ABSTRACT
@#Objective To evaluate the effectiveness of the artificial intelligence-assisted diagnosis and treatment system in distinguishing benign and malignant lung nodules and the infiltration degree. Methods Clinical data of 87 patients with pulmonary nodules admitted to the First Affiliated Hospital of Xiamen University from January 2019 to August 2020 were retrospectively analyzed, including 33 males aged 55.1±10.4 years, and 54 females aged 54.5±14.1 years. A total of 90 nodules were included, which were divided into a malignant tumor group (n=80) and a benign lesion group (n=10), and the malignant tumor group was subdivided into an invasive adenocarcinoma group (n=60) and a non-invasive adenocarcinoma group (n=20). The malignant probability and doubling time of each group were compared and its ability to predict the benign and malignant nodules and the invasion degree was analyzed. Results Between the malignant tumor group and the benign lesion group, the malignant probability was significantly different, and the malignant probability could better distinguish malignant nodules and benign lesions (87.2%±9.1% vs. 28.8%±29.0%, P=0.000). The area under the curve (AUC) was 0.949. The maximum diameter of nodules in the benign lesion group was significantly longer than that in the malignant tumor group (1.270±0.481 cm vs. 0.990±0.361 cm, P=0.026); the doubling time of benign lesions was significantly longer than that of malignant nodules (1 083.600±258.180 d vs. 527.025±173.176 d, P=0.000), and the AUC was 0.975. The maximum diameter of the nodule in the invasive adenocarcinoma group was longer than that of the non-invasive adenocarcinoma group (1.350±0.355 cm vs. 0.863±0.271 cm, P=0.000), and there was no statistical difference in the probability of malignancy between the invasive adenocarcinoma group and the non-invasive adenocarcinoma group (89.7%±5.7% vs. 86.4%±9.9%, P=0.082). The AUC was 0.630. The doubling time of the invasive adenocarcinoma group was significantly shorter than that of the non-invasive adenocarcinoma group (392.200±138.050 d vs. 571.967±160.633 d, P=0.000), and the AUC was 0.829. Conclusion The malignant probability and doubling time of lung nodules calculated by the artificial intelligence-assisted diagnosis and treatment system can be used in the assessment of the preoperative benign and malignant lung nodules and the infiltration degree.
ABSTRACT
BACKGROUND@#It has been known that the volume doubling time (VDT) of different lung nodule types is different. At present, there is still a lack of studies about the volume doubling time of lung cancer with different pathological types. The purpose of the study is to explore the factors influencing the progression of the early-stage adenocarcinoma, and provide some reference for the follow-up strategy of lung nodules by retrospective analysis of the image data of 143 early-stage adenocarcinoma.@*METHODS@#143 cases of the early adenocarcinoma were classified according to the 2015 World Health Organization Classification of Lung Tumors and the Eighth edition of the tumor-node-metastasis (TNM) classification of lung cancer. The volume doubling time was calculated with reference to the revised Schwartz formula.@*RESULTS@#Among the 143 cases of the early adenocarcinoma, 50 cases (34.97%) were in progression. By multivarIate analysis, there were several factors associated with the progression of the early adenocarcinoma: the follow-up time, the dimension of nodule, the pathological type, the nodule type and the pathological stage. The VDT of lepidic predominant adenocarcinoma (LPA) is (594±272) d. The VDT of the invasive adenocarcinoma with lepidic part, but not predominant, is (520±285) d. The VDT of the invasive adenocarcinoma without lepidic part is (371±183) d.@*CONCLUSIONS@#About 35% of the early adenocarcinoma is in progress. Whether with the lepidic component is a positive factor to the speed of tumor progression.
