Prediction of cervix cancer stage and grade from diffusion weighted imaging using EfficientNet.

Purpose. This study aims to introduce an innovative noninvasive method that leverages a single image for both grading and staging prediction. The grade and the stage of cervix cancer (CC) are determined from diffusion-weighted imaging (DWI) in particular apparent diffusion coefficient (ADC) maps using deep convolutional neural networks (DCNN).Methods. datasets composed of 85 patients having annotated tumor stage (I, II, III, and IV), out of this, 66 were with grade (II and III) and the remaining patients with no reported grade were retrospectively collected. The study was IRB approved. For each patient, sagittal and axial slices containing the gross tumor volume (GTV) were extracted from ADC maps. These were computed using the mono exponential model from diffusion weighted images (b-values = 0, 100, 1000) that were acquired prior to radiotherapy treatment. Balanced training sets were created using the Synthetic Minority Oversampling Technique (SMOTE) and fed to the DCNN. EfficientNetB0 and EfficientNetB3 were transferred from the ImageNet application to binary and four-class classification tasks. Five-fold stratified cross validation was performed for the assessment of the networks. Multiple evaluation metrics were computed including the area under the receiver operating characteristic curve (AUC). Comparisons with Resnet50, Xception, and radiomic analysis were performed.Results. for grade prediction, EfficientNetB3 gave the best performance with AUC = 0.924. For stage prediction, EfficientNetB0 was the best with AUC = 0.931. The difference between both models was, however, small and not statistically significant EfficientNetB0-B3 outperformed ResNet50 (AUC = 0.71) and Xception (AUC = 0.89) in stage prediction, and demonstrated comparable results in grade classification, where AUCs of 0.89 and 0.90 were achieved by ResNet50 and Xception, respectively. DCNN outperformed radiomic analysis that gave AUC = 0.67 (grade) and AUC = 0.66 (stage).Conclusion.the prediction of CC grade and stage from ADC maps is feasible by adapting EfficientNet approaches to the medical context.

Cancerous and Non-Cancerous MRI Classification Using Dual DCNN Approach.

Brain cancer is a life-threatening disease requiring close attention. Early and accurate diagnosis using non-invasive medical imaging is critical for successful treatment and patient survival. However, manual diagnosis by radiologist experts is time-consuming and has limitations in processing large datasets efficiently. Therefore, efficient systems capable of analyzing vast amounts of medical data for early tumor detection are urgently needed. Deep learning (DL) with deep convolutional neural networks (DCNNs) emerges as a promising tool for understanding diseases like brain cancer through medical imaging modalities, especially MRI, which provides detailed soft tissue contrast for visualizing tumors and organs. DL techniques have become more and more popular in current research on brain tumor detection. Unlike traditional machine learning methods requiring manual feature extraction, DL models are adept at handling complex data like MRIs and excel in classification tasks, making them well-suited for medical image analysis applications. This study presents a novel Dual DCNN model that can accurately classify cancerous and non-cancerous MRI samples. Our Dual DCNN model uses two well-performed DL models, i.e., inceptionV3 and denseNet121. Features are extracted from these models by appending a global max pooling layer. The extracted features are then utilized to train the model with the addition of five fully connected layers and finally accurately classify MRI samples as cancerous or non-cancerous. The fully connected layers are retrained to learn the extracted features for better accuracy. The technique achieves 99%, 99%, 98%, and 99% of accuracy, precision, recall, and f1-scores, respectively. Furthermore, this study compares the Dual DCNN's performance against various well-known DL models, including DenseNet121, InceptionV3, ResNet architectures, EfficientNetB2, SqueezeNet, VGG16, AlexNet, and LeNet-5, with different learning rates. This study indicates that our proposed approach outperforms these established models in terms of performance.

68Ga-DOTATATE PET in Restaging and Response to Therapy in Neuroblastoma: A Case Series and a Mini Review.

