Spatially resolved immune microenvironmental profiling for follicular thyroid carcinoma with minimal capsular invasion

Saburi, Sumiyo; Tsujikawa, Takahiro; Miyagawa‐Hayashino, Aya; Mitsuda, Junichi; Yoshimura, Kanako; Kimura, Alisa; Morimoto, Hiroki; Ohmura, Gaku; Arai, Akihito; Ogi, Hiroshi; Konishi, Eiichi; Itoh, Kyoko; Sugino, Kiminori; Hirano, Shigeru

doi:10.1038/s41379-021-00993-6

Cited by 7 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few previous studies were carried out on differential diagnosis of FTC and FA, most of which focused on improvements in diagnosis methods in cytology or pathology 6 , 7 , 36 . Our study exhibited a noninvasive, high-precision preoperative predicting system on follicular thyroid neoplasms for the first time.…”

Section: Discussionmentioning

confidence: 99%

“…The only reliable way of differentiating them is through diagnostic surgery to investigate definite capsular invasion (CI) and/or vascular invasion (VI) by pathological examinations 1 , 4 - 6 . Although differentiated thyroid carcinoma (DTC) presents a perfect prognosis with a 5-year disease-free survival rate of over 98%, FTC is, in contrast, generally considered to be more aggressive and carries risks of distant metastasis 1 , 7 , 8 . Thus, patients with suspicious FNs are recommended to undergo diagnostic surgeries in clinical guidelines, leading to a large portion of patients receiving surgery for FN that were later pathologically confirmed to be benign tumors 9 , 10 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated diagnosis and management of follicular thyroid nodules based on the devised small-dataset interpretable foreground optimization network deep learning: a multicenter diagnostic study

Yang

Yao

Heng

et al. 2023

International Journal of Surgery

View full text Add to dashboard Cite

Background: Currently, follicular thyroid carcinoma (FTC) has a relatively low incidence with a lack of effective preoperative diagnostic means. To reduce the need for invasive diagnostic procedures and to address information deficiencies inherent in a small dataset, we utilized interpretable foreground optimization network deep learning to develop a reliable preoperative FTC detection system. Methods: In this study, a deep learning model (FThyNet) was established using preoperative ultrasound images. Data on patients in the training and internal validation cohort (n=432) were obtained from Ruijin Hospital, China. Data on patients in the external validation cohort (n=71) were obtained from four other clinical centers. We evaluated the predictive performance of FThyNet and its ability to generalize across multiple external centers and compared the results yielded with assessments from physicians directly predicting FTC outcomes. In addition, the influence of texture information around the nodule edge on the prediction results was evaluated. Results: FThyNet had a consistently high accuracy in predicting FTC with an area under the receiver operating characteristic curve (AUC) of 89.0% [95% CI 87.0–90.9]. Particularly, the AUC for grossly invasive FTC reached 90.3%, which was significantly higher than that of the radiologists (56.1% [95% CI 51.8–60.3]). The parametric visualization study found that those nodules with blurred edges and relatively distorted surrounding textures were more likely to have FTC. Furthermore, edge texture information played an important role in FTC prediction with an AUC of 68.3% [95% CI 61.5–75.5], and highly invasive malignancies had the highest texture complexity. Conclusion: FThyNet could effectively predict FTC, provide explanations consistent with pathological knowledge, and improve clinical understanding of the disease.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automated diagnosis and management of follicular thyroid nodules based on the devised small-dataset interpretable foreground optimization network deep learning: a multicenter diagnostic study

Yang

Yao

Heng

et al. 2023

International Journal of Surgery

View full text Add to dashboard Cite

show abstract

“…Current research indicates that PD-L1 suppresses the anti-tumor immune response by inhibiting the activation of T cells, which is the most common blocking target of immune checkpoints [93]. Saburi et al noticed that PD-L1 was highly expressed in FTC, and its expression was higher in the invasive edge of the tumor and the infiltrating tumor-correlated immune cells than in the tumor center, which may be linked to the high concentration of T cells in this region [94]. Anti-PD-1 therapy has become one of the most effective treatments for advanced TC [95].…”

Section: Interaction Between Tumor Infiltrating Lymphocytes In Follic...mentioning

confidence: 99%

Crosstalk between Thyroid Carcinoma and Tumor-Correlated Immune Cells in the Tumor Microenvironment

