Fei Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fei Chen has a total of 137 co-authors. Here are the top co-authors by number of shared publications:
Aylin Simsir
Department of Pathology and Laboratory Medicine, New York University Grossman School of Medicine and NYU Langone Health, New York, NY
4 shared publications- Liang Cheng
Department of Pathology and Laboratory Medicine, Department of Surgery (Urology), Brown University Warren Alpert Medical School, the Legorreta Cancer Center at Brown University, and Brown University Health, Providence, RI
3 shared publications - Antonio Lopez-Beltran
Department of Pathology, Cordoba University Medical School, Cordoba, Spain
2 shared publications Tamar C Brandler
Department of Pathology, New York University Langone Health , New York, NY
2 shared publicationsAhmed Shabaik
Department of Pathology, UC San Diego School of Medicine, La Jolla, USA
1 shared publicationAlessia Cimadamore
Pathological Anatomy, University of Udine, Udine, Italy
1 shared publication
Latest Publications
- Open Access
- 2 October 2026
- Published by MDPI AG in Microorganisms
- Vol. 14 (10) , 2214
Syndromic Testing in Clinical Microbiology and Infectious Diseases: An Updated Review of Diagnostic Performance, Clinical and Healthcare Impact, and Emerging Developments
Syndromic testing, defined as the simultaneous nucleic acid amplification-based detection of multiple potential pathogens and antimicrobial resistance (AMR) determinants directly from clinical specimens, has transformed laboratory diagnosis of infectious diseases in the United States over the past two decades. In contrast to traditional microbiology workflows that rely on culture, phenotypic susceptibility testing, and sequential single-target assays with turnaround times of 24–72 h or longer, syndromic multiplex panels provide comprehensive pathogen identification within 1–5 h, enabling timely clinical decision-making, targeted antimicrobial therapy, and improved patient outcomes. In this review, the current landscape of FDA-cleared syndromic testing panels across seven major clinical syndromes is examined, including respiratory tract infections, pneumonia, bloodstream infections, gastrointestinal infections, meningitis/encephalitis, joint and bone infections, and global febrile/travel-related illnesses. For each syndrome, commercially available panels in the United States are summarized, with emphasis on diagnostic performance, clinical applications, and limitations. Available evidence demonstrates that syndromic testing, when integrated with institutional diagnostic and antimicrobial stewardship programs, can reduce time to optimal therapy and unnecessary antimicrobial use and, in selected settings, shorten hospital length of stay. A mortality benefit has been reported in some patient populations, particularly those with bloodstream infections. Nevertheless, rapid turnaround time and earlier pathogen identification do not necessarily translate into timely clinical action and improved patient outcomes. Challenges related to implementation and optimization of appropriate panel utilization, including evolving AMR epidemiology, dynamic and geographically variable pathogen distributions, the critical role of diagnostic and antimicrobial stewardship, and emerging developments for diagnosis and management of infectious disease, are also discussed.
- 2 October 2026
- Published by MDPI AG in Microorganisms
- Vol. 14 (10) , 2214
Open AccessSyndromic Testing in Clinical Microbiology and Infectious Diseases: An Updated Review of Diagnostic Performance, Clinical and Healthcare Impact, and Emerging Developments
Syndromic testing, defined as the simultaneous nucleic acid amplification-based detection of multiple potential pathogens and antimicrobial resistance (AMR) determinants directly from clinical specimens, has transformed laboratory diagnosis of infectious diseases in the United States over the past two decades. In contrast to traditional microbiology workflows that rely on culture, phenotypic susceptibility testing, and sequential single-target assays with turnaround times of 24–72 h or longer, syndromic multiplex panels provide comprehensive pathogen identification within 1–5 h, enabling timely clinical decision-making, targeted antimicrobial therapy, and improved patient outcomes. In this review, the current landscape of FDA-cleared syndromic testing panels across seven major clinical syndromes is examined, including respiratory tract infections, pneumonia, bloodstream infections, gastrointestinal infections, meningitis/encephalitis, joint and bone infections, and global febrile/travel-related illnesses. For each syndrome, commercially available panels in the United States are summarized, with emphasis on diagnostic performance, clinical applications, and limitations. Available evidence demonstrates that syndromic testing, when integrated with institutional diagnostic and antimicrobial stewardship programs, can reduce time to optimal therapy and unnecessary antimicrobial use and, in selected settings, shorten hospital length of stay. A mortality benefit has been reported in some patient populations, particularly those with bloodstream infections. Nevertheless, rapid turnaround time and earlier pathogen identification do not necessarily translate into timely clinical action and improved patient outcomes. Challenges related to implementation and optimization of appropriate panel utilization, including evolving AMR epidemiology, dynamic and geographically variable pathogen distributions, the critical role of diagnostic and antimicrobial stewardship, and emerging developments for diagnosis and management of infectious disease, are also discussed.
