1
|
Zhang Y, Qu H, Tian Y, Na F, Yan J, Wu Y, Cui X, Li Z, Zhao M. PB-LNet: a model for predicting pathological subtypes of pulmonary nodules on CT images. BMC Cancer 2023; 23:936. [PMID: 37789252 PMCID: PMC10548640 DOI: 10.1186/s12885-023-11364-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Accepted: 09/04/2023] [Indexed: 10/05/2023] Open
Abstract
OBJECTIVE To investigate the correlation between CT imaging features and pathological subtypes of pulmonary nodules and construct a prediction model using deep learning. METHODS We collected information of patients with pulmonary nodules treated by surgery and the reference standard for diagnosis was post-operative pathology. After using elastic distortion for data augmentation, the CT images were divided into a training set, a validation set and a test set in a ratio of 6:2:2. We used PB-LNet to analyze the nodules in pre-operative CT and predict their pathological subtypes. Accuracy was used as the model evaluation index and Class Activation Map was applied to interpreting the results. Comparative experiments with other models were carried out to achieve the best results. Finally, images from the test set without data augmentation were analyzed to judge the clinical utility. RESULTS Four hundred seventy-seven patients were included and the nodules were divided into six groups: benign lesions, precursor glandular lesions, minimally invasive adenocarcinoma, invasive adenocarcinoma Grade 1, Grade 2 and Grade 3. The accuracy of the test set was 0.84. Class Activation Map confirmed that PB-LNet classified the nodules mainly based on the lungs in CT images, which is in line with the actual situation in clinical practice. In comparative experiments, PB-LNet obtained the highest accuracy. Finally, 96 images from the test set without data augmentation were analyzed and the accuracy was 0.89. CONCLUSIONS In classifying CT images of lung nodules into six categories based on pathological subtypes, PB-LNet demonstrates satisfactory accuracy without the need of delineating nodules, while the results are interpretable. A high level of accuracy was also obtained when validating on real data, therefore demonstrates its usefulness in clinical practice.
Collapse
Affiliation(s)
- Yuchong Zhang
- Department of Medical Oncology, the First Hospital of China Medical University, NO.155, North Nanjing Street, Heping District, Shenyang, Liaoning Province, 110001, China
| | - Hui Qu
- College of Medicine and Biological Information Engineering, Northeastern University, NO. 3-11, Wenhua Road, Heping District, Shenyang, 110819, Liaoning Province, China
| | - Yumeng Tian
- Department of Medical Oncology, the First Hospital of China Medical University, NO.155, North Nanjing Street, Heping District, Shenyang, Liaoning Province, 110001, China
| | - Fangjian Na
- Network Information Center, China Medical University, NO.77 Puhe Road, Shenbei New District, Shenyang, Liaoning Province, 110122, China
| | - Jinshan Yan
- Department of Medical Oncology, the First Hospital of China Medical University, NO.155, North Nanjing Street, Heping District, Shenyang, Liaoning Province, 110001, China
| | - Ying Wu
- Phase I Clinical Trails Center, the First Hospital of China Medical University, 210 1st Baita Street, Hunnan Distriction, Shenyang, Liaoning Province, 110101, China
| | - Xiaoyu Cui
- College of Medicine and Biological Information Engineering, Northeastern University, NO. 3-11, Wenhua Road, Heping District, Shenyang, 110819, Liaoning Province, China.
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Shenyang, China.
| | - Zhi Li
- Department of Medical Oncology, the First Hospital of China Medical University, NO.155, North Nanjing Street, Heping District, Shenyang, Liaoning Province, 110001, China.
| | - Mingfang Zhao
- Department of Medical Oncology, the First Hospital of China Medical University, NO.155, North Nanjing Street, Heping District, Shenyang, Liaoning Province, 110001, China.
| |
Collapse
|
2
|
Onuma K, Sato Y, Okuyama H, Uematsu H, Homma K, Ohue M, Kondo J, Inoue M. Aberrant activation of Rho/ROCK signaling in impaired polarity switching of colorectal micropapillary carcinoma. J Pathol 2021; 255:84-94. [PMID: 34156098 DOI: 10.1002/path.5748] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2021] [Revised: 06/07/2021] [Accepted: 06/17/2021] [Indexed: 12/17/2022]
Abstract
Micropapillary carcinoma (MPC) is a morphologically distinctive form of carcinoma, composed of small nests of cancer cells surrounded by lacunar spaces. Invasive MPC is associated with poor prognosis. The nests of tumor cells in MPC reportedly exhibit reverse polarity, although the molecular mechanisms underlying MPC patterns are poorly understood. Using the cancer tissue-originated spheroid (CTOS) method, we previously reported polarity switching in colorectal cancer (CRC). When cultured in suspension, the apical membrane promptly switches from the outside surface of the CTOSs to the surface of the lumen inside the CTOSs under extracellular matrix (ECM)-embedded conditions, and vice versa. Here, we investigated two CTOS lines from CRC patient tumors with MPC lesions. Xenograft tumors from the CTOSs exhibited the MPC phenotype. The MPC-CTOSs did not switch polarity in vitro. Time-course analysis of polarity switching using real-time imaging of the apical membrane revealed that local switching was continually propagated in non-MPC-CTOSs, while MPC-CTOSs were unable to complete the process. Integrin β4 translocated to the outer membrane when embedded in ECM in both MPC and non-MPC-CTOSs. Protein levels, as well as the active form of RhoA, were higher in MPC-CTOSs. The suppression of RhoA activity by GAP overexpression enabled MPC-CTOSs to complete polarity switching both in vitro and in vivo, while overexpression of active RhoA did not affect polarity switching in non-MPC-CTOSs. Pretreatment with a ROCK inhibitor enabled MPC-CTOSs to complete polarity switching both in vitro and in vivo, although delayed treatment after becoming embedded in ECM failed to do so. Thus, the inability to switch polarity might be a cause of MPC, in which the aberrant activation of RhoA plays a critical role. © 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.
