Optimizing lung cancer classification through hyperparameter tuning.

Artificial intelligence is steadily permeating various sectors, including healthcare. This research specifically addresses lung cancer, the world's deadliest disease with the highest mortality rate. Two primary factors contribute to its onset: genetic predisposition and environmental factors, such as smoking and exposure to pollutants. Recognizing the need for more effective diagnosis techniques, our study embarked on devising a machine learning strategy tailored to boost precision in lung cancer detection. Our aim was to devise a diagnostic method that is both less invasive and cost-effective. To this end, we proposed four methods, benchmarking them against prevalent techniques using a universally recognized dataset from Kaggle. Among our methods, one emerged as particularly promising, outperforming the competition in accuracy, precision and sensitivity. This method utilized hyperparameter tuning, focusing on the Gamma and C parameters, which were set at a value of 10. These parameters influence kernel width and regularization strength, respectively. As a result, we achieved an accuracy of 99.16%, a precision of 98% and a sensitivity rate of 100%. In conclusion, our enhanced prediction mechanism has proven to surpass traditional and contemporary strategies in lung cancer detection.

Genetic variations of penicillin-binding protein 1A: insights into the current status of amoxicillin-based regimens for Helicobacter pylori eradication in Malaysia.

Introduction. Resistance towards amoxicillin in Helicobacter pylori causes significant therapeutic impasse in healthcare settings worldwide. In Malaysia, the standard H. pylori treatment regimen includes a 14-day course of high-dose proton-pump inhibitor (rabeprazole, 20 mg) with amoxicillin (1000 mg) dual therapy.Hypothesis/Gap Statement. The high eradication rate with amoxicillin-based treatment could be attributed to the primary resistance rates of amoxicillin being relatively low at 0%, however, a low rate of secondary resistance has been documented in Malaysia recently.Aim. This study aims to investigate the amino acid mutations and related genetic variants in PBP1A of H. pylori, correlating with amoxicillin resistance in the Malaysian population.Methodology. The full-length pbp1A gene was amplified via PCR from 50 genomic DNA extracted from gastric biopsy samples of H. pylori-positive treatment-naïve Malaysian patients. The sequences were then compared with reference H. pylori strain ATCC 26695 for mutation and variant detection. A phylogenetic analysis of 50 sequences along with 43 additional sequences from the NCBI database was performed. These additional sequences included both amoxicillin-resistant strains (n=20) and amoxicillin-sensitive strains (n=23).Results. There was a total of 21 variants of amino acids, with three of them located in or near the PBP-motif (SKN402-404). The percentages of these three variants are as follows: K403X, 2%; S405I, 2% and E406K, 16%. Based on the genetic markers identified, the resistance rate for amoxicillin in our sample remained at 0%. The phylogenetic examination suggested that H. pylori might exhibit unique conserved pbp1A sequences within the Malaysian context.Conclusions. Overall, the molecular analysis of PBP1A supported the therapeutic superiority of amoxicillin-based regimens. Therefore, it is crucial to continue monitoring the amoxicillin resistance background of H. pylori with a larger sample size to ensure the sustained effectiveness of amoxicillin-based treatments in Malaysia.

Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures.

