Automated segmentation of brain metastases with deep learning: a multi-center, randomized crossover, multi-reader evaluation study.

BACKGROUND: Artificial intelligence has been proposed for brain metastasis (BM) segmentation but it has not been fully clinically validated. The aim of this study was to develop and evaluate a system for BM segmentation. METHODS: A deep-learning-based BM segmentation system (BMSS) was developed using contrast-enhanced MR images from 488 patients with 10,338 brain metastases. A randomized crossover, multi-reader study was then conducted to evaluate the performance of the BMSS for BM segmentation using data prospectively collected from 50 patients with 203 metastases at five centers. Five radiology residents and five attending radiologists were randomly assigned to contour the same prospective set in assisted and unassisted modes. Aided and unaided Dice similarity coefficients (DSCs) and contouring times per lesion were compared. RESULTS: The BMSS alone yielded a median DSC of 0.91 (95% confidence interval, 0.90-0.92) in the multi-center set and showed comparable performance between the internal and external sets (p = 0.67). With BMSS assistance, the readers increased the median DSC from 0.87 (0.87-0.88) to 0.92 (0.92-0.92) (p < 0.001) with a median time saving of 42% (40-45%) per lesion. Resident readers showed a greater improvement than attending readers in contouring accuracy (improved median DSC, 0.05 [0.05-0.05] vs. 0.03 [0.03-0.03]; p < 0.001), but a similar time reduction (reduced median time, 44% [40-47%] vs. 40% [37-44%]; p = 0.92) with BMSS assistance. CONCLUSIONS: The BMSS can be optimally applied to improve the efficiency of brain metastasis delineation in clinical practice.

Increased GPC4 and clusterin associated with insulin resistance in patients with PCOS.

The aim of the study was to investigate the changes in serum glypican 4 (GPC4) and clusterin (CLU) levels in patients with polycystic ovary syndrome (PCOS) as well as their correlation with sex hormones and metabolic parameters. A total of 40 PCOS patients and 40 age-matched healthy women were selected. Serum GPC4 and CLU levels were compared between the PCOS and control groups, and binary logistic regression was used to analyze the relative risk of PCOS at different tertiles of serum GPC4 and CLU concentrations. Stepwise linear regression was used to identify the factors influencing serum GPC4 and CLU levels in PCOS patients. Serum GPC4 (1.82 ± 0.49 vs 1.30 ± 0.61 ng/mL, P < 0.001) and CLU (468.79 ± 92.85 vs 228.59 ± 82.42 µg/mL, P < 0.001) were significantly higher in PCOS patients than in healthy women after adjustment for body mass index (BMI). In the PCOS group, serum GPC4 was positively correlated with follicle-stimulating hormone, fasting plasma glucose (FPG), fasting insulin (FINS), homeostatic model assessment of insulin resistance (HOMA-IR), triglyceride, and CLU (P < 0.05), whereas serum CLU was positively correlated with BMI, FPG, FINS, and HOMA-IR (P < 0.05). Multiple stepwise linear regression analysis showed that HOMA-IR was independently associated with serum GPC4, and BMI and HOMA-IR were independently associated with CLU (P < 0.05). Serum GPC4 and CLU levels were significantly higher in PCOS patients than in healthy women, suggesting that GPC4 and CLU may be markers associated with insulin resistance in women with PCOS.

False-negative and false-positive outcomes of computer-aided detection on brain metastasis: Secondary analysis of a multicenter, multireader study.

