Breast cancer is a highly heterogeneous malignancy, and molecular functional imaging techniques such as positron emission tomography (PET) and single-photon emission computed tomography (SPECT) play a critical role in its accurate diagnosis. While imaging provides a crucial foundation for precise breast cancer diagnosis, the most used imaging agent, 18 F-FDG, presents certain limitations in this context. Consequently, there has been an increased focus on the research and development of novel radiolabeled probes for both in situ imaging of primary tumors and the detection of distant metastases. This paper reviewed the recent advancements in radiolabeled probes for breast cancer diagnosis and treatment, with an emphasis on novel targets that exploit specific surface markers on tumor cells and elements of the tumor microenvironment and categorized their practical applications in clinical settings.
Hypoxia, a common status of most solid tumors, is associated with tumor progression, metastasis, radiotherapy and chemotherapy resistance. Positron emission tomography (PET) and single-photon emission computed tomography (SPECT) using hypoxic-targeting radiopharmaceuticals have been applied to non-invasive monitoring of tumor hypoxia. Nitroimidazole, which could be selectively trapped within hypoxia cells, has become an important pharmacophore for targeting hypoxia. Recently, hypoxic-targeting radiopharmaceuticals containing nitroimidazole have been developed for detecting tumor hypoxia. In this review, the progress of hypoxic-targeting radiopharmaceuticals containing nitroimidazole in recent ten years was introduced and the future development direction was also prospected.
Objective: To construct a positron emission tomography (PET) probe, 68 Ga-NOTA-376, targeting CLDN18.2 using a non-site-specific labeling method, and to evaluate its in vitro and in vivo properties. Methods: The chelating agent p-SCN-Bn-NOTA was used to non-site-specifically conjugate the nanobody 376 targeting CLDN18.2, resulting in the precursor NOTA-376, which was then radiolabeled with 68 Ga. The labeling efficiency, radiochemical purity, and in vitro stability of the probe were determined by radio- thin layer chromatography (Radio-TLC), and micro-PET/ computed tomography (CT) imaging experiments were conducted in a nude mouse model of human gastric adenocarcinoma. Results: 68 Ga-NOTA-376 demonstrated a high labeling yield (89.98±0.07) %, high radiochemical purity (97.67±0.02)% and high specific activity (16.69±6.60) GBq/μmol, and remained stable in 5% human serum albumin (HSA) and phosphate-buffered saline (PBS). Micro-PET/CT results indicated that the maximum standardized uptake value (SUV max ) of the probe in CLDN18.2-positive tumors was significantly higher than in CLDN18.2-negative tumors. At 4.0 h, the SUV max of CLDN18.2- positive tumors and CLDN18.2-negative tumors were 9.08±0.33 and 1.92±0.32, respectively. Conclusion: This study successfully constructed a CLDN18.2-targeting probe 68 Ga-NOTA-376 using a non-site-specific labeling method, which showed high labeling efficiency, good stability, and targeting capability, making it a potential PET probe for the detection of CLDN18.2 protein expression levels.
