Automated marine oil spill detection algorithm based on single-image generative adversarial network and YOLO-v8 under small samples.

As marine resources and transportation develop, oil spill incidents are increasing, endangering marine ecosystems and human lives. Rapidly and accurately identifying marine oil spill is of utmost importance in protecting marine ecosystems. Marine oil spill detection methods based on deep learning and computer vision have the great potential significantly enhance detection efficiency and accuracy, but their performance is often limited by the scarcity of real oil spill samples, posing a challenging to train a precise detection model. This study introduces a detection method specifically designed for scenarios with limited sample sizes. First, the small sample dataset of marine oil spill taken by Landsat-8 satellite is used as the training set. Then, a single image generative adversarial network (SinGAN) capable of training with a single oil spill image is constructed for expanding the dataset, generating diverse marine oil spill samples with different shapes. Second, a YOLO-v8 model is pretrained via the method of transfer learning and then trained with dataset before and after augmentation separately for real-time and efficient oil spill detection. Experimental results have demonstrated that the YOLO-v8 model, trained on an expanded dataset, exhibits notable enhancements in recall, precision, and average precision, with improvements of 12.3 %, 6.3 %, and 11.3 % respectively, compared to the unexpanded dataset. It reveals that our marine oil spill detection model based on YOLO-v8 exhibits leading or comparable performance in terms of recall, precision, and AP metrics. The data augmentation technique based on SinGAN contributes to the performance of other popular object detection algorithms as well.

Effect of 10.6-µm CO2 laser moxibustion on the fastest 15-m walking time in patients with knee osteoarthritis: a double-blind, sham-controlled, multi-site randomized trial.

BACKGROUND: In this study, we investigated the impact of 10.6-µm CO2 laser moxibustion (LM) on the fastest 15-m walking time in individuals suffering from knee osteoarthritis (KOA). METHODS: A total of 392 individuals diagnosed with KOA and meeting the specified eligibility criteria were assigned randomly into two groups: the LM treatment group and the sham LM control group (ratio 1:1). Both groups received either LM therapy or simulated LM therapy to address the affected area of the knee joint. This treatment was administered three times a week for a duration of 4 weeks. RESULTS: In the LM group, the fastest 15-m walking times at both Week 4 and Week 12 were significantly reduced compared to the times before treatment (all P < 0.05). However, in the sham LM group, there were no notable differences in the fastest 15-m walking times after treatment (all P > 0.05). Moreover, the LM group exhibited shorter 15-m walking times than the sham LM group at both Week 4 and Week 12 (all P < 0.05). CONCLUSION: The use of CO2 LM can lead to a substantial enhancement in the fastest 15-m walking time of individuals suffering from KOA, and its therapeutic impact can last for a minimum of 8 weeks post-treatment. The fastest 15-m walking time serves as an indicator of alterations in the walking capacity of patients with KOA.

Comparison of 10.6 µm Laser Moxibustion with Traditional Moxibustion in Knee Osteoarthritic Therapy: A Randomized Noninferiority Clinical Trial.

Objective: To investigate the noninferiority of 10.6 µm laser moxibustion (LM) to traditional moxibustion (TM) in knee osteoarthritis (KOA). Methods: Ninety-two patients were recruited and randomly placed into one of two groups: 10.6 µm LM or TM in a 1:1 ratio. Each patient received 12 sessions of LM or TM, focusing on the ST-35 and Ashi acupoint. The sessions took place over 4 weeks, three times a week, and were followed up over 8 weeks. The endpoint outcomes were separated into two categories, primary and secondary. The primary endpoint was assessed at the end of the 4-week treatment, using the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) pain score. The secondary endpoint was evaluated at the end of the trial and consisted of the WOMAC function and stiffness score, visual analog pain [visual analog scale (VAS)] score, and 15-m walking time test. In addition, safety evaluation was performed throughout the trial. Results: Among the 92 randomized participants, 86 (93.48%) completed the trial; 43 in each group. The WOMAC pain score improved dramatically between the LM and TM groups, with a mean difference of 20.61 [95% confidence interval (CI): -2.28 to 43.50]. Given that the lower boundary of 95% CI was greater than -18.49, noninferiority was established. In addition, both LM and TM significantly decreased the WOMAC (pain, function and stiffness) score, VAS score (p < 0.05), and the 15-m walking time at the end of the trial. Interestingly, there were not significant differences between LM and TM (p > 0.05), suggesting that both are equally effective in treating KOA. Finally, among the 92 patients, 17 (18.48%) adverse effects were documented, namely 5 (10.87%) in the LM-treated group and 11 (26.09%) in the TM-treated group. Conclusions: 10.6 µm LM is not inferior to TM in treating KOA. Moreover, both LM and TM dramatically alleviated knee pain and enhanced function of knees. Clinical Trial Registration number: ISRCTN registry trial identifier: 14604492.