BACKGROUND: Errors have seldom been evaluated in computer-aided detection on brain metastases. This study aimed to analyze false negatives (FNs) and false positives (FPs) generated by a brain metastasis detection system (BMDS) and by readers. METHODS: A deep learning-based BMDS was developed and prospectively validated in a multicenter, multireader study. Ad hoc secondary analysis was restricted to the prospective participants (148 with 1,066 brain metastases and 152 normal controls). Three trainees and 3 experienced radiologists read the MRI images without and with the BMDS. The number of FNs and FPs per patient, jackknife alternative free-response receiver operating characteristic figure of merit (FOM), and lesion features associated with FNs were analyzed for the BMDS and readers using binary logistic regression. RESULTS: The FNs, FPs, and the FOM of the stand-alone BMDS were 0.49, 0.38, and 0.97, respectively. Compared with independent reading, BMDS-assisted reading generated 79% fewer FNs (1.98 vs 0.42, P < .001); 41% more FPs (0.17 vs 0.24, P < .001) but 125% more FPs for trainees (P < .001); and higher FOM (0.87 vs 0.98, P < .001). Lesions with small size, greater number, irregular shape, lower signal intensity, and located on nonbrain surface were associated with FNs for readers. Small, irregular, and necrotic lesions were more frequently found in FNs for BMDS. The FPs mainly resulted from small blood vessels for the BMDS and the readers. CONCLUSIONS: Despite the improvement in detection performance, attention should be paid to FPs and small lesions with lower enhancement for radiologists, especially for less-experienced radiologists.

PD-1 inhibitor-associated type 1 diabetes: A case report and systematic review.

Objective: This study aimed to summarize the clinical characteristics of programmed death receptor 1 (PD-1) inhibitor-associated type 1 diabetes so as to improve the ability of clinicians to correctly diagnose and treat it. Methods: We reported a case of a 70-year-old woman with gastric cancer who developed hyperosmolar hyperglycemic coma during camrelizumab (a PD-1 inhibitor) treatment and was diagnosed with PD-1 inhibitor-associated type 1 diabetes. We conducted a systematic review of 74 case reports of type 1 diabetes associated with PD-1 inhibitor therapy published before June 2022. Results: The patient developed type 1 diabetes with hyperosmolar hyperglycemic coma after receiving camrelizumab chemotherapy for 6 months (9 cycles). We searched 69 English articles comprising 75 patients, all of whom had been treated with a PD-1 inhibitor (nivolumab or pembrolizumab) and progressed to diabetes after an average of 6.11 (1-28) cycles. Nivolumab combined with ipilimumab (a cytotoxic T lymphocyte-associated protein 4 inhibitor) had the shortest onset (4.47 cycles on average). A total of 76% (57/75) of patients developed diabetic ketoacidosis (DKA) at onset, and 50.67% (38/75) of patients had C-peptide <0.1 ng/mL. Most of the patients were tested for insulin autoantibodies, with a positive rate of 33.33% (23/69); of these, 86.96% (20/23) were tested for glutamate decarboxylase antibody and 46.67% (35/75) were tested for human leukocyte antigen (HLA). HLA-DR4 was the most common type. Conclusions: The progression of type 1 diabetes induced by PD-1 inhibitors is relatively rapid. Islet failure often occurs when detected, seriously endangering patients' lives. Patients treated with PD-1 inhibitors should closely monitor their plasma glucose level during treatment to detect, diagnose, and treat diabetes on time.

Development and validation of a deep-learning model for detecting brain metastases on 3D post-contrast MRI: a multi-center multi-reader evaluation study.

BACKGROUND: Accurate detection is essential for brain metastasis (BM) management, but manual identification is laborious. This study developed, validated, and evaluated a BM detection (BMD) system. METHODS: Five hundred seventy-three consecutive patients (10 448 lesions) with newly diagnosed BMs and 377 patients without BMs were retrospectively enrolled to develop a multi-scale cascaded convolutional network using 3D-enhanced T1-weighted MR images. BMD was validated using a prospective validation set comprising an internal set (46 patients with 349 lesions; 44 patients without BMs) and three external sets (102 patients with 717 lesions; 108 patients without BMs). The lesion-based detection sensitivity and the number of false positives (FPs) per patient were analyzed. The detection sensitivity and reading time of three trainees and three experienced radiologists from three hospitals were evaluated using the validation set. RESULTS: The detection sensitivity and FPs were 95.8% and 0.39 in the test set, 96.0% and 0.27 in the internal validation set, and ranged from 88.9% to 95.5% and 0.29 to 0.66 in the external sets. The BMD system achieved higher detection sensitivity (93.2% [95% CI, 91.6-94.7%]) than all radiologists without BMD (ranging from 68.5% [95% CI, 65.7-71.3%] to 80.4% [95% CI, 78.0-82.8%], all P < .001). Radiologist detection sensitivity improved with BMD, reaching 92.7% to 95.0%. The mean reading time was reduced by 47% for trainees and 32% for experienced radiologists assisted by BMD relative to that without BMD. CONCLUSIONS: BMD enables accurate BM detection. Reading with BMD improves radiologists' detection sensitivity and reduces their reading times.