- 3 September 2026
- Published by Wolters Kluwer Health in American Journal of Surgical Pathology
- Vol. 50 (12) , 1424-1436
Renal Synovial Sarcoma Revisited
Synovial sarcoma is a rare malignant mesenchymal neoplasm that typically occurs in soft tissue sites, and the kidney is an uncommon primary location. Previous studies of primary renal synovial sarcoma are limited by small sample sizes, and our understanding remains incomplete. Here, we present the largest multi-institutional case series to date of primary renal synovial sarcoma, with a focus on novel and molecular findings. A total of 70 cases were contributed by multiple institutions. Comprehensive clinical and histopathologic data were collected and analyzed. The mean patient age was 40 years, with a male-to-female ratio of 1.9:1. The most common presenting signs and symptoms were pain and hematuria. The mean tumor size was 11.6 cm (range: 2.3 to 26 cm), with frequent cystic change and necrosis. The mean follow-up was 29 months (range: 2 to 129 mo), and the rates of metastasis, recurrence, and death due to disease were 62.7%, 33.3%, and 50.0%, respectively. Histologically, 56.1% were monophasic synovial sarcoma, 15.1% were biphasic, and 28.8% were poorly differentiated or showed round cell features. Molecularly, SS18::SSX2 fusion was detected in the majority of cases assessed (n=19), followed by SS18::SSX1 fusion (n=6) and a rare SS18::NEDD4 fusion (n=1). Given the morphologic and immunohistochemical overlaps with many other neoplasms, accurate diagnosis with preferably molecular techniques is crucial for appropriate prognostication and treatment of this aggressive tumor.
- 3 September 2026
- Published by Wolters Kluwer Health in American Journal of Surgical Pathology
- Vol. 50 (12) , 1424-1436
Renal Synovial Sarcoma Revisited
Synovial sarcoma is a rare malignant mesenchymal neoplasm that typically occurs in soft tissue sites, and the kidney is an uncommon primary location. Previous studies of primary renal synovial sarcoma are limited by small sample sizes, and our understanding remains incomplete. Here, we present the largest multi-institutional case series to date of primary renal synovial sarcoma, with a focus on novel and molecular findings. A total of 70 cases were contributed by multiple institutions. Comprehensive clinical and histopathologic data were collected and analyzed. The mean patient age was 40 years, with a male-to-female ratio of 1.9:1. The most common presenting signs and symptoms were pain and hematuria. The mean tumor size was 11.6 cm (range: 2.3 to 26 cm), with frequent cystic change and necrosis. The mean follow-up was 29 months (range: 2 to 129 mo), and the rates of metastasis, recurrence, and death due to disease were 62.7%, 33.3%, and 50.0%, respectively. Histologically, 56.1% were monophasic synovial sarcoma, 15.1% were biphasic, and 28.8% were poorly differentiated or showed round cell features. Molecularly, SS18::SSX2 fusion was detected in the majority of cases assessed (n=19), followed by SS18::SSX1 fusion (n=6) and a rare SS18::NEDD4 fusion (n=1). Given the morphologic and immunohistochemical overlaps with many other neoplasms, accurate diagnosis with preferably molecular techniques is crucial for appropriate prognostication and treatment of this aggressive tumor.
