Jingjing Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jingjing Lu has a total of 99 co-authors. Here are the top co-authors by number of shared publications:
- Zhengyu Jin
Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
9 shared publications Feng Feng
Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No.1, Wangfujing Street, Dongcheng District, Bejing, 100730, People's Republic of China
5 shared publicationsFang Wang
Department of Radiology, PUMC Hospital, CAMS and PUMC, Beijing 100730, China
3 shared publications- Hui You
Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
3 shared publications Bo Jiang
Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No.1, Wangfujing Street, Dongcheng District, Bejing, 100730, People's Republic of China
2 shared publications- Dingrong Zhong
Department of Pathology, China-Japan Friendship Hospital
2 shared publications
Latest Publications
- 6 April 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 103, 103562
UAE: Universal Anatomical Embedding on multi-modality medical images
- 6 April 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 103, 103562
UAE: Universal Anatomical Embedding on multi-modality medical images
- 10 February 2024
- Published by Springer Nature in Chinese Journal of Academic Radiology
- Vol. 7 (2) , 130-136
The CT features of ovarian cystadenofibroma and the differences between benign serous OCAFs and mucinous OCAFs
- 10 February 2024
- Published by Springer Nature in Chinese Journal of Academic Radiology
- Vol. 7 (2) , 130-136
The CT features of ovarian cystadenofibroma and the differences between benign serous OCAFs and mucinous OCAFs
- Open Access
SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images
Radiological images such as computed tomography (CT) and X-rays render anatomy with intrinsic structures. Being able to reliably locate the same anatomical structure across varying images is a fundamental task in medical image analysis. In principle it is possible to use landmark detection or semantic segmentation for this task, but to work well these require large numbers of labeled data for each anatomical structure and sub-structure of interest. A more universal approach would learn the intrinsic structure from unlabeled images. We introduce such an approach, called Self-supervised Anatomical eMbedding (SAM). SAM generates semantic embeddings for each image pixel that describes its anatomical location or body part. To produce such embeddings, we propose a pixel-level contrastive learning framework. A coarse-to-fine strategy ensures both global and local anatomical information are encoded. Negative sample selection strategies are designed to enhance the embedding's discriminability. Using SAM, one can label any point of interest on a template image and then locate the same body part in other images by simple nearest neighbor searching. We demonstrate the effectiveness of SAM in multiple tasks with 2D and 3D image modalities. On a chest CT dataset with 19 landmarks, SAM outperforms widely-used registration algorithms while only taking 0.23 seconds for inference. On two X-ray datasets, SAM, with only one labeled template image, surpasses supervised methods trained on 50 labeled images. We also apply SAM on whole-body follow-up lesion matching in CT and obtain an accuracy of 91%. SAM can also be applied for improving image registration and initializing CNN weights.
Open AccessSAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images
Radiological images such as computed tomography (CT) and X-rays render anatomy with intrinsic structures. Being able to reliably locate the same anatomical structure across varying images is a fundamental task in medical image analysis. In principle it is possible to use landmark detection or semantic segmentation for this task, but to work well these require large numbers of labeled data for each anatomical structure and sub-structure of interest. A more universal approach would learn the intrinsic structure from unlabeled images. We introduce such an approach, called Self-supervised Anatomical eMbedding (SAM). SAM generates semantic embeddings for each image pixel that describes its anatomical location or body part. To produce such embeddings, we propose a pixel-level contrastive learning framework. A coarse-to-fine strategy ensures both global and local anatomical information are encoded. Negative sample selection strategies are designed to enhance the embedding's discriminability. Using SAM, one can label any point of interest on a template image and then locate the same body part in other images by simple nearest neighbor searching. We demonstrate the effectiveness of SAM in multiple tasks with 2D and 3D image modalities. On a chest CT dataset with 19 landmarks, SAM outperforms widely-used registration algorithms while only taking 0.23 seconds for inference. On two X-ray datasets, SAM, with only one labeled template image, surpasses supervised methods trained on 50 labeled images. We also apply SAM on whole-body follow-up lesion matching in CT and obtain an accuracy of 91%. SAM can also be applied for improving image registration and initializing CNN weights.