Objective: To appropriately extend the in vivo circulation time of ginsenoside-like prostate-specific membrane antigen (PSMA) targeting probes and develop a novel 68 Ga-labeled diagnostic probe for prostate cancer. Methods: The ligand P214 (using p-SCN-Bn-DOTA as a bifunctional chelator) was synthesized using solid-phase synthesis, and its affinity was measured. The ligand was added to a buffer containing 68 Ga 3+ ions, reacted at 95 ℃ for 5 min, and then purified. The radiochemical purity was determined using radioactive thin-layer chromatography. The in vitro stability, lipophilicity and human serum protein binding rate of 68 Ga-P214 were evaluated, followed by cell uptake experiments. 68 Ga-P214 was injected into 22Rv1 tumor-bearing mice, and micro-positron emission tomography (PET)/computed tomography (CT) imaging was performed at specific time points, with comparative imaging using 68 Ga-P137. Mice were sacrificed at 30, 60 and 120 min post-injection via tail vein, and organs of interest were weighed, counted, and the percentage of injected dose per gram of tissue (%ID/g) was calculated. Results: The target ligand P214 was successfully synthesized with a K i value of 0.085 nmol/L, and the radiochemical purity exceeded 95%. The labeled product 68 Ga-P214 remained stable in saline and 37 ℃ mouse serum for 2 h. The lipophilicity (partition coefficient) of 68 Ga-P214 was -3.17±0.09, and the human serum albumin binding rate was (88.86±0.51)%, significantly higher than that of 68 Ga-P137 (74.01±1.17)%. Cell experiments demonstrated that 68 Ga-P214 was effectively taken up by PSMA+cells (22Rv1), with uptake rates of (0.39±0.14), (0.55±0.09), and (0.54±0.12) %ID/10 5 cells at 30, 60, and 120 min of incubation, respectively, which could be inhibited by the PSMA inhibitor ZJ43. At 60 min post-injection, 68 Ga-P214 had a higher maximum standard uptake value (SUV max ) in the tumor region (1.40±0.11 vs 0.80±0.04), which increased over time. Biodistribution in tumor-bearing mice showed that 68 Ga-P214 had significantly higher uptake in tumors compared to 68 Ga-P137 [(44.15±6.25)%ID/g vs (19.76±3.56)%ID/g at 120 min post-injection], with superior tumor/muscle, tumor/blood, and tumor/liver ratios (127.63, 33.87, and 12.68, respectively). Conclusion: 68 Ga-P214 exhibits ideal biodistribution, appropriately extends the in vivo circulation time of ginsenoside-like probes, and significantly increases uptake in PSMA-positive tumors, making it a promising candidate for prostate cancer diagnosis with considerable potential to be developed into a therapeutic probe.
Objective: To evaluate the potential of 68 Ga-PSMA-4PY, a prostate cancer imaging agent characterized by rapid clearance from the body, for clinical application. Methods: The precursor was kit-labeled with 68 Ga-PSMA-4PY, and quality control measures ensured its purity and safety. Dynamic positron emission tomography (PET) imaging was used to study the radiotracer uptake and clearance dynamics of 68 Ga-PSMA-4PY in the blood, liver, and kidneys of mice. Clinical imaging studies compared the distribution characteristics of 68 Ga-PSMA-4PY with those of 68 Ga-PSMA-11 in prostate cancer patients. Results: The kit-labeled 68 Ga-PSMA-4PY exhibited good labeling efficiency and stability. Dynamic PET imaging in mice revealed that the clearance profile of 68 Ga-PSMA-4PY in the blood was comparable to that of 68 Ga-PSMA-11. The renal radiotracer uptake of 68 Ga-PSMA-4PY peaked within 2 min and was rapidly cleared, whereas 68 Ga-PSMA-11 uptake in the kidneys increased continuously, reaching 11 times higher than that of 68 Ga-PSMA-4PY at 60 min. Clinical studies demonstrated that 68 Ga-PSMA-4PY accumulated in prostate cancer lesions, with significantly lower radiotracer retention in the liver, kidneys, and spleen compared to 68 Ga-PSMA-11, and a reduction of 57.5% in salivary gland uptake. Conclusion:68 Ga-PSMA-4PY can rapidly accumulate in PSMA-positive tumors and clear quickly from normal tissues, which will help reduce nonspecific uptake and associated side effects, making it a promising prostate cancer imaging agent.