68Ga-DOTATATE PET/CT is widely used for the evaluation of neuroendocrine tumors. Some reports exist on its use in the management of neuroblastoma. Building on the prior reports as well as our previous experience in using this technique for initial staging, we propose to describe its practical benefits in restaging and response to therapy. We describe different aspects including supply logistics, preparation, spatial resolution, and other practical applications. Methods: We reviewed the medical records for 8 patients who were evaluated with 68Ga-DOTATATE PET/CT at our institution over 2 y. A note was made of the patient and disease characteristics and the indication for PET imaging, and the results were retrospectively analyzed for feasibility, logistics, radiation exposure, and utility in answering the clinical question. Results: Eight children (5 girls and 3 boys; age range, 4-60 mo; median age, 30 mo) diagnosed with neuroblastoma were imaged with 68Ga-DOTATATE PET/CT and 5 with 123I-metaiodobenzylguanidine (123I-MIBG) SPECT/CT over 2 y. Three 68Ga-DOTATATE PET scans were done for staging, 10 for response evaluation, and 2 for restaging. 68Ga-DOTATATE PET accurately identified neuroblastoma lesions suspected or seen on anatomic imaging. It has been shown to be more specific and more sensitive than 123I-MIBG and at times also MRI. It had better spatial and contrast resolution than 123I-MIBG. 68Ga-DOTATATE PET was better than 123I-MIBG SPECT/CT, CT, and MRI in the detection of early progression and viable tumor delineation for response assessment, as well as in target volume definition for external-beam radiotherapy and proton-beam radiotherapy. 68Ga-DOTATATE PET was also better at assessing bony and bone marrow disease changes with time. Conclusion: 68Ga-DOTATATE PET/CT offers added value and a superior edge to other imaging modalities in restaging and response assessment in neuroblastoma patients. Further multicenter evaluations in larger cohorts are needed.

177Lu-PSMA Therapy for Metastatic Castration-Resistant Prostate Cancer: A Mini-Review of State-of-the-Art.

BACKGROUND: Prostate specific membrane antigen (PSMA) ligand labeled with Lutetium-177 (177Lu) is a promising therapeutic option for metastatic castration-resistant prostate cancer (mCRPC). Several prospective and retrospective studies as well as clinical trials are completed or underway. This has ultimately led to the approval of this therapy by the US Food and Drug Administration (FDA) on March 23 2022. Our work aims to present a mini-review of the most recent research performed and the potential future directions of 177Lu-PSMA-radioligand therapy (RLT) for mCRPC patients. MAIN BODY: For patients with mCRPCwho have met the eligibility criteria for 177Lu-PSMA RLT, numerous studies and trials are either ongoing or have been completed. The studies included in this review have reported overall biochemical response, defined as a prostate-specific antigen (PSA) decline of at least 50%, in at least 44% of patients with mCRPC. The median ranges of overall survival (OS) and radiographic progression-free survival (rPFS) were reported within 10.7-56 and 3.6-16 months, respectively. With data from several retrospective and prospective studies published, the safety of 177Lu-PSMA RLT in mCRPC has been confirmed and demonstrated by its low toxicity profile. Various studies have published pharmacokinetic/pharmacodynamic models to better understand the absorption, distribution, metabolism, and excretion of the RLT in this patient population. Findings have been published for 177Lu-PSMA RLT alone and in combination with other agents. We summarize their findings in our review. CONCLUSIONS: The efficacy of 177Lu-PSMA RLT for patients with mCRPC has been proven thus far with promising results: PSA response, OS and rPFS when used alone or in combination with other treatment options, relative to the standard treatment options alone. The low toxicity profile noted also proves the safety of 177Lu-PSMA RLT in these patients.

Amino Acid PET Imaging with 18F-DOPA in the evaluation of Pediatric Brain Tumors.