- 30 August 2021
- Published by Chinese Medical Sciences Journal in Chinese Medical Sciences Journal
- Vol. 36 (3) , 196-203
Advances of Artificial Intelligence Application in Medical Imaging of Ovarian Cancers
Ovarian cancer is one of the three most common gynecological cancers in the world, and is regarded as a priority in terms of women's cancer. In the past few years, many researchers have attempted to develop and apply artificial intelligence (AI) techniques to multiple clinical scenarios of ovarian cancer, especially in the field of medical imaging. AI-assisted imaging studies have involved computer tomography (CT), ultrasonography (US), and magnetic resonance imaging (MRI). In this review, we perform a literature search on the published studies that using AI techniques in the medical care of ovarian cancer, and bring up the advances in terms of four clinical aspects, including medical diagnosis, pathological classification, targeted biopsy guidance, and prognosis prediction. Meanwhile, current status and existing issues of the researches on AI application in ovarian cancer are discussed.
- 30 August 2021
- Published by Chinese Medical Sciences Journal in Chinese Medical Sciences Journal
- Vol. 36 (3) , 196-203
Advances of Artificial Intelligence Application in Medical Imaging of Ovarian Cancers
Ovarian cancer is one of the three most common gynecological cancers in the world, and is regarded as a priority in terms of women's cancer. In the past few years, many researchers have attempted to develop and apply artificial intelligence (AI) techniques to multiple clinical scenarios of ovarian cancer, especially in the field of medical imaging. AI-assisted imaging studies have involved computer tomography (CT), ultrasonography (US), and magnetic resonance imaging (MRI). In this review, we perform a literature search on the published studies that using AI techniques in the medical care of ovarian cancer, and bring up the advances in terms of four clinical aspects, including medical diagnosis, pathological classification, targeted biopsy guidance, and prognosis prediction. Meanwhile, current status and existing issues of the researches on AI application in ovarian cancer are discussed.
- 20 February 2021
- Published by Springer Nature
- p. 79-87
Magnetic Resonance Imaging Manifestations and Classification of Adenomyosis
- 20 February 2021
- Published by Springer Nature
- p. 79-87
Magnetic Resonance Imaging Manifestations and Classification of Adenomyosis
- Open Access
- 30 September 2020
- Published by Chinese Medical Sciences Journal in Chinese Medical Sciences Journal
- Vol. 35 (3) , 254-261
Similarities and Differences of Early Pulmonary CT Features of Pneumonia Caused by SARS-CoV-2, SARS-CoV and MERS-CoV: Comparison Based on a Systemic Review
To compare the similarities and differences of early CT manifestations of three types of viral pneumonia induced by SARS-CoV-2 (COVED-19), SARS-CoV (SARS) and MERS-CoV (MERS) using a systemic review. Electronic database were searched to identify all original articles and case reports presenting chest CT features for adult patients with COVID-19, SARS and MERS pneumonia respectively. Quality of literature and completeness of presented data were evaluated by consensus reached by three radiologists. Vote-counting method was employed to include cases of each group. Data of patients' manifestations in early chest CT including lesion patterns, distribution of lesions and specific imaging signs for the three groups were extracted and recorded. Data were compared and analyzed using SPSS 22.0. A total of 24 studies were included, composing of 10 studies of COVED-19, 5 studies of MERS and 9 studies of SARS. The included CT exams were 147, 40, and 122 respectively. For the early CT features of the 3 pneumonias, the basic lesion pattern with respect to “mixed ground glass opacity (GGO) and consolidation, GGO mainly, or consolidation mainly” was similar among the 3 groups (χ2 = 7.966, p > 0.05). There were no significant differences on the lesion distribution (χ2= 13.053, p > 0.05) and predominate involvement of the subpleural area of bilateral lower lobes (χ2 = 4.809, p > 0.05) among the 3 groups. The lesions appeared more focal in COVID-19 pneumonia at early phase (χ2= 23.509, p < 0.05). The proportions of crazy-paving pattern (χ2 = 23.037, p < 0.001), organizing pneumonia pattern (p < 0.05) and pleural effusions (p < 0.001) in COVID-19 pneumonia were significantly lower than the other two. Although rarely shown in the early CT findings of all three viral pneumonias, the fibrotic changes were more frequent in SAKS than COVID-19 and MERS (χ2 = 6.275, P<0.05). For other imaging signs, only the MERS pneumonia demonstrated tree-in-buds, cavitation, and its incidence rate of interlobular or intralobular septal thickening presented significantly increased as compared to the other two pneumonia (χ2 = 22.412, p < 0.05). No pneumothorax, pneumomediastinum and lymphadenopathy was present for each group. Imaging findings on early stage of these three coronavirus pneumonias showed similar basic lesion patterns, including GGO and consolidation, bilateral distribution, and predominant involvement of the subpleural area and the lower lobes. Early signs of COVID-19 pneumonia showed less severity of inflammation. Early fibrotic changes appeared in SAKS only, MERS had more severe inflammatory changes including cavitation and pleural effusion. The differences may indicate the specific pathophysiological processes for each coronavirus pneumonia.
