Lung cancer is one of the malignant tumours with the highest morbidity and mortality rates worldwide today, posing a major threat to human health. Accurate diagnosis and standardised treatment play a crucial role in improving the survival rate of lung cancer patients. In recent years, the rapid rise of artificial intelligence (AI) has brought about significant changes in the medical field, providing a new diagnostic and treatment model for lung cancer, and making a series of breakthroughs in lung cancer diagnostic imaging, pathological diagnosis, surgical oncology, radiotherapy, and drug development and treatment. This article introduces the current status of AI application in the field of lung cancer diagnosis and treatment, and extensively discusses the current challenges and future prospects, hoping to provide references and suggestions for future clinical practice.

Objective To explore imaging features of telangiectatic osteosarcoma(TOS).Methods X-ray,CT and MRI data of 37 cases of TOS confirmed by surgical pathology were retrospectively analyzed.Lesion's location,morphology,border,density/signal,enhancement pattern,presence of hemorrhage,tumor bone,fluid-fluid levels,periosteal reaction,septal nodules,epiphyseal involvement,bone destruction and surrounding sclerosis,peripheral edema and pathological fracture or not were recorded.The misdiagnosis rate of each imaging examination was calculated.Results TOS was prone to occur in the femur,humerus and tibia metaphysis,predominantly presented as eccentric,expansive and map-like osteolytic bone destruction with little or no surrounding sclerosis,showing polycystic changes,with fluid-fluid levels,hemorrhagic and tumor bone,along with periosteal reactions and marginal and septal nodule-like enhancement after enhanced scanning.The misdiagnosis rate of X-ray,non-contrast CT,enhanced CT,non-contrast MRI,enhanced MRI and preoperative biopsy for diagnosing TOS was 75.00%(24/32),50.00%(3/6),38.10%(8/21),50.00%(6/12),24.32%(9/37)and 24.32%(9/37),respectively.Conclusion TOS had certain characteristic imaging manifestations.Comprehensive imaging examinations combined with accurate pathological sampling contributed to precise diagnosis and reduction of misdiagnosis rate of TOS.

Objective To explore imaging characteristics of myxofibrosarcoma(MFS)and their correlations with prognosis.Methods Totally 32 patients with pathologically confirmed MFS were retrospectively enrolled and divided into poor prognosis(recurrence/metastasis)group(n=13)and good prognosis group(n=19).Preoperative imaging characteristics of lesions were analyzed and compared between groups,including the location,shape,size,margins,density/signal features of lesions,adjacent bone destruction,peritumoral edema,fascial tail sign,enhancement patterns and tumor vasculature.Results MFS predominantly involved the extremities,especially the lower limbs,and the lesions commonly appeared as iso-to hypodensity masses with internal isodensity fibrous septations on non-enhanced CT.On non-enhanced MRI,MFS commonly demonstrated iso-to hypointense signals on T1WI,markedly hyperintense signals on T2WI,low signal fibrous septa,high signals on diffusion weighted imaging(DWI),as well as tail signs and surrounding soft tissue edema.After administration of contrast agents,solid components of MFS demonstrated marked enhancement.No statistical difference of tumor vascularity was detected between groups(P=0.141,1-β=0.269).Poor prognosis group showed significantly higher rates of diffuse peritumoral edema and fascial tail signs than good prognosis group(both P＜0.05).Conclusion Imaging features of MFS had certain characteristics,and the tail sign and surrounding soft tissue edema were correlated with poor prognosis.

Lung cancer is one of the malignant tumours with the highest morbidity and mortality rates worldwide today, posing a major threat to human health. Accurate diagnosis and standardised treatment play a crucial role in improving the survival rate of lung cancer patients. In recent years, the rapid rise of artificial intelligence (AI) has brought about significant changes in the medical field, providing a new diagnostic and treatment model for lung cancer, and making a series of breakthroughs in lung cancer diagnostic imaging, pathological diagnosis, surgical oncology, radiotherapy, and drug development and treatment. This article introduces the current status of AI application in the field of lung cancer diagnosis and treatment, and extensively discusses the current challenges and future prospects, hoping to provide references and suggestions for future clinical practice.