Objective: To explore the influence of different acquisition time, injection dose and reconstruction algorithm on the image quality of 64 Cu-FAPI-XT positron emission tomography (PET)/computed tomography (CT), so as to provide empirical basis and reference for clinical practice. Methods: Eleven cancer patients from The First Affiliated Hospital of Guangzhou Medical University from June to September, 2023 were retrospectively selected. Six patients were injected with high dose (2.22- 3.22 Mbq/kg) of 64 Cu-FAPI-XT, while other five patients were injected with low dose (1.59-2.18 Mbq/kg) of 64 Cu-FAPI-XT. Ordered subset expectation maximization (OSEM) and HYPER Iterative algorithms were used to reconstruct the 3.0 min/bed image respectively to simulate the image acquisition at 1.0 min/bed, 1.5 min/bed, 2.0 min/bed, 2.5 min/bed and 3.0 min/bed. Two doctors scored all the images subjectively and compared the image quality, noise level and diagnostic value of different groups of images. Mean standard uptake value (SUV mean ), standard deviation (SD) and signal-to-noise ratio (SNR) of blood pools in liver and mediastinum were measured for semi-quantitative analysis. Results: Subjective evaluation: in the high-dose group (2.22-3.22 MBq/kg), the images of 2.0 min/bed were reconstructed respectively by HYPER Iterative and OSEM, the image quality of which met the requirements of daily diagnosis (the scores were all ≥3 points). In the low-dose group (1.59-2.18 MBq/kg), the image quality of 2.0 min/bed reconstructed by HYPER Iterative and 2.5 min/bed reconstructed by OSEM reached the requirements of daily diagnosis (scores≥3). Objective semi-quantitative analysis: at the same acquisition time, injecting different doses of 64 Cu-FAPI-XT to scan PET images, the image quality of HYPER Iterative reconstruction was significantly better than that of OSEM reconstruction (P<0.05). In the high dose group (2.22-3.22 MBq/kg), the image quality of 1.5 min/bed was obviously better than that of 1.0 min/bed (P<0.05), but there was no statistical difference between 1.5 min/bed image and 2.5 min/bed image (P>0.05). There was no statistical difference in image quality between low dose recombinant (1.59-2.18 Mbq/kg) for 2.0 min/bed and 3.0 min/bed (P>0.05). Conclusion: The PET/CT images of UMI Panorama were reconstructed by HYPER Iterative method, and high dose (2.22-3.22 Mbq/kg) of 64 Cu-FAPI-XT was injected, and the quality of PET images collected for 1.5 min/ bed met the requirements of daily diagnosis. Low dose (1.59-2.18 Mbq/kg) of 64 Cu-FAPI-XT was injected and collected for 2.0 min/bed, which can meet the daily diagnosis requirements.
Objective: To explore and analyze the current situation of quality control of radioactive 125 I seeds implantation technology in Shanghai. Methods: According to the evaluation sheet of 125 I seeds implantation technology established by Shanghai Nuclear Medicine Quality Control Center, the data of 20 departments from 16 medical institutions was analyzed. Results: Among the 36 quality control contents evaluated for the basic requirements of medical institutions, personnel, and technical management, the highest compliance rate was 100.0% (36/36), and the lowest compliance rate was 83.33% (30/36), the management and quality situation of different departments in the same hospital also varies. For various indicators related to quality control, the average accuracy rate of implantation indications was 98.75%, the average preoperative treatment plan formulation rate was 94.74%, the average particle activity retest rate was 25.13%, the postoperative radiation dose verification average rate was 83.81%, the average incidence rate of major complications related to puncture within 30 d was 5.67%, the average incidence rate of major complications related to radiation injury within 30 d was 0.85%, and the average effective rate of particle implantation treatment was 92.2%, The all-cause mortality average rate within 30 days was 0.87%. The average follow-up rates for 2 months, 4 months, 6 months, and 1 year were 97.24%, 91.9%, 85.31%, and 71.91%, respectively. The average survival rates for 2 months, 4 months, 6 months, and 1 year were 96.81%, 89.74%, 81.31%, and 66.07%, respectively. Conclusion: In 2022, there were many problems in the quality control of 125 I particle implantation therapy technology in all medical centers in Shanghai. All medical centers should pay attention to it. According to the requirements of the 125 I particle implantation therapy technology evaluation form of nuclear medicine quality control center, medical centers should improve the department rules and regulations, and carry out the technology in full accordance with the diagnostic and therapeutic specifications.
