Combining Artificial Intelligence and Simplified Image Processing for the Automatic Detection of Mycobacterium tuberculosis in Acid-fast Stain: A Cross-institute Training and Validation Study.

Tuberculosis (TB) poses a significant health threat in Taiwan, necessitating efficient detection methods. Traditional screening for acid-fast positive bacilli in acid-fast stain is time-consuming and prone to human error due to staining artifacts. To address this, we present an automated TB detection platform leveraging deep learning and image processing. Whole slide images from 2 hospitals were collected and processed on a high-performance system. The system utilizes an image processing technique to highlight red, rod-like regions and a modified EfficientNet model for binary classification of TB-positive regions. Our approach achieves a 97% accuracy in tile-based TB image classification, with minimal loss during the image processing step. By setting a 0.99 threshold, false positives are significantly reduced, resulting in a 94% detection rate when assisting pathologists, compared with 68% without artificial intelligence assistance. Notably, our system efficiently identifies artifacts and contaminants, addressing challenges in digital slide interpretation. Cross-hospital validation demonstrates the system's adaptability. The proposed artificial intelligence-assisted pipeline improves both detection rates and time efficiency, making it a promising tool for routine pathology work in TB detection.

End-to-end interstitial fibrosis assessment of kidney biopsies with a machine learning-based model.

BACKGROUND: The extent of interstitial fibrosis in the kidney not only correlates with renal function at the time of biopsy but also predicts future renal outcome. However, its assessment by pathologists lacks good agreement. The aim of this study is to construct a machine learning-based model that enables automatic and reliable assessment of interstitial fibrosis in human kidney biopsies. METHODS: Validated cortex, glomerulus and tubule segmentation algorithms were incorporated into a single model to assess the extent of interstitial fibrosis. The model performances were compared with expert renal pathologists and correlated with patients' renal functional data. RESULTS: Compared with human raters, the model had the best agreement [intraclass correlation coefficient (ICC) 0.90] to the reference in 50 test cases. The model also had a low mean bias and the narrowest 95% limits of agreement. The model was robust against colour variation on images obtained at different times, through different scanners, or from outside institutions with excellent ICCs of 0.92-0.97. The model showed significantly better test-retest reliability (ICC 0.98) than humans (ICC 0.76-0.94) and the amount of interstitial fibrosis inferred by the model strongly correlated with 405 patients' serum creatinine (r = 0.65-0.67) and estimated glomerular filtration rate (r = -0.74 to -0.76). CONCLUSIONS: This study demonstrated that a trained machine learning-based model can faithfully simulate the whole process of interstitial fibrosis assessment, which traditionally can only be carried out by renal pathologists. Our data suggested that such a model may provide more reliable results, thus enabling precision medicine.

A Single-Institute Experience with C-ros Oncogene 1 Translocation in Non-Small Cell Lung Cancers in Taiwan.

(1) Background: The C-ros oncogene 1 (ROS1) gene translocation is an important biomarker for selecting patients for crizotinib-targeted therapy. The aim of this study was to understand the incidence, diagnostic algorithm, clinical course and objective response to crizotinib in ROS1 translocated lung non-small cell lung cancers (NSCLCs) in Taiwan. (2) Methods: First, we retrospectively studied the ROS1 status in 100 NSCLC samples using break-apart fluorescent in situ hybridization (FISH) and immunohistochemical (IHC) staining to establish a diagnostic algorithm. Then, we performed routine ROS1 IHC tests in 479 NSCLCs, as crizotinib was available from 2018 in Taiwan. We analyzed the objective response rate and the survival impact of crizotinib. (3) Results: Four ROS1 translocations were clustered in epidermal growth factor receptor (EGFR) wild-type adenocarcinomas but not in cases with EGFR mutations. Strong ROS1 expression was positively correlated with ROS1 translocation (p < 0.001). NSCLCs with ROS1 translocation had a poor prognosis compared to those without ROS1 translocation (p = 0.004) in the pre-crizotinib stage. Twenty NSCLCs were detected with ROS1 translocation in 479 wild-type EGFR specimens from 2018. Therefore, the incidence of ROS1 translocation is approximately 4.18% in EGFR wild-type NSCLCs. In these 20 ROS1 translocation cases, 19 patients received crizotinib treatment, with an objective response rate (ORR) of 78.95% (confidence interval = 69.34% to 88.56%), including 1 complete response, 14 partial responses, 3 stable cases and 1 progressive case. Overall survival and progression-free survival were better in the 19 ROS1-translocated NSCLCs of the prospective group with crizotinib treatment than the four ROS1-translocated NSCLCs of the retrospective group without crizotinib treatment. (4) Conclusions: ROS1-translocated NSCLCs had a poor prognosis and could have a beneficial outcome with crizotinib.

Glomerular disease classification and lesion identification by machine learning.