Objective To explore imaging features of telangiectatic osteosarcoma(TOS).Methods X-ray,CT and MRI data of 37 cases of TOS confirmed by surgical pathology were retrospectively analyzed.Lesion's location,morphology,border,density/signal,enhancement pattern,presence of hemorrhage,tumor bone,fluid-fluid levels,periosteal reaction,septal nodules,epiphyseal involvement,bone destruction and surrounding sclerosis,peripheral edema and pathological fracture or not were recorded.The misdiagnosis rate of each imaging examination was calculated.Results TOS was prone to occur in the femur,humerus and tibia metaphysis,predominantly presented as eccentric,expansive and map-like osteolytic bone destruction with little or no surrounding sclerosis,showing polycystic changes,with fluid-fluid levels,hemorrhagic and tumor bone,along with periosteal reactions and marginal and septal nodule-like enhancement after enhanced scanning.The misdiagnosis rate of X-ray,non-contrast CT,enhanced CT,non-contrast MRI,enhanced MRI and preoperative biopsy for diagnosing TOS was 75.00%(24/32),50.00%(3/6),38.10%(8/21),50.00%(6/12),24.32%(9/37)and 24.32%(9/37),respectively.Conclusion TOS had certain characteristic imaging manifestations.Comprehensive imaging examinations combined with accurate pathological sampling contributed to precise diagnosis and reduction of misdiagnosis rate of TOS.

Objective To explore imaging characteristics of myxofibrosarcoma(MFS)and their correlations with prognosis.Methods Totally 32 patients with pathologically confirmed MFS were retrospectively enrolled and divided into poor prognosis(recurrence/metastasis)group(n=13)and good prognosis group(n=19).Preoperative imaging characteristics of lesions were analyzed and compared between groups,including the location,shape,size,margins,density/signal features of lesions,adjacent bone destruction,peritumoral edema,fascial tail sign,enhancement patterns and tumor vasculature.Results MFS predominantly involved the extremities,especially the lower limbs,and the lesions commonly appeared as iso-to hypodensity masses with internal isodensity fibrous septations on non-enhanced CT.On non-enhanced MRI,MFS commonly demonstrated iso-to hypointense signals on T1WI,markedly hyperintense signals on T2WI,low signal fibrous septa,high signals on diffusion weighted imaging(DWI),as well as tail signs and surrounding soft tissue edema.After administration of contrast agents,solid components of MFS demonstrated marked enhancement.No statistical difference of tumor vascularity was detected between groups(P=0.141,1-β=0.269).Poor prognosis group showed significantly higher rates of diffuse peritumoral edema and fascial tail signs than good prognosis group(both P＜0.05).Conclusion Imaging features of MFS had certain characteristics,and the tail sign and surrounding soft tissue edema were correlated with poor prognosis.

Objective:To investigate the genomic manifestation and pathogenesis of osteosarcoma with different relapse pattens, which were respectively initially presented with bone metastasis or pulmonary metastasis.Methods:From May 1, 2021 to October 1, 2021, 38 fresh tumor specimens and some paraffin-embedded specimens of high-grade osteosarcoma were collected in Peking University People's Hospital, including 29 males and 9 females, aged 19.6±2.2 years (range, 6-61 years). Among the 38 cases, 12 cases had initial bone metastasis (group A) and 26 cases had initial lung metastasis (group B), of which 15 cases (40%, 15/38) had paired specimens of primary and metastatic lesions. Based on Illumina NovaSeq 6000, we analyzed whole-exome sequencing (WES) as well as transcriptome for osteosarcoma with paired samples in different relapse patterns. During all their treatment courses, we also collected their paired samples to reveal these tumors' evolution. We sought to redefine disease subclassifications for osteosarcoma based on genetic alterations and correlate these genetic profiles with clinical treatment courses to elucidate potential evolving cladograms.Results:We found that osteosarcoma in group A mainly carried single-nucleotide variations (83%, 10/12), displaying higher tumor mutation burden [4.9 (2.8, 12.0) & 2.4 (1.4, 4.5), P=0.010] and neoantigen load [743.0 (316.5, 1,034.5) & 128.5 (49.0, 200.5), P=0.003], while those in group B mainly exhibit structural variants (58%, 15/26). The mutation spectrum showed that there was a significant difference in age-related gene imprinting 1 between the bone metastasis group and the lung metastasis group ( P=0.005). Samples were randomly selected from group A (3 patients) to investigate immunologic landscape by multiplex immunohistochemistry, from which we noticed tertiary lymphatic structure from one patient from group A. High conservation of reported genetic sequencing over time was found in their evolving cladograms. Conclusion:Osteosarcoma with mainly single-nucleotide variations other than structural variants might exhibit biological behavior predisposing toward bone metastases with older in age as well as better immunogenicity in tumor microenvironment.

