RESUMEN
OBJECTIVES: This work aims to explore the impact of multicenter data heterogeneity on deep learning brain metastases (BM) autosegmentation performance, and assess the efficacy of an incremental transfer learning technique, namely learning without forgetting (LWF), to improve model generalizability without sharing raw data. MATERIALS AND METHODS: A total of six BM datasets from University Hospital Erlangen (UKER), University Hospital Zurich (USZ), Stanford, UCSF, New York University (NYU), and BraTS Challenge 2023 were used. First, the performance of the DeepMedic network for BM autosegmentation was established for exclusive single-center training and mixed multicenter training, respectively. Subsequently privacy-preserving bilateral collaboration was evaluated, where a pretrained model is shared to another center for further training using transfer learning (TL) either with or without LWF. RESULTS: For single-center training, average F1 scores of BM detection range from 0.625 (NYU) to 0.876 (UKER) on respective single-center test data. Mixed multicenter training notably improves F1 scores at Stanford and NYU, with negligible improvement at other centers. When the UKER pretrained model is applied to USZ, LWF achieves a higher average F1 score (0.839) than naive TL (0.570) and single-center training (0.688) on combined UKER and USZ test data. Naive TL improves sensitivity and contouring accuracy, but compromises precision. Conversely, LWF demonstrates commendable sensitivity, precision and contouring accuracy. When applied to Stanford, similar performance was observed. CONCLUSION: Data heterogeneity (e.g., variations in metastases density, spatial distribution, and image spatial resolution across centers) results in varying performance in BM autosegmentation, posing challenges to model generalizability. LWF is a promising approach to peer-to-peer privacy-preserving model training.
Asunto(s)
Neoplasias Encefálicas , Aprendizaje Profundo , Humanos , Neoplasias Encefálicas/secundario , Neoplasias Encefálicas/radioterapia , PrivacidadRESUMEN
Background and purpose: Magnetic resonance imaging (MRI) scans are highly sensitive to acquisition and reconstruction parameters which affect feature stability and model generalizability in radiomic research. This work aims to investigate the effect of image pre-processing and harmonization methods on the stability of brain MRI radiomic features and the prediction performance of radiomic models in patients with brain metastases (BMs). Materials and methods: Two T1 contrast enhanced brain MRI data-sets were used in this study. The first contained 25 BMs patients with scans at two different time points and was used for features stability analysis. The effect of gray level discretization (GLD), intensity normalization (Z-score, Nyul, WhiteStripe, and in house-developed method named N-Peaks), and ComBat harmonization on features stability was investigated and features with intraclass correlation coefficient >0.8 were considered as stable. The second data-set containing 64 BMs patients was used for a classification task to investigate the informativeness of stable features and the effects of harmonization methods on radiomic model performance. Results: Applying fixed bin number (FBN) GLD, resulted in higher number of stable features compare to fixed bin size (FBS) discretization (10 ± 5.5 % higher). `Harmonization in feature domain improved the stability for non-normalized and normalized images with Z-score and WhiteStripe methods. For the classification task, keeping the stable features resulted in good performance only for normalized images with N-Peaks along with FBS discretization. Conclusions: To develop a robust MRI based radiomic model we recommend using an intensity normalization method based on a reference tissue (e.g N-Peaks) and then using FBS discretization.
RESUMEN
Defining the exact histological features of salivary gland malignancies before treatment remains an unsolved problem that compromises the ability to tailor further therapeutic steps individually. Radiomics, a new methodology to extract quantitative information from medical images, could contribute to characterizing the individual cancer phenotype already before treatment in a fast and non-invasive way. Consequently, the standardization and implementation of radiomic analysis in the clinical routine work to predict histology of salivary gland cancer (SGC) could also provide improvements in clinical decision-making. In this study, we aimed to investigate the potential of radiomic features as imaging biomarker to distinguish between high grade and low-grade salivary gland malignancies. We have also investigated the effect of image and feature level harmonization on the performance of radiomic models. For this study, our dual center cohort consisted of 126 patients, with histologically proven SGC, who underwent curative-intent treatment in two tertiary oncology centers. We extracted and analyzed the radiomics features of 120 pre-therapeutic MRI images with gadolinium (T1 sequences), and correlated those with the definitive post-operative histology. In our study the best radiomic model achieved average AUC of 0.66 and balanced accuracy of 0.63. According to the results, there is significant difference between the performance of models based on MRI intensity normalized images + harmonized features and other models (p value < 0.05) which indicates that in case of dealing with heterogeneous dataset, applying the harmonization methods is beneficial. Among radiomic features minimum intensity from first order, and gray level-variance from texture category were frequently selected during multivariate analysis which indicate the potential of these features as being used as imaging biomarker. The present bicentric study presents for the first time the feasibility of implementing MR-based, handcrafted radiomics, based on T1 contrast-enhanced sequences and the ComBat harmonization method in an effort to predict the formal grading of salivary gland carcinoma with satisfactory performance.
