1
|
Seoni S, Shahini A, Meiburger KM, Marzola F, Rotunno G, Acharya UR, Molinari F, Salvi M. All you need is data preparation: A systematic review of image harmonization techniques in Multi-center/device studies for medical support systems. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 250:108200. [PMID: 38677080 DOI: 10.1016/j.cmpb.2024.108200] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/27/2024] [Revised: 04/20/2024] [Accepted: 04/22/2024] [Indexed: 04/29/2024]
Abstract
BACKGROUND AND OBJECTIVES Artificial intelligence (AI) models trained on multi-centric and multi-device studies can provide more robust insights and research findings compared to single-center studies. However, variability in acquisition protocols and equipment can introduce inconsistencies that hamper the effective pooling of multi-source datasets. This systematic review evaluates strategies for image harmonization, which standardizes appearances to enable reliable AI analysis of multi-source medical imaging. METHODS A literature search using PRISMA guidelines was conducted to identify relevant papers published between 2013 and 2023 analyzing multi-centric and multi-device medical imaging studies that utilized image harmonization approaches. RESULTS Common image harmonization techniques included grayscale normalization (improving classification accuracy by up to 24.42 %), resampling (increasing the percentage of robust radiomics features from 59.5 % to 89.25 %), and color normalization (enhancing AUC by up to 0.25 in external test sets). Initially, mathematical and statistical methods dominated, but machine and deep learning adoption has risen recently. Color imaging modalities like digital pathology and dermatology have remained prominent application areas, though harmonization efforts have expanded to diverse fields including radiology, nuclear medicine, and ultrasound imaging. In all the modalities covered by this review, image harmonization improved AI performance, with increasing of up to 24.42 % in classification accuracy and 47 % in segmentation Dice scores. CONCLUSIONS Continued progress in image harmonization represents a promising strategy for advancing healthcare by enabling large-scale, reliable analysis of integrated multi-source datasets using AI. Standardizing imaging data across clinical settings can help realize personalized, evidence-based care supported by data-driven technologies while mitigating biases associated with specific populations or acquisition protocols.
Collapse
Affiliation(s)
- Silvia Seoni
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Alen Shahini
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Kristen M Meiburger
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Francesco Marzola
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Giulia Rotunno
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia; Centre for Health Research, University of Southern Queensland, Australia
| | - Filippo Molinari
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Massimo Salvi
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy.
| |
Collapse
|
2
|
Feng Y, Cong Y, Xing S, Wang H, Zhao C, Zhang X, Yao Q. Distance Matters: A Distance-Aware Medical Image Segmentation Algorithm. ENTROPY (BASEL, SWITZERLAND) 2023; 25:1169. [PMID: 37628199 PMCID: PMC10453236 DOI: 10.3390/e25081169] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/05/2023] [Revised: 08/01/2023] [Accepted: 08/03/2023] [Indexed: 08/27/2023]
Abstract
The transformer-based U-Net network structure has gained popularity in the field of medical image segmentation. However, most networks overlook the impact of the distance between each patch on the encoding process. This paper proposes a novel GC-TransUnet for medical image segmentation. The key innovation is that it takes into account the relationships between patch blocks based on their distances, optimizing the encoding process in traditional transformer networks. This optimization results in improved encoding efficiency and reduced computational costs. Moreover, the proposed GC-TransUnet is combined with U-Net to accomplish the segmentation task. In the encoder part, the traditional vision transformer is replaced by the global context vision transformer (GC-VIT), eliminating the need for the CNN network while retaining skip connections for subsequent decoders. Experimental results demonstrate that the proposed algorithm achieves superior segmentation results compared to other algorithms when applied to medical images.
Collapse
Affiliation(s)
- Yuncong Feng
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (Y.C.); (S.X.); (H.W.); (C.Z.); (Q.Y.)
- Artificial Intelligence Research Institute, Changchun University of Technology, Changchun 130012, China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
| | - Yeming Cong
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (Y.C.); (S.X.); (H.W.); (C.Z.); (Q.Y.)
| | - Shuaijie Xing
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (Y.C.); (S.X.); (H.W.); (C.Z.); (Q.Y.)
| | - Hairui Wang
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (Y.C.); (S.X.); (H.W.); (C.Z.); (Q.Y.)
| | - Cuixing Zhao
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (Y.C.); (S.X.); (H.W.); (C.Z.); (Q.Y.)
| | - Xiaoli Zhang
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
| | - Qingan Yao
- College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; (Y.F.); (Y.C.); (S.X.); (H.W.); (C.Z.); (Q.Y.)