Objective:To investigate the clinical manifestations, imaging features, histopathological features, diagnostic pitfalls, treatment and prognosis of clear cell chondrosarcoma (CCCS).Methods:23 cases of CCCS admitted and operated from January 2010 to January 2020 were analyzed retrospectively. Among the 23 cases, 21 were males and 2 were females. There were 8 cases (35%) aged 21-40, 10 cases (43%) aged 41-60 and 5 cases (23%) aged 61-80. There were 8 femurs, 7 pelvis, 4 thoracolumbar spine, 3 sacrum and 1 tibia. The specimens were fixed with 10% phosphate-buffered formalin, decalcified with 5% nitric acid, embedded in paraffin and stained with hematoxylin and eosin (HE) and immunohistochemistry (Envision). The preoperative imaging and clinical symptoms, and the postoperative histopathological and immunophenotype under the microscope were collected. And the relevant literature was reviewed to summarize the clinical, imaging and pathomorphological characteristics of CCCS.Results:23 cases of CCCS showed bone destruction in imaging, some cases were well-circumscribed lytic lesions, some cases had sclerotic margin. The serum alkaline phosphatase was increased in 7 patients before operation. The tumor tissue was gray-white and gray-red in general and some cases showed porcelain white cartilage-like areas. Microscopically, the tumor cells are round or polygonal, some of them have clear cytoplasm and boundary, some of them are eosinophilic, some of them have round and centrally located nuclei, and mitotic image is rare. It is often seen that there are nodular distribution of cartilage-like matrix and immature woven bone, multinucleated osteoclast-like giant cell scattered in those components. Immunohistochemical staining: S-100, D2-40, EMA, Vimentin, p16, SATB2 can be positive in varying degrees. The surgical treatment is mainly through en bloc excision. 10 patients had recurrence and no distant metastasis.Conclusion:CCCS is a rare subtype of chondrosarcoma, which has low-grade malignant biological behavior and is easy to be misdiagnosed clinically and pathologically. Pathological diagnosis needs to be careful. Careful observation of microscopic histology is necessary in order to avoid over-diagnosis of osteosarcoma leading to clinical treatment errors. Once the biopsy is confirmed, it needs en bloc excision in order to reduce the recurrence rate. Long-term follow-up is needed after the operation, the overall prognosis was good.

Although classic morphology is the cornerstone for the diagnosis of bone tumors, the rapidly developed molecular pathology based on Next Generation Sequencing (NGS) has evolved current diagnostic techniques. At the same time, new disease entities based on molecular abnormalities were constantly reported, which converted the morphological pathological classifications into molecular categories. At present, bone tumors could be roughly classified as tumors with simple karyotypes and those with complex karyotypes by molecular alterations. The previous classification can be subclassified as tumors that carry specific translocations, somatic gene mutations, or those with specific amplifications. However, the later groups usually lack specific alterations. The present review discusses various updates on molecular pathology in detail based on new categories of bone tumors proposed by World Health Organization (WHO) in 2019 aiming to further provide guidance for evidenced-based treatment. Some examples are included, such as giant cell tumor of bone (H3F3A p.G34W), chondroblastoma (H3F3B p.K36M), chondrosarcoma (IDH1/2 mutation), aneurysmal bone cyst (USP6 rearrangements) and so on. All mutual alterations play an increasingly important role in reaching a diagnosis and in patients management.