Asunto(s)
Imagen por Resonancia Magnética , Neoplasias de las Glándulas Salivales , Humanos , Neoplasias de las Glándulas Salivales/diagnóstico por imagen , Neoplasias de las Glándulas Salivales/patología , Imagen por Resonancia Magnética/métodos , Femenino , Masculino , Persona de Mediana Edad , Anciano , Adulto , Anciano de 80 o más Años , Procesamiento de Imagen Asistido por Computador/métodos , RadiómicaRESUMEN
The papain-like protease (PLpro) plays a critical role in SARS-CoV-2 (SCoV-2) pathogenesis and is essential for viral replication and for allowing the virus to evade the host immune response. Inhibitors of PLpro have great therapeutic potential, however, developing them has been challenging due to PLpro's restricted substrate binding pocket. In this report, we screened a 115 000-compound library for PLpro inhibitors and identified a new pharmacophore, based on a mercapto-pyrimidine fragment that is a reversible covalent inhibitor (RCI) of PLpro and inhibits viral replication in cells. Compound 5 had an IC50 of 5.1 µM for PLpro inhibition and hit optimization yielded a derivative with increased potency (IC50 0.85 µM, 6-fold higher). Activity based profiling of compound 5 demonstrated that it reacts with PLpro cysteines. We show here that compound 5 represents a new class of RCIs, which undergo an addition elimination reaction with cysteines in their target proteins. We further show that their reversibility is catalyzed by exogenous thiols and is dependent on the size of the incoming thiol. In contrast, traditional RCIs are all based upon the Michael addition reaction mechanism and their reversibility is base-catalyzed. We identify a new class of RCIs that introduces a more reactive warhead with a pronounced selectivity profile based on thiol ligand size. This could allow the expansion of RCI modality use towards a larger group of proteins important for human disease.
RESUMEN
Covalent inhibitors of the papain-like protease (PLpro) from SARS-CoV-2 have great potential as antivirals, but their non-specific reactivity with thiols has limited their development. In this report, we performed an 8000 molecule electrophile screen against PLpro and identified an α-chloro amide fragment, termed compound 1, which inhibited SARS-CoV-2 replication in cells, and also had low non-specific reactivity with thiols. Compound 1 covalently reacts with the active site cysteine of PLpro, and had an IC50 of 18 µM for PLpro inhibition. Compound 1 also had low non-specific reactivity with thiols and reacted with glutathione 1-2 orders of magnitude slower than other commonly used electrophilic warheads. Finally, compound 1 had low toxicity in cells and mice and has a molecular weight of only 247 daltons and consequently has great potential for further optimization. Collectively, these results demonstrate that compound 1 is a promising lead fragment for future PLpro drug discovery campaigns.
RESUMEN
BACKGROUND: Microbubbles are widely used in diagnostic ultrasound applications as contrast agents. Recently, many studies have shown that microbubbles have good potential for the use in therapeutic applications such as drug and gene delivery and opening of blood- brain barrier locally and transiently. When microbubbles are located inside an elastic microvessel and activated by ultrasound, they oscillate and induce mechanical stresses on the vessel wall. However, the mechanical stresses have beneficial therapeutic effects, they may induce vessel damage if they are too high. Microstreaming-induced shear stress is one of the most important wall stresses. OBJECTIVE: The overall aim of this study is to simulate the interaction between confined bubble inside an elastic microvessel and ultrasound field and investigate the effective parameters on microstreaming-induced shear stress. MATERIAL AND METHODS: In this Simulation study, we conducted a 2D finite element simulation to study confined microbubble dynamics, also we investigated both acoustical and bubble material parameters on microbubble oscillation and wall stress. RESULTS: Based on our results, for acoustic parameters in the range of therapeutic applications, the maximum shear stress was lower than 4 kPa. Shear stress was approximately independent from shell viscosity whereas it decreased by increasing the shell stiffness. Moreover, shear stress showed an increasing trend with acoustic pressure. CONCLUSION: Beside the acoustical parameters, bubble properties have important effects on bubble behavior so that the softer and larger bubbles are more appropriate for therapeutic application as they can decrease the required frequency and acoustic pressure while inducing the same biological effects.
