1
|
Gong K, Dai Q, Wang J, Zheng Y, Shi T, Yu J, Chen J, Huang S, Wang Z. Unified ICH quantification and prognosis prediction in NCCT images using a multi-task interpretable network. Front Neurosci 2023; 17:1118340. [PMID: 36998725 PMCID: PMC10043313 DOI: 10.3389/fnins.2023.1118340] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2022] [Accepted: 02/23/2023] [Indexed: 03/15/2023] Open
Abstract
With the recent development of deep learning, the regression, classification, and segmentation tasks of Computer-Aided Diagnosis (CAD) using Non-Contrast head Computed Tomography (NCCT) for spontaneous IntraCerebral Hematoma (ICH) have become popular in the field of emergency medicine. However, a few challenges such as time-consuming of ICH volume manual evaluation, excessive cost demanding patient-level predictions, and the requirement for high performance in both accuracy and interpretability remain. This paper proposes a multi-task framework consisting of upstream and downstream components to overcome these challenges. In the upstream, a weight-shared module is trained as a robust feature extractor that captures global features by performing multi-tasks (regression and classification). In the downstream, two heads are used for two different tasks (regression and classification). The final experimental results show that the multi-task framework has better performance than single-task framework. And it also reflects its good interpretability in the heatmap generated by Gradient-weighted Class Activation Mapping (Grad-CAM), which is a widely used model interpretation method, and will be presented in subsequent sections.
Collapse
Affiliation(s)
- Kai Gong
- The First Affiliated Hospital of Xiamen University, Xiamen University, Xiamen, Fujian, China
| | - Qian Dai
- Department of Computer Science, School of Informatics, Xiamen University, Xiamen, Fujian, China
| | - Jiacheng Wang
- Department of Computer Science, School of Informatics, Xiamen University, Xiamen, Fujian, China
| | - Yingbin Zheng
- The First Affiliated Hospital of Xiamen University, Xiamen University, Xiamen, Fujian, China
| | - Tao Shi
- Ningbo Medical Center Lihuili Hospital, Ningbo, Zhejiang, China
| | - Jiaxing Yu
- Department of Computer Science, School of Informatics, Xiamen University, Xiamen, Fujian, China
| | - Jiangwang Chen
- Department of Computer Science, School of Informatics, Xiamen University, Xiamen, Fujian, China
| | - Shaohui Huang
- Department of Computer Science, School of Informatics, Xiamen University, Xiamen, Fujian, China
- *Correspondence: Shaohui Huang
| | - Zhanxiang Wang
- The First Affiliated Hospital of Xiamen University, Xiamen University, Xiamen, Fujian, China
- Zhanxiang Wang
| |
Collapse
|
2
|
Ghorbani S, Letafati A, Khatami A, farzi R, Shabani S, Moradi P, Tambrchi V, Saadati H, Papizadeh S, rad MV, Tabatabaei R, Bahadory S, Tavakoli A, Bokharaei-Salim F, Monavari SH, Fatemipour M, Hoseini M, Kiani SJ. Association between human herpesvirus-6 and primary brain tumors: a systematic review and meta-analysis. Future Virol 2022. [DOI: 10.2217/fvl-2021-0096] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
Abstract
Aim: The present study aimed to find out the prevalence and any possible association between human herpesvirus (HHV-6) and primary brain tumors. Materials & methods: The systematic literature search was performed by finding related articles from major databases. Analysis was performed by comprehensive meta-analysis software. Results: A total of 13 (25 datasets) articles were included in the study, seven (15 datasets) of which were case/control and the rest (ten datasets) were cross-sectional studies. The pooled prevalence of HHV-6 among primary brain cancer patients was 29% (95% CI: 24–33%; I2 = 97.89%). An association was found between HHV-6 and primary brain cancer (summary odds ratio: 3.77% [95% CI: 2.59–5.49%; I2 = 19.0%]). Conclusion: Our analysis demonstrated that HHV-6 is associated with primary brain cancer. Reactivation of the virus could be triggered by the tumor, therefore, we cannot be certain that the virus appeared before the cancer development.
