1
|
Neder AT, da Costa AC, de Barros RSM, Nakachima LR, Rodrigues MP, de Souza SCA, de Oliveira RK, da Gama SAM, Sabongi RG, Hirakawa CK. Hand tumors. REVISTA DA ASSOCIACAO MEDICA BRASILEIRA (1992) 2024; 70:e2024S108. [PMID: 38865528 PMCID: PMC11164264 DOI: 10.1590/1806-9282.2024s108] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/29/2023] [Accepted: 12/11/2023] [Indexed: 06/14/2024]
Affiliation(s)
- Antonio Tufi Neder
- Universidade de São Paulo/Faculty of Medicine of Ribeirão Preto - Hand Surgery at Rede Mater Dei de Saúde and Instituto Orizonti – Belo Horizonte (MG), Brazil
| | - Antonio Carlos da Costa
- Medical School of Santa Casa de São Paulo, Hand Surgery and Microsurgery Group at Santa Casa de São Paulo – Belo Horizonte (MG), Brazil
| | | | - Luis Renato Nakachima
- Universidade Federal de São Paulo, Paulista School of Medicine, Department of Orthopedics and Traumatology – Belo Horizonte (MG), Brazil
| | - Mauricio Pinto Rodrigues
- Universidade de São Paulo, Institute of Orthopedics and Traumatology, Clinical Hospital, Faculty of Medicine – Belo Horizonte (MG), Brazil
| | | | | | - Sérgio Augusto Machado da Gama
- Universidade de São Paulo, Clinical Hospital, Faculty of Medicine, Pontifícia Universidade Católica de Campinas Hand Group – Belo Horizonte (MG), Brazil
| | - Rodrigo Guerra Sabongi
- Universidade Federal de São Paulo, Paulista School of Medicine – Belo Horizonte (MG), Brazil
| | - Celso Kiyoshi Hirakawa
- Universidade Federal de São Paulo, Paulista School of Medicine, Department of Orthopedics and Traumatology – Belo Horizonte (MG), Brazil
| |
Collapse
|
2
|
Xie H, Zhang Y, Dong L, Lv H, Li X, Zhao C, Tian Y, Xie L, Wu W, Yang Q, Liu L, Sun D, Qiu L, Shen L, Zhang Y. Deep learning driven diagnosis of malignant soft tissue tumors based on dual-modal ultrasound images and clinical indexes. Front Oncol 2024; 14:1361694. [PMID: 38846984 PMCID: PMC11153704 DOI: 10.3389/fonc.2024.1361694] [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] [Received: 12/26/2023] [Accepted: 05/08/2024] [Indexed: 06/09/2024] Open
Abstract
Background Soft tissue tumors (STTs) are benign or malignant superficial neoplasms arising from soft tissues throughout the body with versatile pathological types. Although Ultrasonography (US) is one of the most common imaging tools to diagnose malignant STTs, it still has several drawbacks in STT diagnosis that need improving. Objectives The study aims to establish this deep learning (DL) driven Artificial intelligence (AI) system for predicting malignant STTs based on US images and clinical indexes of the patients. Methods We retrospectively enrolled 271 malignant and 462 benign masses to build the AI system using 5-fold validation. A prospective dataset of 44 malignant masses and 101 benign masses was used to validate the accuracy of system. A multi-data fusion convolutional neural network, named ultrasound clinical soft tissue tumor net (UC-STTNet), was developed to combine gray scale and color Doppler US images and clinic features for malignant STTs diagnosis. Six radiologists (R1-R6) with three experience levels were invited for reader study. Results The AI system achieved an area under receiver operating curve (AUC) value of 0.89 in the retrospective dataset. The diagnostic performance of the AI system was higher than that of one of the senior radiologists (AUC of AI vs R2: 0.89 vs. 0.84, p=0.022) and all of the intermediate and junior radiologists (AUC of AI vs R3, R4, R5, R6: 0.89 vs 0.75, 0.81, 0.80, 0.63; p <0.01). The AI system also achieved an AUC of 0.85 in the prospective dataset. With the assistance of the system, the diagnostic performances and inter-observer agreement of the radiologists was improved (AUC of R3, R5, R6: 0.75 to 0.83, 0.80 to 0.85, 0.63 to 0.69; p<0.01). Conclusion The AI system could be a useful tool in diagnosing malignant STTs, and could also help radiologists improve diagnostic performance.
Collapse
Affiliation(s)
- Haiqin Xie
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Yudi Zhang
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China
| | - Licong Dong
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Heng Lv
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Xuechen Li
- National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China
| | - Chenyang Zhao
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Yun Tian
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Lu Xie
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Wangjie Wu
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Qi Yang
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Li Liu
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Desheng Sun
- Shenzhen Hospital, Peking University, Shenzhen, China
| | - Li Qiu
- West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Linlin Shen
- College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China
| | - Yusen Zhang
- Shenzhen Hospital, Peking University, Shenzhen, China
| |
Collapse
|
3
|
Using Machine Learning to Unravel the Value of Radiographic Features for the Classification of Bone Tumors. BIOMED RESEARCH INTERNATIONAL 2021; 2021:8811056. [PMID: 33791381 PMCID: PMC7984886 DOI: 10.1155/2021/8811056] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/27/2020] [Revised: 11/05/2020] [Accepted: 03/03/2021] [Indexed: 11/17/2022]
Abstract
Objectives To build and validate random forest (RF) models for the classification of bone tumors based on the conventional radiographic features of the lesion and patients' clinical characteristics, and identify the most essential features for the classification of bone tumors. Materials and Methods In this retrospective study, 796 patients (benign bone tumors: 412 cases, malignant bone tumors: 215 cases, intermediate bone tumors: 169 cases) with pathologically confirmed bone tumors from Nanfang Hospital of Southern Medical University, Foshan Hospital of TCM, and University of Hong Kong-Shenzhen Hospital were enrolled. RF models were built to classify tumors as benign, malignant, or intermediate based on conventional radiographic features and potentially relevant clinical characteristics extracted by three musculoskeletal radiologists with ten years of experience. SHapley Additive exPlanations (SHAP) was used to identify the most essential features for the classification of bone tumors. The diagnostic performance of the RF models was quantified using receiver operating characteristic (ROC) curves. Results The features extracted by the three radiologists had a satisfactory agreement and the minimum intraclass correlation coefficient (ICC) was 0.761 (CI: 0.686-0.824, P < .001). The binary and tertiary models were built to classify tumors as benign, malignant, or intermediate based on the imaging and clinical features from 627 and 796 patients. The AUC of the binary (19 variables) and tertiary (22 variables) models were 0.97 and 0.94, respectively. The accuracy of binary and tertiary models were 94.71% and 82.77%, respectively. In descending order, the most important features influencing classification in the binary model were margin, cortex involvement, and the pattern of bone destruction, and the most important features in the tertiary model were margin, high-density components, and cortex involvement. Conclusions This study developed interpretable models to classify bone tumors with great performance. These should allow radiographers to identify imaging features that are important for the classification of bone tumors in the clinical setting.
Collapse
|