Although MRI is the workhorse of brain tumor initial evaluation and follow-up, there is a growing amount of data recommending the incorporation of amino-acid PET imaging at different stages of the management of these patients. Recent nuclear medicine and neuro-oncology clinical practice recommendations support the use of amino-acid imaging in brain tumor imaging. Considering 18F-DOPA is FDA approved for the evaluation of parkinsonian syndromes, it could be used clinically for other valuable clinical indications such as brain tumor evaluations. This value seems to be well established in adults and has growing evidence for its use in pediatrics as well. We offer to present four pediatric brain tumor cases imaged with 18F-DOPA and review the literature.

Clinical Management of End-Stage Renal Disease Patients on Dialysis Receiving Radioactive Iodine Treatment.

PURPOSE: Radioactive iodine (RAI) is used to treat thyroid cancer patients with a clear paradigm for most patients. End-stage renal disease (ESRD) patients pose several challenges when undergoing RAI treatment, primarily due to the lack of renal clearance. We retrospectively report our experience with RAI treatment in a cohort of patients with ESRD and provide a set of recommendations on aspects such as the need for adjusted dose activity, balancing scheduling between RAI therapy and dialysis, and radiation safety precautions. PATIENTS AND METHODS: In this study, we report on 5 patients (6 cases), with ESRD on dialysis, treated with RAI for thyroid cancer. Retention measurements to determine individual biological clearance of RAI from the patient's body before and after dialysis sessions were assessed using external exposure dose rates measured at 1 m. RESULTS: Delayed biological clearance of RAI, after the first hemodialysis session, resulted in a longer RAI effective half-life as a consequence of longer retention periods, consistent with observations reported in scientific literature. To achieve a much closer radiation exposure compared with a nondialysis patient, one would recommend administering ~20%-30% of the dose activity normally administered to a thyroid cancer patient based on their medical history, histopathology, and uptake with the appropriate dialysis schedule. CONCLUSIONS: Special precautions should be taken with the administration of RAI in ESRD patients by adjusting the prescribed dose activity, dialysis sessions, and paying special attention to wastes. Pooling data from multiple centers may be useful to build a consensus and substantiated recommendations.

Mechanisms behind the immediate effects of Roux-en-Y gastric bypass surgery on type 2 diabetes.

BACKGROUND: The most common bariatric surgery, Roux-en-Y gastric bypass, leads to glycemia normalization in most patients long before there is any appreciable weight loss. This effect is too large to be attributed purely to caloric restriction, so a number of other mechanisms have been proposed. The most popular hypothesis is enhanced production of an incretin, active glucagon-like peptide-1 (GLP-1), in the lower intestine. We therefore set out to test this hypothesis with a model which is simple enough to be robust and credible. METHOD: Our method involves (1) setting up a set of time-dependent equations for the concentrations of the most relevant species, (2) considering an "adiabatic" (or quasi-equilibrium) state in which the concentrations are slowly varying compared to reaction rates (and which in the present case is a postprandial state), and (3) solving for the dependent concentrations (of e.g. insulin and glucose) as an independent concentration (of e.g. GLP-1) is varied. RESULTS: Even in the most favorable scenario, with maximal values for (i) the increase in active GLP-1 concentration and (ii) the effect of GLP-1 on insulin production, enhancement of GLP-1 alone cannot account for the observations. I.e., the largest possible decrease in glucose predicted by the model is smaller than reported decreases, and the model predicts no decrease whatsoever in glucose ×insulin, in contrast to large observed decreases in homeostatic model assessment insulin resistance (HOMA-IR). On the other hand, both effects can be accounted for if the surgery leads to a substantial increase in some substance that opens an alternative insulin-independent pathway for glucose transport into muscle cells, which perhaps uses the same intracellular pool of GLUT-4 that is employed in an established insulin-independent pathway stimulated by muscle contraction during exercise. CONCLUSIONS: Glycemia normalization following Roux-en-Y gastric bypass is undoubtedly caused by a variety of mechanisms, which may include caloric restriction, enhanced GLP-1, and perhaps others proposed in earlier papers on this subject. However, the present results suggest that another possible mechanism should be added to the list of candidates: enhanced production in the lower intestine of a substance which opens an alternative insulin-independent pathway for glucose transport.