Collapse
Affiliation(s)
- Saied Ghorbani
- Department of Virology, Faculty of Medicine, Iran University of Medical Science, Tehran, Iran
| | - Arash Letafati
- Department of Virology, School of public health, Tehran University of Medical Science, Tehran, Iran
| | - Alireza Khatami
- Department of Virology, Faculty of Medicine, Iran University of Medical Science, Tehran, Iran
| | - Rana farzi
- Department of Virology, Faculty of Medicine, Shiraz University of Medical Science, Shiraz, Iran
| | - Soha Shabani
- Faculty of veterinary medicine, Azad University, Research Sciences Branch, Tehran, Iran
| | - Pouya Moradi
- Department of Virology, Faculty of Medical Sciences, Tarbiat Modares University, Tehran, Iran
| | - Vahid Tambrchi
- Department of Virology, Faculty of Medicine, Iran University of Medical Science, Tehran, Iran
| | - Hassan Saadati
- Department of Epidemiology & Biostatistics, School of Health, North Khorasan University of Medical Sciences, Bojnurd, Iran
| | - Saher Papizadeh
- Department of Medical Microbiology, Kerman University of Medical Sciences, Kerman, Iran
| | - Mona Vasei rad
- Paramedicine Department, Islamic Azad University, Babol Medical Sciences Branch, Babol, Mazandaran, Iran
| | - Raheleh Tabatabaei
- Department of Immunology, School of Medicine, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Saeed Bahadory
- Department of Parasitology, Faculty of Medical Sciences, Tarbiat Modares University, Tehran, Iran
| | - Ahmad Tavakoli
- Department of Virology, Faculty of Medicine, Iran University of Medical Science, Tehran, Iran
- Research Center of Pediatric Infectious Diseases, Institute of Immunology & Infectious Diseases, Iran University of Medical Sciences, Tehran, Iran
| | - Farah Bokharaei-Salim
- Department of Virology, Faculty of Medicine, Iran University of Medical Science, Tehran, Iran
| | | | - Maryam Fatemipour
- Department of Virology, Faculty of Medicine, Iran University of Medical Science, Tehran, Iran
| | - Mahdieh Hoseini
- Department of Virology, Faculty of Medicine, Iran University of Medical Science, Tehran, Iran
| | - Seyed Jalal Kiani
- Department of Virology, Faculty of Medicine, Iran University of Medical Science, Tehran, Iran
| |
Collapse
|
3
|
Khened M, Kori A, Rajkumar H, Krishnamurthi G, Srinivasan B. A generalized deep learning framework for whole-slide image segmentation and analysis. Sci Rep 2021; 11:11579. [PMID: 34078928 PMCID: PMC8172839 DOI: 10.1038/s41598-021-90444-8] [Citation(s) in RCA: 57] [Impact Index Per Article: 19.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2021] [Accepted: 05/04/2021] [Indexed: 12/22/2022] Open
Abstract
Histopathology tissue analysis is considered the gold standard in cancer diagnosis and prognosis. Whole-slide imaging (WSI), i.e., the scanning and digitization of entire histology slides, are now being adopted across the world in pathology labs. Trained histopathologists can provide an accurate diagnosis of biopsy specimens based on WSI data. Given the dimensionality of WSIs and the increase in the number of potential cancer cases, analyzing these images is a time-consuming process. Automated segmentation of tumorous tissue helps in elevating the precision, speed, and reproducibility of research. In the recent past, deep learning-based techniques have provided state-of-the-art results in a wide variety of image analysis tasks, including the analysis of digitized slides. However, deep learning-based solutions pose many technical challenges, including the large size of WSI data, heterogeneity in images, and complexity of features. In this study, we propose a generalized deep learning-based framework for histopathology tissue analysis to address these challenges. Our framework is, in essence, a sequence of individual techniques in the preprocessing-training-inference pipeline which, in conjunction, improve the efficiency and the generalizability of the analysis. The combination of techniques we have introduced includes