Recent Imaging Updates and Advances in Gynecologic Malignancies

Daoud, Taher; Sardana, Sahil; Stanietzky, Nir; Klekers, Albert R.; Bhosale, Priya; Morani, Ajaykumar C.

doi:10.3390/cancers14225528

Cited by 13 publications

(12 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also requires adequate sampling and interpretation by trained personnel. Cytology alone is not sufficient for staging cervical cancer or detecting recurrence ( 67 ). Colposcopy is a visual examination of the cervix using a magnifying device.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep-learning models for image-based gynecological cancer diagnosis: a systematic review and meta- analysis

Taddese,

Tilahun,

Awoke

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

IntroductionGynecological cancers pose a significant threat to women worldwide, especially those in resource-limited settings. Human analysis of images remains the primary method of diagnosis, but it can be inconsistent and inaccurate. Deep learning (DL) can potentially enhance image-based diagnosis by providing objective and accurate results. This systematic review and meta-analysis aimed to summarize the recent advances of deep learning (DL) techniques for gynecological cancer diagnosis using various images and explore their future implications.MethodsThe study followed the PRISMA-2 guidelines, and the protocol was registered in PROSPERO. Five databases were searched for articles published from January 2018 to December 2022. Articles that focused on five types of gynecological cancer and used DL for diagnosis were selected. Two reviewers assessed the articles for eligibility and quality using the QUADAS-2 tool. Data was extracted from each study, and the performance of DL techniques for gynecological cancer classification was estimated by pooling and transforming sensitivity and specificity values using a random-effects model.ResultsThe review included 48 studies, and the meta-analysis included 24 studies. The studies used different images and models to diagnose different gynecological cancers. The most popular models were ResNet, VGGNet, and UNet. DL algorithms showed more sensitivity but less specificity compared to machine learning (ML) methods. The AUC of the summary receiver operating characteristic plot was higher for DL algorithms than for ML methods. Of the 48 studies included, 41 were at low risk of bias.ConclusionThis review highlights the potential of DL in improving the screening and diagnosis of gynecological cancer, particularly in resource-limited settings. However, the high heterogeneity and quality of the studies could affect the validity of the results. Further research is necessary to validate the findings of this study and to explore the potential of DL in improving gynecological cancer diagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

“…It may miss lesions in the endocervical canal or outside the transformation zone. It also has limited value for staging cervical cancer or detecting recurrence ( 67 ). MRI is regarded as the gold standard for local staging of most gynecologic malignancies ( 68 ).…”

Section: Discussionmentioning

confidence: 99%

Deep-learning models for image-based gynecological cancer diagnosis: a systematic review and meta- analysis

Taddese,

Tilahun,

Awoke

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Gynecological cancers are among the most common malignancies with significant morbidity and mortality, primarily classified into five major types according to the organ affected ( 38 , 39 ). In this retrospective study, we investigated 184 Chinese patients with gynecological cancer using NGS.…”

Section: Discussionmentioning

confidence: 99%

Clinical characterization and genomic landscape of gynecological cancers among patients attending a Chinese hospital