Automatic classification of colon and lung cancer images is crucial for early detection and accurate diagnostics. However, there is room for improvement to enhance accuracy, ensuring better diagnostic precision. This study introduces two novel dense architectures (D1 and D2) and emphasizes their effectiveness in classifying colon and lung cancer from diverse images. It also highlights their resilience, efficiency, and superior performance across multiple datasets. These architectures were tested on various types of datasets, including NCT-CRC-HE-100K (set of 100,000 non-overlapping image patches from hematoxylin and eosin (H&E) stained histological images of human colorectal cancer (CRC) and normal tissue), CRC-VAL-HE-7K (set of 7180 image patches from N = 50 patients with colorectal adenocarcinoma, no overlap with patients in NCT-CRC-HE-100K), LC25000 (Lung and Colon Cancer Histopathological Image), and IQ-OTHNCCD (Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases), showcasing their effectiveness in classifying colon and lung cancers from histopathological and Computed Tomography (CT) scan images. This underscores the multi-modal image classification capability of the proposed models. Moreover, the study addresses imbalanced datasets, particularly in CRC-VAL-HE-7K and IQ-OTHNCCD, with a specific focus on model resilience and robustness. To assess overall performance, the study conducted experiments in different scenarios. The D1 model achieved an impressive 99.80 % accuracy on the NCT-CRC-HE-100K dataset, with a Jaccard Index (J) of 0.8371, a Matthew's Correlation Coefficient (MCC) of 0.9073, a Cohen's Kappa (Kp) of 0.9057, and a Critical Success Index (CSI) of 0.8213. When subjected to 10-fold cross-validation on LC25000, the D1 model averaged (avg) 99.96 % accuracy (avg J, MCC, Kp, and CSI of 0.9993, 0.9987, 0.9853, and 0.9990), surpassing recent reported performances. Furthermore, the ensemble of D1 and D2 reached 93 % accuracy (J, MCC, Kp, and CSI of 0.7556, 0.8839, 0.8796, and 0.7140) on the IQ-OTHNCCD dataset, exceeding recent benchmarks and aligning with other reported results. Efficiency evaluations were conducted in various scenarios. For instance, training on only 10 % of LC25000 resulted in high accuracy rates of 99.19 % (J, MCC, Kp, and CSI of 0.9840, 0.9898, 0.9898, and 0.9837) (D1) and 99.30 % (J, MCC, Kp, and CSI of 0.9863, 0.9913, 0.9913, and 0.9861) (D2). In NCT-CRC-HE-100K, D2 achieved an impressive 99.53 % accuracy (J, MCC, Kp, and CSI of 0.9906, 0.9946, 0.9946, and 0.9906) with training on only 30 % of the dataset and testing on the remaining 70 %. When tested on CRC-VAL-HE-7K, D1 and D2 achieved 95 % accuracy (J, MCC, Kp, and CSI of 0.8845, 0.9455, 0.9452, and 0.8745) and 96 % accuracy (J, MCC, Kp, and CSI of 0.8926, 0.9504, 0.9503, and 0.8798), respectively, outperforming previously reported results and aligning closely with others. Lastly, training D2 on just 10 % of NCT-CRC-HE-100K and testing on CRC-VAL-HE-7K resulted in significant outperformance of InceptionV3, Xception, and DenseNet201 benchmarks, achieving an accuracy rate of 82.98 % (J, MCC, Kp, and CSI of 0.7227, 0.8095, 0.8081, and 0.6671). Finally, using explainable AI algorithms such as Grad-CAM, Grad-CAM++, Score-CAM, and Faster Score-CAM, along with their emphasized versions, we visualized the features from the last layer of DenseNet201 for histopathological as well as CT-scan image samples. The proposed dense models, with their multi-modality, robustness, and efficiency in cancer image classification, hold the promise of significant advancements in medical diagnostics. They have the potential to revolutionize early cancer detection and improve healthcare accessibility worldwide.

Enhancing lung cancer detection through hybrid features and machine learning hyperparameters optimization techniques.

Machine learning offers significant potential for lung cancer detection, enabling early diagnosis and potentially improving patient outcomes. Feature extraction remains a crucial challenge in this domain. Combining the most relevant features can further enhance detection accuracy. This study employed a hybrid feature extraction approach, which integrates both Gray-level co-occurrence matrix (GLCM) with Haralick and autoencoder features with an autoencoder. These features were subsequently fed into supervised machine learning methods. Support Vector Machine (SVM) Radial Base Function (RBF) and SVM Gaussian achieved perfect performance measures, while SVM polynomial produced an accuracy of 99.89% when utilizing GLCM with an autoencoder, Haralick, and autoencoder features. SVM Gaussian achieved an accuracy of 99.56%, while SVM RBF achieved an accuracy of 99.35% when utilizing GLCM with Haralick features. These results demonstrate the potential of the proposed approach for developing improved diagnostic and prognostic lung cancer treatment planning and decision-making systems.

Sequencing-based detection of 23S rRNA domain V mutations in treatment-naïve Helicobacter pylori patients from Malaysia.

OBJECTIVES: In Malaysia, the prevalence of Helicobacter pylori resistance to clarithromycin is increasing. This study aimed to determine mutations in the 23S rRNA domain V directly using bacterial DNA extracted from gastric biopsy specimens with a urease-positive result. METHODS: A 1085-bp fragment of 23S rRNA domain V from samples of 62 treatment-naïve patients with H. pylori infection was amplified by PCR with newly designed primers, followed by sequencing. RESULTS: Of the 62 cases, 42 patients were treated with clarithromycin-based triple therapy and 20 patients were treated with amoxicillin and proton pump inhibitor only; both therapies showed successful eradication rates of 70-73.8%. Sequencing analysis detected 37 point mutations (6 known and 31 novel) with prevalences ranging from 1.6% (1/62) to 72.6% (45/62). A2147G (aka A2143G) appears to be associated with a low eradication rate [40% (2/5) failure rate and 13.3% (6/45) treatment success rate], supporting its role as a clinically significant point mutation. T2186C (aka T2182C) was found in 71.1% (32/45) and 80% (4/5) of treatment success and failure cases, respectively, suggesting that the mutation is clinically insignificant. The eradication success rate in patients with the novel T2929C mutation was decreased three-fold (6.7%; 3/45) compared with the failure rate (20%; 1/5), suggesting that it may play an important role in clarithromycin resistance, thus warranting further study. CONCLUSION: This study identified multiple known and novel mutations in 23S rRNA domain V through direct sequencing. Molecular detection of clarithromycin resistance directly on biopsies offers an alternative to conventional susceptibility testing.