Online Learning-Based Hybrid Tracking Method for Unmanned Aerial Vehicles.

Tracking unmanned aerial vehicles (UAVs) in outdoor scenes poses significant challenges due to their dynamic motion, diverse sizes, and changes in appearance. This paper proposes an efficient hybrid tracking method for UAVs, comprising a detector, tracker, and integrator. The integrator combines detection and tracking, and updates the target's features online while tracking, thereby addressing the aforementioned challenges. The online update mechanism ensures robust tracking by handling object deformation, diverse types of UAVs, and changes in background. We conducted experiments on custom and public UAV datasets to train the deep learning-based detector and evaluate the tracking methods, including the commonly used UAV123 and UAVL datasets, to demonstrate generalizability. The experimental results show the effectiveness and robustness of our proposed method under challenging conditions, such as out-of-view and low-resolution scenarios, and demonstrate its performance in UAV detection tasks.

Comparison of HU histogram analysis and BMD for proximal femoral fragility fracture assessment: a retrospective single-center case-control study.

OBJECTIVES: To evaluate the feasibility of HU histogram analysis (HUHA) to assess proximal femoral fragility fractures with respect to BMD. METHODS: This retrospective study included 137 patients with femoral fragility fractures who underwent hip CT and 137 control patients without fractures who underwent abdominal CT between January 2018 and February 2019. HUHA was calculated with the 3D volume of interest from the femoral head to the lesser trochanter. HUHAfat (percentage of negative HU values) and HUHAbone (percentage of HU values ≥ 125 HU) were assumed to be fat and bone components, respectively. Statistical significance was assessed using the area under the receiver operating characteristic curve (AUC), Spearman correlation (ρ), and odds ratio. RESULTS: HUHAfat was strongly positively correlated (ρ = 0.56) and BMD was moderately negatively correlated with fragility fractures (ρ = - 0.37). AUC of HUHAfat (0.82, 95% CI [0.77, 0.87]) significantly differed from that of BMD (0.69, 95% CI [0.63, 0.75]) (p < .001). The cutoff value was 15.8% for HUHAfat (sensitivity: 90.4%; specificity: 67.7%) and 0.709 g/cm2 for BMD (sensitivity: 87.5%; specificity: 51.5%), with higher HUHAfat and lower BMD values indicating fragility fractures. The odds ratio of HUHAfat was 19.5 (95% CI [9.9, 38.2], p < .001), which was higher than that of BMD, 7.4 (95% CI [4.0, 13.6], p < .001). CONCLUSION: HUHAfat revealed better performance than BMD and demonstrated feasibility in assessing proximal femoral fragility fractures. KEY POINTS: • HUHAfat showed a strong positive correlation (Spearman ρ = 0.56, p < .001), and BMD showed a moderate negative correlation (Spearman ρ = - 0.37, p < .001) with proximal femoral fragility fractures. • HUHAfat (AUC = 0.82) performed significantly better than BMD in assessing proximal femoral fragility fractures (AUC = 0.69) (p < .001). • The odds ratio of HUHAfat for proximal femoral fragility fractures was higher than that of BMD (19.5 and 7.4, respectively; p < .001).

Predictors of pathological upgrading in low-risk prostate cancer patients without hypointense lesions on an apparent diffusion coefficient map of multiparametric magnetic resonance imaging.