- 30 September 2020
- Published by Chinese Medical Sciences Journal in Chinese Medical Sciences Journal
- Vol. 35 (3) , 254-261
Open AccessSimilarities and Differences of Early Pulmonary CT Features of Pneumonia Caused by SARS-CoV-2, SARS-CoV and MERS-CoV: Comparison Based on a Systemic Review
To compare the similarities and differences of early CT manifestations of three types of viral pneumonia induced by SARS-CoV-2 (COVED-19), SARS-CoV (SARS) and MERS-CoV (MERS) using a systemic review. Electronic database were searched to identify all original articles and case reports presenting chest CT features for adult patients with COVID-19, SARS and MERS pneumonia respectively. Quality of literature and completeness of presented data were evaluated by consensus reached by three radiologists. Vote-counting method was employed to include cases of each group. Data of patients' manifestations in early chest CT including lesion patterns, distribution of lesions and specific imaging signs for the three groups were extracted and recorded. Data were compared and analyzed using SPSS 22.0. A total of 24 studies were included, composing of 10 studies of COVED-19, 5 studies of MERS and 9 studies of SARS. The included CT exams were 147, 40, and 122 respectively. For the early CT features of the 3 pneumonias, the basic lesion pattern with respect to “mixed ground glass opacity (GGO) and consolidation, GGO mainly, or consolidation mainly” was similar among the 3 groups (χ2 = 7.966, p > 0.05). There were no significant differences on the lesion distribution (χ2= 13.053, p > 0.05) and predominate involvement of the subpleural area of bilateral lower lobes (χ2 = 4.809, p > 0.05) among the 3 groups. The lesions appeared more focal in COVID-19 pneumonia at early phase (χ2= 23.509, p < 0.05). The proportions of crazy-paving pattern (χ2 = 23.037, p < 0.001), organizing pneumonia pattern (p < 0.05) and pleural effusions (p < 0.001) in COVID-19 pneumonia were significantly lower than the other two. Although rarely shown in the early CT findings of all three viral pneumonias, the fibrotic changes were more frequent in SAKS than COVID-19 and MERS (χ2 = 6.275, P<0.05). For other imaging signs, only the MERS pneumonia demonstrated tree-in-buds, cavitation, and its incidence rate of interlobular or intralobular septal thickening presented significantly increased as compared to the other two pneumonia (χ2 = 22.412, p < 0.05). No pneumothorax, pneumomediastinum and lymphadenopathy was present for each group. Imaging findings on early stage of these three coronavirus pneumonias showed similar basic lesion patterns, including GGO and consolidation, bilateral distribution, and predominant involvement of the subpleural area and the lower lobes. Early signs of COVID-19 pneumonia showed less severity of inflammation. Early fibrotic changes appeared in SAKS only, MERS had more severe inflammatory changes including cavitation and pleural effusion. The differences may indicate the specific pathophysiological processes for each coronavirus pneumonia.
- 2 November 2018
- Published by Springer Nature
- p. 259-272
APNet: Semantic Segmentation for Pelvic MR Image
- 2 November 2018
- Published by Springer Nature
- p. 259-272
APNet: Semantic Segmentation for Pelvic MR Image
- 26 March 2018
- Published by Springer Nature in Abdominal Radiology
- Vol. 43 (11) , 3142-3146
Increased incidence of abnormally located ovary in patients with Mayer–Rokitansky–Küster–Hauser syndrome: a retrospective analysis with magnetic resonance imaging
To explore the incidence of abnormally located ovary in patients with Mayer–Rokitansky–Küster–Hauser (MRKH) syndrome as compared to a control group with magnetic resonance imaging.