Objective: To evaluate the relationship between International Association for the Study of Lung Cancer (IASLC) classification system and traditional computed tomography (CT) imaging features, and to construct a hierarchical prognosis model based on CT imaging features. Methods: The study retrospectively analyzed the medical records of 102 consecutive patients with primary pathological (p) stage I (T1N0M0 or T2aN0M0) LUAD in Nanjing Chest Hospital from January 2019 to May 2022. According to the 2020 IASLC grading system, patients were classified and the clinical pathological and imaging features were compared between different IASLC histological grades, as well as between recurrent and non recurrent groups. Logistic regression analysis was used to determine CT signs related to IASLC grading, and to determine influencing factors for disease-free survival (DFS) of patients through a multivariate Cox regression model. Results: A total of 102 patients with LUAD were divided into grade 1 (15 cases, 14.7%), grade 2 (63 cases, 61.8%) and grade 3 (24 cases, 23.5%). During the 30.4 months follow-up, 16 patients (15.7%) relapsed. Higher CTR (OR=2.152, 95% CI 1.530-3.264, P=0.005) and higher CT value (OR=3.730, 95% CI 2.841-6.353, P=0.001) were independent risks of higher histological grade. The AUC value for conjoining the above two independent factors to predict grade 3 was 0.912 (95% CI 0.877-0.937, P<0.001), and it was not significantly different from the AUC for using the mean CT value or CTR alone. Multivariate Cox regression analysis showed age (HR=1.05, 95% CI 1.02-1.09, P=0.003), CTR (HR=2.81, 95% CI 1.16-6.77, P=0.022), CT value (HR=2.49, 95% CI 2.30-15.43, P<0.001) and histological grade (HR=4.31, 95% CI 2.28-8.14, P<0.001) were independent risk factors for DFS. Conclusion: Larger CTR and higher average CT value are independent predictors of higher IASLC histological grade. CTR (truncation values<0.25 and ≥0.75) and average CT values (truncation values<-410 HU and ≥-210 HU) can be used as preoperative substitutes for IASLC grading system.
Objective: To quantitatively detect fatty acid composition of various adipose tissue depots using chemical shift- encoded magnetic resonance imaging (CSE-MRI) in patients with rectal cancer, and to explore the application value in evaluating fatty acid effects on rectal carcinogenesis and progression. Methods: Patients with surgically pathologically confirmed rectal adenocarcinoma underwent preoperative routine MRI and multi-echo gradient-echo CSE-MRI in Huadong Hospital, Fudan University from October 2021 to December 2022. The saturated fatty acid (fSFA), monounsaturated fatty acid (fMUFA) and polyunsaturated fatty acid (fPUFA) fractions of adipose tissue from rectal mesentery, ileal mesentery, and gluteal subcutaneous area were detected. Twenty age- and sex-matched controls with non-rectal cancer were enrolled at the same time. Changes in fatty acid fractions of adipose tissue at various sites were analyzed between the rectal cancer group and the control group as well as among rectal cancer patients to evaluate the role of fatty acids in tumorigenesis; changes in fatty acid fractions of adipose tissue at various sites were analyzed between the lymph vascular invasion (LVI) and peripheral nerve invasion (PNI) positive and the negative rectal cancer groups to evaluate the effect of fatty acids on tumor aggressiveness. Interobserver agreement of fatty acid fraction parameter measurements was assessed by intra-group correlation coefficient (ICC). Differences between two groups were analyzed by independent samples t-test or Mann-Whitney U-test; differences between multiple groups were analyzed by one-way ANOVA (One- Way ANOVA) or Kruskal-Wallis H (K) test. Results: A total of 56 patients with rectal adenocarcinoma were included, including 36 males and 20 females, with a mean age of (65.1±10.1) years. There were 11 (19.6%) rectal adenocarcinomas with LVI and 10 (17.9%) patients with PNI; and 20 cases in the control group, including 12 males and 8 females, with a mean age of (66.3±8.8) years. Measurements of each fatty acid fraction at each site correlated well between observers, with ICC>0.60. The SFA fraction of rectal mesenteric adipose tissue was higher in the rectal cancer group than in the control group (37.2±4.2 vs 35.0±2.7, P=0.035); The fMUFA (37.5±2.4, 37.3±8.1 and 40.6±8.7, respectively, P=0.003) and fPUFA (24.9±4.1, 26.3±4.9 and 21.5±4.7, respectively, P<0.001) of adipose tissue from rectal mesentery, ileal mesentery, and gluteal subcutaneous area in patients with rectal cancer were statistically significant. The fMUFA of rectal mesenteric adipose tissue was higher in the LVI (+) rectal cancer than in the LVI (-) group (38.8±1.5 vs 37.1 ± 2.5, P=0.035); none of the differences in the fractions of each fatty acid in adipose tissue of each site were statistically significant between the PNI (+)/(-) rectal cancer groups (P>0.05). Conclusion: ① Differences were found between the SFA fractions of rectal mesenteric fat in rectal cancer patients and normal controls; ② Differences were found between the fMUFA and fPUFA of rectal mesenteric and mesenteric fat of rectal cancer and subcutaneous adipose tissues; ③ Associations were found between the fMUFA of rectal mesenteric fat of rectal cancer and LVI.