BACKGROUND: Classification of glomerular diseases and identification of glomerular lesions require careful morphological examination by experienced nephropathologists, which is labor-intensive, time-consuming, and prone to interobserver variability. In this regard, recent advance in machine learning-based image analysis is promising. METHODS: We combined Mask Region-based Convolutional Neural Networks (Mask R-CNN) with an additional classification step to build a glomerulus detection model using human kidney biopsy samples. A Long Short-Term Memory (LSTM) recurrent neural network was applied for glomerular disease classification, and another two-stage model using ResNeXt-101 was constructed for glomerular lesion identification in cases of lupus nephritis. RESULTS: The detection model showed state-of-the-art performance on variedly stained slides with F1 scores up to 0.944. The disease classification model showed good accuracies up to 0.940 on recognizing different glomerular diseases based on H&E whole slide images. The lesion identification model demonstrated high discriminating power with area under the receiver operating characteristic curve up to 0.947 for various glomerular lesions. Models showed good generalization on external testing datasets. CONCLUSION: This study is the first-of-its-kind showing how each step of kidney biopsy interpretation carried out by nephropathologists can be captured and simulated by machine learning models. The models were integrated into a whole slide image viewing and annotating platform to enable nephropathologists to review, correct, and confirm the inference results. Further improvement on model performances and incorporating inputs from immunofluorescence, electron microscopy, and clinical data might realize actual clinical use.

Safety and Effectiveness of Direct Oral Anticoagulants vs. Warfarin in Patients With Atrial Fibrillation and Endoscopy-Diagnosed Peptic Ulcer.

Background: Patients with active peptic ulcer (PU) were excluded from direct oral anticoagulant (DOAC) trials for stroke prevention in patients with atrial fibrillation (AF). This study evaluated the safety and effectiveness of DOACs in AF patients with active, inactive and no peptic ulcer (PU). Methods: This study accessed electronic medical records from January 1, 2009 to May 31, 2019 at a multi-center healthcare provider in Taiwan and involved 2,955 AF patients who had undergone esophagogastroduodenoscopy ≤ 1 year before anticoagulation. Subjects were classified into 3 groups: active (n = 237), inactive (n = 828) and no-PU (n = 1,890) groups. We compared the risks of major bleeding, gastrointestinal bleeding, and ischemic stroke/systemic embolism (IS/SE) between DOACs and warfarin among the 3 groups. Results: In the active PU group, there were no significant differences in the risks of major bleeding [hazard ratio (HR) = 0.65, 95% confidence interval (CI) 0.08-4.98, p = 0.676], gastrointestinal bleeding (HR = 0.65, 95% CI 0.08-4.98, p = 0.676) and IS/SE (HR = 2.58; 95% CI 0.53-12.70, p = 0.243) between DOAC and warfarin (as the reference). In the inactive PU group, there were no significant differences in the risks of major bleeding (HR = 0.36, 95% CI 0.09-1.39, p = 0.138), gastrointestinal bleeding (HR = 0.21, 95% CI 0.02-1.80, p = 0.153), and IS/SE (HR = 1.04, 95% CI 0.39-2.82, p = 0.934) between DOAC and warfarin (as the reference). In the no-PU group, DOACs were associated with lower risk of major bleeding (HR = 0.26, 95% CI 0.12-0.53, p < 0.001), gastrointestinal bleeding (HR = 0.25, 95% CI 0.01-0.59, p = 0.002), and similar risk of IS/SE (HR = 0.92, 95% CI 0.55-1.54, p = 0.757) compared to warfarin. Conclusions: DOACs were as effective as warfarin in preventing IS/SE irrespective of PU status and safer than warfarin in reducing major bleeding in the no-PU group. In patients with active or inactive PUs, DOAC and warfarin were not significantly different in their effects on major bleeding or gastrointestinal bleeding.

Preliminary study of non-invasive shock wave treatment of capsular contracture after breast implant: animal model.

The incidence rate of capsular contracture after breast implant is about 8% to 12%. Patients would feel extremely uncomfortable after scar formation. Administering oral medications (such as vitamin E and Zafirlukast tablets, etc.) or invasive breast capsulectomy surgery was commonly used for capsular contracture repair in clinical therapy. However, the therapeutic effect is still under investigation. Shock waves can be used to remove soft connective tissue in clinical applications. It has been widely used in orthopedics and rehabilitation. No related research paper about shock wave treatment of capsular contracture has been published yet. It might provide another choice for capsular contracture repair. In order to simulate breast implantation, two silica-gel bags filled with normal saline were implanted into New Zealand rabbit's thighs bilaterally as an animal model. Six weeks later, daily shock wave treatment on the right thigh was performed for six weeks after capsular contractures were formed, while the other thigh was used as a control. Then, magnetic resonance imaging (MRI) was used to compare the difference between treated and un-treated thighs. Afterwards, pathological sections were analyzed to confirm the findings. It has been demonstrated that shock wave treatments are capable of changing the structure and composition of capsular contractures. The structure of scar became myxoid changed or collagen deposition of scar decreased after shock wave treatment, hence, the formation of scars decreased. Increased myxoid and decreased collagen deposition has also been found.