- 26 March 2018
- Published by Springer Nature in Abdominal Radiology
- Vol. 43 (11) , 3142-3146
Increased incidence of abnormally located ovary in patients with Mayer–Rokitansky–Küster–Hauser syndrome: a retrospective analysis with magnetic resonance imaging
To explore the incidence of abnormally located ovary in patients with Mayer–Rokitansky–Küster–Hauser (MRKH) syndrome as compared to a control group with magnetic resonance imaging.
- 3 July 2017
- Published by Springer Nature in European Radiology
- Vol. 27 (12) , 5215-5224
Evaluation of Mayer-Rokitansky-Küster-Hauser syndrome with magnetic resonance imaging: Three patterns of uterine remnants and related anatomical features and clinical settings
- 3 July 2017
- Published by Springer Nature in European Radiology
- Vol. 27 (12) , 5215-5224
Evaluation of Mayer-Rokitansky-Küster-Hauser syndrome with magnetic resonance imaging: Three patterns of uterine remnants and related anatomical features and clinical settings
- Open Access
- 19 October 2016
- Published by Springer Nature in Diagnostic Pathology
- Vol. 11 (1) , 1-9
Clinicopathological features and BRAFV600E mutations in patients with isolated hypothalamic-pituitary Langerhans cell histiocytosis
Isolated hypothalamic-pituitary Langerhans cell histiocytosis (HPLCH) is very rare. We investigated the clinicopathological characteristics, endocrine function changes, BRAFV600E mutations and treatments of isolated HPLCH. We identified seven patients with isolated HPLCH by reviewing the clinical and pathological files in our hospital from 2007 to 2015. The clinical characteristics of the seven patients were retrospectively reviewed, especially the endocrine function changes. Immunostaining and mutation profiling of BRAFV600E were performed. The seven HPLCH patients included three men and four women, aged 9–47 years. All patients presented with symptoms of central diabetes insipidus (CDI), and four displayed anterior pituitary hypofunction as well. Magnetic resonance imaging showed hypothalamic-pituitary axis involvement in all patients. There was no evidence for the involvement of other organs in all seven patients. Langerhans cell histiocytosis was confirmed by neuroendoscopic procedures, and immunohistochemical staining showed that all cases (7/7) were positive for CD68, CD1a, Langerin, and S-100. The BRAFV600E mutation was detected in three of the six cases (3/6). Six patients had follow-up information; all received desmopressin acetate and high-dose corticosteroid therapy, and two patients received radiotherapy. Our study indicated that all patients with isolated HPLCH had CDI as the earliest symptom, and more than half of the patients had anterior pituitary deficiencies. The BRAFV600E mutation is a common genetic change in HPLCH patients. Treatment of HPLCH patients is difficult, and the progressive loss of endocrine function is irreversible in most cases.
- 19 October 2016
- Published by Springer Nature in Diagnostic Pathology
- Vol. 11 (1) , 1-9
Open AccessClinicopathological features and BRAFV600E mutations in patients with isolated hypothalamic-pituitary Langerhans cell histiocytosis
Isolated hypothalamic-pituitary Langerhans cell histiocytosis (HPLCH) is very rare. We investigated the clinicopathological characteristics, endocrine function changes, BRAFV600E mutations and treatments of isolated HPLCH. We identified seven patients with isolated HPLCH by reviewing the clinical and pathological files in our hospital from 2007 to 2015. The clinical characteristics of the seven patients were retrospectively reviewed, especially the endocrine function changes. Immunostaining and mutation profiling of BRAFV600E were performed. The seven HPLCH patients included three men and four women, aged 9–47 years. All patients presented with symptoms of central diabetes insipidus (CDI), and four displayed anterior pituitary hypofunction as well. Magnetic resonance imaging showed hypothalamic-pituitary axis involvement in all patients. There was no evidence for the involvement of other organs in all seven patients. Langerhans cell histiocytosis was confirmed by neuroendoscopic procedures, and immunohistochemical staining showed that all cases (7/7) were positive for CD68, CD1a, Langerin, and S-100. The BRAFV600E mutation was detected in three of the six cases (3/6). Six patients had follow-up information; all received desmopressin acetate and high-dose corticosteroid therapy, and two patients received radiotherapy. Our study indicated that all patients with isolated HPLCH had CDI as the earliest symptom, and more than half of the patients had anterior pituitary deficiencies. The BRAFV600E mutation is a common genetic change in HPLCH patients. Treatment of HPLCH patients is difficult, and the progressive loss of endocrine function is irreversible in most cases.