Bridging the gap: Geometry-centric discriminative manifold distribution alignment for enhanced classification in colorectal cancer imaging.

The early detection of colorectal cancer (CRC) through medical image analysis is a pivotal concern in healthcare, with the potential to significantly reduce mortality rates. Current Domain Adaptation (DA) methods strive to mitigate the discrepancies between different imaging modalities that are critical in identifying CRC, yet they often fall short in addressing the complexity of cancer's presentation within these images. These conventional techniques typically overlook the intricate geometrical structures and the local variations within the data, leading to suboptimal diagnostic performance. This study introduces an innovative application of the Discriminative Manifold Distribution Alignment (DMDA) method, which is specifically engineered to enhance the medical image diagnosis of colorectal cancer. DMDA transcends traditional DA approaches by focusing on both local and global distribution alignments and by intricately learning the intrinsic geometrical characteristics present in manifold space. This is achieved without depending on the potentially misleading pseudo-labels, a common pitfall in existing methodologies. Our implementation of DMDA on three distinct datasets, involving several unique DA tasks, has consistently demonstrated superior classification accuracy and computational efficiency. The method adeptly captures the complex morphological and textural nuances of CRC lesions, leading to a significant leap in domain adaptation technology. DMDA's ability to reconcile global and local distributional disparities, coupled with its manifold-based geometrical structure learning, signals a paradigm shift in medical imaging analysis. The results obtained are not only promising in terms of advancing domain adaptation theory but also in their practical implications, offering the prospect of substantially improved diagnostic accuracy and faster clinical workflows. This heralds a transformative approach in personalized oncology care, aligning with the pressing need for early and accurate CRC detection.

Preliminary studies on intimal injury related to stent retrieval in a canine model.

OBJECTIVE: This pilot study aimed to observe intimal injuries related to stent retrieval in the iliac artery of a canine. BACKGROUND: In-stent restenosis remains challenging owing to permanent stent implantation. A retrievable stent may be alternative for intervention without permanent residue. METHODS: Five retrievable stents with point-to-point overlapped double-layer scaffolds were deployed into the iliac arteries and retrieved on days 14, 21, 28, 35, and 42 from five canines. RESULTS: Arterial diameter decreased by 9-10% before retrieval and 15% on day 14 after retrieval. In the 14-day-stent, the stent surface was clean without visible fibrin. In the 28-day-stent, the overlay was mainly composed of fibrin and fibroblasts. The proliferation of smooth muscle cells has not yet been observed with α-smooth muscle actin staining. In the 42-day-stent, endothelial and smooth muscle cells decreased under the struts, and the internal elastic lamina was interrupted segmentally. Neointima formation involves fibroblasts and smooth muscle cells. Neointimal thickness was negatively correlated with strut space. Stent traces on the artery wall tended to be flat at a follow-up14 days after retrieval. The primary intima was completely covered by neointima. Two stents could not be retrieved because of in-stent thrombosis or capture loss. CONCLUSIONS: The stent was covered mainly by depositional fibrin after 28 days and by typical neointima after 42 days. The stent retrieval procedure did not induce injury to vascular smooth muscle, and the intima repair was performed 14 days after stent retrieval.

Optimizing methadone dose adjustment in patients with opioid use disorder.

Introduction: Opioid use disorder is a cause for concern globally. This study aimed to optimize methadone dose adjustments using mixed modeling and machine learning. Methods: This retrospective study was conducted at Taichung Veterans General Hospital between January 1, 2019, and December 31, 2020. Overall, 40,530 daily dosing records and 1,508 urine opiate test results were collected from 96 patients with opioid use disorder. A two-stage approach was used to create a model of the optimized methadone dose. In Stage 1, mixed modeling was performed to analyze the association between methadone dose, age, sex, treatment duration, HIV positivity, referral source, urine opiate level, last methadone dose taken, treatment adherence, and likelihood of treatment discontinuation. In Stage 2, machine learning was performed to build a model for optimized methadone dose. Results: Likelihood of discontinuation was associated with reduced methadone doses (ß = 0.002, 95% CI = 0.000-0.081). Correlation analysis between the methadone dose determined by physicians and the optimized methadone dose showed a mean correlation coefficient of 0.995 ± 0.003, indicating that the difference between the methadone dose determined by physicians and that determined by the model was within the allowable range (p < 0.001). Conclusion: We developed a model for methadone dose adjustment in patients with opioid use disorders. By integrating urine opiate levels, treatment adherence, and likelihood of treatment discontinuation, the model could suggest automatic adjustment of the methadone dose, particularly when face-to-face encounters are impractical.

Efficacy, tolerability, and safety of oral paliperidone extended release in the treatment of schizophrenia: a 24-week, open-label, prospective switch study in different settings in Taiwan.

PURPOSE: Paliperidone extended release (ER) is an oral psychotropic treatment formulated to release paliperidone at a controlled, gradually ascending rate. We evaluated the efficacy and safety of switching to paliperidone ER in Taiwanese patients with schizophrenia who were unresponsive or intolerant to previous antipsychotic therapy. PATIENTS AND METHODS: This was a 24-week, open-label, single-arm, multicenter, Phase IV trial. Based on consulting psychiatrists' judgment, patients were deemed eligible for the switch to paliperidone ER; the switch was achieved by cross-tapering, using a recommended starting dose of 6 mg. Eligibility considerations included lack of efficacy, tolerability, and/or adherence to previous oral antipsychotic medication. RESULTS: Of the 297 enrolled patients, 178 (59.5%) completed the study. The main reasons for discontinuation included insufficient efficacy (8.7%), patient decision (8.4%), and adverse events (AEs; 6.4%). Improvements in the: Positive and Negative Syndrome Scale total score and Clinical Global Impression-Severity score were observed only in patients treated at medical centers and not in those treated at psychiatric hospitals. The most common AEs were insomnia, headache, constipation, and extrapyramidal syndrome. One or more serious AEs were reported in 11 (3.7%) patients; none resulted in death. No significant changes in body weight, plasma glucose, or lipid levels were observed. CONCLUSION: Switching to paliperidone ER was effective and well tolerated for up to 24 weeks in patients with schizophrenia who were unresponsive or intolerant to previous antipsychotic therapy. The observed differences in treatment between psychiatric hospitals and medical centers with regard to dosage and titration of paliperidone ER warrant further investigation.