, thus limiting the production of accurate segmentation models. This study presents SegPath-the largest annotation dataset (>10 times larger than publicly available annotations)-for the segmentation of hematoxylin and eosin (H&E)-stained sections for eight major cell types in cancer tissue. The SegPath generating pipeline used H&E-stained sections that were destained and subsequently immunofluorescence-stained with carefully selected antibodies. We found that SegPath is comparable with, or outperforms, pathologist annotations. Moreover, annotations by pathologists are biased toward typical morphologies. However, the model trained on SegPath can overcome this limitation. Our results provide foundational datasets for machine-learning research in histopathology.