Xiaoqi Tian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaoqi Tian has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Fang Xie
Department of Child Health Care, Huangshi Maternity and Child Health Care Hospital, Wuhan, China
2 shared publications - Huarui Du
Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China
2 shared publications - Jue Zhang
Academy for Advanced Interdisciplinary Studies, Peking University
2 shared publications - Mingbo Zhang
Henan University (China)
2 shared publications - Shijie Zhang
Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China
2 shared publications - Yaqiong Zhu
Ultrasonography Department, the General Hospital of the People’s Liberation Army, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 27 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 53223-53231
A Novel Interpretable Computer-Aided Diagnosis System of Thyroid Nodules on Ultrasound Based on Clinical Experience
Computer-aided diagnosis systems (CADs) present valuable second opinions to radiologists in diagnosis. Many studies on thyroid nodules have proposed various CADs to provide a binary result, benignity or malignancy, for doctors, ignoring interpretability of more ultrasonic features that could be more useful. We develop an interpretable CADs (iCADS) that utilizes deep-learning networks’ classification power and interpretability potential of clinical guidelines, like TIRADS, a well-established scale for thyroid nodules. iCADS incorporates a main neural-networks model and six neural-network based interpreters. The outputs of the six interpreters are compared with TIRADS guidelines and the matched result will form a report, more than a benignity or malignancy result, for radiologists. Clinical images of 16,946 thyroid nodules from 5,885 patients were used to train the proposed iCADS. An extra experimental data set containing 501 images were used to test the performance of the model. For better illustrating the assistant ability of iCADS, we also recruited ten junior radiologists to make diagnosis decisions with or without the help of different versions of iCADS. The experiments demonstrated that iCADS can largely improve junior radiologists diagnosis with the help of interpreter strategy. These experiments are also the very first attempt to evaluate the effect of interpretability of deep-learning based CADs in clinical practice. Comparison experiments with other deep-learning based CADs and traditional CADs indicated that the interpreter strategy can easily be combined to other intelligent CADs without the loss of performance. The framework of iCADS can also inspire more research on the development of CADs.
- 27 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 53223-53231
Open AccessA Novel Interpretable Computer-Aided Diagnosis System of Thyroid Nodules on Ultrasound Based on Clinical Experience
Computer-aided diagnosis systems (CADs) present valuable second opinions to radiologists in diagnosis. Many studies on thyroid nodules have proposed various CADs to provide a binary result, benignity or malignancy, for doctors, ignoring interpretability of more ultrasonic features that could be more useful. We develop an interpretable CADs (iCADS) that utilizes deep-learning networks’ classification power and interpretability potential of clinical guidelines, like TIRADS, a well-established scale for thyroid nodules. iCADS incorporates a main neural-networks model and six neural-network based interpreters. The outputs of the six interpreters are compared with TIRADS guidelines and the matched result will form a report, more than a benignity or malignancy result, for radiologists. Clinical images of 16,946 thyroid nodules from 5,885 patients were used to train the proposed iCADS. An extra experimental data set containing 501 images were used to test the performance of the model. For better illustrating the assistant ability of iCADS, we also recruited ten junior radiologists to make diagnosis decisions with or without the help of different versions of iCADS. The experiments demonstrated that iCADS can largely improve junior radiologists diagnosis with the help of interpreter strategy. These experiments are also the very first attempt to evaluate the effect of interpretability of deep-learning based CADs in clinical practice. Comparison experiments with other deep-learning based CADs and traditional CADs indicated that the interpreter strategy can easily be combined to other intelligent CADs without the loss of performance. The framework of iCADS can also inspire more research on the development of CADs.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2334-2336
Integrating Clinical Knowledge in a Thyroid Nodule Classification Model Based on
Deep neural network models are currently facing problems due the weak interpretability of predicted results. One solution would involve integrating the clinical knowledge and classifiers. In this study, we utilized mature clinical experiences from TI-RADS, and also trained a multi-label cost-sensitive classification network. The results show that the end-to-end classification model based on cost-sensitive loss function is a more effective way to integrate clinical knowledge into the deep neural network.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2334-2336
Integrating Clinical Knowledge in a Thyroid Nodule Classification Model Based on
Deep neural network models are currently facing problems due the weak interpretability of predicted results. One solution would involve integrating the clinical knowledge and classifiers. In this study, we utilized mature clinical experiences from TI-RADS, and also trained a multi-label cost-sensitive classification network. The results show that the end-to-end classification model based on cost-sensitive loss function is a more effective way to integrate clinical knowledge into the deep neural network.