an ensemble segmentation model, division of the WSI into smaller overlapping patches while addressing class imbalances, efficient techniques for inference, and an efficient, patch-based uncertainty estimation framework. Our ensemble consists of DenseNet-121, Inception-ResNet-V2, and DeeplabV3Plus, where all the networks were trained end to end for every task. We demonstrate the efficacy and improved generalizability of our framework by evaluating it on a variety of histopathology tasks including breast cancer metastases (CAMELYON), colon cancer (DigestPath), and liver cancer (PAIP). Our proposed framework has state-of-the-art performance across all these tasks and is ranked within the top 5 currently for the challenges based on these datasets. The entire framework along with the trained models and the related documentation are made freely available at GitHub and PyPi. Our framework is expected to aid histopathologists in accurate and efficient initial diagnosis. Moreover, the estimated uncertainty maps will help clinicians to make informed decisions and further treatment planning or analysis.
Collapse
Affiliation(s)
- Mahendra Khened
- Department of Engineering Design, Indian Institute of Technology Madras, Chennai, 600036, India
| | - Avinash Kori
- Department of Engineering Design, Indian Institute of Technology Madras, Chennai, 600036, India
| | - Haran Rajkumar
- Department of Engineering Design, Indian Institute of Technology Madras, Chennai, 600036, India
| | - Ganapathy Krishnamurthi
- Department of Engineering Design, Indian Institute of Technology Madras, Chennai, 600036, India.
| | - Balaji Srinivasan
- Department of Mechanical Engineering, Indian Institute of Technology Madras, Chennai, 600036, India
| |
Collapse
|
6
|
Zhang Y, Wang S, Phillips P, Dong Z, Ji G, Yang J. Detection of Alzheimer's disease and mild cognitive impairment based on structural volumetric MR images using 3D-DWT and WTA-KSVM trained by PSOTVAC. Biomed Signal Process Control 2015. [DOI: 10.1016/j.bspc.2015.05.014] [Citation(s) in RCA: 76] [Impact Index Per Article: 8.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
7
|
Classification of fresh and frozen-thawed pork muscles using visible and near infrared hyperspectral imaging and textural analysis. Meat Sci 2014; 99:81-8. [PMID: 25282703 DOI: 10.1016/j.meatsci.2014.09.001] [Citation(s) in RCA: 114] [Impact Index Per Article: 11.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2014] [Revised: 08/31/2014] [Accepted: 09/02/2014] [Indexed: 11/21/2022]
Abstract
The potential of visible and near infrared hyperspectral imaging was investigated as a rapid and nondestructive technique for classifying fresh and frozen-thawed meats by integrating critical spectral and image features extracted from hyperspectral images in the region of 400-1000 nm. Six feature wavelengths (400, 446, 477, 516, 592 and 686 nm) were identified using uninformative variable elimination and successive projections algorithm. Image textural features of the principal component images from hyperspectral images were obtained using histogram statistics (HS), gray level co-occurrence matrix (GLCM) and gray level-gradient co-occurrence matrix (GLGCM). By these spectral and textural features, probabilistic neural network (PNN) models for classification of fresh and frozen-thawed pork meats were established. Compared with the models using the optimum wavelengths only, optimum wavelengths with HS image features, and optimum wavelengths with GLCM image features, the model integrating optimum wavelengths with GLGCM gave the highest classification rate of 93.14% and 90.91% for calibration and validation sets, respectively. Results indicated that the classification accuracy can be improved by combining spectral features with textural features and the fusion of critical spectral and textural features had better potential than single spectral extraction in classifying fresh and frozen-thawed pork meat.
Collapse
|