Explainable Artificial Intelligence (XAI) for Diagnosing and Treating Tumors of the Female Reproductive Systems: Challenges and Advances DOI Open Access
Xin Gao, Haoyu Li,

Chunxia You

et al.

Published: Aug. 21, 2024

Background: Ovarian, cervical, and endometrial cancers stand as fatal health killers for women's mental physical health, especially affecting female reproductive systems. Exploiting weakly supervised learning explainable AI techniques are crucial fast, accurate, robust automatic marker detection, efficient prevention, primary treatment of gynecological tumors. Methods: With respect to the PRIMSA methodology, schemes deep learning-based investigated in cross-subject fields clinical diagnostic imaging technology. Related methods, opening research problems, challenging subjects explored screening tumors performing cancer image diagnosis latest study. Results: Keynote approaches combining ultrasound medicine, AI, technology summarized. In combination with methods medical imaging, prospective insights put forward refreshed concepts on treatments area oncology, a feasible range applications their corresponding techniques. Conclusions: Explainable capable accurate classification between benign malignant tumors, yielding pathway care improving survival rate patients, pacing disease prediction, matching strategic goal "Healthy China 2030".

Language: Английский

Enhanced lung cancer detection: Integrating improved random walker segmentation with artificial neural network and random forest classifier DOI Creative Commons
Sneha S. Nair, V. N. Meena Devi, Saju Bhasi

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(7), P. e29032 - e29032

Published: April 1, 2024

Medical image segmentation is a vital yet difficult job because of the multimodality acquired images. It to locate polluted area before it spreads.

Language: Английский

Citations

6

TNM Staging System in Thymoma: A Critical Appraisal? DOI Open Access
Marcello Carlo Ambrogi, Vittorio Aprile, Alessandra Lenzini

et al.

Journal of Clinical Medicine, Journal Year: 2024, Volume and Issue: 13(2), P. 610 - 610

Published: Jan. 21, 2024

Thymomas are rare tumors of the anterior mediastinum with peculiar clinical and pathological features. They have been deeply analyzed by pioneer authors, who strictly linked their name to main staging classifications. Before latest edition WHO classification thymic epithelial tumors, history thymoma inherited pathologists systematically addressed issue, from Levine-Rosai Muller-Hermelink. Similarly, system is intimately related two surgeons, Masaoka Koga, historically dealt this disease. More recently, traditional tumor-nodes-metastasis (TNM) has developed for condition, in a rational attempt put thymomas conformity other solid tumors. The efforts International Thymic Malignancies Interest Group (ITMIG) Domain Staging Prognostic Factors Committee (TD-SPFC) Association Study Lung Cancer (IASLC) resulted TNM which included eighth American Joint on Cancer’s (AJCC) Manual. Herein, we report narrative review evolution (TET) present critical appraisal actual compared historical Masaoka-Koga classification, special focus proposal ninth TNM, expected 2024.

Language: Английский

Citations

5

Application of artificial intelligence in the diagnosis, treatment, and recurrence prediction of peritoneal carcinomatosis DOI Creative Commons

Gui-Xia Wei,

Yuwen Zhou,

Zhiping Li

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(7), P. e29249 - e29249

Published: April 1, 2024

Peritoneal carcinomatosis (PC) is a type of secondary cancer which not sensitive to conventional intravenous chemotherapy. Treatment strategies for PC are usually palliative rather than curative. Recently, artificial intelligence (AI) has been widely used in the medical field, making early diagnosis, individualized treatment, and accurate prognostic evaluation various cancers, including mediastinal malignancies, colorectal cancer, lung more feasible. As branch computer science, AI specializes image recognition, speech automatic large-scale data extraction output. technologies have also made breakthrough progress field peritoneal based on its powerful learning capacity efficient computational power. successfully applied approaches imaging, blood tests, proteomics, pathological diagnosis. Due function convolutional neural network model machine algorithms, AI-assisted diagnosis types associated with higher accuracy rate compared methods. In addition, treatment surgical resection, intraperitoneal chemotherapy, systemic significantly improves survival patients PC. particular, recurrence prediction emotion combined technology, further improving quality life patients. Here we comprehensively reviewed summarized latest developments application PC, helping oncologists diagnose provide precise

Language: Английский

Citations

4

Enabler or inhibitor? The effect of AI crafting on presenteeism among medical staff DOI
Ran Liu, Wenhao Deng, Tianyu Wang

et al.

European Journal of Work and Organizational Psychology, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 15

Published: April 22, 2025

Language: Английский

Citations

0

A special delivery by a fork: Where does artificial intelligence come from? DOI

Izzy Thornton

New Directions for Evaluation, Journal Year: 2023, Volume and Issue: 2023(178-179), P. 23 - 32

Published: June 1, 2023

Abstract In this article, I discuss the use of artificial intelligence (AI) in evaluation and its relevance to evolution field. begin with a background on how AI models are developed, including machine learning makes sense data algorithms it develops go power models. explain foundational understanding natural language processing informs where might not be effectively used. A critical concern is that only as strong which they trained, evaluators should consider important limitations when using AI, structural inequality. considering relationship between evaluation, must both AI's an evaluative tool role new subject evaluation. As becomes more relevant wider array fields disciplines, will need develop strategies for good (or not), what not) do.

Language: Английский

Citations

6

Effects of Interobserver Segmentation Variability and Intensity Discretization on MRI-Based Radiomic Feature Reproducibility of Lipoma and Atypical Lipomatous Tumor DOI Creative Commons
Salvatore Gitto, Renato Cuocolo,

Vincenzo Giannetta

et al.