Objective: To explore the potential clinical value of spectral detector computed tomography (SDCT) iodine quantification in assessing the split renal function impairment in patients with renal tumor. Methods: This retrospective study included 50 patients with renal tumors who underwent both multiphasic enhanced renal SDCT and renal dynamic imaging within two weeks. SDCT scans were performed using a normal enhanced abdominal protocol. Renal volumes (V), mean CT number (HU), and mean iodine concentration (IC) were delineated manually. The cumulative amount of iodine contrast media (K) was the product of IC and V. Clearance of single kidney was calculated using a simplified “two-point Patlak plot”. The patients’ kidneys were divided into two groups according to 99m Tc-diethylene triamine pentaacetic acid ( 99m Tc-DTPA) Gates glomerular filtration rate (Gates GFR): normal (Gates GFR≥40 mL/min), and impaired (Gates GFR<40 mL/min) group. SDCT parameters were compared between groups using Kruskal-Wallis H test. Correlation between SDCT parameters and Gates GFR was analyzed using Spearman’s coefficient. Receiver operating characteristic (ROC) curve analysis was performed to determine optimal diagnostic threshold for clearance of single kidney to distinguish between normal and impaired renal function. Results: The V, mean HU of arterial phase-HU(t1), mean HU of parenchymal phase-HU (t2), mean IC of arterial phase-IC (t1), mean IC of parenchymal phase-IC (t2), K of arterial phase-K (t1), K of parenchymal phase-K (t2) and the clearance of single kidney between the groups were statistically significant (Z/t=-4.459, 2.815, -3.313, 2.611, -3.609, -4.395, -5.637, -5.815; P<0.05);and those parameters were related to Gates GFR (r=0.489, 0.339, 0.481, 0.361, 0.531, 0.590, 0.724, 0.740; P<0.001). The cutoff value of clearance in distinguishing normal from impaired renal function was 543 mg. Conclusion: All parameters of SDCT could reflect split renal function, among which the clearance had the highest correlation with Gates GFR and could be used in diagnosis of impaired split renal function, which was meaningful in clinical work.
Objective: To utilize the advantages of digital breast tomosynthesis (DBT) in assessing lesion margins and to explore the relationship between the burr sign of DBT images and Ki-67 proliferation index. Methods: DBT imaging data of 99 patients with invasive breast cancer who in the First Affiliated Hospital of Zhengzhou University from March 2022 to April 2023 were retrospectively included, and all of the patients showed a burr-type mass in DBT images. Lump size, length and width of the burr, coverage of the burr at the tumor margin, and number of burrs were analyzed in 99 cases of breast burr-type lumps, and general clinical data of the patients were collected to compare the differences of each parameter between the Ki-67 proliferation index expression states. Independent predictors of Ki-67 proliferation index were analyzed using multifactorial logistic regression, and the diagnostic efficacy was evaluated using subject working curves. Results: The differences in DBT image burr characteristics including burr length and burr width were statistically significant when comparing Ki-67 proliferation index high patients and low patients (P<0.05), whereas the differences in the number of burrs, age of patients, menopausal status, and size of the mass were not statistically significant (P=0.060, P=0.175, P=0.507, and P=0.050, respectively). Multifactorial logistic regression model analysis showed that burr length (OR=0.036, P<0.001) and burr width (OR=8.829, P<0.001) were independent predictors of Ki-67 proliferation index. The best diagnostic efficacy was achieved when combining burr length with burr width, with an AUC of 0.897. Conclusion: Burr sign analysis in DBT images of breast cancer can be used as a noninvasive predictor of the proliferative activity of malignant tumors to determine patient prognosis.