Collapse
Affiliation(s)
- Kunishige Onuma
- Department of Clinical Bio-resource Research and Development, Graduate School of Medicine Kyoto University, Kyoto, Japan
| | - Yumi Sato
- Department of Clinical Bio-resource Research and Development, Graduate School of Medicine Kyoto University, Kyoto, Japan
| | - Hiroaki Okuyama
- Department of Biochemistry, Osaka International Cancer Institute, Osaka, Japan
| | - Hiroyuki Uematsu
- Department of Clinical Bio-resource Research and Development, Graduate School of Medicine Kyoto University, Kyoto, Japan
| | - Keiichiro Homma
- Department of Diagnostic Pathology and Cytology, Osaka International Cancer Institute, Osaka, Japan
| | - Masayuki Ohue
- Department of Gastroenterological Surgery, Osaka International Cancer Institute, Osaka, Japan
| | - Jumpei Kondo
- Department of Clinical Bio-resource Research and Development, Graduate School of Medicine Kyoto University, Kyoto, Japan
| | - Masahiro Inoue
- Department of Clinical Bio-resource Research and Development, Graduate School of Medicine Kyoto University, Kyoto, Japan
| |
Collapse
|
3
|
Dziedzic R, Marjański T, Rzyman W. A narrative review of invasive diagnostics and treatment of early lung cancer. Transl Lung Cancer Res 2021; 10:1110-1123. [PMID: 33718049 PMCID: PMC7947400 DOI: 10.21037/tlcr-20-728] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/08/2023]
Abstract
The diagnosis and treatment of early-stage lung cancer remains a clinical challenge. The broadening implementation of lung cancer screening has resulted in positive findings in numerous patients that are mostly non-malignant. Many other patients have indeterminate nodules that are difficult to assess through simple observation. The critical interpretation of such screening results remains a challenge for radiologists and multidisciplinary teams involved in screening for lung cancer. The evaluation and diagnosis of each participant suspected for malignancy should be based on the basic clinical principles such as a carefully collected medical history, physical examination, and detailed analysis of all imaging tests performed. Indeed, the decision to go ahead with more invasive diagnostics requires consideration of the both the risks and benefits, with reflection upon the complete clinical and radiological picture. Although transthoracic needle aspiration biopsy remains the first-choice method of diagnosis, several newer technologies have slowly begun to emerge as potential replacements. The guiding strategy for method selection is to choose the least harmful approach that offers the most relevant potential insights. Transthoracic biopsy is an effective method that allows the collection of cytological and tissue material from small, peripheral tumors, but it carries a moderate risk of complications. Bronchofiberoscopy, especially in combination with electromagnetic navigation, fluoroscopy or radial EBUS, also allows effective diagnosis of the peripheral pulmonary nodules. One of the most important diagnostic methods is the EBUS examination, which allows determining of staging in addition to diagnosis. Anatomical lung lobe resection and lymphadenectomy or sampling of the hilar and mediastinal lymph nodes is currently the treatment of choice for patients with stage I and II non-small cell lung cancer (NSCLC), but sublobar resections are recommended when a patient has limited pulmonary function or other significant comorbidities. Notably, several studies have highlighted the potential utility of more limited resections in small malignant lesions less than 2cm in diameter, with pure AIS histology, when more than 50% of the diameter of pulmonary nodule has ground-glass opacity (GGO) attenuation on CT, or long volume doubling time (VDT). Videothoracoscopy is the preferred surgical approach for resection of early-stage lung cancer. Patients who are not candidates for surgery or do not agree to surgery can be offered radical radiotherapy. Stereotactic body radiation therapy (SBRT) is a type of radical radiotherapy with proven effectiveness, a high rate of local control and an acceptable risk of the development of later complications. Future trials are expected to define the role of SBRT in the treatment of early lung cancer in healthy subjects.
Collapse
Affiliation(s)
- Robert Dziedzic
- Department of Thoracic Surgery, Medical University of Gdansk, Gdansk, Poland
| | - Tomasz Marjański
- Department of Thoracic Surgery, Medical University of Gdansk, Gdansk, Poland
| | - Witold Rzyman
- Department of Thoracic Surgery, Medical University of Gdansk, Gdansk, Poland
| |
Collapse
|