黑料网

Soft tissue; Patient care; Immunotherapy; Tissue tumors

Introduction

Soft tissue tumors encompass a diverse group of neoplasms arising from non-epithelial structures, including muscles, fat, nerves, and connective tissues. These tumors pose significant diagnostic and therapeutic challenges due to their heterogeneity, rarity, and potential for aggressive behavior. In recent years, there has been a surge of research efforts aimed at understanding the underlying biology of soft tissue tumors and optimizing treatment strategies. This editorial article aims to shed light on the complexities of soft tissue tumors and discuss the advancements that are shaping the landscape of patient care in this field [1].

The Heterogeneity of Soft Tissue Tumors: Soft tissue tumors encompass a wide range of histological subtypes, each exhibiting unique clinical and pathological features. From the relatively common lipomas to the rare and aggressive sarcomas, soft tissue tumors present a complex diagnostic landscape. Achieving accurate diagnosis and classification is crucial for appropriate treatment selection and prognostication [2]. Pathologists play a critical role in identifying specific molecular markers and genetic abnormalities that can aid in the diagnosis and sub classification of these tumors, enabling more precise and tailored therapeutic approaches [3].

Method

Advancements in Molecular Profiling: Recent advances in molecular profiling techniques have revolutionized our understanding of soft tissue tumors. Through genomic and transcriptomic analyses, key molecular alterations and signaling pathways have been identified [4], providing insights into tumor biology and potential therapeutic targets. This molecular characterization has paved the way for personalized medicine approaches, facilitating the development of targeted therapies and individualized treatment strategies.

Multimodal Treatment Approaches the management of soft tissue tumors requires a multimodal approach that integrates surgery, radiation therapy, and systemic therapies. Surgery remains the cornerstone of treatment, aiming for complete tumor resection while preserving function and minimizing morbidity. However, the complexity and anatomical locations of soft tissue tumors often pose challenges for surgical intervention. In such cases, radiation therapy can be employed preoperatively or postoperatively to enhance local control and improve outcomes. Additionally [5], advancements in systemic therapies, including chemotherapy and targeted therapies, have expanded treatment options and improved outcomes for patients with advanced or unrespectable soft tissue tumors.

Emerging Therapeutic Strategies the growing understanding of soft tissue tumor biology has led to the exploration of novel therapeutic strategies. Immunotherapy, which has shown remarkable success in various malignancies, is being investigated in soft tissue tumors, particularly in the context of immune-responsive subtypes and in combination with other treatment modalities [6]. Additionally, targeted therapies directed at specific molecular alterations, such as tyrosine kinase inhibitors and immune checkpoint inhibitors, have shown promising results in subsets of soft tissue tumors. These advancements hold the potential to further improve treatment outcomes and provide new avenues for patients with refractory or metastatic disease [7].

Result

Pathologic diagnosis of soft tissue tumors (STTs) has a significant impact on treatment selection and patient prognosis. Therefore, using hematoxylin and eosinestained images, it is essential to make a preliminary determination regarding the tumor’s benign or malignant status. Soft Tissue Tumor Box (STT-BOX) is a deep learning-based system that uses only hematoxylin and eosin images to distinguish malignant STTs from benign STTs based on their histopathologic similarity. STT-BOX used gastrointestinal stromal tumor as a starting point for malignant STT evaluation. In patients from three hospitals, it was able to distinguish gastrointestinal stromal tumor from leiomyoma and schwannoma with a 100% area under the curve, which was more accurate than the interpretation of experienced pathologists [8]. Particularly, this system accurately highlighted the malignant mass lesion in six common types of malignant STTs from The Cancer Genome Atlas data set. Without any fine-tuning, STTBOX was able to distinguish ovarian malignant sex-cord stromal tumors. The high accuracy of migration verification may reveal the morphologic similarity of the nine types of malignant tumors in this study, which included mesenchymal tumors that originated in the digestive system, bone and soft tissues, and reproductive system. Potential and prospective further evaluation in a pan-STT setting would eliminate the overuse of immunohistochemistry and molecular tests and provide a timely basis for clinical treatment selection [9].

Discussion

Collaborative Efforts and Future Directions: The complexity and rarity of soft tissue tumors necessitate collaboration among various disciplines, including surgical oncology, medical oncology, radiation oncology, pathology, and radiology. Multidisciplinary tumor boards and collaborative research efforts are vital for comprehensive patient evaluation, treatment planning, and advancing scientific knowledge in the field. Furthermore, the establishment of national and international registries and networks facilitates the collection and sharing of data, promoting evidence-based practices and fostering collaborative research [10].