- Open Access
- 8 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-17
Pathologist-like explainable AI for interpretable Gleason grading in prostate cancer
The aggressiveness of prostate cancer is primarily assessed from histopathological data using the Gleason scoring system. Conventional artificial intelligence (AI) approaches can predict Gleason scores, but often lack explainability, which may limit clinical acceptance. Here, we present an alternative, inherently explainable AI that circumvents the need for post-hoc explainability methods. The model was trained on 1,015 tissue microarray core images, annotated with detailed pattern descriptions by 54 international pathologists following standardized guidelines. It uses pathologist-defined terminology and was trained using soft labels to capture data uncertainty. This approach enables robust Gleason pattern segmentation despite high interobserver variability. The model achieved comparable or superior performance to direct Gleason pattern segmentation (Dice score: $${0.713}_{\pm 0.003}$$ vs. $${0.691}_{\pm 0.010}$$ ) while providing interpretable outputs. We release this dataset to encourage further research on segmentation in medical tasks with high subjectivity and to deepen insights into pathologists’ reasoning.- 8 October 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-17
Open AccessPathologist-like explainable AI for interpretable Gleason grading in prostate cancer
The aggressiveness of prostate cancer is primarily assessed from histopathological data using the Gleason scoring system. Conventional artificial intelligence (AI) approaches can predict Gleason scores, but often lack explainability, which may limit clinical acceptance. Here, we present an alternative, inherently explainable AI that circumvents the need for post-hoc explainability methods. The model was trained on 1,015 tissue microarray core images, annotated with detailed pattern descriptions by 54 international pathologists following standardized guidelines. It uses pathologist-defined terminology and was trained using soft labels to capture data uncertainty. This approach enables robust Gleason pattern segmentation despite high interobserver variability. The model achieved comparable or superior performance to direct Gleason pattern segmentation (Dice score: $${0.713}_{\pm 0.003}$$ vs. $${0.691}_{\pm 0.010}$$ ) while providing interpretable outputs. We release this dataset to encourage further research on segmentation in medical tasks with high subjectivity and to deepen insights into pathologists’ reasoning. - 1 July 2025
- Published by American Society of Clinical Oncology (ASCO) in JCO Clinical Cancer Informatics
- Vol. 9 (9) , e2400267
Clinical Application of Large Language Models in Generating Pathologic Images
PURPOSE: This study investigates the potential of DALL·E 3, an artificial intelligence (AI) model, to generate synthetic pathologic images of prostate cancer (PCa) at varying Gleason grades. The aim is to enhance medical education and research resources, particularly by providing diverse case studies and valuable teaching tools. METHODS: This study uses DALL·E 3 to generate 30 synthetic images of PCa across various Gleason grades, guided by standard Gleason pattern descriptions. Nine uropathologists evaluated these images for realism and accuracy compared with actual hematoxylin and eosin (H&E)–stained slides using a scoring system. RESULTS: The average realism and representativeness scores were 6.04 and 6.17, indicating satisfactory quality. Scores varied significantly among Gleason patterns ( P < .05), with Gleason 5 images achieving the highest scores and accurately depicting critical pathologic characteristics. Limitations included a lack of fine nuclear detail, essential for identifying malignancy, which may affect the images' diagnostic utility. CONCLUSION: DALL·E 3 shows promise in generating customized pathologic images that can aid in education and resource expansion within pathology. However, ethical concerns, such as the potential misuse of AI-generated images for data falsification, highlight the need for responsible oversight. Collaboration between technology firms and pathologists is essential for the ethical integration of AI in pathology practices.
- 1 July 2025
- Published by American Society of Clinical Oncology (ASCO) in JCO Clinical Cancer Informatics
- Vol. 9 (9) , e2400267
Clinical Application of Large Language Models in Generating Pathologic Images
PURPOSE: This study investigates the potential of DALL·E 3, an artificial intelligence (AI) model, to generate synthetic pathologic images of prostate cancer (PCa) at varying Gleason grades. The aim is to enhance medical education and research resources, particularly by providing diverse case studies and valuable teaching tools. METHODS: This study uses DALL·E 3 to generate 30 synthetic images of PCa across various Gleason grades, guided by standard Gleason pattern descriptions. Nine uropathologists evaluated these images for realism and accuracy compared with actual hematoxylin and eosin (H&E)–stained slides using a scoring system. RESULTS: The average realism and representativeness scores were 6.04 and 6.17, indicating satisfactory quality. Scores varied significantly among Gleason patterns ( P < .05), with Gleason 5 images achieving the highest scores and accurately depicting critical pathologic characteristics. Limitations included a lack of fine nuclear detail, essential for identifying malignancy, which may affect the images' diagnostic utility. CONCLUSION: DALL·E 3 shows promise in generating customized pathologic images that can aid in education and resource expansion within pathology. However, ethical concerns, such as the potential misuse of AI-generated images for data falsification, highlight the need for responsible oversight. Collaboration between technology firms and pathologists is essential for the ethical integration of AI in pathology practices.
