ABSTRACT
Diagnosing brain tumors is a complex and time-consuming process that relies heavily on radiologists' expertise and interpretive skills. However, the advent of deep learning methodologies has revolutionized the field, offering more accurate and efficient assessments. Attention-based models have emerged as promising tools, focusing on salient features within complex medical imaging data. However, the precise impact of different attention mechanisms, such as channel-wise, spatial, or combined attention within the Channel-wise Attention Mode (CWAM), for brain tumor classification remains relatively unexplored. This study aims to address this gap by leveraging the power of ResNet101 coupled with CWAM (ResNet101-CWAM) for brain tumor classification. The results show that ResNet101-CWAM surpassed conventional deep learning classification methods like ConvNet, achieving exceptional performance metrics of 99.83% accuracy, 99.21% recall, 99.01% precision, 99.27% F1-score and 99.16% AUC on the same dataset. This enhanced capability holds significant implications for clinical decision-making, as accurate and efficient brain tumor classification is crucial for guiding treatment strategies and improving patient outcomes. Integrating ResNet101-CWAM into existing brain classification software platforms is a crucial step towards enhancing diagnostic accuracy and streamlining clinical workflows for physicians.
Subject(s)
Brain Neoplasms , Deep Learning , Humans , Brain Neoplasms/diagnostic imaging , Brain Neoplasms/classification , Brain Neoplasms/pathology , Image Interpretation, Computer-Assisted/methods , Magnetic Resonance Imaging/methodsABSTRACT
OBJECTIVES: Acute paracetamol poisoning is an emerging problem in Sri Lanka. Management guidelines recommend ingested dose and serum paracetamol concentrations to assess the risk. Our aim was to determine the usefulness of the patient's history of an ingested dose of >150 mg/kg and paracetamol concentration obtained by a simple colorimetric method to assess risk in patients with acute paracetamol poisoning. MATERIALS AND METHODS: Serum paracetamol concentrations were determined in 100 patients with a history of paracetamol overdose using High Performance Liquid Chromatography (HPLC); (reference method). The results were compared to those obtained with a colorimetric method. The utility of risk assessment by reported dose ingested and colorimetric analysis were compared. RESULTS: The area under the receiver operating characteristic curve for the history of ingested dose was 0.578 and there was no dose cut-off providing useful risk categorization. Both analytical methods had less than 5% intra- and inter-batch variation and were accurate on spiked samples. The time from blood collection to result was six times faster and ten times cheaper for colorimetry (30 minutes, US$2) than for HPLC (180 minutes, US$20). The correlation coefficient between the paracetamol levels by the two methods was 0.85. The agreement on clinical risk categorization on the standard nomogram was also good (Kappa = 0.62, sensitivity 81%, specificity 89%). CONCLUSIONS: History of dose ingested alone greatly over-estimated the number of patients who need antidotes and it was a poor predictor of risk. Paracetamol concentrations by colorimetry are rapid and inexpensive. The use of these would greatly improve the assessment of risk and greatly reduce unnecessary expenditure on antidotes.