Rationale: Many clinical studies have focused on the epidemiological and clinical characteristics of inpatients with coronavirus disease (COVID-19). However, there are few reports about the clinical follow-up of discharged patients. Objectives: To describe the follow-up of patients with COVID-19 in Wenzhou City, Zhejiang, China. Methods: We retrospectively reviewed 4-week follow-ups in patients with COVID-19, including computed tomographic (CT) chest scanning, blood testing, and oropharyngeal-swab testing for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) ribonucleic acid. The chest CT scans and blood tests were performed on the last day before discharge and 2 weeks and 4 weeks after discharge. The oropharyngeal-swab tests were performed at both 1 week and 2 weeks after discharge. Fifty-one patients with common COVID-19 were enrolled in the study. All the CT and clinical data were collected between January 23 and March 28, 2020. Results: Compared with the abnormalities found on the the last CT scans before discharge, the abnormalities in the lungs at the first and second follow-ups after discharge had been gradually absorbed. The cases with focal ground-glass opacity were reduced from 17.7% to 9.8% of cases. The cases with multiple ground-glass opacities decreased from 80.4% to 23.5%. The cases with consolidation were reduced from 49.0% to 2.0%. The cases with interlobular septal thickening were reduced from 80.4% to 35.3%. The cases with subpleural lines were reduced from 29.4% to 7.8%. The cases with irregular lines were reduced from 41.2% to 15.7%. The lung lesions of 25.5% patients were shown to be fully absorbed on the first CT scans after discharge, and the rate of lung recovery increased to 64.7% after the second follow-up. Nucleic-acid test results became recurrently positive in 17.6% of discharged patients, of whom only 33.3% complained of clinical symptoms. There were no differences in the characteristics of the last CT scans before discharge between the patients with recurrently positive test results and the patients with negative test results. The lung damage was fully absorbed in 55.6% of discharged patients with recurrence of positive test results for SARS-CoV-2 ribonucleic acid. Conclusions: The lung damage due to COVID-19 could be reversible for patients with common COVID-19. A few cases showed recurring positive results of nucleic-acid tests after discharge.

We present a noncontact method to measure ballistocardiogram (BCG) and photoplethysmogram (PPG) simultaneously using a single camera. The method tracks the motion of facial features to determine displacement BCG, and extracts the corresponding velocity and acceleration BCGs by taking first and second temporal derivatives from the displacement BCG, respectively. The measured BCG waveforms are consistent with those reported in the literature and also with those recorded with an accelerometer-based reference method. The method also tracks PPG based on the reflected light from the same facial region, which makes it possible to track both BCG and PPG with the same optics. We verify the robustness and reproducibility of the noncontact method with a small pilot study with 23 subjects. The presented method is the first demonstration of simultaneous BCG and PPG monitoring without wearing any extra equipment or marker by the subject.

The emergence of artificial general intelligence (AGI) is transforming radiation oncology. As prominent vanguards of AGI, large language models (LLMs) such as GPT-4 and PaLM 2 can process extensive texts and large vision models (LVMs) such as the Segment Anything Model (SAM) can process extensive imaging data to enhance the efficiency and precision of radiation therapy. This paper explores full-spectrum applications of AGI across radiation oncology including initial consultation, simulation, treatment planning, treatment delivery, treatment verification, and patient follow-up. The fusion of vision data with LLMs also creates powerful multimodal models that elucidate nuanced clinical patterns. Together, AGI promises to catalyze a shift towards data-driven, personalized radiation therapy. However, these models should complement human expertise and care. This paper provides an overview of how AGI can transform radiation oncology to elevate the standard of patient care in radiation oncology, with the key insight being AGI's ability to exploit multimodal clinical data at scale.

Remote photoplethysmography (rPPG) is attractive for tracking a subject’s physiological parameters without wearing a device. However, rPPG is known to be prone to body movement-induced artifacts, making it unreliable in realistic situations. Here we report a method to minimize the movement-induced artifacts. The method selects an optimal region of interest (ROI) automatically, prunes frames in which the ROI is not clearly captured (e.g., subject moves out of the view), and analyzes rPPG using an algorithm in CIELab color space, rather than the widely used RGB color space. We show that body movement primarily affects image intensity, rather than chromaticity, and separating chromaticity from intensity in CIELab color space thus helps achieve effective reduction of the movement-induced artifacts. We validate the method by performing a pilot study including 17 people with diverse skin tones.

There are very little data available comparing outcomes of intensity-modulated proton therapy (IMPT) to intensity-modulated radiation therapy (IMRT) in patients with locally advanced NSCLC (LA-NSCLC). Seventy-nine consecutively treated patients with LA-NSCLC underwent definitive IMPT (n = 33 [42%]) or IMRT (n = 46 [58%]) from 2016 to 2018 at our institution. Survival rates were calculated using the Kaplan-Meier method and compared with the log-rank test. Acute and subacute toxicities were graded based on Common Terminology Criteria for Adverse Events, version 4.03. Median follow-up was 10.5 months (range, 1-27) for all surviving patients. Most were stage III (80%), received median radiation therapy (RT) dose of 60 Gy (range, 45-72), and had concurrent chemotherapy (65%). At baseline, the IMPT cohort was older (76 vs 69 years, P < .01), were more likely to be oxygen-dependent (18 vs 2%, P = .02), and more often received reirradiation (27 vs 9%, P = .04) than their IMRT counterparts. At 1 year, the IMPT and IMRT cohorts had similar overall survival (68 vs 65%, P = .87), freedom from distant metastasis (71 vs 68%, P = .58), and freedom from locoregional recurrence (86 vs 69%, P = .11), respectively. On multivariate analyses, poorer pulmonary function and older age were associated with grade +3 toxicities during and 3 months after RT, respectively (both P ≤ .02). Only 5 (15%) IMPT and 4 (9%) IMRT patients experienced grade 3 or 4 toxicities 3 months after RT (P = .47). There was 1 treatment-related death from radiation pneumonitis 6 months after IMRT in a patient with idiopathic pulmonary fibrosis. Compared with IMRT, our early experience suggests that IMPT resulted in similar outcomes in a frailer population of LA-NSCLC who were more often being reirradiated. The role of IMPT remains to be defined prospectively.