Objective: To analyze the clinical characteristics and ultrasonic manifestations of breast mucinous carcinoma and explore the diagnostic value of conventional ultrasound combined with ultrasonic elastography in breast mucinous carcinoma. Methods: The retrospective study analyzed 63 patients (63 masses) with mucinous breast carcinoma confirmed by pathological examination in Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School from 2014 to 2022. 50 patients (50 masses) with fibroadenoma confirmed by pathological examination during the same period were randomly selected as the control group. All 113 masses underwent conventional breast ultrasonography and strain elastography to observe and record the mass size, shape, boundary, elasticity score, etc. The masses were also classified according to the Breast Imaging Reporting and Data System (BI-RADS) classification criteria. Among them, 78 masses were quantitatively analyzed using shear wave elastography. The clinical and ultrasonic characteristics of the two groups were compared. Results: The sensitivity (85.71% vs 65.07%), specificity (94.00% vs 88.00%), positive predictive value (94.73% vs 87.23%), negative predictive value (83.93% vs 66.67%) and accuracy (89.38% vs 75.22%) of conventional ultrasound combined with strain elastography were higher than those of conventional ultrasound alone. The diagnostic consistency Kappa index of conventional ultrasonography combined with strain elastography was higher than that of conventional ultrasound (0.787 vs 0.514). Shear wave elastography showed that the maximum, minimum, and average shear wave velocities of the two groups were (7.26±2.41) m/s vs (3.77±1.79) m/s , (3.16±1.09) m/s vs (2.23±0.79) m/s, (4.82±1.39) m/s vs (2.91±1.02) m/s, respectively, with statistically significant differences (P<0.05). Conclusion: Conventional ultrasound combined with elastography has certain clinical value in the diagnosis of mucinous breast carcinoma.
Objective: To explore the application value of contrast-enhanced ultrasound (CEUS) in adjusting the Ovarian- Adnexal Reporting and Data System (O-RADS) grading for ovarian adnexal masses. Methods: A total of 98 patients in Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine with ovarian adnexal masses who underwent two-dimensional ultrasound and CEUS examinations were selected as the study subjects. The two-dimensional ultrasound images were evaluated through O-RADS and CEUS perfusion characteristics were analyzed. With pathological diagnosis as the gold standard, the receiver operating characteristic (ROC) curve was drew, and the diagnostic efficacy of O-RADS and O-RADS+CEUS in ovarian accessory malignant tumors were analyzed. Results: The pathological results showed 25 cases of malignant masses and 73 cases of benign masses. The proportion of malignant masses with cyst wall/septal thickness ≥3 cm, solid components, papillary protrusions≥4, blood flow score 3-4, and ascites were 68.00%, 80.00%, 24.00%, 60.00%, and 60.00%, respectively, which were significantly higher than those of benign masses with 8.22%, 27.40%, 5.48%, 4.11%, and 5.48%, all P<0.05. In terms of CEUS signs, benign masses mainly exhibit uniform enhancement of no/low/equal, and slow/synchronous enhancement; Malignant masses are mainly characterized by uneven high enhancement and rapid enhancement. The ROC curve showed that the area under curve (AUC) value of O-RADS+CEUS in diagnosing ovarian adnexal malignant masses was higher than that of O-RADS (0.972 vs 0.860, P<0.05). Compared with O-RADS, O-RADS+CEUS has significantly higher sensitivity, specificity, positive predictive value, negative predictive value, and accuracy in diagnosing ovarian adnexal malignant masses, and they were 95.03%, 96.78%, 92.02%, 96.84%, and 96.17% respectively (P<0.05). Two ultrasound physicians had high consistency in evaluating the O-RADS classification results of grayscale ultrasound and grayscale ultrasound+CEUS (Kappa=0.885, 0.871). Conclusion: Ultrasound O-RADS classification can accurately determine the risk stratification of ovarian adnexal masses. The addition of CEUS can adjust the O-RADS grading, further improving the accuracy of diagnosis.