- 7 March 2025
- Published by Elsevier in Urologic Oncology: Seminars and Original Investigations
- Vol. 43 (10) , 565-578
Molecular testing in urinary cytology specimens: Current status and future directions
- 7 March 2025
- Published by Elsevier in Urologic Oncology: Seminars and Original Investigations
- Vol. 43 (10) , 565-578
Molecular testing in urinary cytology specimens: Current status and future directions
- 9 September 2024
- Published by Oxford University Press (OUP) in American Journal of Clinical Pathology
- Vol. 163 (2) , 251-257
TERT promoter mutations and additional molecular alterations in thyroid fine-needle aspiration specimens: A multi-institutional study with histopathologic follow-up
TERT promoter mutations are not infrequently encountered in thyroid carcinomas; however, it is unclear if additional molecular alterations may play a role in determining tumor behavior. Fine-needle aspiration (FNA) specimens from 32 patients with TERT promoter mutations detected by ThyroSeq v3 from 4 institutions were included in the study. FNA diagnoses, molecular results, and surgical follow-up were retrospectively reviewed and analyzed. There were 5 benign and 27 malignant neoplasms, including 7 high-grade thyroid carcinomas (HGCs) on histopathologic follow-up. Of 4 cases with an isolated TERT mutation, 3 (75%) cases were malignant. Of 17 cases harboring a co-occurring TERT mutation with 1 additional molecular alteration, 13 (76%) displayed malignancy on histopathologic follow-up. All 11 cases with TERT mutations plus 2 or more additional molecular alterations were malignant on follow-up. Furthermore, HGC was not seen in cases with an isolated TERT mutation, while 80% of cases harboring TERT mutations plus 3 additional molecular alterations showed HGC. TERT promoter mutations are commonly associated with malignancy, particularly HGCs, when multiple co-occurring molecular alterations are present. However, TERT promoter mutations may occasionally be detected in benign thyroid neoplasms when encountered in isolation or with fewer than 2 additional molecular alterations.
- 9 September 2024
- Published by Oxford University Press (OUP) in American Journal of Clinical Pathology
- Vol. 163 (2) , 251-257
TERT promoter mutations and additional molecular alterations in thyroid fine-needle aspiration specimens: A multi-institutional study with histopathologic follow-up
TERT promoter mutations are not infrequently encountered in thyroid carcinomas; however, it is unclear if additional molecular alterations may play a role in determining tumor behavior. Fine-needle aspiration (FNA) specimens from 32 patients with TERT promoter mutations detected by ThyroSeq v3 from 4 institutions were included in the study. FNA diagnoses, molecular results, and surgical follow-up were retrospectively reviewed and analyzed. There were 5 benign and 27 malignant neoplasms, including 7 high-grade thyroid carcinomas (HGCs) on histopathologic follow-up. Of 4 cases with an isolated TERT mutation, 3 (75%) cases were malignant. Of 17 cases harboring a co-occurring TERT mutation with 1 additional molecular alteration, 13 (76%) displayed malignancy on histopathologic follow-up. All 11 cases with TERT mutations plus 2 or more additional molecular alterations were malignant on follow-up. Furthermore, HGC was not seen in cases with an isolated TERT mutation, while 80% of cases harboring TERT mutations plus 3 additional molecular alterations showed HGC. TERT promoter mutations are commonly associated with malignancy, particularly HGCs, when multiple co-occurring molecular alterations are present. However, TERT promoter mutations may occasionally be detected in benign thyroid neoplasms when encountered in isolation or with fewer than 2 additional molecular alterations.
- 13 April 2023
- Published by Oxford University Press (OUP) in American Journal of Clinical Pathology
- Vol. 160 (2) , 137-143
HPV Cotesting of Unsatisfactory Papanicolaou Tests: Implications for Follow-up Intervals
The 2019 American Society of Colposcopy and Cervical Pathology management guidelines recommend that patients with an unsatisfactory Papanicolaou (Pap) test (UPT) and negative human papillomavirus (HPV) cotest undergo repeat age-based screening in 2 to 4 months. The rationale is that a negative HPV test in the setting of an UPT may reflect an inadequate sample and therefore should not be interpreted as truly “negative.” For patients 25 years and older who are cotested, if HPV is positive for the 16 or 18 genotypes, direct referral for colposcopy is recommended. Our study aimed to determine if a negative HPV cotest result is predictive of the absence of a high-grade squamous intraepithelial lesion (HSIL) and whether these patients may be called back for repeat testing at an interval longer than 2 to 4 months. Follow-up cervical cytology and biopsy results in women with UPT and HPV cotests from January 2017 to December 2021 were collected. Original UPT and HPV cotest results were correlated with the follow-up Pap and biopsy results. There were 1,496 (2.28%) UPT cases out of 65,641 total Pap tests. Among the 1,496 UPT cases, 1,010 (67.5%) had HPV cotesting; 676 (45.1%) were followed by repeat Pap or biopsy within 4 months and 850 (56.8%) within 12 months. The total follow-up rate was 81%, with a range of 3 days to 36 months. The HSIL rate in HPV-positive cases was 5.7% (3/53) vs 0.4% (2/539) (P = .006) in HPV-negative cases. In UPT, HPV cotesting showed negative predictive values for low-grade and high-grade squamous intraepithelial lesion detection of 98.5% and 99.6%, respectively, while positive predictive values were 19% and 5.7%. A negative HPV cotest in individuals with UPT predicted the lack of HSIL in our study. Compliance with the recommended follow-up time of 2 to 4 months for women with UPT was low (45.1%). Our study suggests that women with UPT and negative HPV cotest may be safely called back at an interval longer than 4 months.