Song,

Liu,

Sun

et al. 2023

Cancers

View full text Add to dashboard Cite

Thyroid cancer (TC) is the most common malignancy in the endocrine system. Although most TC can achieve a desirable prognosis, some refractory thyroid carcinomas, including radioiodine-refractory differentiated thyroid cancer, as well as anaplastic thyroid carcinoma, face a myriad of difficulties in clinical treatment. These types of tumors contribute to the majority of TC deaths due to limited initial therapy, recurrence, and metastasis of the tumor and tumor resistance to current clinically targeted drugs, which ultimately lead to treatment failure. At present, a growing number of studies have demonstrated crosstalk between TC and tumor-associated immune cells, which affects tumor deterioration and metastasis through distinct signal transduction or receptor activation. Current immunotherapy focuses primarily on cutting off the interaction between tumor cells and immune cells. Since the advent of immunotherapy, scholars have discovered targets for TC immunotherapy, which also provides new strategies for TC treatment. This review methodically and intensively summarizes the current understanding and mechanism of the crosstalk between distinct types of TC and immune cells, as well as potential immunotherapy strategies and clinical research results in the area of the tumor immune microenvironment. We aim to explore the current research advances to formulate better individualized treatment strategies for TC patients and to provide clues and references for the study of potential immune checkpoints and the development of immunotherapy technologies.

show abstract

“…The latest National Comprehensive Cancer Network (NCCN) state that colorectal cancer is usually staged after intraoperative exploration of the abdominal cavity and postoperative pathological examination of surgical specimens. The pathological examination report includes tumor cell grade [2], depth of invasion [3][4][5] and extent of invasion to surrounding structures (T), number of lymph nodes sent for examination,number of metastatic lymph nodes (N) [6], assessment of distant metastasis region to other organs, peritoneal or intraperitoneal structures, and non-regional lymph nodes (M), and the status of the proximal, distal and circumferential margins, lymphovascular invasion [7,8], perineural invasion [9][10][11], and extratumoral nodules [12,13].TNM staging results have an important role in doctors in formulating treatment plans. In the metastasis of colorectal cancer, the most common site of metastasis is the liver [14,15], and once the metastasis occurs, the patient will have a poorer survival status.…”

Section: Introductionmentioning

confidence: 99%

Prognostic analysis based on multi-features calculation and clinical information fusion of colorectal cancer whole slide pathological image

Cai

Zhou

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Colorectal cancer (CRC) is a malignant tumor within digestive tract with both high incidence rate and and mortality. Early detection and intervention could improve patient clinical outcome and survival. Methods: This study computationally investigate a set of prognostic tissue and celluer features from diagnostic tissue slide. With the combination of clinical prognostic variable, the pathological image features could predict the prognosis in CRC patients.ur CRC prognosis prediction pipeline is sequentially consisted of three modules: (1) A DeepTissue Net to delineate outlines of different tissue types within the WSI of CRC for further ROI selection by pathologist; (2) Development of three-level quantitative image metrics related to tissue compositions, cell shape and hidden features from deep network; (3) Fusion of multi-level features to build a prognostic CRC model for predicting survival for CRC. Results: Experimental results suggest that each group of features has a certain relationship with the prognosis of patients in the independent test set. In the fusion features combination experiment, the accuracy rate of predicting patients' prognosis and survival status is 81.52%, and the AUC value is 0.77. Conclusion: This paper constructs a model that can predict postoperative survival of patients by using image features and clinical information.Some features were found to be associated with the prognosis and survival of patients.

show abstract

Spatially resolved immune microenvironmental profiling for follicular thyroid carcinoma with minimal capsular invasion

Cited by 7 publications

References 33 publications

Automated diagnosis and management of follicular thyroid nodules based on the devised small-dataset interpretable foreground optimization network deep learning: a multicenter diagnostic study

Automated diagnosis and management of follicular thyroid nodules based on the devised small-dataset interpretable foreground optimization network deep learning: a multicenter diagnostic study

Crosstalk between Thyroid Carcinoma and Tumor-Correlated Immune Cells in the Tumor Microenvironment

Prognostic analysis based on multi-features calculation and clinical information fusion of colorectal cancer whole slide pathological image

Contact Info

Product

Resources

About