Deleted Journal, Journal Year: 2024, Volume and Issue: 37(3), P. 1187 - 1200

Published: Feb. 8, 2024

Abstract Segmentation and image intensity discretization impact on radiomics workflow. The aim of this study is to investigate the influence interobserver segmentation variability methods reproducibility MRI-based radiomic features in lipoma atypical lipomatous tumor (ALT). Thirty patients with or ALT were retrospectively included. Three readers independently performed manual contour-focused T1-weighted T2-weighted sequences, including whole volume. Additionally, a marginal erosion was applied segmentations evaluate its feature reproducibility. After pre-processing, included employing both fixed bin number width approaches, 1106 extracted from each sequence. Intraclass correlation coefficient (ICC) 95% confidence interval lower bound ≥ 0.75 defined stability. In vs. margin shrinkage segmentation, rates stable images ranged 92.68 95.21% 90.69 95.66% after 95.75 97.65% 95.39 96.47% discretization, respectively, no difference between two approaches ( p 0.175). Higher higher ICC values found when implementing compared number, regardless approach < 0.001). conclusion, MRI are reproducible method, although certain degree highlights need for preliminary reliability analysis future studies.

Language: Английский

Citations

2

Imaging at the nexus: how state of the art imaging techniques can enhance our understanding of cancer and fibrosis DOI Creative Commons
Alireza Baniasadi Dahooiyeh, Jeeban P. Das,

Conor M. Prendergast

et al.

Journal of Translational Medicine, Journal Year: 2024, Volume and Issue: 22(1)

Published: June 13, 2024

Both cancer and fibrosis are diseases involving dysregulation of cell signaling pathways resulting in an altered cellular microenvironment which ultimately leads to progression the condition. The two disease entities share common molecular pathophysiology recent research has illuminated how each promotes other. Multiple imaging techniques have been developed aid early accurate diagnosis disease, given commonalities between conditions, advances one opened new avenues study Here, we detail most up-to-date for they crossed over improve detection monitoring We explore positron emission tomography (PET), magnetic resonance (MRI), second generation harmonic Imaging (SGHI), ultrasound (US), radiomics, artificial intelligence (AI). A diagnostic tool PET/computed (CT) is use radiolabeled fibroblast activation protein inhibitor (FAPI). SGHI uses high-frequency sound waves penetrate deeper into tissue, providing a more detailed view tumor microenvironment. Artificial with advanced deep learning (DL) algorithms highly effective training computer systems diagnose classify neoplastic lesions multiple organs. Ultimately, advancing can lead significantly timely diagnoses both better patient outcomes.

Language: Английский

Citations

2

Development and validation of the MRI-based deep learning classifier for distinguishing perianal fistulizing Crohn’s disease from cryptoglandular fistula: a multicenter cohort study DOI Creative Commons
Heng Zhang, Wenjun Li, Tao Chen

et al.

EClinicalMedicine, Journal Year: 2024, Volume and Issue: 78, P. 102940 - 102940

Published: Nov. 22, 2024

Language: Английский

Citations

2

Personalized Management of Malignant and Non-Malignant Ectopic Mediastinal Thyroid: A Proposed 10-Item Algorithm Approach DOI Open Access
Mara Carşote, Mihai-Lucian Ciobica,

Oana-Claudia Sima

et al.

Cancers, Journal Year: 2024, Volume and Issue: 16(10), P. 1868 - 1868

Published: May 14, 2024

We aimed to analyze the management of ectopic mediastinal thyroid (EMT) with respect EMT-related cancer and non-malignant findings related pathological report, clinical presentation, imaging traits, endocrine profile, connective tissue cervical (eutopic) gland, biopsy or fine needle aspiration (FNA) results, surgical techniques post-operatory outcome. This was a comprehensive review based on revising any type freely PubMed-accessible English, full-length original papers including keywords “ectopic thyroid” “mediastinum” from inception until March 2024. included 89 articles that specified EMTs data. classified them into four main groups: (I) studies/case series (n = 10; N 36 EMT patients); (II) malignant (N 22 subjects; except for one newborn immature teratoma in EMT, only adults were reported; mean age 62.94 years; ranges: 34 90 female male ratio 0.9). Histological analysis showed following: papillary 11/21); follicular variant 2/21); Hürthle cell malignancy 1/21); poorly differentiated anaplastic medullary lymphoma MALT (mucosa-associated lymphoid tissue) (III) benign no anomalies 37 56.32 30 80 1.8); (IV) 23; 5.6; average 52.1 years). panel involved clinical/subclinical hypothyroidism (iatrogenic, congenital, thyroiditis-induced, transitory upon removal); thyrotoxicosis (including autonomous activity suppressed eutopic gland); autoimmune thyroiditis/Graves’s disease; nodules/multinodular goiter prior thyroidectomy (before detection). propose 10-item algorithm might help navigate through domain. To conclude, across this focused-sample (to our knowledge, largest its kind) EMTs, index suspicion remains low; higher rate is reported than data (18.8%), incident imagery-based detection found 10–14% EMTs; surgery offered an overall good A wide range imagery, biopsy/FNA procedures part otherwise complex personalized management.

Language: Английский

Citations

1

Bioinformatics study of DLAT gene in pan-cancer DOI Creative Commons
Renlong Zhou, Hanchao Gao

Asian Journal of Surgery, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 1, 2024

Language: Английский

Citations

1