Optimizing breast cancer diagnosis with photoacoustic imaging: An analysis of intratumoral and peritumoral radiomics

Photoacoustics, Journal Year: 2024, Volume and Issue: 38, P. 100606 - 100606

Published: April 9, 2024

The differentiation between benign and malignant breast tumors extends beyond morphological structures to encompass functional alterations within the nodules. combination of photoacoustic (PA) imaging radiomics unveils insights intricate details that are imperceptible naked eye. This study aims assess efficacy PA in cancer radiomics, focusing on impact peritumoral region size radiomic model accuracy. From January 2022 November 2023, data were collected from 358 patients with nodules, diagnosed via PA/US examination classified as BI-RADS 3-5. used largest lesion dimension images define interest, expanded by 2 mm, 5 8 for extracting features. Techniques statistics machine learning applied feature selection, logistic regression classifiers build models. These models integrated both intratumoral data, regressions identifying key predictive developed nomogram, combining mm clinical features, showed superior diagnostic performance, achieving an AUC 0.950 training cohort 0.899 validation. outperformed those based solely features or other methods, proving most effective research demonstrates significant potential especially advantage integrating approach not only surpasses but also underscores importance comprehensive analysis accurately characterizing

Language: Английский

---

PROMISE: Prognostic Radiomic Outcome Measurement in Acute Subdural Hematoma Evacuation Post-Craniotomy

Brain Sciences, Journal Year: 2025, Volume and Issue: 15(1), P. 58 - 58

Published: Jan. 10, 2025

Background/Objectives: Traumatic acute subdural hematoma (aSDH) often requires surgical intervention, such as craniotomy, to relieve mass lesions and pressure. The extent of evacuation significantly impacts patient outcomes. This study utilizes 3D Slicer software analyse post-craniotomy volume changes evaluate their prognostic significance in aSDH patients. Methods: Among 178 adult patients diagnosed with from January 2015 December 2022, 64 underwent via craniotomy. Initial scans were performed within 24 h trauma, followed by routine postoperative assess residual hematoma. We conducted radiomic analysis preoperative volumes, surface area, Feret diameter, sphericity, flatness, elongation. Clinical parameters, including SOFA score, APACHE pupillary response, comorbidities, age, anticoagulation status, haematocrit haemoglobin levels, also evaluated. Results: Changes Δ area correlated 30-day outcomes (p = 0.03) showed moderate predictive accuracy (AUC 0.65). Patients a > 30,090 mm2 experienced poorer (OR 6.66, p 0.02). Significant features included 0.009), diameter 0.0012). In multivariate analysis, only the remained significant 0.01). Conclusions: Postoperative is, among other variables, strong predictor outcomes, while remains independent predictor. Radiomic may enhance inform tailored therapeutic strategies.

Language: Английский

---

The value of CT-based radiomics for differentiation of pleural effusions in bacterial pneumonia and Mycoplasma pneumoniae pneumonia in children

Translational Pediatrics, Journal Year: 2025, Volume and Issue: 14(1), P. 70 - 79

Published: Jan. 1, 2025

Bacterial pathogens and Mycoplasma pneumoniae are the two main that cause community-acquired pneumonia complicated with pleural effusion (PE) in children, it is important to accurately differentiate between these types of effusions. The aim this study was explore feasibility value a radiomics approach based on non-contrast chest computed tomography (CT) scans differentiation bacterial PE (BPPE) parapneumonic (MPPE) children. clinical CT imaging data hospitalized children detected by from December 2020 2023 were retrospectively collected. A total 167 cases BPPE 368 MPPE included, all randomly divided into training set test ratio 7:3. region interest (ROI) manually segmented images extract features. optimal features screened using Select K Best, max-relevance min-redundancy (mRMR), least absolute shrinkage selection operator (LASSO). Logistic regression (LR) selected construct model. receiver operating characteristic (ROC) curves plotted, area under curve (AUC), 95% confidence interval (CI), sensitivity, specificity, accuracy calculated evaluate model performance. 2,264 extracted each ROI, seven finally selected. AUC 0.942 (95% CI: 0.917-0.967), precision 89.9%, 82.1%, 87.4% 91.7%, respectively. 0.917 0.868-0.965), 87.4%, 80.0%, 85.1% 90.7%, demonstrates potential identify provides new direction for future research.

Language: Английский

---

Predictive classification of lung cancer pathological based on PET/CT radiomics

Japanese Journal of Radiology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 25, 2025

Language: Английский

---

Contrast MR-Based Radiomics and Machine Learning Analysis to Assess Clinical Outcomes following Liver Resection in Colorectal Liver Metastases: A Preliminary Study

Cancers, Journal Year: 2022, Volume and Issue: 14(5), P. 1110 - 1110

Published: Feb. 22, 2022

To assess radiomics features efficacy obtained by arterial and portal MRI phase in the prediction of clinical outcomes colorectal liver metastases patients, evaluating recurrence, mutational status, pathological characteristic (mucinous tumor budding) surgical resection margin. This retrospective analysis was approved local Ethical Committee board, radiological databases were used to select patients with proof study a pre-surgical setting after neoadjuvant chemotherapy. The cohort included training set (51 61 years median age 121 metastases) an external validation (30 single lesion 60 age). For each segmented volume interest on two expert radiologists, 851 extracted as values using PyRadiomics tool. Non-parametric Kruskal-Wallis test, intraclass correlation, receiver operating (ROC) analysis, linear regression modelling pattern recognition methods (support vector machine (SVM), k-nearest neighbors (KNN), artificial neural network (NNET), decision tree (DT)) considered. best predictor discriminate expansive versus infiltrative growth front wavelet_LHH_glrlm_ShortRunLowGrayLevelEmphasis accuracy 82%, sensitivity 84%, specificity 77%. budding wavelet_LLH_firstorder_10Percentile 92%, 96%, 81%. differentiate mucinous type wavelet_LLL_glcm_ClusterTendency 88%, 38%, 100%. identify recurrence wavelet_HLH_ngtdm_Complexity 90%, 71%, 95%. model identification considering 13 textural significant metrics (accuracy 94%, 77% 99%). results eleven KNN 95%, Our confirmed capacity biomarkers several prognostic that could affect treatment choice order obtain more personalized approach.

Language: Английский

---