1
|
Ueda Y, Ogawa D, Ishida T. Patient Re-Identification Based on Deep Metric Learning in Trunk Computed Tomography Images Acquired from Devices from Different Vendors. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:1124-1136. [PMID: 38366292 PMCID: PMC11169436 DOI: 10.1007/s10278-024-01017-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/27/2023] [Revised: 12/05/2023] [Accepted: 12/27/2023] [Indexed: 02/18/2024]
Abstract
During radiologic interpretation, radiologists read patient identifiers from the metadata of medical images to recognize the patient being examined. However, it is challenging for radiologists to identify "incorrect" metadata and patient identification errors. We propose a method that uses a patient re-identification technique to link correct metadata to an image set of computed tomography images of a trunk with lost or wrongly assigned metadata. This method is based on a feature vector matching technique that uses a deep feature extractor to adapt to the cross-vendor domain contained in the scout computed tomography image dataset. To identify "incorrect" metadata, we calculated the highest similarity score between a follow-up image and a stored baseline image linked to the correct metadata. The re-identification performance tests whether the image with the highest similarity score belongs to the same patient, i.e., whether the metadata attached to the image are correct. The similarity scores between the follow-up and baseline images for the same "correct" patients were generally greater than those for "incorrect" patients. The proposed feature extractor was sufficiently robust to extract individual distinguishable features without additional training, even for unknown scout computed tomography images. Furthermore, the proposed augmentation technique further improved the re-identification performance of the subset for different vendors by incorporating changes in width magnification due to changes in patient table height during each examination. We believe that metadata checking using the proposed method would help detect the metadata with an "incorrect" patient identifier assigned due to unavoidable errors such as human error.
Collapse
Affiliation(s)
- Yasuyuki Ueda
- Division of Health Sciences, Graduate School of Medicine, Osaka University, 1-7 Yamadaoka, Suita, Osaka, 565-0871, Japan.
| | - Daiki Ogawa
- School of Allied Health Sciences, Faculty of Medicine, Osaka University, 1-7 Yamadaoka, Suita, Osaka, 565-0871, Japan
| | - Takayuki Ishida
- Division of Health Sciences, Graduate School of Medicine, Osaka University, 1-7 Yamadaoka, Suita, Osaka, 565-0871, Japan
| |
Collapse
|
2
|
Herdiantoputri RR, Komura D, Ochi M, Fukawa Y, Kayamori K, Tsuchiya M, Kikuchi Y, Ushiku T, Ikeda T, Ishikawa S. Benchmarking Deep Learning-Based Image Retrieval of Oral Tumor Histology. Cureus 2024; 16:e62264. [PMID: 39011227 PMCID: PMC11247249 DOI: 10.7759/cureus.62264] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/09/2024] [Indexed: 07/17/2024] Open
Abstract
INTRODUCTION Oral tumors necessitate a dependable computer-assisted pathological diagnosis system considering their rarity and diversity. A content-based image retrieval (CBIR) system using deep neural networks has been successfully devised for digital pathology. No CBIR system for oral pathology has been investigated because of the lack of an extensive image database and feature extractors tailored to oral pathology. MATERIALS AND METHODS This study uses a large CBIR database constructed from 30 categories of oral tumors to compare deep learning methods as feature extractors. RESULTS The highest average area under the receiver operating characteristic curve (AUC) was achieved by models trained on database images using self-supervised learning (SSL) methods (0.900 with SimCLR and 0.897 with TiCo). The generalizability of the models was validated using query images from the same cases taken with smartphones. When smartphone images were tested as queries, both models yielded the highest mean AUC (0.871 with SimCLR and 0.857 with TiCo). We ensured the retrieved image result would be easily observed by evaluating the top 10 mean accuracies and checking for an exact diagnostic category and its differential diagnostic categories. CONCLUSION Training deep learning models with SSL methods using image data specific to the target site is beneficial for CBIR tasks in oral tumor histology to obtain histologically meaningful results and high performance. This result provides insight into the effective development of a CBIR system to help improve the accuracy and speed of histopathology diagnosis and advance oral tumor research in the future.
Collapse
Affiliation(s)
| | - Daisuke Komura
- Department of Preventive Medicine, The University of Tokyo, Tokyo, JPN
| | - Mieko Ochi
- Department of Preventive Medicine, The University of Tokyo, Tokyo, JPN
| | - Yuki Fukawa
- Department of Oral Pathology, Tokyo Medical and Dental University, Tokyo, JPN
| | - Kou Kayamori
- Department of Oral Pathology, Tokyo Medical and Dental University, Tokyo, JPN
| | - Maiko Tsuchiya
- Department of Pathology, Teikyo University School of Medicine, Tokyo, JPN
| | - Yoshinao Kikuchi
- Department of Pathology, Teikyo University School of Medicine, Tokyo, JPN
| | - Tetsuo Ushiku
- Department of Pathology, The University of Tokyo, Tokyo, JPN
| | - Tohru Ikeda
- Department of Oral Pathology, Tokyo Medical and Dental University, Tokyo, JPN
| | - Shumpei Ishikawa
- Department of Preventive Medicine, The University of Tokyo, Tokyo, JPN
| |
Collapse
|
3
|
Nejat P, Alsaafin A, Alabtah G, Comfere NI, Mangold AR, Murphree DH, Zot P, Yasir S, Garcia JJ, Tizhoosh HR. Creating an atlas of normal tissue for pruning WSI patching through anomaly detection. Sci Rep 2024; 14:3932. [PMID: 38366094 PMCID: PMC10873359 DOI: 10.1038/s41598-024-54489-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2023] [Accepted: 02/13/2024] [Indexed: 02/18/2024] Open
Abstract
Patching whole slide images (WSIs) is an important task in computational pathology. While most of them are designed to classify or detect the presence of pathological lesions in a WSI, the confounding role and redundant nature of normal histology are generally overlooked. In this paper, we propose and validate the concept of an "atlas of normal tissue" solely using samples of WSIs obtained from normal biopsies. Such atlases can be employed to eliminate normal fragments of tissue samples and hence increase the representativeness of the remaining patches. We tested our proposed method by establishing a normal atlas using 107 normal skin WSIs and demonstrated how established search engines like Yottixel can be improved. We used 553 WSIs of cutaneous squamous cell carcinoma to demonstrate the advantage. We also validated our method applied to an external dataset of 451 breast WSIs. The number of selected WSI patches was reduced by 30% to 50% after utilizing the proposed normal atlas while maintaining the same indexing and search performance in leave-one-patient-out validation for both datasets. We show that the proposed concept of establishing and using a normal atlas shows promise for unsupervised selection of the most representative patches of the abnormal WSI patches.
Collapse
Affiliation(s)
- Peyman Nejat
- KIMIA Lab, Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, USA
| | - Areej Alsaafin
- KIMIA Lab, Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, USA
| | - Ghazal Alabtah
- KIMIA Lab, Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, USA
| | | | | | - Dennis H Murphree
- Department of Dermatology, Mayo Clinic, Rochester, MN, USA
- Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, USA
| | - Patricija Zot
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - Saba Yasir
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - Joaquin J Garcia
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - H R Tizhoosh
- KIMIA Lab, Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, USA.
| |
Collapse
|