Jiang

Liu

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

BackgroundGynecological cancers are the most lethal malignancies among females, most of which are associated with gene mutations. Few studies have compared the differences in the genomic landscape among various types of gynecological cancers. In this study, we evaluated the diversity of mutations in different gynecological cancers.MethodsA total of 184 patients with gynecological cancer, including ovarian, cervical, fallopian tube, and endometrial cancer, were included. Next-generation sequencing was performed to detect the mutations and tumor mutational burden (TMB). Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) enrichment analyses were also conducted.ResultsWe found that 94.57% of patients had at least one mutation, among which single nucleotide variants, insertions and InDels were in the majority. TP53, PIK3CA, PTEN, KRAS, BRCA1, BRCA2, ARID1A, KMT2C, FGFR2, and FGFR3 were the top 10 most frequently mutated genes. Patients with ovarian cancer tended to have higher frequencies of BRCA1 and BRCA2 mutations, and the frequency of germline BRCA1 mutations (18/24, 75.00%) was higher than that of BRCA2 (11/19, 57.89%). A new mutation hotspot in BRCA2 (I770) was firstly discovered among Chinese patients with gynecological cancer. Patients with TP53, PIK3CA, PTEN, and FGFR3 mutations had significantly higher TMB values than those with wild-type genes. A significant cross was discovered between the enriched KEGG pathways of gynecological and breast cancers. GO enrichment revealed that the mutated genes were crucial for the cell cycle, neuronal apoptosis, and DNA repair.ConclusionVarious gynecological cancer types share similarities and differences both in clinical characterization and genomic mutations. Taken together with the results of TMB and enriched pathways, this study provided useful information on the molecular mechanism underlying gynecological cancers and the development of targeted drugs and precision medicine.

show abstract

“…An alternative to the surgical staging might be magnetic resonance imaging (MRI). MRI is recommended for locoregional LN staging, particularly in advanced disease and prior to primary radiotherapy, but it comes with limited sensitivity of 43.5-72% [4,5,[18][19][20]. Combining MRI with [18F]-fluorodeoxyglucose-positron emission tomography (FDG-PET) offers potential, yet FDG-PET/MRI data are limited, and its use is mostly reserved for clinical trials, high-risk patients, and the evaluation of tumor recurrence [4,5,18,21,22].…”

Section: Introductionmentioning

confidence: 99%

Additional Value of FDG-PET/MRI Complementary to Sentinel Lymphonodectomy for Minimal Invasive Lymph Node Staging in Patients with Endometrial Cancer: A Prospective Study

Weissinger,

Bala,

Brucker

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Background: Lymph node metastases (LNM) are rare in early-stage endometrial cancer, but a diagnostic systematic lymphadenectomy (LNE) is often performed to achieve reliable N-staging. Therefore, this prospective study aimed to evaluate the benefit of [18F]-Fluorodeoxyglucose (FDG) PET/MRI complementary to SPECT/CT guided sentinel lymphonodectomy (SLNE) for a less invasive N-staging Methods: 79 patients underwent a whole-body FDG-PET/MRI, SLN mapping with 99mTc-Nanocolloid SPECT/CT and indocyanine green (ICG) fluoroscopy followed by LNE which served as ground truth. Results: FDG-PET/MRI was highly specific in N-staging (97.2%) but revealed limited sensitivity (66.7%) due to missed micrometastases. In contrast, bilateral SLN mapping failed more often in patients with macrometastases. The combination of SLN mapping and FDG-PET/MRI increased the sensitivity from 66.7% to 77.8%. Additional SLN labeling with dye (ICG) revealed a complete SLN mapping in 80% (8/10) of patients with failed or incomplete SLN detection in SPECT/CT, reducing the need for diagnostic systematic LNE up to 87%. FDG-PET/MRI detected para-aortic LNM in three out of four cases and a liver metastasis. Conclusions: The combination of FDG-PET/MRI and SLNE can reduce the need for diagnostic systematic LNE by up to 87%. PET/MRI complements the SLN technique particularly in the detection of para-aortic LNM and occasional distant metastases.

show abstract

Recent Imaging Updates and Advances in Gynecologic Malignancies

Cited by 13 publications

References 51 publications

Deep-learning models for image-based gynecological cancer diagnosis: a systematic review and meta- analysis

Deep-learning models for image-based gynecological cancer diagnosis: a systematic review and meta- analysis

Clinical characterization and genomic landscape of gynecological cancers among patients attending a Chinese hospital

Additional Value of FDG-PET/MRI Complementary to Sentinel Lymphonodectomy for Minimal Invasive Lymph Node Staging in Patients with Endometrial Cancer: A Prospective Study

Contact Info

Product

Resources

About