Feasibility and potential benefits of defining the internal gross tumor volume of hepatocellular carcinoma using contrast-enhanced 4D CT images obtained by deformable registration.

OBJECTIVE: To study the feasibility and the potential benefits of defining the internal gross tumor volume (IGTV) of hepatocellular carcinoma (HCC) using contrast-enhanced 4D CT images obtained by combining arterial-phase (AP) contrast-enhanced (CE) 3D CT and non-contrast-enhanced (NCE) 4D CT images using deformable registration (DR). METHODS: Ten HCC patients who had received radiotherapy beforehand were selected for this study. The following CT simulation images were acquired sequentially: NCE 4D CT in free breathing, NCE 3D CT and APCE 3D CT in end-expiration breath holding. All 4D CT images were sorted into ten phases according to breath cycle (CT00 ~ CT90). Gross tumor volumes (GTVs) were contoured on all CT images and the IGTV-1 was obtained by merging the GTVs in each phase of 4D CT images. The GTV on the APCE 3D CT image was deformably registered to each 4D CT phase image according to liver shape using RayStation(TM) 3.99.0.7 version treatment planning system. The IGTV-DR was obtained by merging the GTVs after DR on the 4D CT images. Volume differences among the GTVs and between the IGTV-1 and the IGTV-DR were compared. RESULTS: The edge of most lesions could be definitively identified using APCE 3D CT images compared to NCE 4D and 3D CT images. The GTV volume on APCE 3D CT images increased by an average of 34.79% (P<0.05). There was no significant difference among the GTV volumes obtained using NCE 4D and 3D CT images (P>0.05). The GTV volumes after DR on 4D CT different phase images increased by an average of 36.29% (P<0.05), as was observed using the APCE 3D CT image (P>0.05). Lastly, the volume of IGTV-DR increased by an average of 19.91% compared to that of IGTV-1 (P<0.05). CONCLUSION: NCE 4D CT imaging alone has the potential risk of missing a partial volume of the HCC. The combination of APCE 3D CT and NCE 4D CT images using the DR technique improved the accuracy of the definition of the IGTV in HCC.

Predictive value of primary fluorine-18 fluorodeoxyglucose standard uptake value for a better choice of systematic nodal dissection or sampling in clinical stage ia non--small-cell lung cancer.

PURPOSE: To determine whether the standard uptake value (SUV) of the primary lesion can predict mediastinal lymph node metastasis in clinical stage IA non--small-cell lung cancer (NSCLC). MATERIALS AND METHODS: At 5 centers, patients with clinical stage IA NSCLC from February 2004 to August 2010 were analyzed retrospectively. Data from Shandong Cancer Hospital and from the Cancer Hospital Affiliated to Harbin Medical University were used as a testing set, and data from the other 3 institutions were used as the validation set. Final diagnosis was established based on the histopathologic examination. RESULTS: Data from 144 patients were collected for the study. The primary results in our study showed that maximal SUV (SUVmax) of primary tumor might be a predictor of lymph node metastasis (χ(2) = 10.424; P = .001) and the best cutoff value was 7.25 (P = .029). For the testing set, lymph node metastasis rates in low-grade group (SUVmax < 7.25) and high-grade group (SUVmax > 7.25) were 5% (2/43) and 36% (9/25) (P = .001) For the total data set, lymph node metastasis rate was 7% (6/93) in low-grade group (SUVmax < 7.25) and 26% (13/51) in high-grade group (SUVmax > 7.25) (χ(2)= 10.424; P = .001). A multivariate analysis revealed that no factors were applied to predict the probability of metastasis. But the analysis showed a weak correlation between SUVmax and nodal status (r = 0.21; P = .011) with bivariate correlation. CONCLUSION: Analysis of our data suggested that fluorine-18 fluorodeoxyglucose SUVmax of the primary tumor might be a predictor of lymph node involvement in stage IA NSCLC. The rate of mediastinal lymph node metastasis of patients with a lower fluorine-18 fluorodeoxyglucose positron emission tomography-computed tomography SUVmax might be relatively low, which provides more evidence for clinical procedures of clinical stage IA NSCLC.