Objective: To evaluate the performance of a deep learning model based on the Kupffer phase of perflubutane microspheres for injection (product name Sonazoid) contrast-enhanced ultrasound in predicting microvascular invasion (MVI) of hepatocellular carcinoma (HCC), comparing it with radiomics model and clinical model. Methods: This study retrospective included 146 patients with primary HCC who underwent Sonazoid contrast-enhanced ultrasound examination in The First Affiliated Hospital of Guangxi Medical University from July 2020 to September 2022, randomly divided into a training set of 102 and a validation set of 44 in a 7∶3 ratios. Based on the region of interest in tumors, ResNet101 model was used to extract deep learning features through transfer learning, and PyRadiomics was utilized to extract radiomics features. Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) algorithm were employed to reduce features dimension. LASSO regression was used to construct both the deep learning model and radiomics model, a clinical model was also built based on clinical features. The diagnostic performance of models was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. DeLong testing algorithm was used to compare the diagnostic performance between models. Results: In the training set, the AUC (95% CI) for the deep learning model, radiomics model, clinical model was 0.931 (0.880-0.981), 0.823 (0.744-0.903) and 0.719 (0.614-0.824), respectively. In the validation set, the
AUC (95% CI) for the deep learning model, radiomics model, clinical model was 0.895 (0.757-1.000), 0.711 (0.514-0.909) and 0.606 (0.390-0.822), respectively. DeLong testing indicated that in both the training and validation sets, the diagnostic performance of the deep learning model was superior to that of the radiomics model and clinical model (P<0.05). Both univariate and multivariate logistic regression analyses showed that AFP (P<0.05) and Barcelona Clinic Liver Cancer staging (P<0.001) could be used as independent predictors of MVI in HCC patients. Conclusion: The deep learning model based on the Kupffer phase of Sonazoid contrast-enhanced ultrasound demonstrates excellent performance in predicting MVI in HCC patients. It has the potential to become a non-invasive imaging biomarker for predicting MVI.
In recent years, China has made significant progress in the field of liver ultrasound research, providing more accurate and reliable means for clinical diagnosis and treatment. Reviewing the clinical research on liver ultrasound in China in 2023, the hotspots in clinical research on diffuse liver diseases are mainly the quantitative assessment of fatty liver and the diagnosis of liver fibrosis with new ultrasound technologies. The clinical research on focal liver diseases focuses on the precise diagnosis of liver tumors and the related applications of artificial intelligence technology. In the field of diagnosis and treatment of liver disease with minimally invasive interventional ultrasound, it covers the optimization of ablation treatment strategies in liver tumors, the risk assessment of post-ablation complications, and prognosis evaluation, etc. The achievements in the field of liver guidelines and consensus in 2023 will also be introduced in this article.
In recent years, artificial intelligence (AI) technology has experienced a rapid development in the field of medical imaging, with increasing applications in bone tumor imaging. These applications encompass tasks such as tumor segmentation, classification, chemotherapy efficacy evaluation, and prognostic prediction. These advancements facilitate the development of related computer-aided diagnostic tools, which assist in reducing misdiagnoses and unnecessary biopsies. Furthermore, they can guide the formulation of clinical decisions and personalized treatment strategies, thereby advancing the process of precise treatment for bone tumors. Multiple studies have established the superiority of AI technology. With the gradual expansion of sample sizes and continuous refinement of models, AI models are expected to gradually be integrated into clinical practice and emerge as essential tools in the diagnosis and treatment of bone tumors, aiding precision medicine.
Responsible Institution: Fudan University Sponsored by: Fudan University Shanghai Cancer Center Edited by: Editorial Board of Oncoradiology Editors-in-Chief:
CHANG Cai
PENG Weijun
FAN Wei Editorial Director: NI Ming Published by: Editorial Office of Oncoradiology Address: 270 Dong’an Road, Shanghai 200032, China Tel: (021)64188274 Website: www.zhongliuyingxiangxue.com E-mail:
zlyxx@zhongliuyingxiangxue.com CSSN:ISSN 2096-6210
CN 31-2087/R