Subject(s)
Female , Humans , Male , Middle Aged , Disease Progression , Lung Neoplasms , Diagnostic Imaging , Pathology , Retrospective Studies , Tomography, X-Ray ComputedABSTRACT
Objective To evaluate volume doubling time (VDT) and net mass doubling time of tumor (nMDT) of pulmonary pure ground glass nodules (PGGN) of different pathological types and to investigate whether VDT and nMDT can help to differentiate invasive pulmonary adenocarcinomas from minimally invasive adenocarcinomas and preinvasive lesions.Methods Fifty-one pathologically confirmed pGGNs in 46 patients were retrospectively evaluated,in whom at least two HRCT scans were obtained preoperatively (median scan times,3 times;range,2-6 times) with 1-month or longer follow-up interval (median follow-up interval,251 days;range,30-1 552 days).According to the rechecked results of the postoperative pathological section,51 pGGNs were divided into two groups:group A,invasive adenocarcinoma (IAC),30 pGGNs (58.8％);group B,21 pGGNs (41.2％),including 8 minimally invasive adenocarcinoma (MIA),7 adenocarcinomas in situ (AIS) and 6 atypical adenomatous hyperplasia (AAH).The volume,cumulative percentage of volume growth and VDTs of pGGNs were automatically acquired by Lung VCAR (advantage windows 4.6,GE HealthCare).Subsequently,the mass,cumulative percentage of mass growth and nMDTs of pGGNs were calculated.The count data and measurement data between two groups were compared using Fisher exact probability and Mann-Whitney U test,respectively.A pairwise comparision were performed by using Wilcoxon signed-rank test.Subsequently,the receiver operating characteristic (ROC) curve was used to determine the optimal cut-off values of VDT and nMDT for the differential diagnosis of IAC and MIA/AIS/AAH,and calculated the area under the curve (AUC).Results The median VDT and nMDT of 51 pGGNs were 1 854.11 days (range,165.22—+∞ days) and 1 138.45 days (range,95.92—+ ∞ days),respectively.The median nMDT was shorter than the median VDT,and the difference was significant (Z=-2.444,P=-0.O15).The median VDTs of IAC and MIA/AIS/AAH were 847.07 days (165.22—+∞ days) and 4 460.09 days (691.14—+∞ days),respectively.The median nMDTs of IAC,MIA/AIS/AAH were 769.93 days (95.92—+∞ days) and 3814.77 days (611.56—+∞ days),respectively.The median VDT and nMDT of IAC were significantly shorter than those of MIA/AIS/AAH (Z=-3.443,-3.860,P＜ 0.01,respectively).Differentiating IAC from MIA/AIS/AAH,the optimal cutoff value of VDT was 2095.86 days (sensitivity,71.4％;specificity,80.0％),the optimal cutoff value of nMDT was 1 169.77 days (sensitivity,81.0％;specificity,76.7％).Conclusions In pulmonary pGGNs,IAC showed significantly shorter VDT and nMDT than MIA/AIS/AAH.When VDT is shorter than 2 095.86 days or nMDT is shorter than 1 169.77 days,IAC is suggested.
ABSTRACT
Objective To measure volume of breast cancer , calculate tumor volume doubling time (TVDT), and analyze the correlated factors affecting TVDT using three-dimensional ultrasound (3D-US). Methods We applied 3D-US to measure the volume of breast cancer of BI-RADS-US 4A classified by conventional ultrasound. The breast cancer case scanned by 3D-US at least twice (the interval is 3 months at least) without any medical intervention were included in the study. We calculated TVDT according to the formula, and analyzed the affecting factors of TVDT using multiple linear regression. Results Sixty-nine cases were enrolled in the study. The TVDT of breast cancer were from 66 to 521 days , in an average of 185 ± 126 days and the median time of 164 days. We found that: ① there were no statistics significances in TVDT between different breast cancer pattern , smoothing border lines , speculated sign , hyperechoic halo , microcalcification and different rear echo (P > 0.05). ② TVDT of different age groups, lymph node metastasis, pathological grade and NPI score were significantly different (P 0.05). ③ TVDT of patients with different expression of ER, PR and Ki-67, molecular typing showed statistically difference (P 0.05). ④ multi-factor analysis showed that the NPI score, lymph node metastasis, Ki-67 and molecular typing of breast cancer were relative factors in TVDT (P < 0.05). Conclusions The NPI score , lymph node metastasis , Ki-67 and molecular typing significantly correlate with TVDT of breast cancer. Triple-negative breast cancer in molecular typing has the fastest growth rate.