| |
Collapse
|
3
|
Martos O, Hoque MZ, Keskinarkaus A, Kemi N, Näpänkangas J, Eskuri M, Pohjanen VM, Kauppila JH, Seppänen T. Optimized detection and segmentation of nuclei in gastric cancer images using stain normalization and blurred artifact removal. Pathol Res Pract 2023; 248:154694. [PMID: 37494804 DOI: 10.1016/j.prp.2023.154694] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/04/2023] [Revised: 07/03/2023] [Accepted: 07/13/2023] [Indexed: 07/28/2023]
Abstract
Histological analysis with microscopy is the gold standard to diagnose and stage cancer, where slides or whole slide images are analyzed for cell morphological and spatial features by pathologists. The nuclei of cancerous cells are characterized by nonuniform chromatin distribution, irregular shapes, and varying size. As nucleus area and shape alone carry prognostic value, detection and segmentation of nuclei are among the most important steps in disease grading. However, evaluation of nuclei is a laborious, time-consuming, and subjective process with large variation among pathologists. Recent advances in digital pathology have allowed significant applications in nuclei detection, segmentation, and classification, but automated image analysis is greatly affected by staining factors, scanner variability, and imaging artifacts, requiring robust image preprocessing, normalization, and segmentation methods for clinically satisfactory results. In this paper, we aimed to evaluate and compare the digital image analysis techniques used in clinical pathology and research in the setting of gastric cancer. A literature review was conducted to evaluate potential methods of improving nuclei detection. Digitized images of 35 patients from a retrospective cohort of gastric adenocarcinoma at Oulu University Hospital in 1987-2016 were annotated for nuclei (n = 9085) by expert pathologists and 14 images of different cancer types from public TCGA dataset with annotated nuclei (n = 7000) were used as a comparison to evaluate applicability in other cancer types. The detection and segmentation accuracy with the selected color normalization and stain separation techniques were compared between the methods. The extracted information can be supplemented by patient's medical data and fed to the existing statistical clinical tools or subjected to subsequent AI-assisted classification and prediction models. The performance of each method is evaluated by several metrics against the annotations done by expert pathologists. The F1-measure of 0.854 ± 0.068 is achieved with color normalization for the gastric cancer dataset, and 0.907 ± 0.044 with color deconvolution for the public dataset, showing comparable results to the earlier state-of-the-art works. The developed techniques serve as a basis for further research on application and interpretability of AI-assisted tools for gastric cancer diagnosis.
Collapse
Affiliation(s)
- Oleg Martos
- Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
| | - Md Ziaul Hoque
- Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland.
| | - Anja Keskinarkaus
- Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
| | - Niko Kemi
- Department of Pathology, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Juha Näpänkangas
- Department of Pathology, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Maarit Eskuri
- Department of Pathology, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Vesa-Matti Pohjanen
- Department of Pathology, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Joonas H Kauppila
- Department of Surgery, Oulu University Hospital, Finland, and University of Oulu, Finland
| | - Tapio Seppänen
- Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
| |
Collapse
|
4
|
Wang J, Qin L, Chen D, Wang J, Han BW, Zhu Z, Qiao G. An improved Hover-net for nuclear segmentation and classification in histopathology images. Neural Comput Appl 2023. [DOI: 10.1007/s00521-023-08394-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/29/2023]
|
5
|
Basu A, Senapati P, Deb M, Rai R, Dhal KG. A survey on recent trends in deep learning for nucleus segmentation from histopathology images. EVOLVING SYSTEMS 2023; 15:1-46. [PMID: 38625364 PMCID: PMC9987406 DOI: 10.1007/s12530-023-09491-3] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2022] [Accepted: 02/13/2023] [Indexed: 03/08/2023]
Abstract
Nucleus segmentation is an imperative step in the qualitative study of imaging datasets, considered as an intricate task in histopathology image analysis. Segmenting a nucleus is an important part of diagnosing, staging, and grading cancer, but overlapping regions make it hard to separate and tell apart independent nuclei. Deep Learning is swiftly paving its way in the arena of nucleus segmentation, attracting quite a few researchers with its numerous published research articles indicating its efficacy in the field. This paper presents a systematic survey on nucleus segmentation using deep learning in the last five years (2017-2021), highlighting various segmentation models (U-Net, SCPP-Net, Sharp U-Net, and LiverNet) and exploring their similarities, strengths, datasets utilized, and unfolding research areas.