RESUMEN
The aim of this work is to investigate the applicability of radiomic features alone and in combination with clinical information for the prediction of renal cell carcinoma (RCC) patients' overall survival after partial or radical nephrectomy. Clinical studies of 210 RCC patients from The Cancer Imaging Archive (TCIA) who underwent either partial or radical nephrectomy were included in this study. Regions of interest (ROIs) were manually defined on CT images. A total of 225 radiomic features were extracted and analyzed along with the 59 clinical features. An elastic net penalized Cox regression was used for feature selection. Accelerated failure time (AFT) with the shared frailty model was used to determine the effects of the selected features on the overall survival time. Eleven radiomic and twelve clinical features were selected based on their non-zero coefficients. Tumor grade, tumor malignancy, and pathology t-stage were the most significant predictors of overall survival (OS) among the clinical features (p < 0.002, < 0.02, and < 0.018, respectively). The most significant predictors of OS among the selected radiomic features were flatness, area density, and median (p < 0.02, < 0.02, and < 0.05, respectively). Along with important clinical features, such as tumor heterogeneity and tumor grade, imaging biomarkers such as tumor flatness, area density, and median are significantly correlated with OS of RCC patients.
Asunto(s)
Carcinoma de Células Renales , Neoplasias Renales , Carcinoma de Células Renales/diagnóstico por imagen , Humanos , Neoplasias Renales/diagnóstico por imagen , Estudios Retrospectivos , Tomografía Computarizada por Rayos XRESUMEN
OBJECTIVE: The aim of this study was to identify the most important features and assess their discriminative power in the classification of the subtypes of NSCLC. METHODS: This study involved 354 pathologically proven NSCLC patients including 134 squamous cell carcinoma (SCC), 110 large cell carcinoma (LCC), 62 not other specified (NOS), and 48 adenocarcinoma (ADC). In total, 1433 radiomics features were extracted from 3D volumes of interest drawn on the malignant lesion identified on CT images. Wrapper algorithm and multivariate adaptive regression splines were implemented to identify the most relevant/discriminative features. A multivariable multinomial logistic regression was employed with 1000 bootstrapping samples based on the selected features to classify four main subtypes of NSCLC. RESULTS: The results revealed that the texture features, specifically gray level size zone matrix features (GLSZM), were the significant indicators of NSCLC subtypes. The optimized classifier achieved an average precision, recall, F1-score, and accuracy of 0.710, 0.703, 0.706, and 0.865, respectively, based on the selected features by the wrapper algorithm. CONCLUSIONS: Our CT radiomics approach demonstrated impressive potential for the classification of the four main histological subtypes of NSCLC, It is anticipated that CT radiomics could be useful in treatment planning and precision medicine.
Asunto(s)
Adenocarcinoma , Carcinoma de Pulmón de Células no Pequeñas , Neoplasias Pulmonares , Carcinoma de Pulmón de Células no Pequeñas/diagnóstico por imagen , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Estudios Retrospectivos , Tomografía Computarizada por Rayos XRESUMEN
OBJECTIVE: This study aimed to assess the relationship between malocclusion severity and oral health-related quality of life (QoL) of 18 to 25-year-old Iranians who sought orthodontic treatment. MATERIALS AND METHODS: A total of 126 patients between 18 and 25 years attending some private orthodontic clinics answered the oral health impact profile-14 (OHIP-14) and a demographic questionnaire. Two calibrated orthodontists recorded the Index of Orthodontic Treatment Need-Dental Health Component (IOTN-DHC) determining the severity of malocclusion (Kappa = 0.8). The IOTN-Aesthetic Component (IOTN-AC) was reported by patients for assessing the perception of their esthetic severity of malocclusion. Logistic regression analysis was used. Level of significance was set at α = 0.05. RESULTS: The mean score of OHIP-14 was 20.87 ± 8.6. The frequency of patients with no/slight, borderline, and definite need for orthodontic treatment was determined as 13.4%, 23.8%, and 62.7%, respectively, by IOTN-DHC. There were significant correlations between borderline or definite need treatment and OHIP-14 overall score (P < 0.05). Patients with borderline and definite need for orthodontic treatment had 5 and 21 times lower QoL, respectively, than those with a slight need for orthodontic treatment. Based on IOTN-AC, 50.8% of the patients mentioned slight or no need based on IOTN-AC. No significant association was noted between IOTN-AC and OHIP-14 overall scores. CONCLUSIONS: The results showed negative impact of malocclusion severity on the QoL. This study highlighted the importance of individual assessment of orthodontic patients.