Journal of Thyroid Disorders & Therapy
Open Access

Jiamei Jin

Biography

Dr. Jia-Mei Jin is a researcher affiliated with Fudan University, contributing significantly to the fields of thyroid nodule assessment and the application of deep learning in medical imaging. With an h-index of 3, Dr. Jin has co-authored five publications, collectively garnering 156 citations, underscoring the impact of her work in the academic community. One of Dr. Jin's notable studies is titled "Follicular Thyroid Neoplasm on Conventional and Contrast-Enhanced Ultrasound," which aims to identify features of follicular thyroid neoplasms using both conventional ultrasound (US) and contrast-enhanced ultrasound (CEUS). The research involved 21 follicular thyroid cancers (FTCs) and 35 follicular adenomas (FAs), analyzing sonographic features to differentiate between malignant and benign conditions. The study concluded that CEUS provided additional sonographic features helpful in predicting the potential malignancy of follicular thyroid neoplasms. Dr. Jin's research interests include the integration of deep learning techniques in ultrasound imaging to enhance diagnostic accuracy and efficiency. Her contributions have advanced the understanding and application of ultrasound technology in medical diagnostics, particularly in the evaluation of thyroid conditions.

Publications

• Research Article
  Ultrasonographic United Stiffness Score System: Resolving the Discrepancy between Acoustic Radiation Force Impulse and Real-time Elastography in Evaluating the Thyroid Nodules Stiffness
  Author(s): Jia Zhan, Xuehong Diao, Jiamei Jin, Lin Chen and Yue Chen Jia Zhan, Xuehong Diao, Jiamei Jin, Lin Chen and Yue Chen
  
  Objective: The aim of this study was to assess the ultrasonographic united stiffness score system (UUSSS) in diagnosing thyroid nodules, and retrospectively analyze the discrepancy between acoustic radiation force impulse (ARFI) and real-time elastography (RTE). Methods: 170 conventional ultrasound (US) proven thyroid nodules in 70 patients were included and all were examined by RTE and ARFI. RTE and ARFI were first analyzed respectively, comparing with pathological findings. Then nodules have discrepancy between ARFI and RTE were retrospectively analyzed by UUSSS. Results: The AUC (area under curve) of ARFI combined RTE in 170 nodules was 0.87 (sensitivity=79.4% (54/68), specificity=84.3% (86/102), PPV=77.1% (54/70), NPV=86.0% (86/100), accuracy for ARFI were 82.4% (140/170), relatively to RTE was 0.83, 80.9%, 65... View More»
  DOI: 10.4172/2167-7948.1000219

  Abstract PDF

Relevant Topics