1
|
Zhang S, Yuan Z, Wang Y, Bai Y, Chen B, Wang H. REUR: A unified deep framework for signet ring cell detection in low-resolution pathological images. Comput Biol Med 2021; 136:104711. [PMID: 34388466 DOI: 10.1016/j.compbiomed.2021.104711] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2021] [Revised: 07/28/2021] [Accepted: 07/29/2021] [Indexed: 11/15/2022]
Abstract
Detecting signet ring cells (SRCs) in pathological images is essential for carcinoma diagnosis. However, it is time consuming for pathologists to detect SRCs manually from pathological images, and the accuracy of detecting them is also relatively low because of their small sizes. Recently, the exploration of deep learning methods in pathology analysis has been widely investigated by researchers. Nevertheless, the automatic detection of SRCs from real pathological images faces two problems. One is that labeled pathological images are insufficient and usually incomplete. The other is that the training data and the real clinical data have a large difference in resolution. Hence, adopting the transfer learning method affects the performance of deep learning methods. To address these two problems, we present a unified framework named REUR [RetinaNet combining USRNet (unfolding super-resolution network) with the RGHMC (revised gradient harmonizing mechanism classification) loss] that can accurately detect SRCs in low-resolution (LR) pathological images. First, the framework with the super-resolution (SR) module can address the difference in resolution between the training data and the real clinical data. Second, the framework with the label correction module can obtain the revised ground-truth labels from noisy examples, which are embedded into the gradient harmonizing mechanism to acquire the RGHMC loss. The results of the numerical experiments showed that the framework can perform better than other one-stage detectors based on the RetinaNet architecture in the high-resolution (HR) noisy dataset. It achieved a kappa value of 0.74 and an accuracy of 0.89 in the test with 27 randomly selected whole slide images (WSIs), and, thus, it can assist pathologists in better analyzing WSIs. The framework provides an essential method in computer-aided diagnosis for medical applications.
Collapse
Affiliation(s)
- Shuchang Zhang
- Department of Mathematics, National University of Defense Technology, Changsha, China.
| | - Ziyang Yuan
- Department of Mathematics, National University of Defense Technology, Changsha, China.
| | - Yadong Wang
- Department of Laboratory Pathology, Baiyun Branch, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Yang Bai
- Department of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Bo Chen
- Suzhou Research Center, Institute of Automation, Chinese Academy of Sciences, Suzhou, China
| | - Hongxia Wang
- Department of Mathematics, National University of Defense Technology, Changsha, China.
| |
Collapse
|
2
|
Feng F, Gao Q, Wu Y, Liu C, Yu Y, Li B, Chu K, Yi B, Cheng Q, Jiang X. Cytoreductive surgery combined with hyperthermic intraperitoneal chemotherapy vs. cytoreductive surgery alone for intrahepatic cholangiocarcinoma with peritoneal metastases: A retrospective cohort study. EUROPEAN JOURNAL OF SURGICAL ONCOLOGY 2021; 47:2363-2368. [PMID: 34119376 DOI: 10.1016/j.ejso.2021.05.014] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2021] [Revised: 04/20/2021] [Accepted: 05/07/2021] [Indexed: 02/07/2023]
Abstract
BACKGROUND Cytoreductive surgery (CRS) combined with hyperthermic intraperitoneal chemotherapy (HIPEC) has survival benefits in patients with intraperitoneal malignant lesions, but there is no study specific to intrahepatic cholangiocarcinoma (ICC). PURPOSE To compare the prognosis of patients with advanced ICC undergoing CRS + HIPEC compared with CRS alone. METHODS This study was a retrospective cohort study of patients with advanced ICC treated at the Shanghai Eastern Hepatobiliary Surgery Hospital between 01/2014 and 12/2018. The patients were divided into either CRS + HIPEC or CRS group based on the treatment they received. Overall survival (OS), complications, hospital stay, biochemical indicators, tumor markers, and number of HIPEC were examined. RESULTS There were 51 and 61 patients in the CRS + HIPEC and CRS groups, respectively. There were no differences between the groups regarding preoperative CA19-9 levels (421 ± 381 vs. 523 ± 543 U/mL, P = 0.208). The hospital stay was longer in the CRS + HIPEC group (22.2 ± 10.0 vs. 18.6 ± 7.6 days, P = 0.033). The occurrence of overall complications was similar in the two groups (37.2% vs. 34.4%, P = 0.756). The postoperative CA19-9 levels were lower in the CRS + HIPEC group compared with the CRS group (196 ± 320 vs. 337 ± 396 U/mL, P = 0.044). The median OS was longer in the CRS + HIPEC group than in the CRS group (25.53 vs. 11.17 months, P < 0.001). Compared with the CRS group, the CRS + HIPEC group showed a higher occurrence of leukopenia (7.8% vs. 0, P = 0.040) but a lower occurrence of total bilirubin elevation (15.7% vs. 37.7%, P = 0.032). CONCLUSION CRS + HIPEC could be a treatment option for patients with advanced ICC, with improved OS and similar complications and adverse events compared with CRS alone.
Collapse
Affiliation(s)
- Feiling Feng
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China
| | - Qingxiang Gao
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China
| | - Yue Wu
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China
| | - Chen Liu
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China
| | - Yong Yu
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China
| | - Bin Li
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China
| | - Kaijian Chu
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China
| | - Bin Yi
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China
| | - Qingbao Cheng
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China.
| | - Xiaoqing Jiang
- Department of Biliary Tract I, Eastern Hepatobiliary Surgery Hospital, No.225, Changhai Road, Yangpu District, Shanghai, 200433, PR China.
| |
Collapse
|