Collapse
Affiliation(s)
- Anusua Basu
- Department of Computer Science and Application, Midnapore College (Autonomous), Paschim Medinipur, Midnapore, West Bengal India
| | - Pradip Senapati
- Department of Computer Science and Application, Midnapore College (Autonomous), Paschim Medinipur, Midnapore, West Bengal India
| | - Mainak Deb
- Wipro Technologies, Pune, Maharashtra India
| | - Rebika Rai
- Department of Computer Applications, Sikkim University, Sikkim, India
| | - Krishna Gopal Dhal
- Department of Computer Science and Application, Midnapore College (Autonomous), Paschim Medinipur, Midnapore, West Bengal India
| |
Collapse
|
6
|
Haider A, Arsalan M, Hyun Nam S, Sultan H, Ryoung Park K. Computer-aided Fish Assessment in an Underwater Marine Environment Using Parallel and Progressive Spatial Information Fusion. JOURNAL OF KING SAUD UNIVERSITY - COMPUTER AND INFORMATION SCIENCES 2023. [DOI: 10.1016/j.jksuci.2023.02.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/24/2023]
|
7
|
Mahmood T, Choi J, Ryoung Park K. Artificial Intelligence-based Classification of Pollen Grains Using Attention-guided Pollen Features Aggregation Network. JOURNAL OF KING SAUD UNIVERSITY - COMPUTER AND INFORMATION SCIENCES 2023. [DOI: 10.1016/j.jksuci.2023.01.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/24/2023]
|
8
|
Haider A, Arsalan M, Park C, Sultan H, Park KR. Exploring deep feature-blending capabilities to assist glaucoma screening. Appl Soft Comput 2022. [DOI: 10.1016/j.asoc.2022.109918] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
|
9
|
Effectiveness of Artificial Intelligence for Personalized Medicine in Neoplasms: A Systematic Review. BIOMED RESEARCH INTERNATIONAL 2022; 2022:7842566. [PMID: 35434134 PMCID: PMC9010213 DOI: 10.1155/2022/7842566] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/23/2021] [Revised: 01/29/2022] [Accepted: 03/06/2022] [Indexed: 02/07/2023]
Abstract
Purpose Artificial intelligence (AI) techniques are used in precision medicine to explore novel genotypes and phenotypes data. The main aims of precision medicine include early diagnosis, screening, and personalized treatment regime for a patient based on genetic-oriented features and characteristics. The main objective of this study was to review AI techniques and their effectiveness in neoplasm precision medicine. Materials and Methods A comprehensive search was performed in Medline (through PubMed), Scopus, ISI Web of Science, IEEE Xplore, Embase, and Cochrane databases from inception to December 29, 2021, in order to identify the studies that used AI methods for cancer precision medicine and evaluate outcomes of the models. Results Sixty-three studies were included in this systematic review. The main AI approaches in 17 papers (26.9%) were linear and nonlinear categories (random forest or decision trees), and in 21 citations, rule-based systems and deep learning models were used. Notably, 62% of the articles were done in the United States and China. R package was the most frequent software, and breast and lung cancer were the most selected neoplasms in the papers. Out of 63 papers, in 34 articles, genomic data like gene expression, somatic mutation data, phenotype data, and proteomics with drug-response which is functional data was used as input in AI methods; in 16 papers' (25.3%) drug response, functional data was utilized in personalization of treatment. The maximum values of the assessment indicators such as accuracy, sensitivity, specificity, precision, recall, and area under the curve (AUC) in included studies were 0.99, 1.00, 0.96, 0.98, 0.99, and 0.9929, respectively. Conclusion The findings showed that in many cases, the use of artificial intelligence methods had effective application in personalized medicine.
Collapse
|
10
|
Sultan H, Owais M, Choi J, Mahmood T, Haider A, Ullah N, Park KR. Artificial Intelligence-Based Solution in Personalized Computer-Aided Arthroscopy of Shoulder Prostheses. J Pers Med 2022; 12:jpm12010109. [PMID: 35055427 PMCID: PMC8780458 DOI: 10.3390/jpm12010109] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2021] [Revised: 12/30/2021] [Accepted: 01/07/2022] [Indexed: 01/01/2023] Open
Abstract
Background: Early recognition of prostheses before reoperation can reduce perioperative morbidity and mortality. Because of the intricacy of the shoulder biomechanics, accurate classification of implant models before surgery is fundamental for planning the correct medical procedure and setting apparatus for personalized medicine. Expert surgeons usually use X-ray images of prostheses to set the patient-specific apparatus. However, this subjective method is time-consuming and prone to errors. Method: As an alternative, artificial intelligence has played a vital role in orthopedic surgery and clinical decision-making for accurate prosthesis placement. In this study, three different deep learning-based frameworks are proposed to identify different types of shoulder implants in X-ray scans. We mainly propose an efficient ensemble network called the Inception Mobile Fully-Connected Convolutional Network (IMFC-Net), which is comprised of our two designed convolutional neural networks and a classifier. To evaluate the performance of the IMFC-Net and state-of-the-art models, experiments were performed with a public data set of 597 de-identified patients (597 shoulder implants). Moreover, to demonstrate the generalizability of IMFC-Net, experiments were performed with two augmentation techniques and without augmentation, in which our model ranked first, with a considerable difference from the comparison models. A gradient-weighted class activation map technique was also used to find distinct implant characteristics needed for IMFC-Net classification decisions. Results: The results confirmed that the proposed IMFC-Net model yielded an average accuracy of 89.09%, a precision rate of 89.54%, a recall rate of 86.57%, and an F1.score of 87.94%, which were higher than those of the comparison models. Conclusion: The proposed model is efficient and can minimize the revision complexities of implants.
