Search

Simple Summary: This study investigates the latest achievements, challenges, and future research directions of deep learning techniques for lung cancer and pulmonary nodule detection. Hopefully, these research findings will help scientists, investigators, and clinicians develop new and effective medical imaging tools to improve lung nodule diagnosis accuracy, sensitivity, and specificity. Medical imaging tools are essential in early-stage lung cancer diagnostics and the monitoring of lung cancer during treatment. Various medical imaging modalities, such as chest X-ray, magnetic resonance imaging, positron emission tomography, computed tomography, and molecular imaging techniques, have been extensively studied for lung cancer detection. These techniques have some limitations, including not classifying cancer images automatically, which is unsuitable for patients with other pathologies. It is urgently necessary to develop a sensitive and accurate approach to the early diagnosis of lung cancer. Deep learning is one of the fastest-growing topics in medical imaging, with rapidly emerging applications spanning medical image-based and textural data modalities. With the help of deep learning-based medical imaging tools, clinicians can detect and classify lung nodules more accurately and quickly. This paper presents the recent development of deep learning-based imaging techniques for early lung cancer detection. [ABSTRACT FROM AUTHOR]

Simple Summary: Fertility-sparing treatment for young women with endometrial atypical hyperplasia or endometrioid endometrial cancer has become an important priority. The aim of our retrospective study was to evaluate the effects of different weight statuses and related metabolic disorders on the oncological and reproductive outcomes of fertility-sparing treatment. We found that there was a parabola-shaped relationship between the cumulative complete response rate of treatment and BMI. The apex of the curve was observed at a BMI of 21–22 kg/m2. Furthermore, we demonstrated that hyperuricemia was an independent risk factor for the failure of conservative treatment, correlating with a lower cumulative 32-week CR rate and longer treatment duration. Our results indicate that a target BMI interval for weight management should be appropriately established for patients with EAH/EEC. Early active interventions for related metabolic disorders, preferably before 32 weeks of treatment, should be provided to improve treatment efficacy. Background: Although obesity was an independent risk factor for fertility-sparing treatment in endometrial atypical hyperplasia (EAH) and endometrioid endometrial cancer (EEC), the roles of other weight statuses and related metabolism were unclear. This study aimed to investigate the body mass index (BMI) interval that produced optimal treatment efficacy and the effects of related metabolic disorders in EAH/EEC patients. Methods: A total of 286 patients (including 209 EAH and 77 well-differentiated EEC) under progestin therapy were retrospectively analyzed. The cumulative complete response (CR) rate, relapse rate, and fertility outcomes were compared among different weight or metabolic statuses. Results: Underweight and overweight/obese status significantly decreased the cumulative 16-week and 32-week CR rate (p = 0.004, p = 0.022, respectively). The highest 16-week CR rate was observed at a BMI of 21–22 kg/m2 in the overall population (p = 0.033). Obesity (HR 0.37, 95%CI 0.15–0.90, p = 0.029) and PCOS (HR 0.55, 95%CI 0.31–0.99, p = 0.047) were associated with lower 16-week CR rate. Hyperuricemia (HR 0.66, 95%CI 0.45–0.99, p = 0.043) was associated with lower 32-week CR rate. The 16-week and 32-week CR rate (p = 0.036, p = 0.008, respectively) were significantly lower in patients exhibiting both obesity and hyperuricemia. Conclusions: The optimal fertility-sparing treatment efficacy was observed at a BMI of 21–22 kg/m2 in EAH/EEC. Hyperuricemia was an independent risk factor for long-term treatment outcomes. [ABSTRACT FROM AUTHOR]