- 13 April 2023
- Published by Oxford University Press (OUP) in American Journal of Clinical Pathology
- Vol. 160 (2) , 137-143
HPV Cotesting of Unsatisfactory Papanicolaou Tests: Implications for Follow-up Intervals
The 2019 American Society of Colposcopy and Cervical Pathology management guidelines recommend that patients with an unsatisfactory Papanicolaou (Pap) test (UPT) and negative human papillomavirus (HPV) cotest undergo repeat age-based screening in 2 to 4 months. The rationale is that a negative HPV test in the setting of an UPT may reflect an inadequate sample and therefore should not be interpreted as truly “negative.” For patients 25 years and older who are cotested, if HPV is positive for the 16 or 18 genotypes, direct referral for colposcopy is recommended. Our study aimed to determine if a negative HPV cotest result is predictive of the absence of a high-grade squamous intraepithelial lesion (HSIL) and whether these patients may be called back for repeat testing at an interval longer than 2 to 4 months. Follow-up cervical cytology and biopsy results in women with UPT and HPV cotests from January 2017 to December 2021 were collected. Original UPT and HPV cotest results were correlated with the follow-up Pap and biopsy results. There were 1,496 (2.28%) UPT cases out of 65,641 total Pap tests. Among the 1,496 UPT cases, 1,010 (67.5%) had HPV cotesting; 676 (45.1%) were followed by repeat Pap or biopsy within 4 months and 850 (56.8%) within 12 months. The total follow-up rate was 81%, with a range of 3 days to 36 months. The HSIL rate in HPV-positive cases was 5.7% (3/53) vs 0.4% (2/539) (P = .006) in HPV-negative cases. In UPT, HPV cotesting showed negative predictive values for low-grade and high-grade squamous intraepithelial lesion detection of 98.5% and 99.6%, respectively, while positive predictive values were 19% and 5.7%. A negative HPV cotest in individuals with UPT predicted the lack of HSIL in our study. Compliance with the recommended follow-up time of 2 to 4 months for women with UPT was low (45.1%). Our study suggests that women with UPT and negative HPV cotest may be safely called back at an interval longer than 4 months.
- 19 August 2022
- Published by Wiley in Diagnostic Cytopathology
- Vol. 50 (12) , E386-E389
Liver fluke eggs in bile duct brush cytology: An unexpected diagnosis during evaluation of a biliary stricture
Clonorchis sinensis, a liver fluke parasite, infects humans through ingestion of raw or undercooked fish, crabs, or crayfish in endemic areas where the parasite is found. Clonorchis sinensis infects the liver, gallbladder, and bile duct in humans, causing Clonorichiasis. Although the majority of patients are asymptomatic, long-lasting infections may cause severe disease. Without treatment, human infection may persist for the parasite's lifespan (25-30 years). Pathologic diagnosis can be challenging as sampling may demonstrate limited cellularity with minuscule eggs that may be overlooked. Here, we report a rare case of liver fluke eggs diagnosed in bile duct brush cytology.
- 19 August 2022
- Published by Wiley in Diagnostic Cytopathology
- Vol. 50 (12) , E386-E389
Liver fluke eggs in bile duct brush cytology: An unexpected diagnosis during evaluation of a biliary stricture
Clonorchis sinensis, a liver fluke parasite, infects humans through ingestion of raw or undercooked fish, crabs, or crayfish in endemic areas where the parasite is found. Clonorchis sinensis infects the liver, gallbladder, and bile duct in humans, causing Clonorichiasis. Although the majority of patients are asymptomatic, long-lasting infections may cause severe disease. Without treatment, human infection may persist for the parasite's lifespan (25-30 years). Pathologic diagnosis can be challenging as sampling may demonstrate limited cellularity with minuscule eggs that may be overlooked. Here, we report a rare case of liver fluke eggs diagnosed in bile duct brush cytology.