Realizing a terahertz far-field sub-diffraction optical needle with sub-wavelength concentric ring structure array.

The terahertz (THz) lens is an essential and strategic element of THz optical systems, while a conventional THz lens cannot even reach high resolution due to the diffraction limit. Optical super-oscillation paves a way to generate sub-diffraction hotspots in the far field, and demonstrates the capacity for resolution improvement of microscopic imaging in the visible range. However, there are few demonstrations of THz lenses for focusing hotspots or needles based on super-oscillation. We propose and experimentally demonstrate a far-field sub-diffraction focusing planar lens, consisting of a sub-wavelength concentric ring structure array, for a wavelength of 118.8 µm with focal length 420λ and radius 160λ. Utilizing the silicon-etching process, a sub-diffraction focusing lens is fabricated. The experimental results show that the planar lens can generate a sub-diffraction needle with length 19.7λ in the focal region along the optic axis. Moreover, the smallest focal spot, with a transverse size of 1.212λ, is smaller than the diffraction limit of 1.476λ. The proposed sub-diffraction optical needle planar lens can substitute for its traditional counterpart, and it has great potential in super-resolution tomography THz imaging systems.

A research on shape-controllable synthesis of Ag3PO4/AgBr and its degradation of ciprofloxacin.

Antibiotic ciprofloxacin is one of the commonly used broad spectrum fluoroquinolone human and veterinary drugs. Because of the overuse of human beings, the presence of ciprofloxacin has been detected in a variety of environmental matrices. To solve this problem, a facile, environmentally-friendly Ag3PO4/AgBr composite photocatalyst was synthesized by a simple precipitation method at room temperature in the presence of cetyltrimethyl ammonium bromide (CTAB). CTAB was served as surfactant and the source of bromide ions. The as-prepared Ag3PO4/AgBr microspheres were characterized by means of powder X-ray diffraction (XRD), scanning electron microscope (SEM) and UV-visible diffuse reflectance spectroscopy (UV-vis DRS). The results revealed that the Ag3PO4/AgBr sample (synthesized with CTAB, 0.8 g) exhibited the highest photocatalytic activity to the photodegradation rate of 96.36%. Moreover, mechanism detection experiment indicated that h+ was the major active species in the degradation process. So the enhanced photocatalytic activity of Ag3PO4/AgBr composites is attributed to its excellent separation of photogenerated electron-hole pairs through Ag3PO4/AgBr heterojunction. Also, Ag3PO4/AgBr heterojunction has a lower band gap compared to pure Ag3PO4 and pure AgBr, so higher efficiency of light harvesting is equipped.

Efficient photocatalytic degradation of tetracycline hydrochloride by Ag3PO4 under visible-light irradiation.

A facile, environmental-friendly Ag3PO4-PN photocatalyst was synthesized by a simple precipitation method at room temperature in the presence of ammonia and polyvinyl pyrrolidone (PVP). As-synthesized samples were characterized by scanning electron microscopy (SEM), X-ray diffraction (XRD), X-ray photoelectron spectroscopy (XPS), and UV-visible diffuse reflectance spectroscopy (UV-vis DRS). The enhancement of photocatalytic efficiency of Ag3PO4-PN is strongly dependent on the excellent photo-absorption capacity, sharp edges and corners, and synergistic effect of PVP and NH3·H2O. The effects of catalyst dosage, TC concentration and solution pH were explored with tetracycline hydrochloride (TC) as target contamination. The mineralization was evaluated by total organic carbon (TOC) analysis and determination of the concentration of inorganic ions such as NO3 (-) and Cl(-). Radical detection experiment indicated the h(+) and ·O(2-) are major active species in the degradation of TC by Ag3PO4-PN. Moreover, photocatalyst stability and regeneration experiments exhibited the favorable stability and rejuvenation ability, suggesting a promising prospect of practical application of Ag3PO4 in the wastewater treatment.