Malignant and benign STTs are typically distinguished primarily by the arrangement, atypia, and nuclear mitosis of tumor cells, as well as the pattern of tumor margin growth and secondary changes like hemorrhage and tumor necrosis. The present study focused on STTs originated from the digestive system, soft tissue, and bone, as well as mesenchymal tumors from the reproductive system, in order to establish and test the deep learning-based system known as Soft Tissue Tumor Box (STT-BOX) in distinguishing malignant STTs from benign STTs (Supplemental Figure S1 provides the system interface of STT-BOX) [11]. Unfortunately, some malignant STTs are similar in growth pattern and morphologic features to initially, gastrointestinal stromal tumors (GISTs) served as the training material for the system’s core model. Histopathological, it is typically difficult to distinguish GISTs from benign tumors with spindle cell morphology, such as leiomyoma and schwannoma, both in gross specimens and H&E-stained slides. GIST is the most common malignant STT of the gastrointestinal tract and has varying degrees of recurrence and metastasis risk. To distinguish GISTs from benign STTs with similar histopathologic characteristics, pathologists must use an IHC antibody panel. The majority of GISTs have gain-of-function mutations in either the c-KIT or the plateletderived growth factor receptor a (PDGFRA) oncogene in their genetic makeup. Pathologists make use of molecular detection and a panel of protein biomarkers to make a definitive diagnosis and direct precise target therapy [12]. Since many pathology departments lack diagnostic expertise and auxiliary pathologic technology, this presents significant obstacles. A novel CNN-based system may therefore assist in the diagnosis of malignant STTs represented by GIST, taking into account CNNs’ success in distinguishing carcinoma histopathologic features.

Conclusion

Soft tissue tumors present a unique set of challenges in terms of diagnosis, classification, and treatment. However, with the rapid advancements in molecular profiling, multimodal treatment approaches, and emerging therapeutic strategies, there is renewed hope for patients with soft tissue tumors. By unraveling the complexities of these tumors and fostering collaborative efforts, we can continue to improve patient outcomes, refine treatment strategies, and pave the way for more personalized and effective interventions in the field of soft tissue oncology. Pathologic diagnosis of epithelial cancer has been greatly improved by artificial intelligence (AI) in recent years. The diagnosis of carcinomas of the skin,1 breast,2e6 prostate,7,8 lung,9 kidney,10,11 stomach,12 colorectum,13e15, and liver16 using deep learning based on convolutional neural networks (CNNs) has improved diagnostic efficiency and accuracy, even demonstrating a trend that is more objective and forward-looking than pathologists’ diagnoses. In contrast, AI diagnosis of soft tissue tumors (STTs) receives little research. Hematoxylin and eosin (H&E)-stained slides alone make it difficult for pathologists to determine whether an STT is benign or malignant. Mesenchymal connective tissue is the source of a variety of benign, borderline, and malignant tumors in STT. Spindle cells or some spindle cells make up the majority of tumors.

1. McLoughlin GS, Sciubba DM, Wolinsky JP (2008) . Neurosurg Clin N Am 19:57-63.

, ,

2. Chick JF, Chauhan NR, Madan R (2013) AJR Am J Roentgenol 200: 238-248.

, ,

3. Gengler C, Guillou L (2006) Histopathology 48: 63-74.

, ,

4. Ogose A, Hotta T, Kawashima H, Hatano H, Umezu H, et al. (2001) Elevation of serum alkaline phosphatase in clear cell chondrosarcoma of bone. Anticancer Res 21:649-655.

,

5. Flint A, Weiss SW (1995) Hum Pathol 26: 428-431.

, ,

6. Doyle LA (2014) Cancer 120: 1763-74.

, ,

7. Laitinen M, Nieminen J, Pakarinen T-K (2014) . Case Rep Orthop e109569.

, ,

8. Dalton WT, Zolliker AS, McCaughey WT (1979) Cancer 44: 1465-1475.

, ,

9. Briselli M, Mark EJ, Dickersin GR (1981) . Cancer 47: 2678-2689.

, ,

10. Kumar R, David R, Cierney G (1985) Clear cell chondrosarcoma. Radiology 154:45-48.

,

11. Kaim AH, Hugli R, Bonél HM, Jundt G (2002) . Skeletal Radiol 31:88–95.

, ,

12. Witkin GB, Rosai J (1989) Am J Surg Pathol 13: 547-557?

, ,