PURPOSE: To examine the clinicopathological features and identify the predictors of pathological upgrading in low-risk prostate cancer (PCa) patients without hypointense lesions on the apparent diffusion coefficient (ADC) map calculated from multiparametric magnetic resonance imaging. METHODS: We reviewed the medical records of 1905 PCa patients who underwent radical prostatectomy between 2007 and 2015. All ADC images were graded using the five-grade Likert scale; the positive hypointense lesions were graded 4-5. We analyzed 256 patients with low-risk classifications according to D'Amico criteria. Patients were classified into two groups according to the pathologic upgrading in the surgical specimens. The predictive factors for pathologic upgrading were evaluated using a multivariate logistic regression analysis. RESULTS: In 256 patients with low-risk PCa, the percentage of positive cores [odds ratio (OR) 1.09; 95 % confidence interval (CI) 1.02-1.16], the percentage of cancer in the positive cores (OR 1.07, 95 % CI 1.03-1.12), and the presence of hypointensity on an ADC map (OR 2.28; 95 % CI 1.23-4.22) were independent predictors of pathologic upgrading. Notably, 138 of low-risk patients (53.9 %) had no hypointense lesions on an ADC map. Of these 138 patients, the percentage of positive cores (OR 1.09; 95 % CI 1.01-1.18) and the percentage of cancer in the positive cores (OR 1.06; 95 % CI 1.01-1.12) remained independent predictors of pathologic upgrading. CONCLUSIONS: In low-risk PCa patients without hypointense lesions on an ADC map, biopsy-related parameters such as the percentage of positive cores and the percentage of cancer in the positive cores were independent predictors of pathological upgrading following radical prostatectomy.

Revision for unsatisfactory outcomes of scalp micropigmentation.

BACKGROUND: Scalp micropigmentation (SMP) is becoming increasingly popular. Accordingly, complications of the procedure are on the rise. However, the results of improperly performed SMP are exceedingly challenging to rectify and ultimately lead to severe mental stress and feelings of inferiority in patients. AIMS: This retrospective study aimed to explore various aspects of unsatisfactory SMP outcomes and examine corrective measures available after the procedure. MATERIALS AND METHODS: A total of 120 patients who underwent corrective surgery or procedures due to unsatisfactory outcomes after SMP were enrolled in the study. Their photographs and medical charts were reviewed retrospectively. RESULTS: Out of 120 participants, 76 were women and 43 men. In total, 107 patients (89.2%) had been treated at a tattooing or cosmetic facility at a beauty salon performing permanent makeup, 12 (10.0%) at another clinic, and one (0.8%) at an oriental medicine clinic. Of 120 patients, hair transplant surgery was performed on 74 patients (61.7%). Twenty-five (20.8%) underwent both hair transplant surgery and complementary SMP. Sixteen (13.3%) patients received laser tattoo removal and underwent SMP anew. Five patients (4.2%) had a previous tattoo removed without additional treatment. Patients' subjective satisfaction scores averaged 4.5/5. The physician's objective satisfaction score was 4.6/5. CONCLUSION: In cases where SMP is inadequately performed, satisfactory results can be achieved through appropriate revisions, such as tattoo removal, repeated SMP, or hair transplant surgery to conceal the tattoo by highly experienced medical professionals. LEVEL OF EVIDENCE: IV.

AMST2: aggregated multi-level spatial and temporal context-based transformer for robust aerial tracking.

Recently, many existing visual trackers have made significant progress by incorporating either spatial information from multi-level convolution layers or temporal information for tracking. However, the complementary advantages of both spatial and temporal information cannot be leveraged when these two types of information are used separately. In this paper, we present a new approach for robust visual tracking using a transformer-based model that incorporates both spatial and temporal context information at multiple levels. To integrate the refined similarity maps through multi-level spatial and temporal encoders, we propose an aggregation encoder. Consequently, the output of the proposed aggregation encoder contains useful features that integrate the global contexts of multi-level spatial and the temporal contexts. The feature we propose offers a contrasting yet complementary representation of multi-level spatial and temporal contexts. This characteristic is particularly beneficial in complex aerial scenarios, where tracking failures can occur due to occlusion, motion blur, small objects, and scale variations. Also, our tracker utilizes a light-weight network backbone, ensuring fast and effective object tracking in aerial datasets. Additionally, the proposed architecture can achieve more robust object tracking against significant variations by updating the features of the latest object while retaining the initial template information. Extensive experiments on seven challenging short-term and long-term aerial tracking benchmarks have demonstrated that the proposed tracker outperforms state-of-the-art tracking methods in terms of both real-time processing speed and performance.

CT screening for lung cancer: the value of short-term CT follow-up.