Mediastinal lymph nodes staging by 18F-FDG PET/CT for early stage non-small cell lung cancer: a multicenter study.

PURPOSE: Accurate staging of mediastinal lymph nodes metastases is critical for determining the application of stereotactic body radiation therapy (SBRT) for patients with early stage non-small cell lung cancer (NSCLC). In this multicenter study the accuracy of (18)F-FDG PET/CT to detect lymph node metastases was evaluated for early stage NSCLC. MATERIALS AND METHODS: The data from the patients with stage1 NSCLC who received preoperative (18)F-FDG PET/CT staging and radical surgery was retrospectively reviewed of five centers from February 2004 to August 2010. The lymph node metastases were confirmed histopathologically after radical surgery. And the sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) were calculated for PET/CT staging. RESULTS: Two hundred patients were enrolled. The sensitivity, specificity, accuracy, PPV and NPV for lymph node metastases on PET/CT were 44%, 83%, 78%, 29% and 91%, respectively. There were eight and 19 cases positive for lymph node metastases with central (n=62) and peripheral (n=138) NSCLC (P>0.05), respectively. CONCLUSION: (18)F-FDG PET/CT was specific in N(0) staging for T(1-2) NSCLC. The NPV was about 91% in clinical N(0) patients, suggested that (18)F-FDG PET/CT may help to accurately stage N(0) patients and thus identify patients for SBRT.

Measuring tumor cell proliferation with 18F-FLT PET during radiotherapy of esophageal squamous cell carcinoma: a pilot clinical study.

UNLABELLED: The primary aim of this study was to use serial (18)F-3'-deoxy-3'-fluorothymidine (FLT) PET/CT to measure tumor cell proliferation during radiotherapy of squamous cell carcinoma (SCC) of the esophagus. METHODS: Twenty-one patients with inoperable locally advanced SCC of the esophagus underwent serial (18)F-FLT PET/CT during radiotherapy. Each patient received a pretreatment scan, followed by 1-3 scans after delivery of 2, 6, 10, 20, 30, 40, 50, or 60 Gy to the tumor. RESULTS: Among the 19 patients who completed radiotherapy without interruption, parameters reflecting (18)F-FLT uptake in the tumor (i.e., maximum tumor standardized uptake value [SUVmax] and proliferation target volume) decreased steadily. All patients demonstrated an almost complete absence of proliferating esophageal tumor after 30 Gy and a complete absence after 40 Gy. In the 2 patients whose radiotherapy course was interrupted, (18)F-FLT uptake in the tumor was greater after the interruption than before the interruption. Marked early reduction of (18)F-FLT uptake in irradiated bone marrow was observed in all patients, even after only 2 Gy. All showed a complete absence of proliferating marrow in irradiated regions after 10 Gy. Both patients who underwent scans after completing the entire radiotherapy course showed no tumor uptake on (18)F-FLT PET/CT but high uptake on (18)F-FDG PET/CT. Pathologic examination of these regions revealed inflammatory infiltrates but no residual tumor. CONCLUSION: (18)F-FLT uptake can be used to monitor the biologic response of esophageal SCC and normal tissue to radiotherapy. Increased uptake of (18)F-FLT after treatment interruptions may reflect accelerated repopulation. (18)F-FLT PET/CT may have an advantage over (18)F-FDG PET/CT in differentiating inflammation from tumor.