Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence
Abstract The emergence of digital pathology has opened new horizons for histopathology. Artificial intelligence (AI) algorithms are able to operate on digitized slides to assist pathologists with different tasks. Whereas AI-involving classification and segmentation methods have obvious benefits for...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2020-03-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-020-0238-2 |
| _version_ | 1827614293964619776 |
|---|---|
| author | Shivam Kalra H. R. Tizhoosh Sultaan Shah Charles Choi Savvas Damaskinos Amir Safarpoor Sobhan Shafiei Morteza Babaie Phedias Diamandis Clinton J. V. Campbell Liron Pantanowitz |
| author_facet | Shivam Kalra H. R. Tizhoosh Sultaan Shah Charles Choi Savvas Damaskinos Amir Safarpoor Sobhan Shafiei Morteza Babaie Phedias Diamandis Clinton J. V. Campbell Liron Pantanowitz |
| author_sort | Shivam Kalra |
| collection | DOAJ |
| description | Abstract The emergence of digital pathology has opened new horizons for histopathology. Artificial intelligence (AI) algorithms are able to operate on digitized slides to assist pathologists with different tasks. Whereas AI-involving classification and segmentation methods have obvious benefits for image analysis, image search represents a fundamental shift in computational pathology. Matching the pathology of new patients with already diagnosed and curated cases offers pathologists a new approach to improve diagnostic accuracy through visual inspection of similar cases and computational majority vote for consensus building. In this study, we report the results from searching the largest public repository (The Cancer Genome Atlas, TCGA) of whole-slide images from almost 11,000 patients. We successfully indexed and searched almost 30,000 high-resolution digitized slides constituting 16 terabytes of data comprised of 20 million 1000 × 1000 pixels image patches. The TCGA image database covers 25 anatomic sites and contains 32 cancer subtypes. High-performance storage and GPU power were employed for experimentation. The results were assessed with conservative “majority voting” to build consensus for subtype diagnosis through vertical search and demonstrated high accuracy values for both frozen section slides (e.g., bladder urothelial carcinoma 93%, kidney renal clear cell carcinoma 97%, and ovarian serous cystadenocarcinoma 99%) and permanent histopathology slides (e.g., prostate adenocarcinoma 98%, skin cutaneous melanoma 99%, and thymoma 100%). The key finding of this validation study was that computational consensus appears to be possible for rendering diagnoses if a sufficiently large number of searchable cases are available for each cancer subtype. |
| first_indexed | 2024-03-09T08:52:51Z |
| format | Article |
| id | doaj.art-236179d0be3f4c138cb25ddc2e00fa92 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T08:52:51Z |
| publishDate | 2020-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-236179d0be3f4c138cb25ddc2e00fa922023-12-02T13:39:51ZengNature Portfolionpj Digital Medicine2398-63522020-03-013111510.1038/s41746-020-0238-2Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligenceShivam Kalra0H. R. Tizhoosh1Sultaan Shah2Charles Choi3Savvas Damaskinos4Amir Safarpoor5Sobhan Shafiei6Morteza Babaie7Phedias Diamandis8Clinton J. V. Campbell9Liron Pantanowitz10Huron Digital PathologyKimia Lab, University of WaterlooHuron Digital PathologyHuron Digital PathologyHuron Digital PathologyKimia Lab, University of WaterlooKimia Lab, University of WaterlooKimia Lab, University of WaterlooGeneral Hospital/Research Institute (UHN)Stem Cell and Cancer Research Institute, McMaster UniversityDepartment of Pathology, University of Pittsburgh Medical CenterAbstract The emergence of digital pathology has opened new horizons for histopathology. Artificial intelligence (AI) algorithms are able to operate on digitized slides to assist pathologists with different tasks. Whereas AI-involving classification and segmentation methods have obvious benefits for image analysis, image search represents a fundamental shift in computational pathology. Matching the pathology of new patients with already diagnosed and curated cases offers pathologists a new approach to improve diagnostic accuracy through visual inspection of similar cases and computational majority vote for consensus building. In this study, we report the results from searching the largest public repository (The Cancer Genome Atlas, TCGA) of whole-slide images from almost 11,000 patients. We successfully indexed and searched almost 30,000 high-resolution digitized slides constituting 16 terabytes of data comprised of 20 million 1000 × 1000 pixels image patches. The TCGA image database covers 25 anatomic sites and contains 32 cancer subtypes. High-performance storage and GPU power were employed for experimentation. The results were assessed with conservative “majority voting” to build consensus for subtype diagnosis through vertical search and demonstrated high accuracy values for both frozen section slides (e.g., bladder urothelial carcinoma 93%, kidney renal clear cell carcinoma 97%, and ovarian serous cystadenocarcinoma 99%) and permanent histopathology slides (e.g., prostate adenocarcinoma 98%, skin cutaneous melanoma 99%, and thymoma 100%). The key finding of this validation study was that computational consensus appears to be possible for rendering diagnoses if a sufficiently large number of searchable cases are available for each cancer subtype.https://doi.org/10.1038/s41746-020-0238-2 |
| spellingShingle | Shivam Kalra H. R. Tizhoosh Sultaan Shah Charles Choi Savvas Damaskinos Amir Safarpoor Sobhan Shafiei Morteza Babaie Phedias Diamandis Clinton J. V. Campbell Liron Pantanowitz Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence npj Digital Medicine |
| title | Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence |
| title_full | Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence |
| title_fullStr | Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence |
| title_full_unstemmed | Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence |
| title_short | Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence |
| title_sort | pan cancer diagnostic consensus through searching archival histopathology images using artificial intelligence |
| url | https://doi.org/10.1038/s41746-020-0238-2 |
| work_keys_str_mv | AT shivamkalra pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT hrtizhoosh pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT sultaanshah pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT charleschoi pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT savvasdamaskinos pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT amirsafarpoor pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT sobhanshafiei pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT mortezababaie pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT phediasdiamandis pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT clintonjvcampbell pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence AT lironpantanowitz pancancerdiagnosticconsensusthroughsearchingarchivalhistopathologyimagesusingartificialintelligence |