Collapse
|
11
|
Hwang JH, Kim HJ, Park H, Lee BS, Son HY, Kim YB, Jun SY, Park JH, Lee J, Cho JW. Implementation and Practice of Deep Learning-Based Instance Segmentation Algorithm for Quantification of Hepatic Fibrosis at Whole Slide Level in Sprague-Dawley Rats. Toxicol Pathol 2021; 50:186-196. [PMID: 34866512 DOI: 10.1177/01926233211057128] [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] [Indexed: 12/18/2022]
Abstract
Exponential development in artificial intelligence or deep learning technology has resulted in more trials to systematically determine the pathological diagnoses using whole slide images (WSIs) in clinical and nonclinical studies. In this study, we applied Mask Regions with Convolution Neural Network (Mask R-CNN), a deep learning model that uses instance segmentation, to detect hepatic fibrosis induced by N-nitrosodimethylamine (NDMA) in Sprague-Dawley rats. From 51 WSIs, we collected 2011 cropped images with hepatic fibrosis annotations. Training and detection of hepatic fibrosis via artificial intelligence methods was performed using Tensorflow 2.1.0, powered by an NVIDIA 2080 Ti GPU. From the test process using tile images, 95% of model accuracy was verified. In addition, we validated the model to determine whether the predictions by the trained model can reflect the scoring system by the pathologists at the WSI level. The validation was conducted by comparing the model predictions in 18 WSIs at 20× and 10× magnifications with ground truth annotations and board-certified pathologists. Predictions at 20× showed a high correlation with ground truth (R 2 = 0.9660) and a good correlation with the average fibrosis rank by pathologists (R 2 = 0.8887). Therefore, the Mask R-CNN algorithm is a useful tool for detecting and quantifying pathological findings in nonclinical studies.
Collapse
Affiliation(s)
- Ji-Hee Hwang
- Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea
| | - Hyun-Ji Kim
- Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea.,College of Veterinary Medicine, Chungnam National University, Daejeon, Korea
| | - Heejin Park
- Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea
| | - Byoung-Seok Lee
- Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea
| | - Hwa-Young Son
- College of Veterinary Medicine, Chungnam National University, Daejeon, Korea
| | - Yong-Bum Kim
- Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea
| | | | | | - Jaeku Lee
- Research & Development Team, LAC Inc, Seoul, Korea
| | - Jae-Woo Cho
- Toxicologic Pathology Research Group, Department of Advanced Toxicology Research, Korea Institute of Toxicology, Daejeon, Korea
| |
Collapse
|
12
|
Owais M, Baek NR, Park KR. Domain-Adaptive Artificial Intelligence-Based Model for Personalized Diagnosis of Trivial Lesions Related to COVID-19 in Chest Computed Tomography Scans. J Pers Med 2021; 11:1008. [PMID: 34683149 PMCID: PMC8537687 DOI: 10.3390/jpm11101008] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2021] [Revised: 10/01/2021] [Accepted: 10/02/2021] [Indexed: 01/12/2023] Open
Abstract
BACKGROUND Early and accurate detection of COVID-19-related findings (such as well-aerated regions, ground-glass opacity, crazy paving and linear opacities, and consolidation in lung computed tomography (CT) scan) is crucial for preventive measures and treatment. However, the visual assessment of lung CT scans is a time-consuming process particularly in case of trivial lesions and requires medical specialists. METHOD A recent breakthrough in deep learning methods has boosted the diagnostic capability of computer-aided diagnosis (CAD) systems and further aided health professionals in making effective diagnostic decisions. In this study, we propose a domain-adaptive CAD framework, namely the dilated aggregation-based lightweight network (DAL-Net), for effective recognition of trivial COVID-19 lesions in CT scans. Our network design achieves a fast execution speed (inference time is 43 ms on a single image) with optimal memory consumption (almost 9 MB). To evaluate the performances of the proposed and state-of-the-art models, we considered two publicly accessible datasets, namely COVID-19-CT-Seg (comprising a total of 3520 images of 20 different patients) and MosMed (including a total of 2049 images of 50 different patients). RESULTS Our method exhibits average area under the curve (AUC) up to 98.84%, 98.47%, and 95.51% for COVID-19-CT-Seg, MosMed, and cross-dataset, respectively, and outperforms various state-of-the-art methods. CONCLUSIONS These results demonstrate that deep learning-based models are an effective tool for building a robust CAD solution based on CT data in response to present disaster of COVID-19.
Collapse
Affiliation(s)
| | | | - Kang Ryoung Park
- Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Korea; (M.O.); (N.R.B.)
| |
Collapse
|