Simple Summary: Dynamic contrast-enhanced (DCE) MRI has become a quantitative standard for assessing vascular permeability and perfusion. However, conventional pharmacokinetic (PK) modeling in DCE MRI is complex and time-consuming for dynamic MR scans with thousands of pixels per image. We have previously developed a deep learning approach using convolutional neural networks (CNN) as an efficient and accurate tool for the generation of PK parameter maps from DCE MRI of glioblastoma (GBM) mice. In the present study, the utility of this approach is further established through transfer learning between GBM-trained CNN and whole-brain radiotherapy (WBRT)-treated brain metastasis (BM) mice. The purpose of this study is to further validate the utility of our previously developed CNN in an alternative small animal model of BM through transfer learning. Unlike the glioma model, the BM mouse model develops multifocal intracranial metastases, including both contrast enhancing and non-enhancing lesions on DCE MRI, thus serving as an excellent brain tumor model to study tumor vascular permeability. Here, we conducted transfer learning by transferring the previously trained GBM CNN to DCE MRI datasets of BM mice. The CNN was re-trained to learn about the relationship between BM DCE images and target permeability maps extracted from the Extended Tofts Model (ETM). The transferred network was found to accurately predict BM permeability and presented with excellent spatial correlation with the target ETM PK maps. The CNN model was further tested in another cohort of BM mice treated with WBRT to assess vascular permeability changes induced via radiotherapy. The CNN detected significantly increased permeability parameter Ktrans in WBRT-treated tumors (p < 0.01), which was in good agreement with the target ETM PK maps. In conclusion, the proposed CNN can serve as an efficient and accurate tool for characterizing vascular permeability and treatment responses in small animal brain tumor models. [ABSTRACT FROM AUTHOR]

Simple Summary: The inv(16)/t(16;16) AML is a disease that is considered relatively easy and straightforward to be diagnosed in the clinical laboratories. Up to date, CBFB FISH and/or CBFB-MYH11 RT-PCR are still the major diagnostic assays utilized in the clinical laboratories. However, incidental CBFB FISH findings and their implication in clinical laboratory diagnostics and management, especially in the era of next-generation sequencing (NGS)-based methods, have not been systemically investigated. In this study, we systemically studied over 1600 AML cases tested with CBFB FISH. Over 5% of cases with a confirmed CBFB rearrangement were challenging, including those with discrepant FISH and RT-PCR results and/or atypical FISH findings. Meanwhile, atypical FISH findings usually indicate additional chromosome 16 aberrations (AC16As) overlooked by other methods including RT-PCR and almost all NGS-based methods if following the published parameters. The information revealed in this study will be useful for further workup and interpreting atypical CBFB FISH findings and confirmation of inv(16)/t(16;16) AML diagnosis and related treatment, as well as selection of samples to better validate NGS-based new diagnostic methods. Fluorescence in situ hybridization (FISH) is a confirmatory test to establish a diagnosis of inv(16)/t(16;16) AML. However, incidental findings and their clinical diagnostic implication have not been systemically studied. We studied 1629 CBFB FISH cases performed in our institution, 262 (16.1%), 1234 (75.7%), and 133 (8.2%) were reported as positive, normal, and abnormal, respectively. The last included CBFB copy number changes (n = 120) and atypical findings such as 3′CBFB deletion (n = 11), 5′CBFB deletion (n = 1), and 5′CBFB gain (n = 1). Correlating with CBFB-MYH11 RT-PCR results, totally 271 CBFB rearrangement cases were identified, including five with discrepancies between FISH and RT-PCR due to new partner genes (n = 3), insertion (n = 1), or rare CBFB-MYH11 variant (n = 1) and eight with 3′CBFB deletion. All cases with atypical findings and/or discrepancies presented clinical diagnostic challenges. Correlating FISH signal patterns and karyotypes, additional chromosome 16 aberrations (AC16As) show impacts on the re-definition of a complex karyotype and prognostic prediction. The CBFB rearrangement but not all AC16As will be detected by NGS-based methods. Therefore, FISH testing is currently still needed to provide a quick and straightforward confirmatory inv(16)/t(16;16) AML diagnosis and additional information related to clinical management. [ABSTRACT FROM AUTHOR]