Enhanced enchondroma detection from x‐ray images using deep learning: A step towards accurate and cost‐effective diagnosis

Journal of Orthopaedic Research®, Год журнала: 2024, Номер 42(12), С. 2826 - 2834

Опубликована: Июль 15, 2024

This study investigates the automated detection of enchondromas, benign cartilage tumors, from x-ray images using deep learning techniques. Enchondromas pose diagnostic challenges due to their potential for malignant transformation and overlapping radiographic features with other conditions. Leveraging a data set comprising 1645 1173 patients, deep-learning model implemented Detectron2 achieved an accuracy 0.9899 in detecting enchondromas. The employed rigorous validation processes compared its findings existing literature, highlighting superior performance approach. Results indicate machine improving reducing healthcare costs associated advanced imaging modalities. underscores significance early accurate enchondromas effective patient management suggests avenues further research musculoskeletal tumor detection.

Язык: Английский

---

Optimum machine learning models for osteosarcoma cancer detection and classification

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Авг. 5, 2024

Osteosarcoma is a bone-forming tumor which more common with children and young adults than adults. Timely detection classification of its type crucial to proper treatment possible survival. Machine learning models, trained on datasets the disease, are effective tool hand-crafted features highly dependent pathologists’ expertise. Publicly available raw osteosarcoma dataset was explored preprocessed (including data denoising normalization). Three different were then derived: dataset, selected via principal component analysis combination variance mutual information gain. Using three eight machine (ML) algorithms, this study proposed sets optimum ML models (altogether 24 models) their hyperparameters optimized using grid search. Then, learned compared validated repeated stratified 10-fold cross-validation 5 × 2 paired t-test select best for our task. The model based k-nearest neighbors algorithm proved be best, as it detected classified cancer in 344 ms 100% Top-1 accuracy F1- score zero Type I II errors. This performance exceeds those existing algorithms prediction. Thus, promising cutting-edge techniques detecting aid timely diagnosis, prognosis treatment.

Язык: Английский

---

Detection of Osteosarcoma Bone Cancer Using Supervised Deep Learning and Convolutional Neural Networks

Lecture notes in networks and systems, Год журнала: 2024, Номер unknown, С. 337 - 346

Опубликована: Янв. 1, 2024

Язык: Английский

---

Whole-Exome Analysis and Osteosarcoma: A Game Still Open

International Journal of Molecular Sciences, Год журнала: 2024, Номер 25(24), С. 13657 - 13657

Опубликована: Дек. 20, 2024

Osteosarcoma (OS) is the most prevalent malignant bone tumor in adolescents and young adults. OS cells grow a permissive local microenvironment which modulates their behavior facilitates all steps development (e.g., proliferation/quiescence, invasion/migration, drug resistance) contributes to intrinsic heterogeneity. The lung parenchyma common metastatic site OS, foci are frequently associated with poor clinical outcome. Although multiple factors may be responsible for disease, including genetic mutations Rb p53), molecular mechanism of remains unclear, conventional treatment still based on sequential approach that combines chemotherapy surgery. Also, despite increase trials, survival rates have not improved. Non-specific targeting therapies thus show therapeutic effects, along side effects at high doses. For these reasons, many efforts been made characterize complex genome thanks whole-exome analysis, aim identifying predictive biomarkers give patients better option. This review aims summarize discuss main recent advances research precision medicine.

Язык: Английский

---