Utility of artificial intelligence in a binary classification of soft tissue tumors
Soft tissue tumors (STTs) pose diagnostic and therapeutic challenges due to their rarity, complexity, and morphological overlap. Accurate differentiation between benign and malignant STTs is important to set treatment directions, however, this task can be difficult. The integration of machine learni...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2153353924000075 |
| _version_ | 1826932973057867776 |
|---|---|
| author | Jing Di Caylin Hickey Cody Bumgardner Mustafa Yousif Mauricio Zapata Therese Bocklage Bonnie Balzer Marilyn M. Bui Jerad M. Gardner Liron Pantanowitz Shadi A. Qasem |
| author_facet | Jing Di Caylin Hickey Cody Bumgardner Mustafa Yousif Mauricio Zapata Therese Bocklage Bonnie Balzer Marilyn M. Bui Jerad M. Gardner Liron Pantanowitz Shadi A. Qasem |
| author_sort | Jing Di |
| collection | DOAJ |
| description | Soft tissue tumors (STTs) pose diagnostic and therapeutic challenges due to their rarity, complexity, and morphological overlap. Accurate differentiation between benign and malignant STTs is important to set treatment directions, however, this task can be difficult. The integration of machine learning and artificial intelligence (AI) models can potentially be helpful in classifying these tumors. The aim of this study was to investigate AI and machine learning tools in the classification of STT into benign and malignant categories. This study consisted of three components: (1) Evaluation of whole-slide images (WSIs) to classify STT into benign and malignant entities. Five specialized soft tissue pathologists from different medical centers independently reviewed 100 WSIs, representing 100 different cases, with limited clinical information and no additional workup. The results showed an overall concordance rate of 70.4% compared to the reference diagnosis. (2) Identification of cell-specific parameters that can distinguish benign and malignant STT. Using an image analysis software (QuPath) and a cohort of 95 cases, several cell-specific parameters were found to be statistically significant, most notably cell count, nucleus/cell area ratio, nucleus hematoxylin density mean, and cell max caliper. (3) Evaluation of machine learning library (Scikit-learn) in differentiating benign and malignant STTs. A total of 195 STT cases (156 cases in the training group and 39 cases in the validation group) achieved approximately 70% sensitivity and specificity, and an AUC of 0.68. Our limited study suggests that the use of WSI and AI in soft tissue pathology has the potential to enhance diagnostic accuracy and identify parameters that can differentiate between benign and malignant STTs. We envision the integration of AI as a supportive tool to augment the pathologists' diagnostic capabilities. |
| first_indexed | 2024-04-25T01:13:07Z |
| format | Article |
| id | doaj.art-e65007d7f266420ea9e4f2c562340354 |
| institution | Directory Open Access Journal |
| issn | 2153-3539 |
| language | English |
| last_indexed | 2025-02-17T17:24:16Z |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-e65007d7f266420ea9e4f2c5623403542024-12-15T06:15:12ZengElsevierJournal of Pathology Informatics2153-35392024-12-0115100368Utility of artificial intelligence in a binary classification of soft tissue tumorsJing Di0Caylin Hickey1Cody Bumgardner2Mustafa Yousif3Mauricio Zapata4Therese Bocklage5Bonnie Balzer6Marilyn M. Bui7Jerad M. Gardner8Liron Pantanowitz9Shadi A. Qasem10University of Kentucky College of Medicine, Lexington, KY, United StatesUniversity of Kentucky College of Medicine, Lexington, KY, United StatesUniversity of Kentucky College of Medicine, Lexington, KY, United StatesUniversity of Michigan, Ann Arbor, MI, United StatesNorthside Hospital, Georgia, United StatesUniversity of Kentucky College of Medicine, Lexington, KY, United StatesCedars-Sinai Medical Center, Los Angeles, CA, United StatesMoffitt Cancer Center & Research Institute, Tampa, FL, United StatesGeisinger Medical Center, Danville, PA, United StatesUniversity of Pittsburgh Medical Center, Pittsburgh, PA, United StatesUniversity of Kentucky College of Medicine, Lexington, KY, United States; Baptist Health Jacksonville, Jacksonville, FL, United States; Corresponding author at: Baptist Health Jacksonville, 800 Prudential Drive, Jacksonville, FL 32256, USA.Soft tissue tumors (STTs) pose diagnostic and therapeutic challenges due to their rarity, complexity, and morphological overlap. Accurate differentiation between benign and malignant STTs is important to set treatment directions, however, this task can be difficult. The integration of machine learning and artificial intelligence (AI) models can potentially be helpful in classifying these tumors. The aim of this study was to investigate AI and machine learning tools in the classification of STT into benign and malignant categories. This study consisted of three components: (1) Evaluation of whole-slide images (WSIs) to classify STT into benign and malignant entities. Five specialized soft tissue pathologists from different medical centers independently reviewed 100 WSIs, representing 100 different cases, with limited clinical information and no additional workup. The results showed an overall concordance rate of 70.4% compared to the reference diagnosis. (2) Identification of cell-specific parameters that can distinguish benign and malignant STT. Using an image analysis software (QuPath) and a cohort of 95 cases, several cell-specific parameters were found to be statistically significant, most notably cell count, nucleus/cell area ratio, nucleus hematoxylin density mean, and cell max caliper. (3) Evaluation of machine learning library (Scikit-learn) in differentiating benign and malignant STTs. A total of 195 STT cases (156 cases in the training group and 39 cases in the validation group) achieved approximately 70% sensitivity and specificity, and an AUC of 0.68. Our limited study suggests that the use of WSI and AI in soft tissue pathology has the potential to enhance diagnostic accuracy and identify parameters that can differentiate between benign and malignant STTs. We envision the integration of AI as a supportive tool to augment the pathologists' diagnostic capabilities.http://www.sciencedirect.com/science/article/pii/S2153353924000075Artificial intelligenceDigital pathologySarcomaSoft tissue tumorsWhole-slide imagesDeep learning |
| spellingShingle | Jing Di Caylin Hickey Cody Bumgardner Mustafa Yousif Mauricio Zapata Therese Bocklage Bonnie Balzer Marilyn M. Bui Jerad M. Gardner Liron Pantanowitz Shadi A. Qasem Utility of artificial intelligence in a binary classification of soft tissue tumors Journal of Pathology Informatics Artificial intelligence Digital pathology Sarcoma Soft tissue tumors Whole-slide images Deep learning |
| title | Utility of artificial intelligence in a binary classification of soft tissue tumors |
| title_full | Utility of artificial intelligence in a binary classification of soft tissue tumors |
| title_fullStr | Utility of artificial intelligence in a binary classification of soft tissue tumors |
| title_full_unstemmed | Utility of artificial intelligence in a binary classification of soft tissue tumors |
| title_short | Utility of artificial intelligence in a binary classification of soft tissue tumors |
| title_sort | utility of artificial intelligence in a binary classification of soft tissue tumors |
| topic | Artificial intelligence Digital pathology Sarcoma Soft tissue tumors Whole-slide images Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2153353924000075 |
| work_keys_str_mv | AT jingdi utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT caylinhickey utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT codybumgardner utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT mustafayousif utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT mauriciozapata utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT theresebocklage utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT bonniebalzer utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT marilynmbui utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT jeradmgardner utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT lironpantanowitz utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors AT shadiaqasem utilityofartificialintelligenceinabinaryclassificationofsofttissuetumors |