BACKGROUND: Although CT screening for lung cancer results in a diagnosis of stage I > 80% of the time, benign noncalcified nodules are also found. We recognized that some nodules appeared to represent infectious bronchopneumonia or other inflammatory processes, as they resolved on follow-up CT, sometimes after antibiotic therapy. To determine the extent to which short-term CT radiographic follow-up might shorten the workup of nodules, we reviewed our experience with baseline and annual repeat CT screenings performed subsequent to the original Early Lung Cancer Action Project series. METHODS: The initial CT of 1,968 consecutive baseline and 2,343 annual repeat screenings performed from 1999 to 2002 was reviewed. We identified all those recommended for antibiotics on the initial CT who had a follow-up CT within 2 months and determined whether the nodule(s) resolved, decreased in size, remained unchanged, or grew. We then determined whether further follow-up resulted in a diagnosis of cancer. RESULTS: At baseline, among the 41 individuals who had follow-up CT within 2 months of the initial CT, 12 patients (29%) had complete or partial resolution; none of them subsequently received a diagnosis of lung cancer. On annual repeat screening, among the 39 individuals who had follow-up CT within 2 months of the initial CT, 29 patients (74%) had complete or partial resolution; none of them subsequently received a diagnosis of lung cancer. Among the 29 patients with nodules at baseline that were unchanged or grew, a total of 15 cancers were subsequently diagnosed; among the 10 patients on annual repeat scanning, there were 2 cancers. CONCLUSIONS: In asymptomatic individuals undergoing CT screening for lung cancer, short-term follow-up CT within 2 months with or without antibiotics may circumvent the need for further evaluation in some individuals, particularly on annual repeat screening.

The general radiologist's role in breast cancer risk assessment: breast density measurement on chest CT.

To determine if general radiologists can accurately measure breast density on low-dose chest computed tomographic (CT) scans, two board-certified radiologists with expertise in mammography and CT scan interpretation, and seven general radiologists performed retrospective review of 100 women's low-dose chest CT scans. CT breast density grade based on Breast Imaging Reporting and Data System grades was independently assigned for each case. Kappa statistic was used to compare agreement between the expert consensus grading and those of the general radiologists. Kappa statistics were 0.61-0.88 for the seven radiologists, showing substantial to excellent agreement and leading to the conclusion that general radiologists can be trained to determine breast density on chest CT.

CT screening for lung cancer: prevalence and incidence of mediastinal masses.

PURPOSE: To determine the frequency and natural course of mediastinal masses in asymptomatic people at high risk for lung cancer who were undergoing computed tomographic (CT) screening. MATERIALS AND METHODS: Informed consent and institutional review board approval for this HIPAA-compliant study were obtained at each participating institution. All documented mediastinal masses among the 9263 baseline and 11 126 annual repeat screenings performed in the Early Lung Cancer Action Project (ELCAP) and its successor project, the New York ELCAP, were identified. Two radiologists confirmed all cases, identified the location and measured the diameter (average of length and width) of each mass, and reviewed all subsequent CT and clinical and surgical results. The prevalence and incidence of mediastinal masses were then determined. RESULTS: Of the 9263 individuals, 71 had a mediastinal mass seen at baseline screening (prevalence of 0.77%). Of the 71 masses, 41 were thymic, 16 were thyroidal, two were esophageal cancers, six were tracheal-esophageal diverticula, and six were other masses. Among the 11 126 annual repeat screenings, only one new mediastinal mass was identified (incidence of 0.01%). This suggests a long average duration for mediastinal masses in asymptomatic people. Among the 41 thymic masses, five were larger than 3.0 cm in diameter, and all five were resected; of these five, one was a thymic carcinoma and four were noninvasive thymomas. Of the remaining 36 thymic masses, 25 were evaluated at follow-up CT 1 year later: Five had increased in diameter, two had decreased, and 18 remained unchanged. All 16 thyroid masses were due to goiter; none of these were changed at follow-up CT 1 year later. CONCLUSION: Mediastinal masses found in the context of CT screening for lung cancer in asymptomatic people should be approached in a "conservative" manner; this includes thymic masses smaller than 3 cm in diameter, as most of these remain unchanged or even decrease in size.